From 384ad7e99c1828eeadcca7a68be2b44ee0b0266b Mon Sep 17 00:00:00 2001 From: iabhi4 Date: Wed, 10 Sep 2025 12:59:03 -0700 Subject: [PATCH 01/34] fix: avoid deepcopy crash with non-pickleables in Gemini/Vertex --- litellm/litellm_core_utils/core_helpers.py | 27 ++++++++--- litellm/main.py | 6 +-- .../litellm_core_utils/test_core_helpers.py | 46 ++++++++++++++++++- 3 files changed, 69 insertions(+), 10 deletions(-) diff --git a/litellm/litellm_core_utils/core_helpers.py b/litellm/litellm_core_utils/core_helpers.py index 4aeb9d4d64..7423e55b62 100644 --- a/litellm/litellm_core_utils/core_helpers.py +++ b/litellm/litellm_core_utils/core_helpers.py @@ -228,9 +228,11 @@ def safe_deep_copy(data): """ Safe Deep Copy - The LiteLLM Request has some object that can-not be pickled / deep copied - - Use this function to safely deep copy the LiteLLM Request + The LiteLLM request may contain objects that cannot be pickled/deep-copied + (e.g., tracing spans, locks, clients). + + This helper deep-copies each top-level key independently; on failure keeps + original ref """ import copy @@ -255,9 +257,22 @@ def safe_deep_copy(data): "litellm_parent_otel_span" ) data["litellm_metadata"]["litellm_parent_otel_span"] = "placeholder" - new_data = copy.deepcopy(data) - # Step 2: re-add the litellm_parent_otel_span after doing a deep copy + # Step 2: Per-key deepcopy with fallback + if isinstance(data, dict): + new_data = {} + for k, v in data.items(): + try: + new_data[k] = copy.deepcopy(v) + except Exception: + new_data[k] = v + else: + try: + new_data = copy.deepcopy(data) + except Exception: + new_data = data + + # Step 3: re-add the litellm_parent_otel_span after doing a deep copy if isinstance(data, dict) and litellm_parent_otel_span is not None: if "metadata" in data and "litellm_parent_otel_span" in data["metadata"]: data["metadata"]["litellm_parent_otel_span"] = litellm_parent_otel_span @@ -268,4 +283,4 @@ def safe_deep_copy(data): data["litellm_metadata"][ "litellm_parent_otel_span" ] = litellm_parent_otel_span - return new_data + return new_data \ No newline at end of file diff --git a/litellm/main.py b/litellm/main.py index 786a0196e5..e7130caa49 100644 --- a/litellm/main.py +++ b/litellm/main.py @@ -116,6 +116,7 @@ from litellm.utils import ( from ._logging import verbose_logger from .caching.caching import disable_cache, enable_cache, update_cache +from .litellm_core_utils.core_helpers import safe_deep_copy from .litellm_core_utils.fallback_utils import ( async_completion_with_fallbacks, completion_with_fallbacks, @@ -2772,8 +2773,7 @@ def completion( # type: ignore # noqa: PLR0915 ) api_base = api_base or litellm.api_base or get_secret("GEMINI_API_BASE") - - new_params = deepcopy(optional_params) + new_params = safe_deep_copy(optional_params or {}) response = vertex_chat_completion.completion( # type: ignore model=model, messages=messages, @@ -2817,7 +2817,7 @@ def completion( # type: ignore # noqa: PLR0915 api_base = api_base or litellm.api_base or get_secret("VERTEXAI_API_BASE") - new_params = deepcopy(optional_params) + new_params = safe_deep_copy(optional_params or {}) if vertex_partner_models_chat_completion.is_vertex_partner_model(model): model_response = vertex_partner_models_chat_completion.completion( model=model, diff --git a/tests/test_litellm/litellm_core_utils/test_core_helpers.py b/tests/test_litellm/litellm_core_utils/test_core_helpers.py index 32f3ad3f55..89cc11c40d 100644 --- a/tests/test_litellm/litellm_core_utils/test_core_helpers.py +++ b/tests/test_litellm/litellm_core_utils/test_core_helpers.py @@ -9,7 +9,11 @@ sys.path.insert( 0, os.path.abspath("../../..") ) # Adds the parent directory to the system path -from litellm.litellm_core_utils.core_helpers import get_litellm_metadata_from_kwargs, safe_divide +from litellm.litellm_core_utils.core_helpers import ( + get_litellm_metadata_from_kwargs, + safe_divide, + safe_deep_copy +) def test_get_litellm_metadata_from_kwargs(): @@ -127,3 +131,43 @@ def test_safe_divide_weight_scenario(): expected_zero = [0, 0, 0] assert normalized_zero_weights == expected_zero, f"Expected {expected_zero}, got {normalized_zero_weights}" + + +def test_safe_deep_copy_with_non_pickleables_and_span(): + """ + Verify safe_deep_copy: + - does not crash when non-pickleables are present, + - preserves structure/keys, + - deep-copies JSON-y payloads (e.g., messages), + - keeps non-pickleables by reference, + - redacts OTEL span in the copy and restores it in the original. + """ + import threading + rlock = threading.RLock() + data = { + "metadata": {"litellm_parent_otel_span": rlock, "x": 1}, + "messages": [{"role": "user", "content": "hi"}], + "optional_params": {"handle": rlock}, + "ok": True, + } + + copied = safe_deep_copy(data) + + # Structure preserved + assert set(copied.keys()) == set(data.keys()) + + # Messages are deep-copied (new object, same content) + assert copied["messages"] is not data["messages"] + assert copied["messages"][0] == data["messages"][0] + + # Non-pickleable subtree kept by reference (no crash) + assert copied["optional_params"] is data["optional_params"] + assert copied["optional_params"]["handle"] is rlock + + # OTEL span: redacted in the copy, restored in original + assert copied["metadata"]["litellm_parent_otel_span"] == "placeholder" + assert data["metadata"]["litellm_parent_otel_span"] is rlock + + # Other simple fields unchanged + assert copied["ok"] is True + assert copied["metadata"]["x"] == 1 From e6a6300b707d21b4e60c9e68f4f6547c2a1da5cf Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Vedran=20Vidovi=C4=87?= Date: Thu, 11 Sep 2025 15:28:55 +0200 Subject: [PATCH 02/34] Describing the `labels` field use in the Vertex AI --- docs/my-website/docs/providers/vertex.md | 38 ++++++++++++++++++++++++ 1 file changed, 38 insertions(+) diff --git a/docs/my-website/docs/providers/vertex.md b/docs/my-website/docs/providers/vertex.md index fda0cee862..5a76189de9 100644 --- a/docs/my-website/docs/providers/vertex.md +++ b/docs/my-website/docs/providers/vertex.md @@ -2758,6 +2758,44 @@ curl http://localhost:4000/v1/fine_tuning/jobs \ +## Labels + + +Google enables you to add custom metadata to its `generateContent` and `streamGenerateContent` calls. +This mechanism is useful in Vertex AI because it allows costs and usage tracking over multiple +different applications or users. + + +### Usage + +You can use that feature through LiteLLM by sending `labels` or `metadata` field in your requests. + +If the client sets the `labels` field in the request to the LiteLLM, +the LiteLLM will pass the `labels` field to the Vertex AI backend. + +If the client sets the `metadata` field in the request to the LiteLLM and the `labels` field is not set, +the LiteLLM will create the `labels` field filled with `metadata` key/value pairs for all string values and +pass it to the Vertex AI backend. + + +Here is an example JSON request demonstrating the labels usage: + +```json +{ + "model": "gemini-2.0-flash-lite", + "messages": [ + { "role": "user", "content": "respond in 20 words. who are you?" } + ], + "labels": { + "client_app": "acme_comp_financial_app", + "department": "finance", + "project": "acme_ai" + } +} +``` + + + ## Extra ### Using `GOOGLE_APPLICATION_CREDENTIALS` From 61565901906594ded90be233679d8c70469a9585 Mon Sep 17 00:00:00 2001 From: mubashir1osmani Date: Sat, 13 Sep 2025 01:38:08 -0400 Subject: [PATCH 03/34] added spend metrics --- .../integrations/datadog/datadog_llm_obs.py | 48 +++++- litellm/types/integrations/datadog_llm_obs.py | 6 + .../datadog/test_datadog_llm_observability.py | 146 +++++++++++++++++- 3 files changed, 192 insertions(+), 8 deletions(-) diff --git a/litellm/integrations/datadog/datadog_llm_obs.py b/litellm/integrations/datadog/datadog_llm_obs.py index 2eaf13442e..457fafd75b 100644 --- a/litellm/integrations/datadog/datadog_llm_obs.py +++ b/litellm/integrations/datadog/datadog_llm_obs.py @@ -185,7 +185,6 @@ class DataDogLLMObsLogger(DataDogLogger, CustomBatchLogger): messages = standard_logging_payload["messages"] messages = self._ensure_string_content(messages=messages) - response_obj = standard_logging_payload.get("response") metadata = kwargs.get("litellm_params", {}).get("metadata", {}) @@ -495,6 +494,12 @@ class DataDogLLMObsLogger(DataDogLogger, CustomBatchLogger): latency_metrics = self._get_latency_metrics(standard_logging_payload) _metadata.update({"latency_metrics": dict(latency_metrics)}) + ######################################################### + # Add spend metrics to metadata + ######################################################### + spend_metrics = self._get_spend_metrics(standard_logging_payload) + _metadata.update({"spend_metrics": dict(spend_metrics)}) + ## extract tool calls and add to metadata tool_call_metadata = self._extract_tool_call_metadata(standard_logging_payload) _metadata.update(tool_call_metadata) @@ -543,6 +548,47 @@ class DataDogLLMObsLogger(DataDogLogger, CustomBatchLogger): ) return latency_metrics + + def _get_spend_metrics( + self, standard_logging_payload: StandardLoggingPayload + ) -> DDLLMObsSpendMetrics: + """ + Get the spend metrics from the standard logging payload + """ + spend_metrics: DDLLMObsSpendMetrics = DDLLMObsSpendMetrics() + + # Get response cost for litellm_spend_metric + response_cost = standard_logging_payload.get("response_cost", 0.0) + if response_cost > 0: + spend_metrics["litellm_spend_metric"] = response_cost + + # Get budget information from metadata + metadata = standard_logging_payload.get("metadata", {}) + + # API key max budget + user_api_key_max_budget = metadata.get("user_api_key_max_budget") + if user_api_key_max_budget is not None: + spend_metrics["litellm_api_key_max_budget_metric"] = user_api_key_max_budget + + # API key budget remaining hours + user_api_key_budget_reset_at = metadata.get("user_api_key_budget_reset_at") + if user_api_key_budget_reset_at is not None: + try: + from datetime import datetime + if isinstance(user_api_key_budget_reset_at, str): + # Parse ISO string if it's a string + budget_reset_at = datetime.fromisoformat(user_api_key_budget_reset_at.replace('Z', '+00:00')) + else: + budget_reset_at = user_api_key_budget_reset_at + + remaining_hours = ( + budget_reset_at - datetime.now(budget_reset_at.tzinfo) + ).total_seconds() / 3600 + spend_metrics["litellm_api_key_budget_remaining_hours_metric"] = max(0, remaining_hours) + except Exception as e: + verbose_logger.debug(f"Error calculating remaining hours for budget reset: {e}") + + return spend_metrics def _process_input_messages_preserving_tool_calls( self, messages: List[Any] diff --git a/litellm/types/integrations/datadog_llm_obs.py b/litellm/types/integrations/datadog_llm_obs.py index 41489ace30..8b94dd7b59 100644 --- a/litellm/types/integrations/datadog_llm_obs.py +++ b/litellm/types/integrations/datadog_llm_obs.py @@ -81,3 +81,9 @@ class DDLLMObsLatencyMetrics(TypedDict, total=False): time_to_first_token_ms: float litellm_overhead_time_ms: float guardrail_overhead_time_ms: float + +class DDLLMObsSpendMetrics(TypedDict, total=False): + litellm_spend_metric: float + litellm_api_key_max_budget_metric: float + litellm_remaining_api_key_budget_metric: float + litellm_api_key_budget_remaining_hours_metric: float diff --git a/tests/test_litellm/integrations/datadog/test_datadog_llm_observability.py b/tests/test_litellm/integrations/datadog/test_datadog_llm_observability.py index 39b8427fcf..f167eb24b2 100644 --- a/tests/test_litellm/integrations/datadog/test_datadog_llm_observability.py +++ b/tests/test_litellm/integrations/datadog/test_datadog_llm_observability.py @@ -657,21 +657,109 @@ def test_guardrail_information_in_metadata(mock_env_vars): assert guardrail_info["guardrail_response"]["score"] == 0.1 +def create_standard_logging_payload_with_spend_metrics() -> StandardLoggingPayload: + """Create a StandardLoggingPayload object with spend metrics for testing""" + from datetime import datetime, timezone + + # Create a budget reset time 24 hours from now + budget_reset_at = datetime.now(timezone.utc) + timedelta(hours=24) + + return { + "id": "test-request-id-spend", + "trace_id": "test-trace-id-spend", + "call_type": "completion", + "stream": None, + "response_cost": 0.15, + "response_cost_failure_debug_info": None, + "status": "success", + "custom_llm_provider": "openai", + "total_tokens": 30, + "prompt_tokens": 10, + "completion_tokens": 20, + "startTime": 1234567890.0, + "endTime": 1234567891.0, + "completionStartTime": 1234567890.5, + "response_time": 1.0, + "model_map_information": { + "model_map_key": "gpt-4", + "model_map_value": None + }, + "model": "gpt-4", + "model_id": "model-123", + "model_group": "openai-gpt", + "api_base": "https://api.openai.com", + "metadata": { + "user_api_key_hash": "test_hash", + "user_api_key_org_id": None, + "user_api_key_alias": "test_alias", + "user_api_key_team_id": "test_team", + "user_api_key_user_id": "test_user", + "user_api_key_team_alias": "test_team_alias", + "user_api_key_user_email": None, + "user_api_key_end_user_id": None, + "user_api_key_request_route": None, + "user_api_key_max_budget": 10.0, # $10 max budget + "user_api_key_budget_reset_at": budget_reset_at.isoformat(), + "spend_logs_metadata": None, + "requester_ip_address": "127.0.0.1", + "requester_metadata": None, + "requester_custom_headers": None, + "prompt_management_metadata": None, + "mcp_tool_call_metadata": None, + "vector_store_request_metadata": None, + "applied_guardrails": None, + "usage_object": None, + "cold_storage_object_key": None, + }, + "cache_hit": False, + "cache_key": None, + "saved_cache_cost": 0.0, + "request_tags": [], + "end_user": None, + "requester_ip_address": "127.0.0.1", + "messages": [{"role": "user", "content": "Hello, world!"}], + "response": {"choices": [{"message": {"content": "Hi there!"}}]}, + "error_str": None, + "error_information": None, + "model_parameters": {"stream": False}, + "hidden_params": { + "model_id": "model-123", + "cache_key": None, + "api_base": "https://api.openai.com", + "response_cost": "0.15", + "litellm_overhead_time_ms": None, + "additional_headers": None, + "batch_models": None, + "litellm_model_name": None, + "usage_object": None, + }, + "guardrail_information": None, + "standard_built_in_tools_params": None, + } # type: ignore + + def create_standard_logging_payload_with_tool_calls() -> StandardLoggingPayload: """Create a StandardLoggingPayload object with tool calls for testing""" return { "id": "test-request-id-tool-calls", + "trace_id": "test-trace-id-tool-calls", "call_type": "completion", + "stream": None, "response_cost": 0.05, "response_cost_failure_debug_info": None, "status": "success", + "custom_llm_provider": "openai", "total_tokens": 50, "prompt_tokens": 20, "completion_tokens": 30, "startTime": 1234567890.0, "endTime": 1234567891.0, "completionStartTime": 1234567890.5, - "model_map_information": {"model_map_key": "gpt-4", "model_map_value": None}, + "response_time": 1.0, + "model_map_information": { + "model_map_key": "gpt-4", + "model_map_value": None + }, "model": "gpt-4", "model_id": "model-123", "model_group": "openai-gpt", @@ -746,6 +834,7 @@ def create_standard_logging_payload_with_tool_calls() -> StandardLoggingPayload: ] }, "error_str": None, + "error_information": None, "model_parameters": {"temperature": 0.7}, "hidden_params": { "model_id": "model-123", @@ -758,14 +847,9 @@ def create_standard_logging_payload_with_tool_calls() -> StandardLoggingPayload: "litellm_model_name": None, "usage_object": None, }, - "stream": None, - "response_time": 1.0, - "error_information": None, "guardrail_information": None, "standard_built_in_tools_params": None, - "trace_id": "test-trace-id-tool-calls", - "custom_llm_provider": "openai", - } + } # type: ignore class TestDataDogLLMObsLoggerToolCalls: @@ -897,3 +981,51 @@ class TestDataDogLLMObsLoggerToolCalls: assert len(output_tool_calls) == 1 output_function_info = output_tool_calls[0].get("function", {}) assert output_function_info.get("name") == "format_response" + + +def test_spend_metrics_in_datadog_payload(mock_env_vars): + """Test that spend metrics are correctly included in DataDog LLM Observability payloads""" + with patch( + "litellm.integrations.datadog.datadog_llm_obs.get_async_httpx_client" + ), patch("asyncio.create_task"): + logger = DataDogLLMObsLogger() + + standard_payload = create_standard_logging_payload_with_spend_metrics() + + kwargs = { + "standard_logging_object": standard_payload, + "litellm_params": {"metadata": {}}, + } + + start_time = datetime.now() + end_time = datetime.now() + + payload = logger.create_llm_obs_payload(kwargs, start_time, end_time) + + # Verify basic payload structure + assert payload.get("name") == "litellm_llm_call" + assert payload.get("status") == "ok" + + # Verify spend metrics are included in metadata + meta = payload.get("meta", {}) + assert meta is not None, "Meta section should exist in payload" + + metadata = meta.get("metadata", {}) + assert metadata is not None, "Metadata section should exist in meta" + + spend_metrics = metadata.get("spend_metrics", {}) + assert spend_metrics, "Spend metrics should exist in metadata" + + # Check that all three spend metrics are present + assert "litellm_spend_metric" in spend_metrics + assert "litellm_api_key_max_budget_metric" in spend_metrics + assert "litellm_api_key_budget_remaining_hours_metric" in spend_metrics + + # Verify the values are correct + assert spend_metrics["litellm_spend_metric"] == 0.15 # response_cost + assert spend_metrics["litellm_api_key_max_budget_metric"] == 10.0 # max budget + + # Verify remaining hours is a reasonable value (should be close to 24 since we set it to 24 hours from now) + remaining_hours = spend_metrics["litellm_api_key_budget_remaining_hours_metric"] + assert isinstance(remaining_hours, (int, float)) + assert 20 <= remaining_hours <= 25 # Should be close to 24 hours From 9fcad0382cbf5f4c4a0a701fcb820c3a99d2a0d8 Mon Sep 17 00:00:00 2001 From: soojin Date: Sat, 13 Sep 2025 22:01:45 +0900 Subject: [PATCH 04/34] fix: improve response api handling and cold storage configuration - Fix s3_path configuration in cold storage logging to use actual logger instance path - Add proper null/empty response validation in session handler to prevent processing invalid responses --- litellm/litellm_core_utils/litellm_logging.py | 13 +++++++++++-- .../session_handler.py | 2 +- 2 files changed, 12 insertions(+), 3 deletions(-) diff --git a/litellm/litellm_core_utils/litellm_logging.py b/litellm/litellm_core_utils/litellm_logging.py index 2f21d28089..07cb1d8662 100644 --- a/litellm/litellm_core_utils/litellm_logging.py +++ b/litellm/litellm_core_utils/litellm_logging.py @@ -4150,15 +4150,24 @@ class StandardLoggingPayloadSetup: from litellm.integrations.s3 import get_s3_object_key # Only generate object key if cold storage is configured - if litellm.configured_cold_storage_logger is None: + configured_cold_storage_logger = litellm.configured_cold_storage_logger + if configured_cold_storage_logger is None: return None try: # Generate file name in same format as litellm.utils.get_logging_id s3_file_name = f"time-{start_time.strftime('%H-%M-%S-%f')}_{response_id}" + # Get the actual s3_path from the configured cold storage logger instance + s3_path = "" # default value + + # Get the actual logger instance from the logger name + custom_logger = litellm.logging_callback_manager.get_active_custom_logger_for_callback_name(configured_cold_storage_logger) + if custom_logger and hasattr(custom_logger, 's3_path') and custom_logger.s3_path: + s3_path = custom_logger.s3_path + s3_object_key = get_s3_object_key( - s3_path="", # Use empty path as default + s3_path=s3_path, # Use actual s3_path from logger configuration team_alias_prefix="", # Don't split by team alias for cold storage start_time=start_time, s3_file_name=s3_file_name, diff --git a/litellm/responses/litellm_completion_transformation/session_handler.py b/litellm/responses/litellm_completion_transformation/session_handler.py index bfb996a238..d1e009e62d 100644 --- a/litellm/responses/litellm_completion_transformation/session_handler.py +++ b/litellm/responses/litellm_completion_transformation/session_handler.py @@ -141,7 +141,7 @@ class ResponsesSessionHandler: # Add Output messages for this Spend Log ############################################################ _response_output = spend_log.get("response", "{}") - if isinstance(_response_output, dict): + if isinstance(_response_output, dict) and _response_output and _response_output != {}: # transform `ChatCompletion Response` to `ResponsesAPIResponse` model_response = ModelResponse(**_response_output) for choice in model_response.choices: From 488b3738359acdde26754350ff3f3d3ecda89724 Mon Sep 17 00:00:00 2001 From: soojin Date: Sat, 13 Sep 2025 23:10:15 +0900 Subject: [PATCH 05/34] test: add unit tests for response api bug fixes --- .../test_litellm_logging.py | 91 +++++++++++++++++++ .../test_session_handler.py | 50 ++++++++++ 2 files changed, 141 insertions(+) diff --git a/tests/test_litellm/litellm_core_utils/test_litellm_logging.py b/tests/test_litellm/litellm_core_utils/test_litellm_logging.py index fa5164b9c1..2aa29d4342 100644 --- a/tests/test_litellm/litellm_core_utils/test_litellm_logging.py +++ b/tests/test_litellm/litellm_core_utils/test_litellm_logging.py @@ -438,6 +438,97 @@ async def test_e2e_generate_cold_storage_object_key_successful(): assert isinstance(result, str) +@pytest.mark.asyncio +async def test_e2e_generate_cold_storage_object_key_with_custom_logger_s3_path(): + """ + Test that _generate_cold_storage_object_key uses s3_path from custom logger instance. + """ + from datetime import datetime, timezone + from unittest.mock import MagicMock, patch + + from litellm.litellm_core_utils.litellm_logging import StandardLoggingPayloadSetup + + # Create test data + start_time = datetime(2025, 1, 15, 10, 30, 45, 123456, timezone.utc) + response_id = "chatcmpl-test-12345" + + # Create mock custom logger with s3_path + mock_custom_logger = MagicMock() + mock_custom_logger.s3_path = "storage" + + with patch("litellm.configured_cold_storage_logger", "s3_v2"), \ + patch("litellm.logging_callback_manager.get_active_custom_logger_for_callback_name") as mock_get_logger, \ + patch("litellm.integrations.s3.get_s3_object_key") as mock_get_s3_key: + + # Setup mocks + mock_get_logger.return_value = mock_custom_logger + mock_get_s3_key.return_value = "storage/2025-01-15/time-10-30-45-123456_chatcmpl-test-12345.json" + + # Call the function + result = StandardLoggingPayloadSetup._generate_cold_storage_object_key( + start_time=start_time, + response_id=response_id + ) + + # Verify logger was queried correctly + mock_get_logger.assert_called_once_with("s3_v2") + + # Verify the S3 function was called with the custom logger's s3_path + mock_get_s3_key.assert_called_once_with( + s3_path="storage", # Should use custom logger's s3_path + team_alias_prefix="", + start_time=start_time, + s3_file_name="time-10-30-45-123456_chatcmpl-test-12345" + ) + + # Verify the result + assert result == "storage/2025-01-15/time-10-30-45-123456_chatcmpl-test-12345.json" + + +@pytest.mark.asyncio +async def test_e2e_generate_cold_storage_object_key_with_logger_no_s3_path(): + """ + Test that _generate_cold_storage_object_key falls back to empty s3_path when logger has no s3_path. + """ + from datetime import datetime, timezone + from unittest.mock import MagicMock, patch + + from litellm.litellm_core_utils.litellm_logging import StandardLoggingPayloadSetup + + # Create test data + start_time = datetime(2025, 1, 15, 10, 30, 45, 123456, timezone.utc) + response_id = "chatcmpl-test-12345" + + # Create mock custom logger without s3_path + mock_custom_logger = MagicMock() + mock_custom_logger.s3_path = None # or could be missing attribute + + with patch("litellm.configured_cold_storage_logger", "s3_v2"), \ + patch("litellm.logging_callback_manager.get_active_custom_logger_for_callback_name") as mock_get_logger, \ + patch("litellm.integrations.s3.get_s3_object_key") as mock_get_s3_key: + + # Setup mocks + mock_get_logger.return_value = mock_custom_logger + mock_get_s3_key.return_value = "2025-01-15/time-10-30-45-123456_chatcmpl-test-12345.json" + + # Call the function + result = StandardLoggingPayloadSetup._generate_cold_storage_object_key( + start_time=start_time, + response_id=response_id + ) + + # Verify the S3 function was called with empty s3_path (fallback) + mock_get_s3_key.assert_called_once_with( + s3_path="", # Should fall back to empty string + team_alias_prefix="", + start_time=start_time, + s3_file_name="time-10-30-45-123456_chatcmpl-test-12345" + ) + + # Verify the result + assert result == "2025-01-15/time-10-30-45-123456_chatcmpl-test-12345.json" + + @pytest.mark.asyncio async def test_e2e_generate_cold_storage_object_key_not_configured(): """ diff --git a/tests/test_litellm/responses/litellm_completion_transformation/test_session_handler.py b/tests/test_litellm/responses/litellm_completion_transformation/test_session_handler.py index 2e1fe2241a..637f8d449a 100644 --- a/tests/test_litellm/responses/litellm_completion_transformation/test_session_handler.py +++ b/tests/test_litellm/responses/litellm_completion_transformation/test_session_handler.py @@ -364,3 +364,53 @@ async def test_should_check_cold_storage_for_full_payload(): with patch.object(litellm, 'configured_cold_storage_logger', None): result5 = ResponsesSessionHandler._should_check_cold_storage_for_full_payload(proxy_request_with_truncated_pdf) assert result5 == False, "Should return False when cold storage is not configured, even with truncated content" + + +@pytest.mark.asyncio +async def test_get_chat_completion_message_history_empty_response_dict(): + """ + Test that empty response dict is handled correctly without processing. + This tests the fix for response validation to check for empty dict responses. + """ + from unittest.mock import AsyncMock, patch + + # Mock spend logs with empty response dict + mock_spend_logs = [ + { + "request_id": "chatcmpl-test-empty-response", + "call_type": "aresponses", + "api_key": "test_key", + "spend": 0.001, + "total_tokens": 0, + "prompt_tokens": 0, + "completion_tokens": 0, + "startTime": "2025-01-15T10:30:00.000+00:00", + "endTime": "2025-01-15T10:30:01.000+00:00", + "model": "gpt-4", + "session_id": "test-session", + "proxy_server_request": { + "input": "test input", + "model": "gpt-4" + }, + "response": {} # Empty dict - should not be processed + } + ] + + with patch.object(ResponsesSessionHandler, "get_all_spend_logs_for_previous_response_id") as mock_get_spend_logs: + mock_get_spend_logs.return_value = mock_spend_logs + + # Call the function + result = await ResponsesSessionHandler.get_chat_completion_message_history_for_previous_response_id( + "chatcmpl-test-empty-response" + ) + + # Verify that user message was added but no assistant response + # Since response is empty dict, no assistant response should be processed + # But user input from proxy_server_request should still be included + messages = result["messages"] + assert len(messages) == 1 # Only user message, no assistant response + assert messages[0]["role"] == "user" + assert messages[0]["content"] == "test input" + + # Verify the session was still created correctly + assert result["litellm_session_id"] == "test-session" From e694cc102a3f0050b2a0a7ea9da518d74b9cbe28 Mon Sep 17 00:00:00 2001 From: mubashir1osmani Date: Sun, 14 Sep 2025 14:42:26 -0400 Subject: [PATCH 06/34] feat: Add Spend metrics in datadog --- .../integrations/datadog/datadog_llm_obs.py | 21 +- litellm/types/integrations/datadog_llm_obs.py | 3 +- .../datadog/test_datadog_llm_observability.py | 357 ++++++++++++------ 3 files changed, 260 insertions(+), 121 deletions(-) diff --git a/litellm/integrations/datadog/datadog_llm_obs.py b/litellm/integrations/datadog/datadog_llm_obs.py index 457fafd75b..574079908b 100644 --- a/litellm/integrations/datadog/datadog_llm_obs.py +++ b/litellm/integrations/datadog/datadog_llm_obs.py @@ -148,10 +148,27 @@ class DataDogLLMObsLogger(DataDogLogger, CustomBatchLogger): ), ), } - verbose_logger.debug("payload %s", json.dumps(payload, indent=4)) + # serialize datetime objects - for budget reset time in spend metrics + import json + from datetime import datetime, date + + def custom_json_encoder(obj): + if isinstance(obj, (datetime, date)): + return obj.isoformat() + raise TypeError(f"Object of type {type(obj)} is not JSON serializable") + + # Serialize payload with custom encoder for debugging + try: + verbose_logger.debug("payload %s", json.dumps(payload, indent=4, default=custom_json_encoder)) + except Exception as debug_error: + verbose_logger.debug("payload serialization failed: %s", str(debug_error)) + + # Convert payload to JSON string with custom encoder for HTTP request + json_payload = json.dumps(payload, default=custom_json_encoder) + response = await self.async_client.post( url=self.intake_url, - json=payload, + content=json_payload, headers={ "DD-API-KEY": self.DD_API_KEY, "Content-Type": "application/json", diff --git a/litellm/types/integrations/datadog_llm_obs.py b/litellm/types/integrations/datadog_llm_obs.py index 8b94dd7b59..85110191d2 100644 --- a/litellm/types/integrations/datadog_llm_obs.py +++ b/litellm/types/integrations/datadog_llm_obs.py @@ -85,5 +85,4 @@ class DDLLMObsLatencyMetrics(TypedDict, total=False): class DDLLMObsSpendMetrics(TypedDict, total=False): litellm_spend_metric: float litellm_api_key_max_budget_metric: float - litellm_remaining_api_key_budget_metric: float - litellm_api_key_budget_remaining_hours_metric: float + litellm_api_key_budget_remaining_hours_metric: float \ No newline at end of file diff --git a/tests/test_litellm/integrations/datadog/test_datadog_llm_observability.py b/tests/test_litellm/integrations/datadog/test_datadog_llm_observability.py index f167eb24b2..853eff7e64 100644 --- a/tests/test_litellm/integrations/datadog/test_datadog_llm_observability.py +++ b/tests/test_litellm/integrations/datadog/test_datadog_llm_observability.py @@ -657,87 +657,6 @@ def test_guardrail_information_in_metadata(mock_env_vars): assert guardrail_info["guardrail_response"]["score"] == 0.1 -def create_standard_logging_payload_with_spend_metrics() -> StandardLoggingPayload: - """Create a StandardLoggingPayload object with spend metrics for testing""" - from datetime import datetime, timezone - - # Create a budget reset time 24 hours from now - budget_reset_at = datetime.now(timezone.utc) + timedelta(hours=24) - - return { - "id": "test-request-id-spend", - "trace_id": "test-trace-id-spend", - "call_type": "completion", - "stream": None, - "response_cost": 0.15, - "response_cost_failure_debug_info": None, - "status": "success", - "custom_llm_provider": "openai", - "total_tokens": 30, - "prompt_tokens": 10, - "completion_tokens": 20, - "startTime": 1234567890.0, - "endTime": 1234567891.0, - "completionStartTime": 1234567890.5, - "response_time": 1.0, - "model_map_information": { - "model_map_key": "gpt-4", - "model_map_value": None - }, - "model": "gpt-4", - "model_id": "model-123", - "model_group": "openai-gpt", - "api_base": "https://api.openai.com", - "metadata": { - "user_api_key_hash": "test_hash", - "user_api_key_org_id": None, - "user_api_key_alias": "test_alias", - "user_api_key_team_id": "test_team", - "user_api_key_user_id": "test_user", - "user_api_key_team_alias": "test_team_alias", - "user_api_key_user_email": None, - "user_api_key_end_user_id": None, - "user_api_key_request_route": None, - "user_api_key_max_budget": 10.0, # $10 max budget - "user_api_key_budget_reset_at": budget_reset_at.isoformat(), - "spend_logs_metadata": None, - "requester_ip_address": "127.0.0.1", - "requester_metadata": None, - "requester_custom_headers": None, - "prompt_management_metadata": None, - "mcp_tool_call_metadata": None, - "vector_store_request_metadata": None, - "applied_guardrails": None, - "usage_object": None, - "cold_storage_object_key": None, - }, - "cache_hit": False, - "cache_key": None, - "saved_cache_cost": 0.0, - "request_tags": [], - "end_user": None, - "requester_ip_address": "127.0.0.1", - "messages": [{"role": "user", "content": "Hello, world!"}], - "response": {"choices": [{"message": {"content": "Hi there!"}}]}, - "error_str": None, - "error_information": None, - "model_parameters": {"stream": False}, - "hidden_params": { - "model_id": "model-123", - "cache_key": None, - "api_base": "https://api.openai.com", - "response_cost": "0.15", - "litellm_overhead_time_ms": None, - "additional_headers": None, - "batch_models": None, - "litellm_model_name": None, - "usage_object": None, - }, - "guardrail_information": None, - "standard_built_in_tools_params": None, - } # type: ignore - - def create_standard_logging_payload_with_tool_calls() -> StandardLoggingPayload: """Create a StandardLoggingPayload object with tool calls for testing""" return { @@ -983,49 +902,253 @@ class TestDataDogLLMObsLoggerToolCalls: assert output_function_info.get("name") == "format_response" -def test_spend_metrics_in_datadog_payload(mock_env_vars): +def create_standard_logging_payload() -> StandardLoggingPayload: + """Create a standard logging payload for testing""" + return { + "id": "test_id", + "trace_id": "test_trace_id", + "call_type": "completion", + "stream": False, + "response_cost": 0.1, + "response_cost_failure_debug_info": None, + "status": "success", + "custom_llm_provider": None, + "total_tokens": 30, + "prompt_tokens": 20, + "completion_tokens": 10, + "startTime": 1234567890.0, + "endTime": 1234567891.0, + "completionStartTime": 1234567890.5, + "response_time": 1.0, + "model_map_information": { + "model_map_key": "gpt-3.5-turbo", + "model_map_value": None + }, + "model": "gpt-3.5-turbo", + "model_id": "model-123", + "model_group": "openai-gpt", + "api_base": "https://api.openai.com", + "metadata": { + "user_api_key_hash": "test_hash", + "user_api_key_org_id": None, + "user_api_key_alias": "test_alias", + "user_api_key_team_id": "test_team", + "user_api_key_user_id": "test_user", + "user_api_key_team_alias": "test_team_alias", + "user_api_key_end_user_id": None, + "user_api_key_request_route": None, + "user_api_key_max_budget": None, + "user_api_key_budget_reset_at": None, + "user_api_key_user_email": None, + "spend_logs_metadata": None, + "requester_ip_address": "127.0.0.1", + "requester_metadata": None, + "requester_custom_headers": None, + "prompt_management_metadata": None, + "mcp_tool_call_metadata": None, + "vector_store_request_metadata": None, + "applied_guardrails": None, + "usage_object": None, + "cold_storage_object_key": None, + }, + "cache_hit": False, + "cache_key": None, + "saved_cache_cost": 0.0, + "request_tags": [], + "end_user": None, + "requester_ip_address": "127.0.0.1", + "messages": [{"role": "user", "content": "Hello, world!"}], + "response": {"choices": [{"message": {"content": "Hi there!"}}]}, + "error_str": None, + "model_parameters": {"stream": True}, + "hidden_params": { + "model_id": "model-123", + "cache_key": None, + "api_base": "https://api.openai.com", + "response_cost": "0.1", + "additional_headers": None, + "litellm_overhead_time_ms": None, + "batch_models": None, + "litellm_model_name": None, + "usage_object": None, + }, + "error_information": None, + "guardrail_information": None, + "standard_built_in_tools_params": None, + } # type: ignore + + +def create_standard_logging_payload_with_spend_metrics() -> StandardLoggingPayload: + """Create a StandardLoggingPayload object with spend metrics for testing""" + from datetime import datetime, timezone + + # Create a budget reset time 24 hours from now + budget_reset_at = datetime.now(timezone.utc) + timedelta(hours=24) + + return { + "id": "test-request-id-spend", + "trace_id": "test-trace-id-spend", + "call_type": "completion", + "stream": None, + "response_cost": 0.15, + "response_cost_failure_debug_info": None, + "status": "success", + "custom_llm_provider": "openai", + "total_tokens": 30, + "prompt_tokens": 10, + "completion_tokens": 20, + "startTime": 1234567890.0, + "endTime": 1234567891.0, + "completionStartTime": 1234567890.5, + "response_time": 1.0, + "model_map_information": { + "model_map_key": "gpt-4", + "model_map_value": None + }, + "model": "gpt-4", + "model_id": "model-123", + "model_group": "openai-gpt", + "api_base": "https://api.openai.com", + "metadata": { + "user_api_key_hash": "test_hash", + "user_api_key_org_id": None, + "user_api_key_alias": "test_alias", + "user_api_key_team_id": "test_team", + "user_api_key_user_id": "test_user", + "user_api_key_team_alias": "test_team_alias", + "user_api_key_user_email": None, + "user_api_key_end_user_id": None, + "user_api_key_request_route": None, + "user_api_key_max_budget": 10.0, # $10 max budget + "user_api_key_budget_reset_at": budget_reset_at.isoformat(), + "spend_logs_metadata": None, + "requester_ip_address": "127.0.0.1", + "requester_metadata": None, + "requester_custom_headers": None, + "prompt_management_metadata": None, + "mcp_tool_call_metadata": None, + "vector_store_request_metadata": None, + "applied_guardrails": None, + "usage_object": None, + "cold_storage_object_key": None, + }, + "cache_hit": False, + "cache_key": None, + "saved_cache_cost": 0.0, + "request_tags": [], + "end_user": None, + "requester_ip_address": "127.0.0.1", + "messages": [{"role": "user", "content": "Hello, world!"}], + "response": {"choices": [{"message": {"content": "Hi there!"}}]}, + "error_str": None, + "error_information": None, + "model_parameters": {"stream": False}, + "hidden_params": { + "model_id": "model-123", + "cache_key": None, + "api_base": "https://api.openai.com", + "response_cost": "0.15", + "litellm_overhead_time_ms": None, + "additional_headers": None, + "batch_models": None, + "litellm_model_name": None, + "usage_object": None, + }, + "guardrail_information": None, + "standard_built_in_tools_params": None, + } # type: ignore + + +@pytest.mark.asyncio +async def test_datadog_llm_obs_spend_metrics(): + """Test that budget metrics are properly extracted and logged""" + datadog_llm_obs_logger = DataDogLLMObsLogger() + + # Create a standard logging payload with budget metadata + payload = create_standard_logging_payload() + + # Add budget information to metadata + payload["metadata"]["user_api_key_max_budget"] = 10.0 + payload["metadata"]["user_api_key_budget_reset_at"] = "2025-09-15T00:00:00+00:00" + + # Test the _get_spend_metrics method + spend_metrics = datadog_llm_obs_logger._get_spend_metrics(payload) + + # Verify budget metrics are present + assert "litellm_api_key_max_budget_metric" in spend_metrics + assert spend_metrics["litellm_api_key_max_budget_metric"] == 10.0 + + assert "litellm_api_key_budget_remaining_hours_metric" in spend_metrics + # The remaining hours should be calculated based on the reset time + assert spend_metrics["litellm_api_key_budget_remaining_hours_metric"] >= 0 + + print(f"Spend metrics: {spend_metrics}") + + +@pytest.mark.asyncio +async def test_datadog_llm_obs_spend_metrics_no_budget(): + """Test that spend metrics work when no budget is set""" + datadog_llm_obs_logger = DataDogLLMObsLogger() + + # Create a standard logging payload without budget metadata + payload = create_standard_logging_payload() + + # Test the _get_spend_metrics method + spend_metrics = datadog_llm_obs_logger._get_spend_metrics(payload) + + # Verify only response cost is present + assert "litellm_spend_metric" in spend_metrics + assert spend_metrics["litellm_spend_metric"] == 0.1 + + # Budget metrics should not be present + assert "litellm_api_key_max_budget_metric" not in spend_metrics + assert "litellm_api_key_budget_remaining_hours_metric" not in spend_metrics + + print(f"Spend metrics (no budget): {spend_metrics}") + + +@pytest.mark.asyncio +async def test_spend_metrics_in_datadog_payload(): """Test that spend metrics are correctly included in DataDog LLM Observability payloads""" - with patch( - "litellm.integrations.datadog.datadog_llm_obs.get_async_httpx_client" - ), patch("asyncio.create_task"): - logger = DataDogLLMObsLogger() + datadog_llm_obs_logger = DataDogLLMObsLogger() - standard_payload = create_standard_logging_payload_with_spend_metrics() + standard_payload = create_standard_logging_payload_with_spend_metrics() - kwargs = { - "standard_logging_object": standard_payload, - "litellm_params": {"metadata": {}}, - } + kwargs = { + "standard_logging_object": standard_payload, + "litellm_params": {"metadata": {}}, + } - start_time = datetime.now() - end_time = datetime.now() + start_time = datetime.now() + end_time = datetime.now() - payload = logger.create_llm_obs_payload(kwargs, start_time, end_time) + payload = datadog_llm_obs_logger.create_llm_obs_payload(kwargs, start_time, end_time) - # Verify basic payload structure - assert payload.get("name") == "litellm_llm_call" - assert payload.get("status") == "ok" + # Verify basic payload structure + assert payload.get("name") == "litellm_llm_call" + assert payload.get("status") == "ok" - # Verify spend metrics are included in metadata - meta = payload.get("meta", {}) - assert meta is not None, "Meta section should exist in payload" - - metadata = meta.get("metadata", {}) - assert metadata is not None, "Metadata section should exist in meta" - - spend_metrics = metadata.get("spend_metrics", {}) - assert spend_metrics, "Spend metrics should exist in metadata" + # Verify spend metrics are included in metadata + meta = payload.get("meta", {}) + assert meta is not None, "Meta section should exist in payload" - # Check that all three spend metrics are present - assert "litellm_spend_metric" in spend_metrics - assert "litellm_api_key_max_budget_metric" in spend_metrics - assert "litellm_api_key_budget_remaining_hours_metric" in spend_metrics + metadata = meta.get("metadata", {}) + assert metadata is not None, "Metadata section should exist in meta" - # Verify the values are correct - assert spend_metrics["litellm_spend_metric"] == 0.15 # response_cost - assert spend_metrics["litellm_api_key_max_budget_metric"] == 10.0 # max budget + spend_metrics = metadata.get("spend_metrics", {}) + assert spend_metrics, "Spend metrics should exist in metadata" + + # Check that all three spend metrics are present + assert "litellm_spend_metric" in spend_metrics + assert "litellm_api_key_max_budget_metric" in spend_metrics + assert "litellm_api_key_budget_remaining_hours_metric" in spend_metrics + + # Verify the values are correct + assert spend_metrics["litellm_spend_metric"] == 0.15 # response_cost + assert spend_metrics["litellm_api_key_max_budget_metric"] == 10.0 # max budget + + # Verify remaining hours is a reasonable value (should be close to 24 since we set it to 24 hours from now) + remaining_hours = spend_metrics["litellm_api_key_budget_remaining_hours_metric"] + assert isinstance(remaining_hours, (int, float)) + assert 20 <= remaining_hours <= 25 # Should be close to 24 hours - # Verify remaining hours is a reasonable value (should be close to 24 since we set it to 24 hours from now) - remaining_hours = spend_metrics["litellm_api_key_budget_remaining_hours_metric"] - assert isinstance(remaining_hours, (int, float)) - assert 20 <= remaining_hours <= 25 # Should be close to 24 hours From e123cae06e32e6d003c0e827b5620bc7710c8fdb Mon Sep 17 00:00:00 2001 From: mubashir1osmani Date: Sun, 14 Sep 2025 14:55:47 -0400 Subject: [PATCH 07/34] fix: lint errors --- litellm/integrations/datadog/datadog_llm_obs.py | 15 +++++++++++++-- 1 file changed, 13 insertions(+), 2 deletions(-) diff --git a/litellm/integrations/datadog/datadog_llm_obs.py b/litellm/integrations/datadog/datadog_llm_obs.py index 574079908b..f7a48e8704 100644 --- a/litellm/integrations/datadog/datadog_llm_obs.py +++ b/litellm/integrations/datadog/datadog_llm_obs.py @@ -585,18 +585,29 @@ class DataDogLLMObsLogger(DataDogLogger, CustomBatchLogger): # API key max budget user_api_key_max_budget = metadata.get("user_api_key_max_budget") if user_api_key_max_budget is not None: - spend_metrics["litellm_api_key_max_budget_metric"] = user_api_key_max_budget + # type casting to make sure its a float value + try: + if isinstance(user_api_key_max_budget, (int, float)): + spend_metrics["litellm_api_key_max_budget_metric"] = float(user_api_key_max_budget) + elif isinstance(user_api_key_max_budget, str): + spend_metrics["litellm_api_key_max_budget_metric"] = float(user_api_key_max_budget) + except (ValueError, TypeError): + verbose_logger.debug(f"Invalid user_api_key_max_budget value: {user_api_key_max_budget}") # API key budget remaining hours user_api_key_budget_reset_at = metadata.get("user_api_key_budget_reset_at") if user_api_key_budget_reset_at is not None: try: from datetime import datetime + budget_reset_at: datetime if isinstance(user_api_key_budget_reset_at, str): # Parse ISO string if it's a string budget_reset_at = datetime.fromisoformat(user_api_key_budget_reset_at.replace('Z', '+00:00')) - else: + elif isinstance(user_api_key_budget_reset_at, datetime): budget_reset_at = user_api_key_budget_reset_at + else: + verbose_logger.debug(f"Invalid user_api_key_budget_reset_at type: {type(user_api_key_budget_reset_at)}") + return spend_metrics remaining_hours = ( budget_reset_at - datetime.now(budget_reset_at.tzinfo) From 1585f5b9209f2358146f646d8f167e507b6e0934 Mon Sep 17 00:00:00 2001 From: soojin Date: Mon, 15 Sep 2025 09:09:28 +0900 Subject: [PATCH 08/34] fix: add exception handling for logger retrieval in cold storage object key generation - Wrap get_active_custom_logger_for_callback_name call in try-except block - Gracefully handle cases where logger instance cannot be retrieved - Fall back to empty s3_path when logger lookup fails - Prevents crashes when cold storage logger is misconfigured or unavailable --- litellm/litellm_core_utils/litellm_logging.py | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) diff --git a/litellm/litellm_core_utils/litellm_logging.py b/litellm/litellm_core_utils/litellm_logging.py index 07cb1d8662..ca8a193164 100644 --- a/litellm/litellm_core_utils/litellm_logging.py +++ b/litellm/litellm_core_utils/litellm_logging.py @@ -4161,10 +4161,14 @@ class StandardLoggingPayloadSetup: # Get the actual s3_path from the configured cold storage logger instance s3_path = "" # default value - # Get the actual logger instance from the logger name - custom_logger = litellm.logging_callback_manager.get_active_custom_logger_for_callback_name(configured_cold_storage_logger) - if custom_logger and hasattr(custom_logger, 's3_path') and custom_logger.s3_path: - s3_path = custom_logger.s3_path + # Try to get the actual logger instance from the logger name + try: + custom_logger = litellm.logging_callback_manager.get_active_custom_logger_for_callback_name(configured_cold_storage_logger) + if custom_logger and hasattr(custom_logger, 's3_path') and custom_logger.s3_path: + s3_path = custom_logger.s3_path + except Exception: + # If any error occurs in getting the logger instance, use default empty s3_path + pass s3_object_key = get_s3_object_key( s3_path=s3_path, # Use actual s3_path from logger configuration From f5f00043cebf3d56f58218eb35df7594a48065b5 Mon Sep 17 00:00:00 2001 From: mubashir1osmani Date: Tue, 16 Sep 2025 00:14:48 -0400 Subject: [PATCH 09/34] fixed tests --- .../integrations/datadog/test_datadog_llm_observability.py | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/tests/test_litellm/integrations/datadog/test_datadog_llm_observability.py b/tests/test_litellm/integrations/datadog/test_datadog_llm_observability.py index 853eff7e64..08ee29bb60 100644 --- a/tests/test_litellm/integrations/datadog/test_datadog_llm_observability.py +++ b/tests/test_litellm/integrations/datadog/test_datadog_llm_observability.py @@ -1060,7 +1060,7 @@ def create_standard_logging_payload_with_spend_metrics() -> StandardLoggingPaylo @pytest.mark.asyncio -async def test_datadog_llm_obs_spend_metrics(): +async def test_datadog_llm_obs_spend_metrics(mock_env_vars): """Test that budget metrics are properly extracted and logged""" datadog_llm_obs_logger = DataDogLLMObsLogger() @@ -1086,7 +1086,7 @@ async def test_datadog_llm_obs_spend_metrics(): @pytest.mark.asyncio -async def test_datadog_llm_obs_spend_metrics_no_budget(): +async def test_datadog_llm_obs_spend_metrics_no_budget(mock_env_vars): """Test that spend metrics work when no budget is set""" datadog_llm_obs_logger = DataDogLLMObsLogger() @@ -1108,7 +1108,7 @@ async def test_datadog_llm_obs_spend_metrics_no_budget(): @pytest.mark.asyncio -async def test_spend_metrics_in_datadog_payload(): +async def test_spend_metrics_in_datadog_payload(mock_env_vars): """Test that spend metrics are correctly included in DataDog LLM Observability payloads""" datadog_llm_obs_logger = DataDogLLMObsLogger() From a2d5bde83745093f27ebf2591eb6ee09ae619909 Mon Sep 17 00:00:00 2001 From: mubashir1osmani Date: Tue, 16 Sep 2025 00:58:08 -0400 Subject: [PATCH 10/34] changed docs --- .../observability/helicone_integration.md | 275 +++++++++++++++--- docs/my-website/docs/proxy/config_settings.md | 31 ++ docs/my-website/docs/proxy/logging_spec.md | 83 ++++++ docs/my-website/docs/troubleshoot.md | 2 +- 4 files changed, 343 insertions(+), 48 deletions(-) diff --git a/docs/my-website/docs/observability/helicone_integration.md b/docs/my-website/docs/observability/helicone_integration.md index 9b807b8d0f..27e972ddeb 100644 --- a/docs/my-website/docs/observability/helicone_integration.md +++ b/docs/my-website/docs/observability/helicone_integration.md @@ -1,3 +1,6 @@ +import Tabs from '@theme/Tabs'; +import TabItem from '@theme/TabItem'; + # Helicone - OSS LLM Observability Platform :::tip @@ -9,9 +12,68 @@ https://github.com/BerriAI/litellm [Helicone](https://helicone.ai/) is an open source observability platform that proxies your LLM requests and provides key insights into your usage, spend, latency and more. -## Using Helicone with LiteLLM +## Quick Start -LiteLLM provides `success_callbacks` and `failure_callbacks`, allowing you to easily log data to Helicone based on the status of your responses. + + + +Use just 1 line of code to instantly log your responses **across all providers** with Helicone: + +```python +import os +from litellm import completion + +## Set env variables +os.environ["HELICONE_API_KEY"] = "your-helicone-key" +os.environ["OPENAI_API_KEY"] = "your-openai-key" + +# Set callbacks +litellm.success_callback = ["helicone"] + +# OpenAI call +response = completion( + model="gpt-4o", + messages=[{"role": "user", "content": "Hi 👋 - I'm OpenAI"}], +) + +print(response) +``` + + + + +Add Helicone to your LiteLLM proxy configuration: + +```yaml title="config.yaml" +model_list: + - model_name: gpt-4 + litellm_params: + model: gpt-4 + api_key: os.environ/OPENAI_API_KEY + +# Add Helicone callback +litellm_settings: + success_callback: ["helicone"] + +# Set Helicone API key +environment_variables: + HELICONE_API_KEY: "your-helicone-key" +``` + +Start the proxy: +```bash +litellm --config config.yaml +``` + + + + +## Integration Methods + +There are two main approaches to integrate Helicone with LiteLLM: + +1. **Callbacks**: Log to Helicone while using any provider +2. **Proxy Mode**: Use Helicone as a proxy for advanced features ### Supported LLM Providers @@ -26,27 +88,16 @@ Helicone can log requests across [various LLM providers](https://docs.helicone.a - Replicate - And more -### Integration Methods +## Method 1: Using Callbacks -There are two main approaches to integrate Helicone with LiteLLM: +Log requests to Helicone while using any LLM provider directly. -1. Using callbacks -2. Using Helicone as a proxy - -Let's explore each method in detail. - -### Approach 1: Use Callbacks - -Use just 1 line of code to instantly log your responses **across all providers** with Helicone: - -```python -litellm.success_callback = ["helicone"] -``` - -Complete Code + + ```python import os +import litellm from litellm import completion ## Set env variables @@ -66,28 +117,78 @@ response = completion( print(response) ``` -### Approach 2: Use Helicone as a proxy + + + +```yaml title="config.yaml" +model_list: + - model_name: gpt-4 + litellm_params: + model: gpt-4 + api_key: os.environ/OPENAI_API_KEY + - model_name: claude-3 + litellm_params: + model: anthropic/claude-3-sonnet-20240229 + api_key: os.environ/ANTHROPIC_API_KEY + +# Add Helicone logging +litellm_settings: + success_callback: ["helicone"] + +# Environment variables +environment_variables: + HELICONE_API_KEY: "your-helicone-key" + OPENAI_API_KEY: "your-openai-key" + ANTHROPIC_API_KEY: "your-anthropic-key" +``` + +Start the proxy: +```bash +litellm --config config.yaml +``` + +Make requests to your proxy: +```python +import openai + +client = openai.OpenAI( + api_key="anything", # proxy doesn't require real API key + base_url="http://localhost:4000" +) + +response = client.chat.completions.create( + model="gpt-4", # This gets logged to Helicone + messages=[{"role": "user", "content": "Hello!"}] +) +``` + + + + +## Method 2: Using Helicone as a Proxy Helicone's proxy provides [advanced functionality](https://docs.helicone.ai/getting-started/proxy-vs-async) like caching, rate limiting, LLM security through [PromptArmor](https://promptarmor.com/) and more. -To use Helicone as a proxy for your LLM requests: + + -1. Set Helicone as your base URL via: litellm.api_base -2. Pass in Helicone request headers via: litellm.metadata - -Complete Code: +Set Helicone as your base URL and pass authentication headers: ```python import os import litellm from litellm import completion +# Configure LiteLLM to use Helicone proxy litellm.api_base = "https://oai.hconeai.com/v1" litellm.headers = { - "Helicone-Auth": f"Bearer {os.getenv('HELICONE_API_KEY')}", # Authenticate to send requests to Helicone API + "Helicone-Auth": f"Bearer {os.getenv('HELICONE_API_KEY')}", } -response = litellm.completion( +# Set your OpenAI API key +os.environ["OPENAI_API_KEY"] = "your-openai-key" + +response = completion( model="gpt-3.5-turbo", messages=[{"role": "user", "content": "How does a court case get to the Supreme Court?"}] ) @@ -140,32 +241,112 @@ litellm.metadata = { Track multi-step and agentic LLM interactions using session IDs and paths: -```python -litellm.metadata = { - "Helicone-Auth": f"Bearer {os.getenv('HELICONE_API_KEY')}", # Authenticate to send requests to Helicone API - "Helicone-Session-Id": "session-abc-123", # The session ID you want to track - "Helicone-Session-Path": "parent-trace/child-trace", # The path of the session -} -``` - -- `Helicone-Session-Id`: Use this to specify the unique identifier for the session you want to track. This allows you to group related requests together. -- `Helicone-Session-Path`: This header defines the path of the session, allowing you to represent parent and child traces. For example, "parent/child" represents a child trace of a parent trace. - -By using these two headers, you can effectively group and visualize multi-step LLM interactions, gaining insights into complex AI workflows. - -### Retry and Fallback Mechanisms - -Set up retry mechanisms and fallback options: + + ```python +import litellm + +litellm.api_base = "https://oai.hconeai.com/v1" litellm.metadata = { - "Helicone-Auth": f"Bearer {os.getenv('HELICONE_API_KEY')}", # Authenticate to send requests to Helicone API - "Helicone-Retry-Enabled": "true", # Enable retry mechanism - "helicone-retry-num": "3", # Set number of retries - "helicone-retry-factor": "2", # Set exponential backoff factor - "Helicone-Fallbacks": '["gpt-3.5-turbo", "gpt-4"]', # Set fallback models + "Helicone-Auth": f"Bearer {os.getenv('HELICONE_API_KEY')}", + "Helicone-Session-Id": "session-abc-123", + "Helicone-Session-Path": "parent-trace/child-trace", } + +response = litellm.completion( + model="gpt-3.5-turbo", + messages=[{"role": "user", "content": "Start a conversation"}] +) ``` + + + +```python +import openai + +client = openai.OpenAI( + api_key="anything", + base_url="http://localhost:4000" +) + +# First request in session +response1 = client.chat.completions.create( + model="gpt-4", + messages=[{"role": "user", "content": "Hello"}], + extra_headers={ + "Helicone-Session-Id": "session-abc-123", + "Helicone-Session-Path": "conversation/greeting" + } +) + +# Follow-up request in same session +response2 = client.chat.completions.create( + model="gpt-4", + messages=[{"role": "user", "content": "Tell me more"}], + extra_headers={ + "Helicone-Session-Id": "session-abc-123", + "Helicone-Session-Path": "conversation/follow-up" + } +) +``` + + + + +- `Helicone-Session-Id`: Unique identifier for the session to group related requests +- `Helicone-Session-Path`: Hierarchical path to represent parent/child traces (e.g., "parent/child") + +## Retry and Fallback Mechanisms + + + + +```python +import litellm + +litellm.api_base = "https://oai.hconeai.com/v1" +litellm.metadata = { + "Helicone-Auth": f"Bearer {os.getenv('HELICONE_API_KEY')}", + "Helicone-Retry-Enabled": "true", + "helicone-retry-num": "3", + "helicone-retry-factor": "2", # Exponential backoff + "Helicone-Fallbacks": '["gpt-3.5-turbo", "gpt-4"]', +} + +response = litellm.completion( + model="gpt-4", + messages=[{"role": "user", "content": "Hello"}] +) +``` + + + + +```yaml title="config.yaml" +model_list: + - model_name: gpt-4 + litellm_params: + model: gpt-4 + api_key: os.environ/OPENAI_API_KEY + api_base: "https://oai.hconeai.com/v1" + +default_litellm_params: + headers: + Helicone-Auth: "Bearer ${HELICONE_API_KEY}" + Helicone-Retry-Enabled: "true" + helicone-retry-num: "3" + helicone-retry-factor: "2" + Helicone-Fallbacks: '["gpt-3.5-turbo", "gpt-4"]' + +environment_variables: + HELICONE_API_KEY: "your-helicone-key" + OPENAI_API_KEY: "your-openai-key" +``` + + + + > **Supported Headers** - For a full list of supported Helicone headers and their descriptions, please refer to the [Helicone documentation](https://docs.helicone.ai/getting-started/quick-start). > By utilizing these headers and metadata options, you can gain deeper insights into your LLM usage, optimize performance, and better manage your AI workflows with Helicone and LiteLLM. diff --git a/docs/my-website/docs/proxy/config_settings.md b/docs/my-website/docs/proxy/config_settings.md index e33301bcd2..ad090fe098 100644 --- a/docs/my-website/docs/proxy/config_settings.md +++ b/docs/my-website/docs/proxy/config_settings.md @@ -93,6 +93,8 @@ callback_settings: general_settings: completion_model: string + store_prompts_in_spend_logs: boolean + forward_client_headers_to_llm_api: boolean disable_spend_logs: boolean # turn off writing each transaction to the db disable_master_key_return: boolean # turn off returning master key on UI (checked on '/user/info' endpoint) disable_retry_on_max_parallel_request_limit_error: boolean # turn off retries when max parallel request limit is reached @@ -121,6 +123,35 @@ general_settings: alerting: ["slack", "email"] alerting_threshold: 0 use_client_credentials_pass_through_routes: boolean # use client credentials for all pass through routes like "/vertex-ai", /bedrock/. When this is True Virtual Key auth will not be applied on these endpoints + +router_settings: + routing_strategy: simple-shuffle # Literal["simple-shuffle", "least-busy", "usage-based-routing","latency-based-routing"], default="simple-shuffle" - RECOMMENDED for best performance + redis_host: # string + redis_password: # string + redis_port: # string + enable_pre_call_checks: true # bool - Before call is made check if a call is within model context window + allowed_fails: 3 # cooldown model if it fails > 1 call in a minute. + cooldown_time: 30 # (in seconds) how long to cooldown model if fails/min > allowed_fails + disable_cooldowns: True # bool - Disable cooldowns for all models + enable_tag_filtering: True # bool - Use tag based routing for requests + retry_policy: { # Dict[str, int]: retry policy for different types of exceptions + "AuthenticationErrorRetries": 3, + "TimeoutErrorRetries": 3, + "RateLimitErrorRetries": 3, + "ContentPolicyViolationErrorRetries": 4, + "InternalServerErrorRetries": 4 + } + allowed_fails_policy: { + "BadRequestErrorAllowedFails": 1000, # Allow 1000 BadRequestErrors before cooling down a deployment + "AuthenticationErrorAllowedFails": 10, # int + "TimeoutErrorAllowedFails": 12, # int + "RateLimitErrorAllowedFails": 10000, # int + "ContentPolicyViolationErrorAllowedFails": 15, # int + "InternalServerErrorAllowedFails": 20, # int + } + content_policy_fallbacks=[{"claude-2": ["my-fallback-model"]}] # List[Dict[str, List[str]]]: Fallback model for content policy violations + fallbacks=[{"claude-2": ["my-fallback-model"]}] # List[Dict[str, List[str]]]: Fallback model for all errors + ``` ### litellm_settings - Reference diff --git a/docs/my-website/docs/proxy/logging_spec.md b/docs/my-website/docs/proxy/logging_spec.md index a39a62318e..5166b86ae1 100644 --- a/docs/my-website/docs/proxy/logging_spec.md +++ b/docs/my-website/docs/proxy/logging_spec.md @@ -61,6 +61,11 @@ Inherits from `StandardLoggingUserAPIKeyMetadata` and adds: | `requester_metadata` | `Optional[dict]` | Additional requester metadata | | `vector_store_request_metadata` | `Optional[List[StandardLoggingVectorStoreRequest]]` | Vector store request metadata | | `requester_custom_headers` | Dict[str, str] | Any custom (`x-`) headers sent by the client to the proxy. | +| `prompt_management_metadata` | `Optional[StandardLoggingPromptManagementMetadata]` | Prompt management and versioning metadata | +| `mcp_tool_call_metadata` | `Optional[StandardLoggingMCPToolCall]` | MCP (Model Context Protocol) tool call information and cost tracking | +| `applied_guardrails` | `Optional[List[str]]` | List of applied guardrail names | +| `usage_object` | `Optional[dict]` | Raw usage object from the LLM provider | +| `cold_storage_object_key` | `Optional[str]` | S3/GCS object key for cold storage retrieval | | `guardrail_information` | `Optional[StandardLoggingGuardrailInformation]` | Guardrail information | @@ -145,4 +150,82 @@ A literal type with two possible values: | `duration` | `Optional[float]` | Duration of the guardrail in seconds | | `masked_entity_count` | `Optional[Dict[str, int]]` | Count of masked entities | +## StandardLoggingPromptManagementMetadata +Used for tracking prompt versioning and management information. + +| Field | Type | Description | +|-------|------|-------------| +| `prompt_id` | `str` | **Required**. Unique identifier for the prompt template or version | +| `prompt_variables` | `Optional[dict]` | Variables/parameters used in the prompt template (e.g., `{"user_name": "John", "context": "support"}`) | +| `prompt_integration` | `str` | **Required**. Integration or system managing the prompt (e.g., `"langfuse"`, `"promptlayer"`, `"custom"`) | + +## StandardLoggingMCPToolCall + +Used to track Model Context Protocol (MCP) tool calls within LiteLLM requests. This provides detailed logging for external tool integrations. + +| Field | Type | Description | +|-------|------|-------------| +| `name` | `str` | **Required**. The name of the tool being called (e.g., `"get_weather"`, `"search_database"`) | +| `arguments` | `dict` | **Required**. Arguments passed to the tool as key-value pairs | +| `result` | `Optional[dict]` | The response/result returned by the tool execution (populated by custom logging hooks) | +| `mcp_server_name` | `Optional[str]` | Name of the MCP server that handled the tool call (e.g., `"weather-service"`, `"database-connector"`) | +| `mcp_server_logo_url` | `Optional[str]` | URL for the MCP server's logo (used for UI display in LiteLLM dashboard) | +| `namespaced_tool_name` | `Optional[str]` | Fully qualified tool name including server prefix (e.g., `"deepwiki-mcp/get_page_content"`, `"github-mcp/create_issue"`) | +| `mcp_server_cost_info` | `Optional[MCPServerCostInfo]` | Cost tracking information for the tool call | + +### MCPServerCostInfo + +Cost tracking structure for MCP server tool calls: + +| Field | Type | Description | +|-------|------|-------------| +| `default_cost_per_query` | `Optional[float]` | Default cost in USD for any tool call to this MCP server | +| `tool_name_to_cost_per_query` | `Optional[Dict[str, float]]` | Per-tool cost mapping for granular pricing (e.g., `{"search": 0.01, "create": 0.05}`) | + +### Usage + +```python +# Basic MCP tool call metadata +mcp_tool_call = { + "name": "search_documents", + "arguments": { + "query": "machine learning tutorials", + "limit": 10, + "filter": "type:pdf" + }, + "mcp_server_name": "document-search-service", + "namespaced_tool_name": "docs-mcp/search_documents", + "mcp_server_cost_info": { + "default_cost_per_query": 0.02, + "tool_name_to_cost_per_query": { + "search_documents": 0.02, + "get_document": 0.01 + } + } +} + +# optional result field (via custom logging hooks) +mcp_tool_call_with_result = { + "name": "search_documents", + "arguments": { + "query": "machine learning tutorials", + "limit": 10, + "filter": "type:pdf" + }, + "result": { + "documents": [...], + "total_found": 42, + "search_time_ms": 150 + }, + "mcp_server_name": "document-search-service", + "namespaced_tool_name": "docs-mcp/search_documents", + "mcp_server_cost_info": { + "default_cost_per_query": 0.02, + "tool_name_to_cost_per_query": { + "search_documents": 0.02, + "get_document": 0.01 + } + } +} +``` \ No newline at end of file diff --git a/docs/my-website/docs/troubleshoot.md b/docs/my-website/docs/troubleshoot.md index b6a9c6a6b9..9d2b3757ee 100644 --- a/docs/my-website/docs/troubleshoot.md +++ b/docs/my-website/docs/troubleshoot.md @@ -2,7 +2,7 @@ [Schedule Demo 👋](https://calendly.com/d/4mp-gd3-k5k/berriai-1-1-onboarding-litellm-hosted-version) [Community Discord 💭](https://discord.gg/wuPM9dRgDw) -[Community Slack 💭](https://join.slack.com/share/enQtOTE0ODczMzk2Nzk4NC01YjUxNjY2YjBlYTFmNDRiZTM3NDFiYTM3MzVkODFiMDVjOGRjMmNmZTZkZTMzOWQzZGQyZWIwYjQ0MWExYmE3) +[Community Slack 💭](https://litellmossslack.slack.com/) Our numbers 📞 +1 (770) 8783-106 / ‭+1 (412) 618-6238‬ From f08fc45a0fbcf871ae2f37a6de0d74262b2031d0 Mon Sep 17 00:00:00 2001 From: Sameerlite Date: Tue, 16 Sep 2025 15:15:24 +0530 Subject: [PATCH 11/34] add base url support for gemini --- litellm/llms/vertex_ai/vertex_llm_base.py | 5 +- .../test_google_gemini_proxy_request.py | 124 +++++++++++++ .../llms/vertex_ai/test_vertex_llm_base.py | 174 ++++++++++++++++++ 3 files changed, 302 insertions(+), 1 deletion(-) diff --git a/litellm/llms/vertex_ai/vertex_llm_base.py b/litellm/llms/vertex_ai/vertex_llm_base.py index 76998e7669..f89ee92294 100644 --- a/litellm/llms/vertex_ai/vertex_llm_base.py +++ b/litellm/llms/vertex_ai/vertex_llm_base.py @@ -292,6 +292,7 @@ class VertexBase: stream: Optional[bool], auth_header: Optional[str], url: str, + model: str, ) -> Tuple[Optional[str], str]: """ for cloudflare ai gateway - https://github.com/BerriAI/litellm/issues/4317 @@ -301,7 +302,8 @@ class VertexBase: """ if api_base: if custom_llm_provider == "gemini": - url = "{}:{}".format(api_base, endpoint) + # For Gemini (Google AI Studio), construct the full path like other providers + url = "{}/models/{}:{}".format(api_base, model, endpoint) if gemini_api_key is None: raise ValueError( "Missing gemini_api_key, please set `GEMINI_API_KEY`" @@ -373,6 +375,7 @@ class VertexBase: endpoint=endpoint, stream=stream, url=url, + model=model, ) def _handle_reauthentication( diff --git a/tests/proxy_unit_tests/test_google_gemini_proxy_request.py b/tests/proxy_unit_tests/test_google_gemini_proxy_request.py index a8c6741940..388dd4ab17 100644 --- a/tests/proxy_unit_tests/test_google_gemini_proxy_request.py +++ b/tests/proxy_unit_tests/test_google_gemini_proxy_request.py @@ -345,6 +345,130 @@ async def test_generationconfig_to_config_mapping(sample_request_payload): print("✅ generationConfig to config mapping test passed") +@pytest.mark.asyncio +async def test_gemini_custom_api_base_proxy_integration(): + """ + Test that Gemini models work correctly with custom API base URLs in proxy context. + + This test verifies that when a custom api_base is provided for Gemini models, + the URL is correctly constructed using the _check_custom_proxy method. + """ + from litellm.llms.vertex_ai.vertex_llm_base import VertexBase + + # Test the _check_custom_proxy method directly + vertex_base = VertexBase() + + # Test case 1: Custom API base for Gemini + custom_api_base = "https://proxy.zapier.com/generativelanguage.googleapis.com/v1beta" + model = "gemini-2.5-flash-lite" + endpoint = "generateContent" + + auth_header, result_url = vertex_base._check_custom_proxy( + api_base=custom_api_base, + custom_llm_provider="gemini", + gemini_api_key="test-api-key", + endpoint=endpoint, + stream=False, + auth_header=None, + url=f"https://generativelanguage.googleapis.com/v1beta/models/{model}:{endpoint}", + model=model, + ) + + # Verify the URL is correctly constructed + expected_url = f"{custom_api_base}/models/{model}:{endpoint}" + assert result_url == expected_url, f"Expected {expected_url}, got {result_url}" + + # Verify the auth header is set to the API key + assert auth_header == "test-api-key", f"Expected 'test-api-key', got {auth_header}" + + print(f"✅ Custom API base URL construction test passed: {result_url}") + + # Test case 2: Custom API base with streaming + auth_header_streaming, result_url_streaming = vertex_base._check_custom_proxy( + api_base=custom_api_base, + custom_llm_provider="gemini", + gemini_api_key="test-api-key", + endpoint=endpoint, + stream=True, + auth_header=None, + url=f"https://generativelanguage.googleapis.com/v1beta/models/{model}:{endpoint}", + model=model, + ) + + # Verify streaming URL has ?alt=sse parameter + expected_streaming_url = f"{custom_api_base}/models/{model}:{endpoint}?alt=sse" + assert result_url_streaming == expected_streaming_url, f"Expected {expected_streaming_url}, got {result_url_streaming}" + + print(f"✅ Custom API base streaming URL test passed: {result_url_streaming}") + + # Test case 3: Error handling - missing API key + with pytest.raises(ValueError, match="Missing gemini_api_key"): + vertex_base._check_custom_proxy( + api_base=custom_api_base, + custom_llm_provider="gemini", + gemini_api_key=None, # Missing API key + endpoint=endpoint, + stream=False, + auth_header=None, + url=f"https://generativelanguage.googleapis.com/v1beta/models/{model}:{endpoint}", + model=model, + ) + + print("✅ Missing API key error handling test passed") + + +@pytest.mark.asyncio +async def test_gemini_proxy_config_with_custom_api_base(): + """ + Test that proxy configuration correctly handles custom API base for Gemini models. + + This test simulates the proxy configuration scenario where a model is configured + with a custom api_base in the config.yaml file. + """ + from litellm.llms.vertex_ai.vertex_llm_base import VertexBase + + # Simulate proxy configuration + model_config = { + "model_name": "byok-gemini/*", + "litellm_params": { + "model": "gemini/*", + "api_key": "dummy-key-for-testing", + "api_base": "https://proxy.zapier.com/generativelanguage.googleapis.com/v1beta" + } + } + + vertex_base = VertexBase() + + # Test with different Gemini models + test_models = [ + "gemini-2.5-flash-lite", + "gemini-2.5-pro", + "gemini-1.5-flash", + "gemini-1.5-pro" + ] + + for model in test_models: + # Test generateContent endpoint + auth_header, result_url = vertex_base._check_custom_proxy( + api_base=model_config["litellm_params"]["api_base"], + custom_llm_provider="gemini", + gemini_api_key=model_config["litellm_params"]["api_key"], + endpoint="generateContent", + stream=False, + auth_header=None, + url=f"https://generativelanguage.googleapis.com/v1beta/models/{model}:generateContent", + model=model, + ) + + expected_url = f"{model_config['litellm_params']['api_base']}/models/{model}:generateContent" + assert result_url == expected_url, f"Expected {expected_url}, got {result_url} for model {model}" + assert auth_header == model_config["litellm_params"]["api_key"], f"Expected API key, got {auth_header} for model {model}" + + print(f"✅ Model {model} configuration test passed: {result_url}") + + print("✅ Proxy configuration with custom API base test passed") + + if __name__ == "__main__": # Run the tests pytest.main([__file__, "-v"]) diff --git a/tests/test_litellm/llms/vertex_ai/test_vertex_llm_base.py b/tests/test_litellm/llms/vertex_ai/test_vertex_llm_base.py index c1cefa41ae..bec60434c2 100644 --- a/tests/test_litellm/llms/vertex_ai/test_vertex_llm_base.py +++ b/tests/test_litellm/llms/vertex_ai/test_vertex_llm_base.py @@ -704,3 +704,177 @@ class TestVertexBase: vertex_base.get_api_base(api_base=api_base, vertex_location=vertex_location) == expected ), f"Expected {expected} with api_base {api_base} and vertex_location {vertex_location}" + + @pytest.mark.parametrize( + "api_base, custom_llm_provider, gemini_api_key, endpoint, stream, auth_header, url, model, expected_auth_header, expected_url", + [ + # Test case 1: Gemini with custom API base + ( + "https://proxy.zapier.com/generativelanguage.googleapis.com/v1beta", + "gemini", + "test-api-key", + "generateContent", + False, + None, + "https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-flash-lite:generateContent", + "gemini-2.5-flash-lite", + "test-api-key", + "https://proxy.zapier.com/generativelanguage.googleapis.com/v1beta/models/gemini-2.5-flash-lite:generateContent" + ), + # Test case 2: Gemini with custom API base and streaming + ( + "https://proxy.zapier.com/generativelanguage.googleapis.com/v1beta", + "gemini", + "test-api-key", + "generateContent", + True, + None, + "https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-flash-lite:generateContent", + "gemini-2.5-flash-lite", + "test-api-key", + "https://proxy.zapier.com/generativelanguage.googleapis.com/v1beta/models/gemini-2.5-flash-lite:generateContent?alt=sse" + ), + # Test case 3: Non-Gemini provider with custom API base + ( + "https://custom-vertex-api.com", + "vertex_ai", + None, + "generateContent", + False, + "Bearer token123", + "https://aiplatform.googleapis.com/v1/projects/test-project/locations/us-central1/publishers/google/models/gemini-pro:generateContent", + "gemini-pro", + "Bearer token123", + "https://custom-vertex-api.com:generateContent" + ), + # Test case 4: No API base provided (should return original values) + ( + None, + "gemini", + "test-api-key", + "generateContent", + False, + "Bearer token123", + "https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-flash-lite:generateContent", + "gemini-2.5-flash-lite", + "Bearer token123", + "https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-flash-lite:generateContent" + ), + # Test case 5: Gemini without API key (should raise ValueError) + ( + "https://proxy.zapier.com/generativelanguage.googleapis.com/v1beta", + "gemini", + None, + "generateContent", + False, + None, + "https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-flash-lite:generateContent", + "gemini-2.5-flash-lite", + None, # This should raise an exception + None + ), + ], + ) + def test_check_custom_proxy( + self, + api_base, + custom_llm_provider, + gemini_api_key, + endpoint, + stream, + auth_header, + url, + model, + expected_auth_header, + expected_url + ): + """Test the _check_custom_proxy method for handling custom API base URLs""" + vertex_base = VertexBase() + + if custom_llm_provider == "gemini" and api_base and gemini_api_key is None: + # Test case 5: Should raise ValueError for Gemini without API key + with pytest.raises(ValueError, match="Missing gemini_api_key"): + vertex_base._check_custom_proxy( + api_base=api_base, + custom_llm_provider=custom_llm_provider, + gemini_api_key=gemini_api_key, + endpoint=endpoint, + stream=stream, + auth_header=auth_header, + url=url, + model=model, + ) + else: + # Test cases 1-4: Should work correctly + result_auth_header, result_url = vertex_base._check_custom_proxy( + api_base=api_base, + custom_llm_provider=custom_llm_provider, + gemini_api_key=gemini_api_key, + endpoint=endpoint, + stream=stream, + auth_header=auth_header, + url=url, + model=model, + ) + + assert result_auth_header == expected_auth_header, f"Expected auth_header {expected_auth_header}, got {result_auth_header}" + assert result_url == expected_url, f"Expected URL {expected_url}, got {result_url}" + + def test_check_custom_proxy_gemini_url_construction(self): + """Test that Gemini URLs are constructed correctly with custom API base""" + vertex_base = VertexBase() + + # Test various Gemini models with custom API base + test_cases = [ + ("gemini-2.5-flash-lite", "generateContent", "https://proxy.zapier.com/generativelanguage.googleapis.com/v1beta/models/gemini-2.5-flash-lite:generateContent"), + ("gemini-2.5-pro", "generateContent", "https://proxy.zapier.com/generativelanguage.googleapis.com/v1beta/models/gemini-2.5-pro:generateContent"), + ("gemini-1.5-flash", "streamGenerateContent", "https://proxy.zapier.com/generativelanguage.googleapis.com/v1beta/models/gemini-1.5-flash:streamGenerateContent"), + ] + + for model, endpoint, expected_url in test_cases: + _, result_url = vertex_base._check_custom_proxy( + api_base="https://proxy.zapier.com/generativelanguage.googleapis.com/v1beta", + custom_llm_provider="gemini", + gemini_api_key="test-api-key", + endpoint=endpoint, + stream=False, + auth_header=None, + url=f"https://generativelanguage.googleapis.com/v1beta/models/{model}:{endpoint}", + model=model, + ) + + assert result_url == expected_url, f"Expected {expected_url}, got {result_url} for model {model}" + + def test_check_custom_proxy_streaming_parameter(self): + """Test that streaming parameter correctly adds ?alt=sse to URLs""" + vertex_base = VertexBase() + + # Test with streaming enabled + _, result_url_streaming = vertex_base._check_custom_proxy( + api_base="https://proxy.zapier.com/generativelanguage.googleapis.com/v1beta", + custom_llm_provider="gemini", + gemini_api_key="test-api-key", + endpoint="generateContent", + stream=True, + auth_header=None, + url="https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-flash-lite:generateContent", + model="gemini-2.5-flash-lite", + ) + + expected_streaming_url = "https://proxy.zapier.com/generativelanguage.googleapis.com/v1beta/models/gemini-2.5-flash-lite:generateContent?alt=sse" + assert result_url_streaming == expected_streaming_url, f"Expected {expected_streaming_url}, got {result_url_streaming}" + + # Test with streaming disabled + _, result_url_no_streaming = vertex_base._check_custom_proxy( + api_base="https://proxy.zapier.com/generativelanguage.googleapis.com/v1beta", + custom_llm_provider="gemini", + gemini_api_key="test-api-key", + endpoint="generateContent", + stream=False, + auth_header=None, + url="https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-flash-lite:generateContent", + model="gemini-2.5-flash-lite", + ) + + expected_no_streaming_url = "https://proxy.zapier.com/generativelanguage.googleapis.com/v1beta/models/gemini-2.5-flash-lite:generateContent" + assert result_url_no_streaming == expected_no_streaming_url, f"Expected {expected_no_streaming_url}, got {result_url_no_streaming}" From 573230348dd7cfd7dc63b266aa2579daaf82bc3b Mon Sep 17 00:00:00 2001 From: Sameerlite Date: Tue, 16 Sep 2025 15:21:48 +0530 Subject: [PATCH 12/34] fix lint error --- litellm/llms/vertex_ai/vertex_llm_base.py | 17 +++++++++-------- 1 file changed, 9 insertions(+), 8 deletions(-) diff --git a/litellm/llms/vertex_ai/vertex_llm_base.py b/litellm/llms/vertex_ai/vertex_llm_base.py index f89ee92294..139cea08c5 100644 --- a/litellm/llms/vertex_ai/vertex_llm_base.py +++ b/litellm/llms/vertex_ai/vertex_llm_base.py @@ -239,6 +239,7 @@ class VertexBase: stream=stream, auth_header=None, url=default_api_base, + model=model, ) return api_base @@ -387,19 +388,19 @@ class VertexBase: ) -> Tuple[str, str]: """ Handle reauthentication when credentials refresh fails. - + This method clears the cached credentials and attempts to reload them once. It should only be called when "Reauthentication is needed" error occurs. - + Args: credentials: The original credentials project_id: The project ID credential_cache_key: The cache key to clear error: The original error that triggered reauthentication - + Returns: Tuple of (access_token, project_id) - + Raises: The original error if reauthentication fails """ @@ -407,11 +408,11 @@ class VertexBase: f"Handling reauthentication for project_id: {project_id}. " f"Clearing cache and retrying once." ) - + # Clear the cached credentials if credential_cache_key in self._credentials_project_mapping: del self._credentials_project_mapping[credential_cache_key] - + # Retry once with _retry_reauth=True to prevent infinite recursion try: return self.get_access_token( @@ -441,12 +442,12 @@ class VertexBase: 3. Check if loaded credentials have expired 4. If expired, refresh credentials 5. Return access token and project id - + Args: credentials: The credentials to use for authentication project_id: The Google Cloud project ID _retry_reauth: Internal flag to prevent infinite recursion during reauthentication - + Returns: Tuple of (access_token, project_id) """ From 5b896d2757b9ed6a1bdc7640b592d834d8dddd86 Mon Sep 17 00:00:00 2001 From: Sameerlite Date: Tue, 16 Sep 2025 15:47:23 +0530 Subject: [PATCH 13/34] make model param optional --- litellm/llms/vertex_ai/vertex_llm_base.py | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/litellm/llms/vertex_ai/vertex_llm_base.py b/litellm/llms/vertex_ai/vertex_llm_base.py index 139cea08c5..0f0bc776cc 100644 --- a/litellm/llms/vertex_ai/vertex_llm_base.py +++ b/litellm/llms/vertex_ai/vertex_llm_base.py @@ -293,7 +293,7 @@ class VertexBase: stream: Optional[bool], auth_header: Optional[str], url: str, - model: str, + model: Optional[str] = None, ) -> Tuple[Optional[str], str]: """ for cloudflare ai gateway - https://github.com/BerriAI/litellm/issues/4317 @@ -304,6 +304,10 @@ class VertexBase: if api_base: if custom_llm_provider == "gemini": # For Gemini (Google AI Studio), construct the full path like other providers + if model is None: + raise ValueError( + "Model parameter is required for Gemini custom API base URLs" + ) url = "{}/models/{}:{}".format(api_base, model, endpoint) if gemini_api_key is None: raise ValueError( From 0f5ab261df11820f516187aea97d5a8b77dbaea8 Mon Sep 17 00:00:00 2001 From: Ronald Pereira Date: Tue, 16 Sep 2025 16:37:22 -0300 Subject: [PATCH 14/34] Fix error message for missing OCI parameters --- litellm/llms/oci/chat/transformation.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/litellm/llms/oci/chat/transformation.py b/litellm/llms/oci/chat/transformation.py index 3be373ca5e..6755cab22e 100644 --- a/litellm/llms/oci/chat/transformation.py +++ b/litellm/llms/oci/chat/transformation.py @@ -378,7 +378,7 @@ class OCIChatConfig(BaseConfig): or not oci_compartment_id ): raise Exception( - "Missing required parameters: oci_user, oci_fingerprint, oci_tenancy, " + "Missing required parameters: oci_user, oci_fingerprint, oci_tenancy, oci_compartment_id " "and at least one of oci_key or oci_key_file." ) From 68105ce1a7ede4cab40a18c3afd9d75ae4fcb068 Mon Sep 17 00:00:00 2001 From: Ishaan Jaffer Date: Tue, 16 Sep 2025 15:41:52 -0700 Subject: [PATCH 15/34] fix type --- .../openai_endpoints_tests/test_e2e_openai_responses_api.py | 6 ------ 1 file changed, 6 deletions(-) diff --git a/tests/openai_endpoints_tests/test_e2e_openai_responses_api.py b/tests/openai_endpoints_tests/test_e2e_openai_responses_api.py index de60881820..d5208421f1 100644 --- a/tests/openai_endpoints_tests/test_e2e_openai_responses_api.py +++ b/tests/openai_endpoints_tests/test_e2e_openai_responses_api.py @@ -145,9 +145,6 @@ def test_cancel_response(): # verify cancel response structure assert hasattr(cancel_response, "id") - # Note: Cancel response returns ResponsesAPIResponse, not DeleteResponseResult - # The actual response structure depends on the provider implementation - assert isinstance(cancel_response, ResponsesAPIResponse) except Exception as e: if "Cannot cancel a completed response" in str(e): pass @@ -179,9 +176,6 @@ def test_cancel_streaming_response(): cancel_response = client.responses.cancel(response_id) print("CANCEL streaming response=", cancel_response) assert hasattr(cancel_response, "id") - # Note: Cancel response returns ResponsesAPIResponse, not DeleteResponseResult - # The actual response structure depends on the provider implementation - assert isinstance(cancel_response, ResponsesAPIResponse) except Exception as e: if "Cannot cancel a completed response" in str(e): pass From 02db2e8ae878ac55dc40e29914519ca8035f3068 Mon Sep 17 00:00:00 2001 From: Alexsander Hamir Date: Tue, 16 Sep 2025 16:18:23 -0700 Subject: [PATCH 16/34] [Performance] RPS Improvement +500 RPS when sending the `user` field (#14616) * perf tool * fix: cache type issue * fix: exception hanging & cache setting 1. Removed unhandled exceptions 2. Set cache value to dict --- litellm/proxy/auth/auth_checks.py | 19 ++- .../proxy/common_utils/performance_utils.py | 125 ++++++++++++++++++ tests/proxy_unit_tests/test_auth_checks.py | 2 +- 3 files changed, 134 insertions(+), 12 deletions(-) create mode 100644 litellm/proxy/common_utils/performance_utils.py diff --git a/litellm/proxy/auth/auth_checks.py b/litellm/proxy/auth/auth_checks.py index be9e494042..8a138b2a80 100644 --- a/litellm/proxy/auth/auth_checks.py +++ b/litellm/proxy/auth/auth_checks.py @@ -469,16 +469,13 @@ async def get_end_user_object( # check if in cache cached_user_obj = await user_api_key_cache.async_get_cache(key=_key) if cached_user_obj is not None: - if isinstance(cached_user_obj, dict): - return_obj = LiteLLM_EndUserTable(**cached_user_obj) - check_in_budget(end_user_obj=return_obj) - return return_obj - elif isinstance(cached_user_obj, LiteLLM_EndUserTable): - return_obj = cached_user_obj - check_in_budget(end_user_obj=return_obj) - return return_obj + # Convert cached dict to LiteLLM_EndUserTable instance + return_obj = LiteLLM_EndUserTable(**cached_user_obj) + check_in_budget(end_user_obj=return_obj) + return return_obj + # else, check db - try: + try: response = await prisma_client.db.litellm_endusertable.find_unique( where={"user_id": end_user_id}, include={"litellm_budget_table": True}, @@ -487,9 +484,9 @@ async def get_end_user_object( if response is None: raise Exception - # save the end-user object to cache + # save the end-user object to cache (always store as dict for consistency) await user_api_key_cache.async_set_cache( - key="end_user_id:{}".format(end_user_id), value=response + key="end_user_id:{}".format(end_user_id), value=response.dict() ) _response = LiteLLM_EndUserTable(**response.dict()) diff --git a/litellm/proxy/common_utils/performance_utils.py b/litellm/proxy/common_utils/performance_utils.py new file mode 100644 index 0000000000..fe238f2e33 --- /dev/null +++ b/litellm/proxy/common_utils/performance_utils.py @@ -0,0 +1,125 @@ +""" +Performance utilities for LiteLLM proxy server. + +This module provides performance monitoring and profiling functionality for endpoint +performance analysis using cProfile with configurable sampling rates. +""" + +import asyncio +import cProfile +import functools +import threading +from pathlib import Path as PathLib + +from litellm._logging import verbose_proxy_logger + +# Global profiling state +_profile_lock = threading.Lock() +_profiler = None +_last_profile_file_path = None +_sample_counter = 0 +_sample_counter_lock = threading.Lock() + + +def _should_sample(profile_sampling_rate: float) -> bool: + """Determine if current request should be sampled based on sampling rate.""" + if profile_sampling_rate >= 1.0: + return True # Always sample + elif profile_sampling_rate <= 0.0: + return False # Never sample + + # Use deterministic sampling based on counter for consistent rate + global _sample_counter + with _sample_counter_lock: + _sample_counter += 1 + # Sample based on rate (e.g., 0.1 means sample every 10th request) + should_sample = (_sample_counter % int(1.0 / profile_sampling_rate)) == 0 + return should_sample + + +def _start_profiling(profile_sampling_rate: float) -> None: + """Start cProfile profiling once globally.""" + global _profiler + with _profile_lock: + if _profiler is None: + _profiler = cProfile.Profile() + _profiler.enable() + verbose_proxy_logger.info(f"Profiling started with sampling rate: {profile_sampling_rate}") + + +def _start_profiling_for_request(profile_sampling_rate: float) -> bool: + """Start profiling for a specific request (if sampling allows).""" + if _should_sample(profile_sampling_rate): + _start_profiling(profile_sampling_rate) + return True + return False + + +def _save_stats(profile_file: PathLib) -> None: + """Save current stats directly to file.""" + with _profile_lock: + if _profiler is None: + return + try: + # Disable profiler temporarily to dump stats + _profiler.disable() + _profiler.dump_stats(str(profile_file)) + # Re-enable profiler to continue profiling + _profiler.enable() + verbose_proxy_logger.debug(f"Profiling stats saved to {profile_file}") + except Exception as e: + verbose_proxy_logger.error(f"Error saving profiling stats: {e}") + # Make sure profiler is re-enabled even if there's an error + try: + _profiler.enable() + except Exception: + pass + + +def profile_endpoint(sampling_rate: float = 1.0): + """Decorator to sample endpoint hits and save to a profile file. + + Args: + sampling_rate: Rate of requests to profile (0.0 to 1.0) + - 1.0: Profile all requests (100%) + - 0.1: Profile 1 in 10 requests (10%) + - 0.0: Profile no requests (0%) + """ + def decorator(func): + def set_last_profile_path(path: PathLib) -> None: + global _last_profile_file_path + _last_profile_file_path = path + + if asyncio.iscoroutinefunction(func): + @functools.wraps(func) + async def async_wrapper(*args, **kwargs): + is_sampling = _start_profiling_for_request(sampling_rate) + file_path_obj = PathLib("endpoint_profile.pstat") + set_last_profile_path(file_path_obj) + try: + result = await func(*args, **kwargs) + if is_sampling: + _save_stats(file_path_obj) + return result + except Exception: + if is_sampling: + _save_stats(file_path_obj) + raise + return async_wrapper + else: + @functools.wraps(func) + def sync_wrapper(*args, **kwargs): + is_sampling = _start_profiling_for_request(sampling_rate) + file_path_obj = PathLib("endpoint_profile.pstat") + set_last_profile_path(file_path_obj) + try: + result = func(*args, **kwargs) + if is_sampling: + _save_stats(file_path_obj) + return result + except Exception: + if is_sampling: + _save_stats(file_path_obj) + raise + return sync_wrapper + return decorator diff --git a/tests/proxy_unit_tests/test_auth_checks.py b/tests/proxy_unit_tests/test_auth_checks.py index 2c829406c0..24c005443a 100644 --- a/tests/proxy_unit_tests/test_auth_checks.py +++ b/tests/proxy_unit_tests/test_auth_checks.py @@ -48,7 +48,7 @@ async def test_get_end_user_object(customer_spend, customer_budget): ) _cache = DualCache() _key = "end_user_id:{}".format(end_user_id) - _cache.set_cache(key=_key, value=end_user_obj) + _cache.set_cache(key=_key, value=end_user_obj.model_dump()) try: await get_end_user_object( end_user_id=end_user_id, From 7de8811c4c3d7aabc647992cbc5d5881b87b4600 Mon Sep 17 00:00:00 2001 From: Ishaan Jaffer Date: Tue, 16 Sep 2025 16:33:10 -0700 Subject: [PATCH 17/34] test --- .../test_cohere_generate_api.py | 203 ------------------ 1 file changed, 203 deletions(-) delete mode 100644 tests/llm_translation/test_cohere_generate_api.py diff --git a/tests/llm_translation/test_cohere_generate_api.py b/tests/llm_translation/test_cohere_generate_api.py deleted file mode 100644 index 837e077cde..0000000000 --- a/tests/llm_translation/test_cohere_generate_api.py +++ /dev/null @@ -1,203 +0,0 @@ -import os -import sys -import traceback - -from dotenv import load_dotenv - -load_dotenv() -import io -import os - -sys.path.insert( - 0, os.path.abspath("../..") -) # Adds the parent directory to the system path -import json - -import pytest - -import litellm -from litellm import completion -from litellm.llms.cohere.completion.transformation import CohereTextConfig - - -def test_cohere_generate_api_completion(): - try: - from litellm.llms.custom_httpx.http_handler import HTTPHandler - from unittest.mock import patch, MagicMock - - client = HTTPHandler() - litellm.set_verbose = True - messages = [ - {"role": "system", "content": "You're a good bot"}, - { - "role": "user", - "content": "Hey", - }, - ] - - with patch.object(client, "post") as mock_client: - try: - completion( - model="cohere/command", - messages=messages, - max_tokens=10, - client=client, - ) - except Exception as e: - print(e) - mock_client.assert_called_once() - print("mock_client.call_args.kwargs", mock_client.call_args.kwargs) - - assert ( - mock_client.call_args.kwargs["url"] - == "https://api.cohere.ai/v1/generate" - ) - json_data = json.loads(mock_client.call_args.kwargs["data"]) - assert json_data["model"] == "command" - assert json_data["prompt"] == "You're a good bot Hey" - assert json_data["max_tokens"] == 10 - except Exception as e: - pytest.fail(f"Error occurred: {e}") - - -@pytest.mark.asyncio -async def test_cohere_generate_api_stream(): - try: - litellm.set_verbose = True - messages = [ - {"role": "system", "content": "You're a good bot"}, - { - "role": "user", - "content": "Hey", - }, - ] - response = await litellm.acompletion( - model="cohere/command", - messages=messages, - max_tokens=10, - stream=True, - ) - print("async cohere stream response", response) - async for chunk in response: - print(chunk) - except Exception as e: - pytest.fail(f"Error occurred: {e}") - - -def test_completion_cohere_stream_bad_key(): - try: - api_key = "bad-key" - messages = [ - {"role": "system", "content": "You are a helpful assistant."}, - { - "role": "user", - "content": "how does a court case get to the Supreme Court?", - }, - ] - completion( - model="command", - messages=messages, - stream=True, - max_tokens=50, - api_key=api_key, - ) - - except litellm.AuthenticationError as e: - pass - except Exception as e: - pytest.fail(f"Error occurred: {e}") - - -def test_cohere_transform_request(): - try: - config = CohereTextConfig() - messages = [ - {"role": "system", "content": "You're a helpful bot"}, - {"role": "user", "content": "Hello"}, - ] - optional_params = {"max_tokens": 10, "temperature": 0.7} - headers = {} - - transformed_request = config.transform_request( - model="command", - messages=messages, - optional_params=optional_params, - litellm_params={}, - headers=headers, - ) - - print("transformed_request", json.dumps(transformed_request, indent=4)) - - assert transformed_request["model"] == "command" - assert transformed_request["prompt"] == "You're a helpful bot Hello" - assert transformed_request["max_tokens"] == 10 - assert transformed_request["temperature"] == 0.7 - except Exception as e: - pytest.fail(f"Error occurred: {e}") - - -def test_cohere_transform_request_with_tools(): - try: - config = CohereTextConfig() - messages = [{"role": "user", "content": "What's the weather?"}] - tools = [ - { - "type": "function", - "function": { - "name": "get_weather", - "description": "Get weather information", - "parameters": { - "type": "object", - "properties": {"location": {"type": "string"}}, - }, - }, - } - ] - optional_params = {"tools": tools} - - transformed_request = config.transform_request( - model="command", - messages=messages, - optional_params=optional_params, - litellm_params={}, - headers={}, - ) - - print("transformed_request", json.dumps(transformed_request, indent=4)) - assert "tools" in transformed_request - assert transformed_request["tools"] == {"tools": tools} - except Exception as e: - pytest.fail(f"Error occurred: {e}") - - -def test_cohere_map_openai_params(): - try: - config = CohereTextConfig() - openai_params = { - "temperature": 0.7, - "max_tokens": 100, - "n": 2, - "top_p": 0.9, - "frequency_penalty": 0.5, - "presence_penalty": 0.5, - "stop": ["END"], - "stream": True, - } - - mapped_params = config.map_openai_params( - non_default_params=openai_params, - optional_params={}, - model="command", - drop_params=False, - ) - - assert mapped_params["temperature"] == 0.7 - assert mapped_params["max_tokens"] == 100 - assert mapped_params["num_generations"] == 2 - assert mapped_params["p"] == 0.9 - assert mapped_params["frequency_penalty"] == 0.5 - assert mapped_params["presence_penalty"] == 0.5 - assert mapped_params["stop_sequences"] == ["END"] - assert mapped_params["stream"] == True - except Exception as e: - pytest.fail(f"Error occurred: {e}") From ab1fb2b2e7f9877a412671ee83b155579f5d5909 Mon Sep 17 00:00:00 2001 From: Sameer Kankute Date: Wed, 17 Sep 2025 05:13:34 +0530 Subject: [PATCH 18/34] Add Support for Bedrock Guardrails to supportive selective Guarding (#14575) * Add Support for Bedrock Guardrails to supportive selective Guarding * Add method for better handling * Add guarded_text content type * Add guarded_text content type * Update Dockerfile * Update Dockerfile --- docs/my-website/docs/providers/bedrock.md | 46 ++- .../prompt_templates/factory.py | 119 ++++---- .../bedrock/chat/converse_transformation.py | 30 +- litellm/types/llms/bedrock.py | 32 +- litellm/types/llms/openai.py | 1 + .../chat/test_converse_transformation.py | 280 +++++++++++++++++- 6 files changed, 427 insertions(+), 81 deletions(-) diff --git a/docs/my-website/docs/providers/bedrock.md b/docs/my-website/docs/providers/bedrock.md index c191b74226..165ef1d12f 100644 --- a/docs/my-website/docs/providers/bedrock.md +++ b/docs/my-website/docs/providers/bedrock.md @@ -889,6 +889,19 @@ curl http://0.0.0.0:4000/v1/chat/completions \ Example of using [Bedrock Guardrails with LiteLLM](https://docs.aws.amazon.com/bedrock/latest/userguide/guardrails-use-converse-api.html) +### Selective Content Moderation with `guarded_text` + +LiteLLM supports selective content moderation using the `guarded_text` content type. This allows you to wrap only specific content that should be moderated by Bedrock Guardrails, rather than evaluating the entire conversation. + +**How it works:** +- Content with `type: "guarded_text"` gets automatically wrapped in `guardrailConverseContent` blocks +- Only the wrapped content is evaluated by Bedrock Guardrails +- Regular content with `type: "text"` bypasses guardrail evaluation + +:::note +If `guarded_text` is not used, the entire conversation history will be sent to the guardrail for evaluation, which can increase latency and costs. +::: + @@ -915,6 +928,24 @@ response = completion( "trace": "disabled", # The trace behavior for the guardrail. Can either be "disabled" or "enabled" }, ) + +# Selective guardrail usage with guarded_text - only specific content is evaluated +response_guard = completion( + model="anthropic.claude-v2", + messages=[ + { + "role": "user", + "content": [ + {"type": "text", "text": "What is the main topic of this legal document?"}, + {"type": "guarded_text", "text": "This document contains sensitive legal information that should be moderated by guardrails."} + ] + } + ], + guardrailConfig={ + "guardrailIdentifier": "gr-abc123", + "guardrailVersion": "DRAFT" + } +) ``` @@ -993,7 +1024,20 @@ response = client.chat.completions.create(model="bedrock-claude-v1", messages = temperature=0.7 ) -print(response) +# For adding selective guardrail usage with guarded_text +response_guard = client.chat.completions.create(model="bedrock-claude-v1", messages = [ + { + "role": "user", + "content": [ + {"type": "text", "text": "What is the main topic of this legal document?"}, + {"type": "guarded_text", "text": "This document contains sensitive legal information that should be moderated by guardrails."} + ] + } +], +temperature=0.7 +) + +print(response_guard) ``` diff --git a/litellm/litellm_core_utils/prompt_templates/factory.py b/litellm/litellm_core_utils/prompt_templates/factory.py index 65f49cf08b..356d48dcb8 100644 --- a/litellm/litellm_core_utils/prompt_templates/factory.py +++ b/litellm/litellm_core_utils/prompt_templates/factory.py @@ -16,8 +16,8 @@ from litellm import verbose_logger from litellm.llms.custom_httpx.http_handler import HTTPHandler, get_async_httpx_client from litellm.types.files import get_file_extension_from_mime_type from litellm.types.llms.anthropic import * -from litellm.types.llms.bedrock import MessageBlock as BedrockMessageBlock from litellm.types.llms.bedrock import CachePointBlock +from litellm.types.llms.bedrock import MessageBlock as BedrockMessageBlock from litellm.types.llms.custom_http import httpxSpecialProvider from litellm.types.llms.ollama import OllamaVisionModelObject from litellm.types.llms.openai import ( @@ -1067,10 +1067,10 @@ def convert_to_gemini_tool_call_invoke( if tool_calls is not None: for tool in tool_calls: if "function" in tool: - gemini_function_call: Optional[VertexFunctionCall] = ( - _gemini_tool_call_invoke_helper( - function_call_params=tool["function"] - ) + gemini_function_call: Optional[ + VertexFunctionCall + ] = _gemini_tool_call_invoke_helper( + function_call_params=tool["function"] ) if gemini_function_call is not None: _parts_list.append( @@ -1589,9 +1589,9 @@ def anthropic_messages_pt( # noqa: PLR0915 ) if "cache_control" in _content_element: - _anthropic_content_element["cache_control"] = ( - _content_element["cache_control"] - ) + _anthropic_content_element[ + "cache_control" + ] = _content_element["cache_control"] user_content.append(_anthropic_content_element) elif m.get("type", "") == "text": m = cast(ChatCompletionTextObject, m) @@ -1629,9 +1629,9 @@ def anthropic_messages_pt( # noqa: PLR0915 ) if "cache_control" in _content_element: - _anthropic_content_text_element["cache_control"] = ( - _content_element["cache_control"] - ) + _anthropic_content_text_element[ + "cache_control" + ] = _content_element["cache_control"] user_content.append(_anthropic_content_text_element) @@ -2482,8 +2482,7 @@ class BedrockImageProcessor: if is_document: return BedrockImageProcessor._get_document_format( - mime_type=mime_type, - supported_doc_formats=supported_doc_formats + mime_type=mime_type, supported_doc_formats=supported_doc_formats ) else: @@ -2495,12 +2494,9 @@ class BedrockImageProcessor: f"Unsupported image format: {image_format}. Supported formats: {supported_image_and_video_formats}" ) return image_format - + @staticmethod - def _get_document_format( - mime_type: str, - supported_doc_formats: List[str] - ) -> str: + def _get_document_format(mime_type: str, supported_doc_formats: List[str]) -> str: """ Get the document format from the mime type @@ -2519,13 +2515,9 @@ class BedrockImageProcessor: The document format """ valid_extensions: Optional[List[str]] = None - potential_extensions = mimetypes.guess_all_extensions( - mime_type, strict=False - ) + potential_extensions = mimetypes.guess_all_extensions(mime_type, strict=False) valid_extensions = [ - ext[1:] - for ext in potential_extensions - if ext[1:] in supported_doc_formats + ext[1:] for ext in potential_extensions if ext[1:] in supported_doc_formats ] # Fallback to types/files.py if mimetypes doesn't return valid extensions @@ -2689,10 +2681,12 @@ def _convert_to_bedrock_tool_call_invoke( ) bedrock_content_block = BedrockContentBlock(toolUse=bedrock_tool) _parts_list.append(bedrock_content_block) - + # Check for cache_control and add a separate cachePoint block if tool.get("cache_control", None) is not None: - cache_point_block = BedrockContentBlock(cachePoint=CachePointBlock(type="default")) + cache_point_block = BedrockContentBlock( + cachePoint=CachePointBlock(type="default") + ) _parts_list.append(cache_point_block) return _parts_list except Exception as e: @@ -2754,7 +2748,7 @@ def _convert_to_bedrock_tool_call_result( for content in content_list: if content["type"] == "text": content_str += content["text"] - + message.get("name", "") id = str(message.get("tool_call_id", str(uuid.uuid4()))) @@ -2763,7 +2757,7 @@ def _convert_to_bedrock_tool_call_result( content=[tool_result_content_block], toolUseId=id, ) - + content_block = BedrockContentBlock(toolResult=tool_result) return content_block @@ -3085,6 +3079,7 @@ class BedrockConverseMessagesProcessor: messages.append(DEFAULT_USER_CONTINUE_MESSAGE) return messages + @staticmethod async def _bedrock_converse_messages_pt_async( # noqa: PLR0915 messages: List, @@ -3128,6 +3123,12 @@ class BedrockConverseMessagesProcessor: if element["type"] == "text": _part = BedrockContentBlock(text=element["text"]) _parts.append(_part) + elif element["type"] == "guarded_text": + # Wrap guarded_text in guardrailConverseContent block + _part = BedrockContentBlock( + guardrailConverseContent={"text": element["text"]} + ) + _parts.append(_part) elif element["type"] == "image_url": format: Optional[str] = None if isinstance(element["image_url"], dict): @@ -3170,6 +3171,7 @@ class BedrockConverseMessagesProcessor: msg_i += 1 if user_content: + if len(contents) > 0 and contents[-1]["role"] == "user": if ( assistant_continue_message is not None @@ -3199,26 +3201,29 @@ class BedrockConverseMessagesProcessor: current_message = messages[msg_i] tool_call_result = _convert_to_bedrock_tool_call_result(current_message) tool_content.append(tool_call_result) - + # Check if we need to add a separate cachePoint block has_cache_control = False - + # Check for message-level cache_control if current_message.get("cache_control", None) is not None: has_cache_control = True # Check for content-level cache_control in list content elif isinstance(current_message.get("content"), list): for content_element in current_message["content"]: - if (isinstance(content_element, dict) and - content_element.get("cache_control", None) is not None): + if ( + isinstance(content_element, dict) + and content_element.get("cache_control", None) is not None + ): has_cache_control = True break - + # Add a separate cachePoint block if cache_control is present if has_cache_control: - cache_point_block = BedrockContentBlock(cachePoint=CachePointBlock(type="default")) + cache_point_block = BedrockContentBlock( + cachePoint=CachePointBlock(type="default") + ) tool_content.append(cache_point_block) - msg_i += 1 if tool_content: @@ -3299,7 +3304,7 @@ class BedrockConverseMessagesProcessor: image_url=image_url ) assistants_parts.append(assistants_part) - # Add cache point block for assistant content elements + # Add cache point block for assistant content elements _cache_point_block = ( litellm.AmazonConverseConfig()._get_cache_point_block( message_block=cast( @@ -3311,8 +3316,12 @@ class BedrockConverseMessagesProcessor: if _cache_point_block is not None: assistants_parts.append(_cache_point_block) assistant_content.extend(assistants_parts) - elif _assistant_content is not None and isinstance(_assistant_content, str): - assistant_content.append(BedrockContentBlock(text=_assistant_content)) + elif _assistant_content is not None and isinstance( + _assistant_content, str + ): + assistant_content.append( + BedrockContentBlock(text=_assistant_content) + ) # Add cache point block for assistant string content _cache_point_block = ( litellm.AmazonConverseConfig()._get_cache_point_block( @@ -3496,6 +3505,12 @@ def _bedrock_converse_messages_pt( # noqa: PLR0915 if element["type"] == "text": _part = BedrockContentBlock(text=element["text"]) _parts.append(_part) + elif element["type"] == "guarded_text": + # Wrap guarded_text in guardrailConverseContent block + _part = BedrockContentBlock( + guardrailConverseContent={"text": element["text"]} + ) + _parts.append(_part) elif element["type"] == "image_url": format: Optional[str] = None if isinstance(element["image_url"], dict): @@ -3539,6 +3554,7 @@ def _bedrock_converse_messages_pt( # noqa: PLR0915 msg_i += 1 if user_content: + if len(contents) > 0 and contents[-1]["role"] == "user": if ( assistant_continue_message is not None @@ -3565,29 +3581,33 @@ def _bedrock_converse_messages_pt( # noqa: PLR0915 while msg_i < len(messages) and messages[msg_i]["role"] == "tool": tool_call_result = _convert_to_bedrock_tool_call_result(messages[msg_i]) current_message = messages[msg_i] - + # Add the tool result first tool_content.append(tool_call_result) - + # Check if we need to add a separate cachePoint block has_cache_control = False - + # Check for message-level cache_control if current_message.get("cache_control", None) is not None: has_cache_control = True # Check for content-level cache_control in list content elif isinstance(current_message.get("content"), list): for content_element in current_message["content"]: - if (isinstance(content_element, dict) and - content_element.get("cache_control", None) is not None): + if ( + isinstance(content_element, dict) + and content_element.get("cache_control", None) is not None + ): has_cache_control = True break - + # Add a separate cachePoint block if cache_control is present if has_cache_control: - cache_point_block = BedrockContentBlock(cachePoint=CachePointBlock(type="default")) + cache_point_block = BedrockContentBlock( + cachePoint=CachePointBlock(type="default") + ) tool_content.append(cache_point_block) - + msg_i += 1 if tool_content: # if last message was a 'user' message, then add a blank assistant message (bedrock requires alternating roles) @@ -3852,10 +3872,9 @@ def function_call_prompt(messages: list, functions: list): if isinstance(message["content"], str): message["content"] += f""" {function_prompt}""" else: - message["content"].append({ - "type": "text", - "text": f""" {function_prompt}""" - }) + message["content"].append( + {"type": "text", "text": f""" {function_prompt}"""} + ) function_added_to_prompt = True if function_added_to_prompt is False: diff --git a/litellm/llms/bedrock/chat/converse_transformation.py b/litellm/llms/bedrock/chat/converse_transformation.py index e3d65be8bb..88103a86cf 100644 --- a/litellm/llms/bedrock/chat/converse_transformation.py +++ b/litellm/llms/bedrock/chat/converse_transformation.py @@ -501,7 +501,6 @@ class AmazonConverseConfig(BaseConfig): ) and not is_thinking_enabled ): - optional_params["tool_choice"] = ToolChoiceValuesBlock( tool=SpecificToolChoiceBlock(name=RESPONSE_FORMAT_TOOL_NAME) ) @@ -995,7 +994,9 @@ class AmazonConverseConfig(BaseConfig): return message, returned_finish_reason - def _translate_message_content(self, content_blocks: List[ContentBlock]) -> Tuple[ + def _translate_message_content( + self, content_blocks: List[ContentBlock] + ) -> Tuple[ str, List[ChatCompletionToolCallChunk], Optional[List[BedrockConverseReasoningContentBlock]], @@ -1010,9 +1011,9 @@ class AmazonConverseConfig(BaseConfig): """ content_str = "" tools: List[ChatCompletionToolCallChunk] = [] - reasoningContentBlocks: Optional[List[BedrockConverseReasoningContentBlock]] = ( - None - ) + reasoningContentBlocks: Optional[ + List[BedrockConverseReasoningContentBlock] + ] = None for idx, content in enumerate(content_blocks): """ - Content is either a tool response or text @@ -1133,9 +1134,9 @@ class AmazonConverseConfig(BaseConfig): chat_completion_message: ChatCompletionResponseMessage = {"role": "assistant"} content_str = "" tools: List[ChatCompletionToolCallChunk] = [] - reasoningContentBlocks: Optional[List[BedrockConverseReasoningContentBlock]] = ( - None - ) + reasoningContentBlocks: Optional[ + List[BedrockConverseReasoningContentBlock] + ] = None if message is not None: ( @@ -1148,12 +1149,12 @@ class AmazonConverseConfig(BaseConfig): chat_completion_message["provider_specific_fields"] = { "reasoningContentBlocks": reasoningContentBlocks, } - chat_completion_message["reasoning_content"] = ( - self._transform_reasoning_content(reasoningContentBlocks) - ) - chat_completion_message["thinking_blocks"] = ( - self._transform_thinking_blocks(reasoningContentBlocks) - ) + chat_completion_message[ + "reasoning_content" + ] = self._transform_reasoning_content(reasoningContentBlocks) + chat_completion_message[ + "thinking_blocks" + ] = self._transform_thinking_blocks(reasoningContentBlocks) chat_completion_message["content"] = content_str if ( json_mode is True @@ -1171,7 +1172,6 @@ class AmazonConverseConfig(BaseConfig): # Bedrock returns the response wrapped in a "properties" object # We need to extract the actual content from this wrapper try: - response_data = json.loads(json_mode_content_str) # If Bedrock wrapped the response in "properties", extract the content diff --git a/litellm/types/llms/bedrock.py b/litellm/types/llms/bedrock.py index baa7c20520..a829a6b94b 100644 --- a/litellm/types/llms/bedrock.py +++ b/litellm/types/llms/bedrock.py @@ -3,14 +3,9 @@ from typing import Any, List, Literal, Optional, Union from typing_extensions import ( TYPE_CHECKING, - Protocol, Required, - Self, TypedDict, - TypeGuard, - get_origin, override, - runtime_checkable, ) from .openai import ChatCompletionToolCallChunk @@ -93,6 +88,12 @@ class BedrockConverseReasoningContentBlockDelta(TypedDict, total=False): text: str +class GuardrailConverseContentBlock(TypedDict, total=False): + """Content block for selective guardrail evaluation in Bedrock Converse API""" + + text: str + + class ContentBlock(TypedDict, total=False): text: str image: ImageBlock @@ -102,6 +103,7 @@ class ContentBlock(TypedDict, total=False): toolUse: ToolUseBlock cachePoint: CachePointBlock reasoningContent: BedrockConverseReasoningContentBlock + guardrailConverseContent: GuardrailConverseContentBlock class MessageBlock(TypedDict): @@ -581,30 +583,35 @@ class AmazonDeepSeekR1StreamingResponse(TypedDict): class BedrockS3InputDataConfig(TypedDict): """S3 input data configuration for Bedrock batch jobs.""" + s3Uri: str class BedrockInputDataConfig(TypedDict): """Input data configuration for Bedrock batch jobs.""" + s3InputDataConfig: BedrockS3InputDataConfig class BedrockS3OutputDataConfig(TypedDict): """S3 output data configuration for Bedrock batch jobs.""" + s3Uri: str class BedrockOutputDataConfig(TypedDict): """Output data configuration for Bedrock batch jobs.""" + s3OutputDataConfig: BedrockS3OutputDataConfig class BedrockCreateBatchRequest(TypedDict, total=False): """ Request structure for creating a Bedrock batch inference job. - + Reference: https://docs.aws.amazon.com/bedrock/latest/APIReference/API_CreateModelInvocationJob.html """ + jobName: str roleArn: str modelId: str @@ -616,21 +623,17 @@ class BedrockCreateBatchRequest(TypedDict, total=False): BedrockBatchJobStatus = Literal[ - "Submitted", - "InProgress", - "Completed", - "Failed", - "Stopping", - "Stopped" + "Submitted", "InProgress", "Completed", "Failed", "Stopping", "Stopped" ] class BedrockCreateBatchResponse(TypedDict): """ Response structure from creating a Bedrock batch inference job. - + Reference: https://docs.aws.amazon.com/bedrock/latest/APIReference/API_CreateModelInvocationJob.html """ + jobArn: str jobName: str status: BedrockBatchJobStatus @@ -639,9 +642,10 @@ class BedrockCreateBatchResponse(TypedDict): class BedrockGetBatchResponse(TypedDict, total=False): """ Response structure from getting a Bedrock batch inference job. - + Reference: https://docs.aws.amazon.com/bedrock/latest/APIReference/API_GetModelInvocationJob.html """ + jobArn: str jobName: str modelId: str diff --git a/litellm/types/llms/openai.py b/litellm/types/llms/openai.py index 79e3c73dbc..4adb751d90 100644 --- a/litellm/types/llms/openai.py +++ b/litellm/types/llms/openai.py @@ -723,6 +723,7 @@ ValidUserMessageContentTypes = [ "input_audio", "audio_url", "document", + "guarded_text", "video_url", "file", ] # used for validating user messages. Prevent users from accidentally sending anthropic messages. diff --git a/tests/test_litellm/llms/bedrock/chat/test_converse_transformation.py b/tests/test_litellm/llms/bedrock/chat/test_converse_transformation.py index 2fc710664e..df003850f7 100644 --- a/tests/test_litellm/llms/bedrock/chat/test_converse_transformation.py +++ b/tests/test_litellm/llms/bedrock/chat/test_converse_transformation.py @@ -1589,4 +1589,282 @@ async def test_no_cache_control_no_cache_point(): # Tool message should only have tool result, no cachePoint tool_content = result[2]["content"] assert len(tool_content) == 1 - assert "toolResult" in tool_content[0] \ No newline at end of file + assert "toolResult" in tool_content[0] + + +# ============================================================================ +# Guarded Text Feature Tests +# ============================================================================ + +def test_guarded_text_wraps_in_guardrail_converse_content(): + """Test that guarded_text content type gets wrapped in guardrailConverseContent blocks.""" + from litellm.litellm_core_utils.prompt_templates.factory import _bedrock_converse_messages_pt + + messages = [ + { + "role": "user", + "content": [ + {"type": "text", "text": "Regular text content"}, + {"type": "guarded_text", "text": "This should be guarded"}, + {"type": "text", "text": "More regular text"} + ] + } + ] + + result = _bedrock_converse_messages_pt( + messages=messages, + model="us.amazon.nova-pro-v1:0", + llm_provider="bedrock_converse" + ) + + # Should have 1 message + assert len(result) == 1 + assert result[0]["role"] == "user" + + # Should have 3 content blocks + content = result[0]["content"] + assert len(content) == 3 + + # First and third should be regular text + assert "text" in content[0] + assert content[0]["text"] == "Regular text content" + assert "text" in content[2] + assert content[2]["text"] == "More regular text" + + # Second should be guardrailConverseContent + assert "guardrailConverseContent" in content[1] + assert content[1]["guardrailConverseContent"]["text"] == "This should be guarded" + + +def test_guarded_text_with_system_messages(): + """Test guarded_text with system messages using the full transformation.""" + config = AmazonConverseConfig() + + messages = [ + {"role": "system", "content": "You are a helpful assistant."}, + { + "role": "user", + "content": [ + {"type": "text", "text": "What is the main topic of this legal document?"}, + {"type": "guarded_text", "text": "This is a set of very long instructions that you will follow. Here is a legal document that you will use to answer the user's question."} + ] + } + ] + + optional_params = { + "guardrailConfig": { + "guardrailIdentifier": "gr-abc123", + "guardrailVersion": "DRAFT" + } + } + + result = config._transform_request( + model="us.amazon.nova-pro-v1:0", + messages=messages, + optional_params=optional_params, + litellm_params={}, + headers={} + ) + + # Should have system content blocks + assert "system" in result + assert len(result["system"]) == 1 + assert result["system"][0]["text"] == "You are a helpful assistant." + + # Should have 1 message (system messages are removed) + assert "messages" in result + assert len(result["messages"]) == 1 + + # User message should have both regular text and guarded text + user_message = result["messages"][0] + assert user_message["role"] == "user" + content = user_message["content"] + assert len(content) == 2 + + # First should be regular text + assert "text" in content[0] + assert content[0]["text"] == "What is the main topic of this legal document?" + + # Second should be guardrailConverseContent + assert "guardrailConverseContent" in content[1] + assert content[1]["guardrailConverseContent"]["text"] == "This is a set of very long instructions that you will follow. Here is a legal document that you will use to answer the user's question." + + +def test_guarded_text_with_mixed_content_types(): + """Test guarded_text with mixed content types including images.""" + from litellm.litellm_core_utils.prompt_templates.factory import _bedrock_converse_messages_pt + + messages = [ + { + "role": "user", + "content": [ + {"type": "text", "text": "Look at this image"}, + {"type": "image_url", "image_url": {"url": "data:image/png;base64,test"}}, + {"type": "guarded_text", "text": "This sensitive content should be guarded"} + ] + } + ] + + result = _bedrock_converse_messages_pt( + messages=messages, + model="us.amazon.nova-pro-v1:0", + llm_provider="bedrock_converse" + ) + + # Should have 1 message + assert len(result) == 1 + assert result[0]["role"] == "user" + + # Should have 3 content blocks + content = result[0]["content"] + assert len(content) == 3 + + # First should be regular text + assert "text" in content[0] + assert content[0]["text"] == "Look at this image" + + # Second should be image + assert "image" in content[1] + + # Third should be guardrailConverseContent + assert "guardrailConverseContent" in content[2] + assert content[2]["guardrailConverseContent"]["text"] == "This sensitive content should be guarded" + + +@pytest.mark.asyncio +async def test_async_guarded_text(): + """Test async version of guarded_text processing.""" + from litellm.litellm_core_utils.prompt_templates.factory import BedrockConverseMessagesProcessor + + messages = [ + { + "role": "user", + "content": [ + {"type": "text", "text": "Hello"}, + {"type": "guarded_text", "text": "This should be guarded"} + ] + } + ] + + result = await BedrockConverseMessagesProcessor._bedrock_converse_messages_pt_async( + messages=messages, + model="us.amazon.nova-pro-v1:0", + llm_provider="bedrock_converse" + ) + + # Should have 1 message + assert len(result) == 1 + assert result[0]["role"] == "user" + + # Should have 2 content blocks + content = result[0]["content"] + assert len(content) == 2 + + # First should be regular text + assert "text" in content[0] + assert content[0]["text"] == "Hello" + + # Second should be guardrailConverseContent + assert "guardrailConverseContent" in content[1] + assert content[1]["guardrailConverseContent"]["text"] == "This should be guarded" + + +def test_guarded_text_with_tool_calls(): + """Test guarded_text with tool calls in the conversation.""" + from litellm.litellm_core_utils.prompt_templates.factory import _bedrock_converse_messages_pt + + messages = [ + { + "role": "user", + "content": [ + {"type": "text", "text": "What's the weather?"}, + {"type": "guarded_text", "text": "Please be careful with sensitive information"} + ] + }, + { + "role": "assistant", + "content": None, + "tool_calls": [ + { + "id": "call_123", + "type": "function", + "function": {"name": "get_weather", "arguments": "{}"} + } + ] + }, + { + "role": "tool", + "tool_call_id": "call_123", + "content": "It's sunny and 25°C" + } + ] + + result = _bedrock_converse_messages_pt( + messages=messages, + model="us.amazon.nova-pro-v1:0", + llm_provider="bedrock_converse" + ) + + # Should have 3 messages + assert len(result) == 3 + + # First message (user) should have both text and guarded_text + user_message = result[0] + assert user_message["role"] == "user" + content = user_message["content"] + assert len(content) == 2 + + # First should be regular text + assert "text" in content[0] + assert content[0]["text"] == "What's the weather?" + + # Second should be guardrailConverseContent + assert "guardrailConverseContent" in content[1] + assert content[1]["guardrailConverseContent"]["text"] == "Please be careful with sensitive information" + + # Other messages should not have guardrailConverseContent + for i in range(1, 3): + content = result[i]["content"] + for block in content: + assert "guardrailConverseContent" not in block + + +def test_guarded_text_guardrail_config_preserved(): + """Test that guardrailConfig is preserved when using guarded_text.""" + config = AmazonConverseConfig() + + messages = [ + { + "role": "user", + "content": [ + {"type": "text", "text": "Hello"}, + {"type": "guarded_text", "text": "This should be guarded"} + ] + } + ] + + optional_params = { + "guardrailConfig": { + "guardrailIdentifier": "gr-abc123", + "guardrailVersion": "DRAFT" + } + } + + result = config._transform_request( + model="us.amazon.nova-pro-v1:0", + messages=messages, + optional_params=optional_params, + litellm_params={}, + headers={} + ) + + # GuardrailConfig should be present at top level + assert "guardrailConfig" in result + assert result["guardrailConfig"]["guardrailIdentifier"] == "gr-abc123" + + # GuardrailConfig should also be in inferenceConfig + assert "inferenceConfig" in result + assert "guardrailConfig" in result["inferenceConfig"] + assert result["inferenceConfig"]["guardrailConfig"]["guardrailIdentifier"] == "gr-abc123" + + From 1c855385c9ae5e8c2bad767e167248ddfd39dbfb Mon Sep 17 00:00:00 2001 From: Krrish Dholakia Date: Tue, 16 Sep 2025 18:43:57 -0700 Subject: [PATCH 19/34] build(model_cost): add cache_creation_input_token_cost_above_1hr pricing --- litellm/llms/anthropic/chat/transformation.py | 8 ++- ...odel_prices_and_context_window_backup.json | 1 + model_prices_and_context_window.json | 1 + .../test_anthropic_prompt_caching.py | 70 +++++++++++++++++++ 4 files changed, 78 insertions(+), 2 deletions(-) diff --git a/litellm/llms/anthropic/chat/transformation.py b/litellm/llms/anthropic/chat/transformation.py index ce874bfde9..b3b5f5107b 100644 --- a/litellm/llms/anthropic/chat/transformation.py +++ b/litellm/llms/anthropic/chat/transformation.py @@ -200,8 +200,12 @@ class AnthropicConfig(AnthropicModelInfo, BaseConfig): ) _allowed_properties = set(AnthropicInputSchema.__annotations__.keys()) - input_schema_filtered = {k: v for k, v in _input_schema.items() if k in _allowed_properties} - input_anthropic_schema: AnthropicInputSchema = AnthropicInputSchema(**input_schema_filtered) + input_schema_filtered = { + k: v for k, v in _input_schema.items() if k in _allowed_properties + } + input_anthropic_schema: AnthropicInputSchema = AnthropicInputSchema( + **input_schema_filtered + ) _tool = AnthropicMessagesTool( name=tool["function"]["name"], diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 96e19d022c..4394cef383 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -6228,6 +6228,7 @@ "input_cost_per_token": 8e-07, "output_cost_per_token": 4e-06, "cache_creation_input_token_cost": 1e-06, + "cache_creation_input_token_cost_above_1hr": 1.6e-06, "cache_read_input_token_cost": 8e-08, "search_context_cost_per_query": { "search_context_size_low": 0.01, diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 96e19d022c..4394cef383 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -6228,6 +6228,7 @@ "input_cost_per_token": 8e-07, "output_cost_per_token": 4e-06, "cache_creation_input_token_cost": 1e-06, + "cache_creation_input_token_cost_above_1hr": 1.6e-06, "cache_read_input_token_cost": 8e-08, "search_context_cost_per_query": { "search_context_size_low": 0.01, diff --git a/tests/local_testing/test_anthropic_prompt_caching.py b/tests/local_testing/test_anthropic_prompt_caching.py index 4c2b66879e..f2c194a36e 100644 --- a/tests/local_testing/test_anthropic_prompt_caching.py +++ b/tests/local_testing/test_anthropic_prompt_caching.py @@ -300,6 +300,76 @@ async def test_anthropic_api_prompt_caching_basic(): ) +@pytest.mark.asyncio() +async def test_anthropic_api_prompt_caching_basic_with_cache_creation(): + from uuid import uuid4 + + random_id = uuid4() + + litellm.set_verbose = True + response = await litellm.acompletion( + model="anthropic/claude-3-5-sonnet-20240620", + messages=[ + # System Message + { + "role": "system", + "content": [ + { + "type": "text", + "text": "Here is the full text of a complex legal agreement {}".format( + random_id + ) + * 400, + "cache_control": {"type": "ephemeral"}, + } + ], + }, + # marked for caching with the cache_control parameter, so that this checkpoint can read from the previous cache. + { + "role": "user", + "content": [ + { + "type": "text", + "text": "What are the key terms and conditions in this agreement?", + "cache_control": {"type": "ephemeral"}, + } + ], + }, + { + "role": "assistant", + "content": "Certainly! the key terms and conditions are the following: the contract is 1 year long for $10/mo", + }, + # The final turn is marked with cache-control, for continuing in followups. + { + "role": "user", + "content": [ + { + "type": "text", + "text": "What are the key terms and conditions in this agreement?", + "cache_control": {"type": "ephemeral"}, + } + ], + }, + ], + temperature=0.2, + max_tokens=10, + extra_headers={ + "anthropic-version": "2023-06-01", + "anthropic-beta": "prompt-caching-2024-07-31", + }, + ) + + print("response=", response) + + assert "cache_read_input_tokens" in response.usage + assert "cache_creation_input_tokens" in response.usage + + # Assert either a cache entry was created or cache was read - changes depending on the anthropic api ttl + assert (response.usage.cache_read_input_tokens > 0) or ( + response.usage.cache_creation_input_tokens > 0 + ) + + @pytest.mark.asyncio() async def test_anthropic_api_prompt_caching_with_content_str(): system_message = [ From 0fa11c3c2550e7d845423441f170f7d0af41a612 Mon Sep 17 00:00:00 2001 From: Krrish Dholakia Date: Tue, 16 Sep 2025 18:52:37 -0700 Subject: [PATCH 20/34] build(model_prices_and_context_window.json): add "cache_creation_input_token_cost_above_1hr" to all claude-3-5-sonnet models --- .gitignore | 3 +- ...odel_prices_and_context_window_backup.json | 40131 ++++++++-------- model_prices_and_context_window.json | 40131 ++++++++-------- 3 files changed, 40402 insertions(+), 39863 deletions(-) diff --git a/.gitignore b/.gitignore index ed8c88c899..c2ac5137cb 100644 --- a/.gitignore +++ b/.gitignore @@ -95,4 +95,5 @@ test.py litellm_config.yaml .cursor .vscode/launch.json -litellm/proxy/to_delete_loadtest_work/* \ No newline at end of file +litellm/proxy/to_delete_loadtest_work/* +update_model_cost_map.py diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 4394cef383..1452f1465d 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -1,2570 +1,821 @@ { - "sample_spec": { - "max_tokens": "LEGACY parameter. set to max_output_tokens if provider specifies it. IF not set to max_input_tokens, if provider specifies it.", - "max_input_tokens": "max input tokens, if the provider specifies it. if not default to max_tokens", - "max_output_tokens": "max output tokens, if the provider specifies it. if not default to max_tokens", - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "output_cost_per_reasoning_token": 0.0, - "input_cost_per_audio_token": 0.0, - "litellm_provider": "one of https://docs.litellm.ai/docs/providers", - "mode": "one of: chat, embedding, completion, image_generation, audio_transcription, audio_speech, image_generation, moderation, rerank", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_vision": true, - "supports_audio_input": true, - "supports_audio_output": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_reasoning": true, - "supports_web_search": true, - "search_context_cost_per_query": { - "search_context_size_low": 0.0, - "search_context_size_medium": 0.0, - "search_context_size_high": 0.0 - }, - "file_search_cost_per_1k_calls": 0.0, - "file_search_cost_per_gb_per_day": 0.0, - "vector_store_cost_per_gb_per_day": 0.0, - "computer_use_input_cost_per_1k_tokens": 0.0, - "computer_use_output_cost_per_1k_tokens": 0.0, - "code_interpreter_cost_per_session": 0.0, - "supported_regions": [ - "global", - "us-west-2", - "eu-west-1", - "ap-southeast-1", - "ap-northeast-1" - ], - "deprecation_date": "date when the model becomes deprecated in the format YYYY-MM-DD" - }, - "omni-moderation-latest": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 0, - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "openai", - "mode": "moderation" - }, - "omni-moderation-latest-intents": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 0, - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "openai", - "mode": "moderation" - }, - "omni-moderation-2024-09-26": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 0, - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "openai", - "mode": "moderation" - }, - "gpt-4": { - "max_tokens": 4096, - "max_input_tokens": 8192, - "max_output_tokens": 4096, - "input_cost_per_token": 3e-05, - "output_cost_per_token": 6e-05, - "litellm_provider": "openai", - "mode": "chat", - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "gpt-4.1": { - "max_tokens": 32768, - "max_input_tokens": 1047576, - "max_output_tokens": 32768, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 8e-06, - "input_cost_per_token_batches": 1e-06, - "output_cost_per_token_batches": 4e-06, - "cache_read_input_token_cost": 5e-07, - "litellm_provider": "openai", - "mode": "chat", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_pdf_input": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_native_streaming": true - }, - "gpt-4.1-2025-04-14": { - "max_tokens": 32768, - "max_input_tokens": 1047576, - "max_output_tokens": 32768, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 8e-06, - "input_cost_per_token_batches": 1e-06, - "output_cost_per_token_batches": 4e-06, - "cache_read_input_token_cost": 5e-07, - "litellm_provider": "openai", - "mode": "chat", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_pdf_input": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_native_streaming": true - }, - "gpt-4.1-mini": { - "max_tokens": 32768, - "max_input_tokens": 1047576, - "max_output_tokens": 32768, - "input_cost_per_token": 4e-07, - "output_cost_per_token": 1.6e-06, - "input_cost_per_token_batches": 2e-07, - "output_cost_per_token_batches": 8e-07, - "cache_read_input_token_cost": 1e-07, - "litellm_provider": "openai", - "mode": "chat", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_pdf_input": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_native_streaming": true - }, - "gpt-4.1-mini-2025-04-14": { - "max_tokens": 32768, - "max_input_tokens": 1047576, - "max_output_tokens": 32768, - "input_cost_per_token": 4e-07, - "output_cost_per_token": 1.6e-06, - "input_cost_per_token_batches": 2e-07, - "output_cost_per_token_batches": 8e-07, - "cache_read_input_token_cost": 1e-07, - "litellm_provider": "openai", - "mode": "chat", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_pdf_input": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_native_streaming": true - }, - "gpt-4.1-nano": { - "max_tokens": 32768, - "max_input_tokens": 1047576, - "max_output_tokens": 32768, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 4e-07, - "input_cost_per_token_batches": 5e-08, - "output_cost_per_token_batches": 2e-07, - "cache_read_input_token_cost": 2.5e-08, - "litellm_provider": "openai", - "mode": "chat", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_pdf_input": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_native_streaming": true - }, - "gpt-4.1-nano-2025-04-14": { - "max_tokens": 32768, - "max_input_tokens": 1047576, - "max_output_tokens": 32768, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 4e-07, - "input_cost_per_token_batches": 5e-08, - "output_cost_per_token_batches": 2e-07, - "cache_read_input_token_cost": 2.5e-08, - "litellm_provider": "openai", - "mode": "chat", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_pdf_input": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_native_streaming": true - }, - "gpt-4o": { - "max_tokens": 16384, - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "input_cost_per_token": 2.5e-06, - "output_cost_per_token": 1e-05, - "input_cost_per_token_batches": 1.25e-06, - "output_cost_per_token_batches": 5e-06, - "cache_read_input_token_cost": 1.25e-06, - "litellm_provider": "openai", - "mode": "chat", - "supports_pdf_input": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "watsonx/ibm/granite-3-8b-instruct": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 1024, - "input_cost_per_token": 0.0002, - "output_cost_per_token": 0.0002, - "litellm_provider": "watsonx", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_parallel_function_calling": false, - "supports_vision": false, - "supports_audio_input": false, - "supports_audio_output": false, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_system_messages": true - }, - "watsonx/mistralai/mistral-large": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 16384, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1e-05, - "litellm_provider": "watsonx", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_parallel_function_calling": false, - "supports_vision": false, - "supports_audio_input": false, - "supports_audio_output": false, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_system_messages": true - }, - "gpt-4o-search-preview-2025-03-11": { - "max_tokens": 16384, - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "input_cost_per_token": 2.5e-06, - "output_cost_per_token": 1e-05, - "input_cost_per_token_batches": 1.25e-06, - "output_cost_per_token_batches": 5e-06, - "cache_read_input_token_cost": 1.25e-06, - "litellm_provider": "openai", - "mode": "chat", - "supports_pdf_input": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "gpt-4o-search-preview": { - "max_tokens": 16384, - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "input_cost_per_token": 2.5e-06, - "output_cost_per_token": 1e-05, - "input_cost_per_token_batches": 1.25e-06, - "output_cost_per_token_batches": 5e-06, - "cache_read_input_token_cost": 1.25e-06, - "litellm_provider": "openai", - "mode": "chat", - "supports_pdf_input": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_web_search": true, - "search_context_cost_per_query": { - "search_context_size_low": 0.03, - "search_context_size_medium": 0.035, - "search_context_size_high": 0.05 - } - }, - "gpt-4.5-preview": { - "max_tokens": 16384, - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "input_cost_per_token": 7.5e-05, - "output_cost_per_token": 0.00015, - "input_cost_per_token_batches": 3.75e-05, - "output_cost_per_token_batches": 7.5e-05, - "cache_read_input_token_cost": 3.75e-05, - "litellm_provider": "openai", - "mode": "chat", - "supports_pdf_input": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "gpt-4.5-preview-2025-02-27": { - "max_tokens": 16384, - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "input_cost_per_token": 7.5e-05, - "output_cost_per_token": 0.00015, - "input_cost_per_token_batches": 3.75e-05, - "output_cost_per_token_batches": 7.5e-05, - "cache_read_input_token_cost": 3.75e-05, - "litellm_provider": "openai", - "mode": "chat", - "supports_pdf_input": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "deprecation_date": "2025-07-14" - }, - "gpt-4o-audio-preview": { - "max_tokens": 16384, - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "input_cost_per_token": 2.5e-06, - "input_cost_per_audio_token": 0.0001, - "output_cost_per_token": 1e-05, - "output_cost_per_audio_token": 0.0002, - "litellm_provider": "openai", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_audio_input": true, - "supports_audio_output": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "gpt-4o-audio-preview-2024-12-17": { - "max_tokens": 16384, - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "input_cost_per_token": 2.5e-06, - "input_cost_per_audio_token": 4e-05, - "output_cost_per_token": 1e-05, - "output_cost_per_audio_token": 8e-05, - "litellm_provider": "openai", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_audio_input": true, - "supports_audio_output": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "gpt-4o-audio-preview-2024-10-01": { - "max_tokens": 16384, - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "input_cost_per_token": 2.5e-06, - "input_cost_per_audio_token": 0.0001, - "output_cost_per_token": 1e-05, - "output_cost_per_audio_token": 0.0002, - "litellm_provider": "openai", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_audio_input": true, - "supports_audio_output": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "gpt-4o-audio-preview-2025-06-03": { - "max_tokens": 16384, - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "input_cost_per_token": 2.5e-06, - "input_cost_per_audio_token": 4e-05, - "output_cost_per_token": 1e-05, - "output_cost_per_audio_token": 8e-05, - "litellm_provider": "openai", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_audio_input": true, - "supports_audio_output": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "gpt-4o-mini-audio-preview": { - "max_tokens": 16384, - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "input_cost_per_token": 1.5e-07, - "input_cost_per_audio_token": 1e-05, - "output_cost_per_token": 6e-07, - "output_cost_per_audio_token": 2e-05, - "litellm_provider": "openai", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_audio_input": true, - "supports_audio_output": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "gpt-4o-mini-audio-preview-2024-12-17": { - "max_tokens": 16384, - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "input_cost_per_token": 1.5e-07, - "input_cost_per_audio_token": 1e-05, - "output_cost_per_token": 6e-07, - "output_cost_per_audio_token": 2e-05, - "litellm_provider": "openai", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_audio_input": true, - "supports_audio_output": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "gpt-4o-mini": { - "max_tokens": 16384, - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 6e-07, - "input_cost_per_token_batches": 7.5e-08, - "output_cost_per_token_batches": 3e-07, - "cache_read_input_token_cost": 7.5e-08, - "litellm_provider": "openai", - "mode": "chat", - "supports_pdf_input": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "gpt-4o-mini-search-preview-2025-03-11": { - "max_tokens": 16384, - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 6e-07, - "input_cost_per_token_batches": 7.5e-08, - "output_cost_per_token_batches": 3e-07, - "cache_read_input_token_cost": 7.5e-08, - "litellm_provider": "openai", - "mode": "chat", - "supports_pdf_input": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "gpt-4o-mini-search-preview": { - "max_tokens": 16384, - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 6e-07, - "input_cost_per_token_batches": 7.5e-08, - "output_cost_per_token_batches": 3e-07, - "cache_read_input_token_cost": 7.5e-08, - "litellm_provider": "openai", - "mode": "chat", - "supports_pdf_input": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_web_search": true, - "search_context_cost_per_query": { - "search_context_size_low": 0.025, - "search_context_size_medium": 0.0275, - "search_context_size_high": 0.03 - } - }, - "gpt-4o-mini-2024-07-18": { - "max_tokens": 16384, - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 6e-07, - "input_cost_per_token_batches": 7.5e-08, - "output_cost_per_token_batches": 3e-07, - "cache_read_input_token_cost": 7.5e-08, - "litellm_provider": "openai", - "mode": "chat", - "supports_pdf_input": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "search_context_cost_per_query": { - "search_context_size_low": 0.025, - "search_context_size_medium": 0.0275, - "search_context_size_high": 0.03 - } - }, - "gpt-5": { - "max_tokens": 128000, - "max_input_tokens": 400000, - "max_output_tokens": 128000, - "input_cost_per_token": 1.25e-06, - "output_cost_per_token": 1e-05, - "cache_read_input_token_cost": 1.25e-07, - "litellm_provider": "openai", - "mode": "chat", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_pdf_input": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_native_streaming": true, - "supports_reasoning": true - }, - "gpt-5-mini": { - "max_tokens": 128000, - "max_input_tokens": 400000, - "max_output_tokens": 128000, - "input_cost_per_token": 2.5e-07, - "output_cost_per_token": 2e-06, - "cache_read_input_token_cost": 2.5e-08, - "litellm_provider": "openai", - "mode": "chat", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_pdf_input": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_native_streaming": true, - "supports_reasoning": true - }, - "gpt-5-nano": { - "max_tokens": 128000, - "max_input_tokens": 400000, - "max_output_tokens": 128000, - "input_cost_per_token": 5e-08, - "output_cost_per_token": 4e-07, - "cache_read_input_token_cost": 5e-09, - "litellm_provider": "openai", - "mode": "chat", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_pdf_input": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_native_streaming": true, - "supports_reasoning": true - }, - "gpt-5-chat": { - "max_tokens": 128000, - "max_input_tokens": 400000, - "max_output_tokens": 128000, - "input_cost_per_token": 1.25e-06, - "output_cost_per_token": 1e-05, - "cache_read_input_token_cost": 1.25e-07, - "litellm_provider": "openai", - "mode": "chat", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_pdf_input": true, - "supports_function_calling": false, - "supports_parallel_function_calling": false, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": false, - "supports_native_streaming": true, - "supports_reasoning": true - }, - "gpt-5-chat-latest": { - "max_tokens": 128000, - "max_input_tokens": 400000, - "max_output_tokens": 128000, - "input_cost_per_token": 1.25e-06, - "output_cost_per_token": 1e-05, - "cache_read_input_token_cost": 1.25e-07, - "litellm_provider": "openai", - "mode": "chat", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_pdf_input": true, - "supports_function_calling": false, - "supports_parallel_function_calling": false, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": false, - "supports_native_streaming": true, - "supports_reasoning": true - }, - "gpt-5-2025-08-07": { - "max_tokens": 128000, - "max_input_tokens": 400000, - "max_output_tokens": 128000, - "input_cost_per_token": 1.25e-06, - "output_cost_per_token": 1e-05, - "cache_read_input_token_cost": 1.25e-07, - "litellm_provider": "openai", - "mode": "chat", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_pdf_input": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_native_streaming": true, - "supports_reasoning": true - }, - "gpt-5-mini-2025-08-07": { - "max_tokens": 128000, - "max_input_tokens": 400000, - "max_output_tokens": 128000, - "input_cost_per_token": 2.5e-07, - "output_cost_per_token": 2e-06, - "cache_read_input_token_cost": 2.5e-08, - "litellm_provider": "openai", - "mode": "chat", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_pdf_input": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_native_streaming": true, - "supports_reasoning": true - }, - "gpt-5-nano-2025-08-07": { - "max_tokens": 128000, - "max_input_tokens": 400000, - "max_output_tokens": 128000, - "input_cost_per_token": 5e-08, - "output_cost_per_token": 4e-07, - "cache_read_input_token_cost": 5e-09, - "litellm_provider": "openai", - "mode": "chat", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_pdf_input": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_native_streaming": true, - "supports_reasoning": true - }, - "codex-mini-latest": { - "max_tokens": 100000, - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "input_cost_per_token": 1.5e-06, - "output_cost_per_token": 6e-06, - "cache_read_input_token_cost": 3.75e-07, - "litellm_provider": "openai", - "mode": "responses", - "supports_pdf_input": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supported_endpoints": [ - "/v1/responses" - ] - }, - "o1-pro": { - "max_tokens": 100000, - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "input_cost_per_token": 0.00015, - "output_cost_per_token": 0.0006, - "input_cost_per_token_batches": 7.5e-05, - "output_cost_per_token_batches": 0.0003, - "litellm_provider": "openai", - "mode": "responses", - "supports_pdf_input": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_native_streaming": false, - "supports_reasoning": true, - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supported_endpoints": [ - "/v1/responses", - "/v1/batch" - ] - }, - "o1-pro-2025-03-19": { - "max_tokens": 100000, - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "input_cost_per_token": 0.00015, - "output_cost_per_token": 0.0006, - "input_cost_per_token_batches": 7.5e-05, - "output_cost_per_token_batches": 0.0003, - "litellm_provider": "openai", - "mode": "responses", - "supports_pdf_input": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_native_streaming": false, - "supports_reasoning": true, - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supported_endpoints": [ - "/v1/responses", - "/v1/batch" - ] - }, - "o1": { - "max_tokens": 100000, - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "input_cost_per_token": 1.5e-05, - "output_cost_per_token": 6e-05, - "cache_read_input_token_cost": 7.5e-06, - "litellm_provider": "openai", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_response_schema": true, - "supports_reasoning": true, - "supports_tool_choice": true - }, - "o1-mini": { - "max_tokens": 65536, - "max_input_tokens": 128000, - "max_output_tokens": 65536, - "input_cost_per_token": 1.1e-06, - "output_cost_per_token": 4.4e-06, - "cache_read_input_token_cost": 5.5e-07, - "litellm_provider": "openai", - "mode": "chat", - "supports_vision": true, - "supports_pdf_input": true, - "supports_prompt_caching": true - }, - "computer-use-preview": { - "max_tokens": 1024, - "max_input_tokens": 8192, - "max_output_tokens": 1024, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.2e-05, - "litellm_provider": "azure", - "mode": "chat", - "supported_endpoints": [ - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": false, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_reasoning": true - }, - "o3-deep-research": { - "max_tokens": 100000, - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "input_cost_per_token": 1e-05, - "output_cost_per_token": 4e-05, - "input_cost_per_token_batches": 5e-06, - "output_cost_per_token_batches": 2e-05, - "cache_read_input_token_cost": 2.5e-06, - "litellm_provider": "openai", - "mode": "responses", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_pdf_input": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_native_streaming": true - }, - "o3-deep-research-2025-06-26": { - "max_tokens": 100000, - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "input_cost_per_token": 1e-05, - "output_cost_per_token": 4e-05, - "input_cost_per_token_batches": 5e-06, - "output_cost_per_token_batches": 2e-05, - "cache_read_input_token_cost": 2.5e-06, - "litellm_provider": "openai", - "mode": "responses", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_pdf_input": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_native_streaming": true - }, - "o3-pro": { - "max_tokens": 100000, - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "input_cost_per_token": 2e-05, - "input_cost_per_token_batches": 1e-05, - "output_cost_per_token_batches": 4e-05, - "output_cost_per_token": 8e-05, - "litellm_provider": "openai", - "mode": "responses", - "supports_function_calling": true, - "supports_parallel_function_calling": false, - "supports_vision": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_reasoning": true, - "supports_tool_choice": true, - "supported_endpoints": [ - "/v1/responses", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ] - }, - "o3-pro-2025-06-10": { - "max_tokens": 100000, - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "input_cost_per_token": 2e-05, - "input_cost_per_token_batches": 1e-05, - "output_cost_per_token_batches": 4e-05, - "output_cost_per_token": 8e-05, - "litellm_provider": "openai", - "mode": "responses", - "supports_function_calling": true, - "supports_parallel_function_calling": false, - "supports_vision": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_reasoning": true, - "supports_tool_choice": true, - "supported_endpoints": [ - "/v1/responses", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ] - }, - "o3": { - "max_tokens": 100000, - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 8e-06, - "cache_read_input_token_cost": 5e-07, - "litellm_provider": "openai", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": false, - "supports_vision": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_reasoning": true, - "supports_tool_choice": true, - "supported_endpoints": [ - "/v1/responses", - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ] - }, - "o3-2025-04-16": { - "max_tokens": 100000, - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 8e-06, - "cache_read_input_token_cost": 5e-07, - "litellm_provider": "openai", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": false, - "supports_vision": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_reasoning": true, - "supports_tool_choice": true, - "supported_endpoints": [ - "/v1/responses", - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ] - }, - "o3-mini": { - "max_tokens": 100000, - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "input_cost_per_token": 1.1e-06, - "output_cost_per_token": 4.4e-06, - "cache_read_input_token_cost": 5.5e-07, - "litellm_provider": "openai", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": false, - "supports_vision": false, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_reasoning": true, - "supports_tool_choice": true - }, - "o3-mini-2025-01-31": { - "max_tokens": 100000, - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "input_cost_per_token": 1.1e-06, - "output_cost_per_token": 4.4e-06, - "cache_read_input_token_cost": 5.5e-07, - "litellm_provider": "openai", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": false, - "supports_vision": false, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_reasoning": true, - "supports_tool_choice": true - }, - "o4-mini": { - "max_tokens": 100000, - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "input_cost_per_token": 1.1e-06, - "output_cost_per_token": 4.4e-06, - "cache_read_input_token_cost": 2.75e-07, - "litellm_provider": "openai", - "mode": "chat", - "supports_pdf_input": true, - "supports_function_calling": true, - "supports_parallel_function_calling": false, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_reasoning": true, - "supports_tool_choice": true - }, - "o4-mini-deep-research": { - "max_tokens": 100000, - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 8e-06, - "input_cost_per_token_batches": 1e-06, - "output_cost_per_token_batches": 4e-06, - "cache_read_input_token_cost": 5e-07, - "litellm_provider": "openai", - "mode": "responses", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_pdf_input": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_native_streaming": true - }, - "o4-mini-deep-research-2025-06-26": { - "max_tokens": 100000, - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 8e-06, - "input_cost_per_token_batches": 1e-06, - "output_cost_per_token_batches": 4e-06, - "cache_read_input_token_cost": 5e-07, - "litellm_provider": "openai", - "mode": "responses", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_pdf_input": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_native_streaming": true - }, - "o4-mini-2025-04-16": { - "max_tokens": 100000, - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "input_cost_per_token": 1.1e-06, - "output_cost_per_token": 4.4e-06, - "cache_read_input_token_cost": 2.75e-07, - "litellm_provider": "openai", - "mode": "chat", - "supports_pdf_input": true, - "supports_function_calling": true, - "supports_parallel_function_calling": false, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_reasoning": true, - "supports_tool_choice": true - }, - "o1-mini-2024-09-12": { - "max_tokens": 65536, - "max_input_tokens": 128000, - "max_output_tokens": 65536, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.2e-05, - "cache_read_input_token_cost": 1.5e-06, - "litellm_provider": "openai", - "mode": "chat", - "supports_pdf_input": true, - "supports_vision": true, - "supports_reasoning": true, - "supports_prompt_caching": true - }, - "o1-preview": { - "max_tokens": 32768, - "max_input_tokens": 128000, - "max_output_tokens": 32768, - "input_cost_per_token": 1.5e-05, - "output_cost_per_token": 6e-05, - "cache_read_input_token_cost": 7.5e-06, - "litellm_provider": "openai", - "mode": "chat", - "supports_pdf_input": true, - "supports_vision": true, - "supports_reasoning": true, - "supports_prompt_caching": true - }, - "o1-preview-2024-09-12": { - "max_tokens": 32768, - "max_input_tokens": 128000, - "max_output_tokens": 32768, - "input_cost_per_token": 1.5e-05, - "output_cost_per_token": 6e-05, - "cache_read_input_token_cost": 7.5e-06, - "litellm_provider": "openai", - "mode": "chat", - "supports_pdf_input": true, - "supports_vision": true, - "supports_reasoning": true, - "supports_prompt_caching": true - }, - "o1-2024-12-17": { - "max_tokens": 100000, - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "input_cost_per_token": 1.5e-05, - "output_cost_per_token": 6e-05, - "cache_read_input_token_cost": 7.5e-06, - "litellm_provider": "openai", - "mode": "chat", - "supports_pdf_input": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_response_schema": true, - "supports_reasoning": true, - "supports_tool_choice": true - }, - "chatgpt-4o-latest": { - "max_tokens": 4096, - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 5e-06, - "output_cost_per_token": 1.5e-05, - "litellm_provider": "openai", - "mode": "chat", - "supports_pdf_input": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "gpt-4o-2024-05-13": { - "max_tokens": 4096, - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 5e-06, - "output_cost_per_token": 1.5e-05, - "input_cost_per_token_batches": 2.5e-06, - "output_cost_per_token_batches": 7.5e-06, - "litellm_provider": "openai", - "mode": "chat", - "supports_pdf_input": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "gpt-4o-2024-08-06": { - "max_tokens": 16384, - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "input_cost_per_token": 2.5e-06, - "output_cost_per_token": 1e-05, - "input_cost_per_token_batches": 1.25e-06, - "output_cost_per_token_batches": 5e-06, - "cache_read_input_token_cost": 1.25e-06, - "litellm_provider": "openai", - "mode": "chat", - "supports_pdf_input": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "gpt-4o-2024-11-20": { - "max_tokens": 16384, - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "input_cost_per_token": 2.5e-06, - "output_cost_per_token": 1e-05, - "input_cost_per_token_batches": 1.25e-06, - "output_cost_per_token_batches": 5e-06, - "cache_read_input_token_cost": 1.25e-06, - "litellm_provider": "openai", - "mode": "chat", - "supports_pdf_input": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "gpt-realtime": { - "max_tokens": 4096, - "max_input_tokens": 32000, - "max_output_tokens": 4096, - "input_cost_per_token": 4e-06, - "cache_read_input_token_cost": 0.4e-06, - "output_cost_per_token": 16e-06, - "input_cost_per_audio_token": 32e-06, - "output_cost_per_audio_token": 64e-06, - "cache_creation_input_audio_token_cost": 0.4e-06, - "input_cost_per_image": 5e-06, - "litellm_provider": "openai", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_audio_input": true, - "supports_audio_output": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supported_endpoints": [ - "/v1/realtime" - ], - "supported_modalities": [ - "text", - "image", - "audio" - ], - "supported_output_modalities": [ - "text", - "audio" - ] - }, - "gpt-realtime-2025-08-28": { - "max_tokens": 4096, - "max_input_tokens": 32000, - "max_output_tokens": 4096, - "input_cost_per_token": 4e-06, - "cache_read_input_token_cost": 0.4e-06, - "output_cost_per_token": 16e-06, - "input_cost_per_audio_token": 32e-06, - "output_cost_per_audio_token": 64e-06, - "cache_creation_input_audio_token_cost": 0.4e-06, - "input_cost_per_image": 5e-06, - "litellm_provider": "openai", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_audio_input": true, - "supports_audio_output": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supported_endpoints": [ - "/v1/realtime" - ], - "supported_modalities": [ - "text", - "image", - "audio" - ], - "supported_output_modalities": [ - "text", - "audio" - ] - }, - "gpt-4o-realtime-preview-2024-10-01": { - "max_tokens": 4096, - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 5e-06, - "input_cost_per_audio_token": 0.0001, - "cache_read_input_token_cost": 2.5e-06, - "cache_creation_input_audio_token_cost": 2e-05, - "output_cost_per_token": 2e-05, - "output_cost_per_audio_token": 0.0002, - "litellm_provider": "openai", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_audio_input": true, - "supports_audio_output": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "gpt-4o-realtime-preview": { - "max_tokens": 4096, - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 5e-06, - "input_cost_per_audio_token": 4e-05, - "cache_read_input_token_cost": 2.5e-06, - "output_cost_per_token": 2e-05, - "output_cost_per_audio_token": 8e-05, - "litellm_provider": "openai", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_audio_input": true, - "supports_audio_output": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "gpt-4o-realtime-preview-2024-12-17": { - "max_tokens": 4096, - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 5e-06, - "input_cost_per_audio_token": 4e-05, - "cache_read_input_token_cost": 2.5e-06, - "output_cost_per_token": 2e-05, - "output_cost_per_audio_token": 8e-05, - "litellm_provider": "openai", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_audio_input": true, - "supports_audio_output": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "gpt-4o-realtime-preview-2025-06-03": { - "max_tokens": 4096, - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 5e-06, - "input_cost_per_audio_token": 4e-05, - "cache_read_input_token_cost": 2.5e-06, - "output_cost_per_token": 2e-05, - "output_cost_per_audio_token": 8e-05, - "litellm_provider": "openai", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_audio_input": true, - "supports_audio_output": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "gpt-4o-mini-realtime-preview": { - "max_tokens": 4096, - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 6e-07, - "input_cost_per_audio_token": 1e-05, - "cache_read_input_token_cost": 3e-07, - "cache_creation_input_audio_token_cost": 3e-07, - "output_cost_per_token": 2.4e-06, - "output_cost_per_audio_token": 2e-05, - "litellm_provider": "openai", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_audio_input": true, - "supports_audio_output": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "gpt-4o-mini-realtime-preview-2024-12-17": { - "max_tokens": 4096, - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 6e-07, - "input_cost_per_audio_token": 1e-05, - "cache_read_input_token_cost": 3e-07, - "cache_creation_input_audio_token_cost": 3e-07, - "output_cost_per_token": 2.4e-06, - "output_cost_per_audio_token": 2e-05, - "litellm_provider": "openai", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_audio_input": true, - "supports_audio_output": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "gpt-4-turbo-preview": { - "max_tokens": 4096, - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 1e-05, - "output_cost_per_token": 3e-05, - "litellm_provider": "openai", - "mode": "chat", - "supports_pdf_input": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "gpt-4-0314": { - "max_tokens": 4096, - "max_input_tokens": 8192, - "max_output_tokens": 4096, - "input_cost_per_token": 3e-05, - "output_cost_per_token": 6e-05, - "litellm_provider": "openai", - "mode": "chat", - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "gpt-4-0613": { - "max_tokens": 4096, - "max_input_tokens": 8192, - "max_output_tokens": 4096, - "input_cost_per_token": 3e-05, - "output_cost_per_token": 6e-05, - "litellm_provider": "openai", - "mode": "chat", - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "deprecation_date": "2025-06-06", - "supports_tool_choice": true - }, - "gpt-4-32k": { - "max_tokens": 4096, - "max_input_tokens": 32768, - "max_output_tokens": 4096, - "input_cost_per_token": 6e-05, - "output_cost_per_token": 0.00012, - "litellm_provider": "openai", - "mode": "chat", - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "gpt-4-32k-0314": { - "max_tokens": 4096, - "max_input_tokens": 32768, - "max_output_tokens": 4096, - "input_cost_per_token": 6e-05, - "output_cost_per_token": 0.00012, - "litellm_provider": "openai", - "mode": "chat", - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "gpt-4-32k-0613": { - "max_tokens": 4096, - "max_input_tokens": 32768, - "max_output_tokens": 4096, - "input_cost_per_token": 6e-05, - "output_cost_per_token": 0.00012, - "litellm_provider": "openai", - "mode": "chat", - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "gpt-4-turbo": { - "max_tokens": 4096, - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 1e-05, - "output_cost_per_token": 3e-05, - "litellm_provider": "openai", - "mode": "chat", - "supports_pdf_input": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "gpt-4-turbo-2024-04-09": { - "max_tokens": 4096, - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 1e-05, - "output_cost_per_token": 3e-05, - "litellm_provider": "openai", - "mode": "chat", - "supports_pdf_input": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "gpt-4-1106-preview": { - "max_tokens": 4096, - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 1e-05, - "output_cost_per_token": 3e-05, - "litellm_provider": "openai", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "gpt-4-0125-preview": { - "max_tokens": 4096, - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 1e-05, - "output_cost_per_token": 3e-05, - "litellm_provider": "openai", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "gpt-4-vision-preview": { - "max_tokens": 4096, - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 1e-05, - "output_cost_per_token": 3e-05, - "litellm_provider": "openai", - "mode": "chat", - "supports_vision": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "deprecation_date": "2024-12-06", - "supports_tool_choice": true - }, - "gpt-4-1106-vision-preview": { - "max_tokens": 4096, - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 1e-05, - "output_cost_per_token": 3e-05, - "litellm_provider": "openai", - "mode": "chat", - "supports_vision": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "deprecation_date": "2024-12-06", - "supports_tool_choice": true - }, - "gpt-3.5-turbo": { - "max_tokens": 4097, - "max_input_tokens": 16385, - "max_output_tokens": 4096, - "input_cost_per_token": 1.5e-06, - "output_cost_per_token": 2e-06, - "litellm_provider": "openai", - "mode": "chat", - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "gpt-3.5-turbo-0301": { - "max_tokens": 4097, - "max_input_tokens": 4097, - "max_output_tokens": 4096, - "input_cost_per_token": 1.5e-06, - "output_cost_per_token": 2e-06, - "litellm_provider": "openai", - "mode": "chat", - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "gpt-3.5-turbo-0613": { - "max_tokens": 4097, - "max_input_tokens": 4097, - "max_output_tokens": 4096, - "input_cost_per_token": 1.5e-06, - "output_cost_per_token": 2e-06, - "litellm_provider": "openai", - "mode": "chat", - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "gpt-3.5-turbo-1106": { - "max_tokens": 16385, - "max_input_tokens": 16385, - "max_output_tokens": 4096, - "input_cost_per_token": 1e-06, - "output_cost_per_token": 2e-06, - "litellm_provider": "openai", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "gpt-3.5-turbo-0125": { - "max_tokens": 16385, - "max_input_tokens": 16385, - "max_output_tokens": 4096, - "input_cost_per_token": 5e-07, - "output_cost_per_token": 1.5e-06, - "litellm_provider": "openai", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "gpt-3.5-turbo-16k": { - "max_tokens": 16385, - "max_input_tokens": 16385, - "max_output_tokens": 4096, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 4e-06, - "litellm_provider": "openai", - "mode": "chat", - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "gpt-3.5-turbo-16k-0613": { - "max_tokens": 16385, - "max_input_tokens": 16385, - "max_output_tokens": 4096, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 4e-06, - "litellm_provider": "openai", - "mode": "chat", - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "ft:gpt-3.5-turbo": { - "max_tokens": 4096, - "max_input_tokens": 16385, - "max_output_tokens": 4096, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 6e-06, - "input_cost_per_token_batches": 1.5e-06, - "output_cost_per_token_batches": 3e-06, - "litellm_provider": "openai", - "mode": "chat", - "supports_system_messages": true, - "supports_tool_choice": true - }, - "ft:gpt-3.5-turbo-0125": { - "max_tokens": 4096, - "max_input_tokens": 16385, - "max_output_tokens": 4096, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 6e-06, - "litellm_provider": "openai", - "mode": "chat", - "supports_system_messages": true, - "supports_tool_choice": true - }, - "ft:gpt-3.5-turbo-1106": { - "max_tokens": 4096, - "max_input_tokens": 16385, - "max_output_tokens": 4096, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 6e-06, - "litellm_provider": "openai", - "mode": "chat", - "supports_system_messages": true, - "supports_tool_choice": true - }, - "ft:gpt-3.5-turbo-0613": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 6e-06, - "litellm_provider": "openai", - "mode": "chat", - "supports_system_messages": true, - "supports_tool_choice": true - }, - "ft:gpt-4-0613": { - "max_tokens": 4096, - "max_input_tokens": 8192, - "max_output_tokens": 4096, - "input_cost_per_token": 3e-05, - "output_cost_per_token": 6e-05, - "litellm_provider": "openai", - "mode": "chat", - "supports_function_calling": true, - "source": "OpenAI needs to add pricing for this ft model, will be updated when added by OpenAI. Defaulting to base model pricing", - "supports_system_messages": true, - "supports_tool_choice": true - }, - "ft:gpt-4o-2024-08-06": { - "max_tokens": 16384, - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "input_cost_per_token": 3.75e-06, - "output_cost_per_token": 1.5e-05, - "input_cost_per_token_batches": 1.875e-06, - "output_cost_per_token_batches": 7.5e-06, - "litellm_provider": "openai", - "mode": "chat", - "supports_pdf_input": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "ft:gpt-4o-2024-11-20": { - "max_tokens": 16384, - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "input_cost_per_token": 3.75e-06, - "cache_creation_input_token_cost": 1.875e-06, - "output_cost_per_token": 1.5e-05, - "litellm_provider": "openai", - "mode": "chat", - "supports_pdf_input": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "ft:gpt-4o-mini-2024-07-18": { - "max_tokens": 16384, - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "input_cost_per_token": 3e-07, - "output_cost_per_token": 1.2e-06, - "input_cost_per_token_batches": 1.5e-07, - "output_cost_per_token_batches": 6e-07, - "cache_read_input_token_cost": 1.5e-07, - "litellm_provider": "openai", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "ft:davinci-002": { - "max_tokens": 16384, - "max_input_tokens": 16384, - "max_output_tokens": 4096, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 2e-06, - "input_cost_per_token_batches": 1e-06, - "output_cost_per_token_batches": 1e-06, - "litellm_provider": "text-completion-openai", - "mode": "completion" - }, - "ft:babbage-002": { - "max_tokens": 16384, - "max_input_tokens": 16384, - "max_output_tokens": 4096, - "input_cost_per_token": 4e-07, - "output_cost_per_token": 4e-07, - "input_cost_per_token_batches": 2e-07, - "output_cost_per_token_batches": 2e-07, - "litellm_provider": "text-completion-openai", - "mode": "completion" - }, - "text-embedding-3-large": { - "max_tokens": 8191, - "max_input_tokens": 8191, - "output_vector_size": 3072, - "input_cost_per_token": 1.3e-07, - "output_cost_per_token": 0.0, - "input_cost_per_token_batches": 6.5e-08, - "output_cost_per_token_batches": 0.0, - "litellm_provider": "openai", - "mode": "embedding" - }, - "text-embedding-3-small": { - "max_tokens": 8191, - "max_input_tokens": 8191, - "output_vector_size": 1536, - "input_cost_per_token": 2e-08, - "output_cost_per_token": 0.0, - "input_cost_per_token_batches": 1e-08, - "output_cost_per_token_batches": 0.0, - "litellm_provider": "openai", - "mode": "embedding" - }, - "text-embedding-ada-002": { - "max_tokens": 8191, - "max_input_tokens": 8191, - "output_vector_size": 1536, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 0.0, - "litellm_provider": "openai", - "mode": "embedding" - }, - "text-embedding-ada-002-v2": { - "max_tokens": 8191, - "max_input_tokens": 8191, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 0.0, - "input_cost_per_token_batches": 5e-08, - "output_cost_per_token_batches": 0.0, - "litellm_provider": "openai", - "mode": "embedding" - }, - "text-moderation-stable": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 0, - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "openai", - "mode": "moderation" - }, - "text-moderation-007": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 0, - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "openai", - "mode": "moderation" - }, - "text-moderation-latest": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 0, - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "openai", - "mode": "moderation" - }, - "256-x-256/dall-e-2": { + "1024-x-1024/50-steps/bedrock/amazon.nova-canvas-v1:0": { + "litellm_provider": "bedrock", + "max_input_tokens": 2600, "mode": "image_generation", - "input_cost_per_pixel": 2.4414e-07, - "output_cost_per_pixel": 0.0, - "litellm_provider": "openai" + "output_cost_per_image": 0.06 }, - "512-x-512/dall-e-2": { + "1024-x-1024/50-steps/stability.stable-diffusion-xl-v1": { + "litellm_provider": "bedrock", + "max_input_tokens": 77, + "max_tokens": 77, "mode": "image_generation", - "input_cost_per_pixel": 6.86e-08, - "output_cost_per_pixel": 0.0, - "litellm_provider": "openai" + "output_cost_per_image": 0.04 }, "1024-x-1024/dall-e-2": { - "mode": "image_generation", "input_cost_per_pixel": 1.9e-08, - "output_cost_per_pixel": 0.0, - "litellm_provider": "openai" - }, - "hd/1024-x-1792/dall-e-3": { - "mode": "image_generation", - "input_cost_per_pixel": 6.539e-08, - "output_cost_per_pixel": 0.0, - "litellm_provider": "openai" - }, - "hd/1792-x-1024/dall-e-3": { - "mode": "image_generation", - "input_cost_per_pixel": 6.539e-08, - "output_cost_per_pixel": 0.0, - "litellm_provider": "openai" - }, - "hd/1024-x-1024/dall-e-3": { - "mode": "image_generation", - "input_cost_per_pixel": 7.629e-08, - "output_cost_per_pixel": 0.0, - "litellm_provider": "openai" - }, - "standard/1024-x-1792/dall-e-3": { - "mode": "image_generation", - "input_cost_per_pixel": 4.359e-08, - "output_cost_per_pixel": 0.0, - "litellm_provider": "openai" - }, - "standard/1792-x-1024/dall-e-3": { - "mode": "image_generation", - "input_cost_per_pixel": 4.359e-08, - "output_cost_per_pixel": 0.0, - "litellm_provider": "openai" - }, - "standard/1024-x-1024/dall-e-3": { - "mode": "image_generation", - "input_cost_per_pixel": 3.81469e-08, - "output_cost_per_pixel": 0.0, - "litellm_provider": "openai" - }, - "gpt-image-1": { - "mode": "image_generation", - "input_cost_per_pixel": 4.0054321e-08, - "output_cost_per_pixel": 0.0, "litellm_provider": "openai", - "supported_endpoints": [ - "/v1/images/generations" - ] - }, - "low/1024-x-1024/gpt-image-1": { "mode": "image_generation", - "input_cost_per_pixel": 1.0490417e-08, - "output_cost_per_pixel": 0.0, - "litellm_provider": "openai", - "supported_endpoints": [ - "/v1/images/generations" - ] + "output_cost_per_pixel": 0.0 }, - "medium/1024-x-1024/gpt-image-1": { + "1024-x-1024/max-steps/stability.stable-diffusion-xl-v1": { + "litellm_provider": "bedrock", + "max_input_tokens": 77, + "max_tokens": 77, "mode": "image_generation", - "input_cost_per_pixel": 4.0054321e-08, - "output_cost_per_pixel": 0.0, - "litellm_provider": "openai", - "supported_endpoints": [ - "/v1/images/generations" - ] + "output_cost_per_image": 0.08 }, - "high/1024-x-1024/gpt-image-1": { + "256-x-256/dall-e-2": { + "input_cost_per_pixel": 2.4414e-07, + "litellm_provider": "openai", "mode": "image_generation", - "input_cost_per_pixel": 1.59263611e-07, - "output_cost_per_pixel": 0.0, - "litellm_provider": "openai", - "supported_endpoints": [ - "/v1/images/generations" - ] + "output_cost_per_pixel": 0.0 }, - "low/1024-x-1536/gpt-image-1": { + "512-x-512/50-steps/stability.stable-diffusion-xl-v0": { + "litellm_provider": "bedrock", + "max_input_tokens": 77, + "max_tokens": 77, "mode": "image_generation", - "input_cost_per_pixel": 1.0172526e-08, - "output_cost_per_pixel": 0.0, - "litellm_provider": "openai", - "supported_endpoints": [ - "/v1/images/generations" - ] + "output_cost_per_image": 0.018 }, - "medium/1024-x-1536/gpt-image-1": { + "512-x-512/dall-e-2": { + "input_cost_per_pixel": 6.86e-08, + "litellm_provider": "openai", "mode": "image_generation", - "input_cost_per_pixel": 4.0054321e-08, - "output_cost_per_pixel": 0.0, - "litellm_provider": "openai", - "supported_endpoints": [ - "/v1/images/generations" - ] + "output_cost_per_pixel": 0.0 }, - "high/1024-x-1536/gpt-image-1": { + "512-x-512/max-steps/stability.stable-diffusion-xl-v0": { + "litellm_provider": "bedrock", + "max_input_tokens": 77, + "max_tokens": 77, "mode": "image_generation", - "input_cost_per_pixel": 1.58945719e-07, - "output_cost_per_pixel": 0.0, - "litellm_provider": "openai", - "supported_endpoints": [ - "/v1/images/generations" - ] + "output_cost_per_image": 0.036 }, - "low/1536-x-1024/gpt-image-1": { - "mode": "image_generation", - "input_cost_per_pixel": 1.0172526e-08, - "output_cost_per_pixel": 0.0, - "litellm_provider": "openai", - "supported_endpoints": [ - "/v1/images/generations" - ] - }, - "medium/1536-x-1024/gpt-image-1": { - "mode": "image_generation", - "input_cost_per_pixel": 4.0054321e-08, - "output_cost_per_pixel": 0.0, - "litellm_provider": "openai", - "supported_endpoints": [ - "/v1/images/generations" - ] - }, - "high/1536-x-1024/gpt-image-1": { - "mode": "image_generation", - "input_cost_per_pixel": 1.58945719e-07, - "output_cost_per_pixel": 0.0, - "litellm_provider": "openai", - "supported_endpoints": [ - "/v1/images/generations" - ] - }, - "gpt-4o-transcribe": { - "mode": "audio_transcription", - "max_input_tokens": 16000, - "max_output_tokens": 2000, - "input_cost_per_token": 2.5e-06, - "input_cost_per_audio_token": 6e-06, - "output_cost_per_token": 1e-05, - "litellm_provider": "openai", - "supported_endpoints": [ - "/v1/audio/transcriptions" - ] - }, - "gpt-4o-mini-transcribe": { - "mode": "audio_transcription", - "max_input_tokens": 16000, - "max_output_tokens": 2000, - "input_cost_per_token": 1.25e-06, - "input_cost_per_audio_token": 3e-06, - "output_cost_per_token": 5e-06, - "litellm_provider": "openai", - "supported_endpoints": [ - "/v1/audio/transcriptions" - ] - }, - "whisper-1": { - "mode": "audio_transcription", - "input_cost_per_second": 0.0001, - "output_cost_per_second": 0.0001, - "litellm_provider": "openai", - "supported_endpoints": [ - "/v1/audio/transcriptions" - ] - }, - "tts-1": { - "mode": "audio_speech", - "input_cost_per_character": 1.5e-05, - "litellm_provider": "openai", - "supported_endpoints": [ - "/v1/audio/speech" - ] - }, - "tts-1-hd": { - "mode": "audio_speech", - "input_cost_per_character": 3e-05, - "litellm_provider": "openai", - "supported_endpoints": [ - "/v1/audio/speech" - ] - }, - "gpt-4o-mini-tts": { - "mode": "audio_speech", - "input_cost_per_token": 2.5e-06, - "output_cost_per_token": 1e-05, - "output_cost_per_audio_token": 1.2e-05, - "output_cost_per_second": 0.00025, - "litellm_provider": "openai", - "supported_modalities": [ - "text", - "audio" - ], - "supported_output_modalities": [ - "audio" - ], - "supported_endpoints": [ - "/v1/audio/speech" - ] - }, - "azure/gpt-5": { - "max_tokens": 128000, - "max_input_tokens": 272000, - "max_output_tokens": 128000, - "input_cost_per_token": 1.25e-06, - "output_cost_per_token": 1e-05, - "cache_read_input_token_cost": 1.25e-07, - "litellm_provider": "azure", + "ai21.j2-mid-v1": { + "input_cost_per_token": 1.25e-05, + "litellm_provider": "bedrock", + "max_input_tokens": 8191, + "max_output_tokens": 8191, + "max_tokens": 8191, "mode": "chat", + "output_cost_per_token": 1.25e-05 + }, + "ai21.j2-ultra-v1": { + "input_cost_per_token": 1.88e-05, + "litellm_provider": "bedrock", + "max_input_tokens": 8191, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 1.88e-05 + }, + "ai21.jamba-1-5-large-v1:0": { + "input_cost_per_token": 2e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 8e-06 + }, + "ai21.jamba-1-5-mini-v1:0": { + "input_cost_per_token": 2e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 4e-07 + }, + "ai21.jamba-instruct-v1:0": { + "input_cost_per_token": 5e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 70000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 7e-07, + "supports_system_messages": true + }, + "aiml/dall-e-2": { + "litellm_provider": "aiml", + "metadata": { + "notes": "DALL-E 2 via AI/ML API - Reliable text-to-image generation" + }, + "mode": "image_generation", + "output_cost_per_image": 0.021, + "source": "https://docs.aimlapi.com/", "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_pdf_input": true, + "/v1/images/generations" + ] + }, + "aiml/dall-e-3": { + "litellm_provider": "aiml", + "metadata": { + "notes": "DALL-E 3 via AI/ML API - High-quality text-to-image generation" + }, + "mode": "image_generation", + "output_cost_per_image": 0.042, + "source": "https://docs.aimlapi.com/", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "aiml/flux-pro": { + "litellm_provider": "aiml", + "metadata": { + "notes": "Flux Dev - Development version optimized for experimentation" + }, + "mode": "image_generation", + "output_cost_per_image": 0.053, + "source": "https://docs.aimlapi.com/", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "aiml/flux-pro/v1.1": { + "litellm_provider": "aiml", + "mode": "image_generation", + "output_cost_per_image": 0.042, + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "aiml/flux-pro/v1.1-ultra": { + "litellm_provider": "aiml", + "mode": "image_generation", + "output_cost_per_image": 0.063, + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "aiml/flux-realism": { + "litellm_provider": "aiml", + "metadata": { + "notes": "Flux Pro - Professional-grade image generation model" + }, + "mode": "image_generation", + "output_cost_per_image": 0.037, + "source": "https://docs.aimlapi.com/", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "aiml/flux/dev": { + "litellm_provider": "aiml", + "metadata": { + "notes": "Flux Dev - Development version optimized for experimentation" + }, + "mode": "image_generation", + "output_cost_per_image": 0.026, + "source": "https://docs.aimlapi.com/", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "aiml/flux/kontext-max/text-to-image": { + "litellm_provider": "aiml", + "metadata": { + "notes": "Flux Pro v1.1 - Enhanced version with improved capabilities and 6x faster inference speed" + }, + "mode": "image_generation", + "output_cost_per_image": 0.084, + "source": "https://docs.aimlapi.com/", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "aiml/flux/kontext-pro/text-to-image": { + "litellm_provider": "aiml", + "metadata": { + "notes": "Flux Pro v1.1 - Enhanced version with improved capabilities and 6x faster inference speed" + }, + "mode": "image_generation", + "output_cost_per_image": 0.042, + "source": "https://docs.aimlapi.com/", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "aiml/flux/schnell": { + "litellm_provider": "aiml", + "metadata": { + "notes": "Flux Schnell - Fast generation model optimized for speed" + }, + "mode": "image_generation", + "output_cost_per_image": 0.003, + "source": "https://docs.aimlapi.com/", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "amazon.nova-lite-v1:0": { + "input_cost_per_token": 6e-08, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 300000, + "max_output_tokens": 10000, + "max_tokens": 10000, + "mode": "chat", + "output_cost_per_token": 2.4e-07, "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, + "supports_pdf_input": true, "supports_prompt_caching": true, - "supports_system_messages": true, + "supports_response_schema": true, + "supports_vision": true + }, + "amazon.nova-micro-v1:0": { + "input_cost_per_token": 3.5e-08, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 128000, + "max_output_tokens": 10000, + "max_tokens": 10000, + "mode": "chat", + "output_cost_per_token": 1.4e-07, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true + }, + "amazon.nova-pro-v1:0": { + "input_cost_per_token": 8e-07, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 300000, + "max_output_tokens": 10000, + "max_tokens": 10000, + "mode": "chat", + "output_cost_per_token": 3.2e-06, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_vision": true + }, + "amazon.rerank-v1:0": { + "input_cost_per_query": 0.001, + "input_cost_per_token": 0.0, + "litellm_provider": "bedrock", + "max_document_chunks_per_query": 100, + "max_input_tokens": 32000, + "max_output_tokens": 32000, + "max_query_tokens": 32000, + "max_tokens": 32000, + "max_tokens_per_document_chunk": 512, + "mode": "rerank", + "output_cost_per_token": 0.0 + }, + "amazon.titan-embed-image-v1": { + "input_cost_per_image": 6e-05, + "input_cost_per_token": 8e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 128, + "max_tokens": 128, + "metadata": { + "notes": "'supports_image_input' is a deprecated field. Use 'supports_embedding_image_input' instead." + }, + "mode": "embedding", + "output_cost_per_token": 0.0, + "output_vector_size": 1024, + "source": "https://us-east-1.console.aws.amazon.com/bedrock/home?region=us-east-1#/providers?model=amazon.titan-image-generator-v1", + "supports_embedding_image_input": true, + "supports_image_input": true + }, + "amazon.titan-embed-text-v1": { + "input_cost_per_token": 1e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 8192, + "max_tokens": 8192, + "mode": "embedding", + "output_cost_per_token": 0.0, + "output_vector_size": 1536 + }, + "amazon.titan-embed-text-v2:0": { + "input_cost_per_token": 2e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 8192, + "max_tokens": 8192, + "mode": "embedding", + "output_cost_per_token": 0.0, + "output_vector_size": 1024 + }, + "amazon.titan-text-express-v1": { + "input_cost_per_token": 1.3e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 42000, + "max_output_tokens": 8000, + "max_tokens": 8000, + "mode": "chat", + "output_cost_per_token": 1.7e-06 + }, + "amazon.titan-text-lite-v1": { + "input_cost_per_token": 3e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 42000, + "max_output_tokens": 4000, + "max_tokens": 4000, + "mode": "chat", + "output_cost_per_token": 4e-07 + }, + "amazon.titan-text-premier-v1:0": { + "input_cost_per_token": 5e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 42000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 1.5e-06 + }, + "anthropic.claude-3-5-haiku-20241022-v1:0": { + "cache_creation_input_token_cost": 1e-06, + "cache_read_input_token_cost": 8e-08, + "input_cost_per_token": 8e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 4e-06, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "anthropic.claude-3-5-sonnet-20240620-v1:0": { + "input_cost_per_token": 3e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_response_schema": true, "supports_tool_choice": true, - "supports_native_streaming": true, - "supports_reasoning": true + "supports_vision": true }, - "azure/gpt-5-2025-08-07": { - "max_tokens": 128000, - "max_input_tokens": 272000, - "max_output_tokens": 128000, - "input_cost_per_token": 1.25e-06, - "output_cost_per_token": 1e-05, - "cache_read_input_token_cost": 1.25e-07, - "litellm_provider": "azure", + "anthropic.claude-3-5-sonnet-20241022-v2:0": { + "cache_creation_input_token_cost": 3.75e-06, + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 3e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_pdf_input": true, + "output_cost_per_token": 1.5e-05, + "supports_assistant_prefill": true, + "supports_computer_use": true, "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, + "supports_pdf_input": true, "supports_prompt_caching": true, - "supports_system_messages": true, + "supports_response_schema": true, "supports_tool_choice": true, - "supports_native_streaming": true, - "supports_reasoning": true + "supports_vision": true }, - "azure/gpt-5-mini": { - "max_tokens": 128000, - "max_input_tokens": 272000, - "max_output_tokens": 128000, - "input_cost_per_token": 2.5e-07, - "output_cost_per_token": 2e-06, - "cache_read_input_token_cost": 2.5e-08, - "litellm_provider": "azure", + "anthropic.claude-3-7-sonnet-20250219-v1:0": { + "cache_creation_input_token_cost": 3.75e-06, + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 3e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_pdf_input": true, + "output_cost_per_token": 1.5e-05, + "supports_assistant_prefill": true, + "supports_computer_use": true, "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_native_streaming": true, - "supports_reasoning": true - }, - "azure/gpt-5-mini-2025-08-07": { - "max_tokens": 128000, - "max_input_tokens": 272000, - "max_output_tokens": 128000, - "input_cost_per_token": 2.5e-07, - "output_cost_per_token": 2e-06, - "cache_read_input_token_cost": 2.5e-08, - "litellm_provider": "azure", - "mode": "chat", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], "supports_pdf_input": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_native_streaming": true, - "supports_reasoning": true - }, - "azure/gpt-5-nano-2025-08-07": { - "max_tokens": 128000, - "max_input_tokens": 272000, - "max_output_tokens": 128000, - "input_cost_per_token": 5e-08, - "output_cost_per_token": 4e-07, - "cache_read_input_token_cost": 5e-09, - "litellm_provider": "azure", - "mode": "chat", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_pdf_input": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_native_streaming": true, - "supports_reasoning": true - }, - "azure/gpt-5-nano": { - "max_tokens": 128000, - "max_input_tokens": 272000, - "max_output_tokens": 128000, - "input_cost_per_token": 5e-08, - "output_cost_per_token": 4e-07, - "cache_read_input_token_cost": 5e-09, - "litellm_provider": "azure", - "mode": "chat", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_pdf_input": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_native_streaming": true, - "supports_reasoning": true - }, - "azure/gpt-5-chat": { - "max_tokens": 128000, - "max_input_tokens": 272000, - "max_output_tokens": 128000, - "input_cost_per_token": 1.25e-06, - "output_cost_per_token": 1e-05, - "cache_read_input_token_cost": 1.25e-07, - "litellm_provider": "azure", - "mode": "chat", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_pdf_input": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": false, - "supports_native_streaming": true, "supports_reasoning": true, - "source": "https://azure.microsoft.com/en-us/blog/gpt-5-in-azure-ai-foundry-the-future-of-ai-apps-and-agents-starts-here/" + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true }, - "azure/gpt-5-chat-latest": { - "max_tokens": 128000, - "max_input_tokens": 272000, - "max_output_tokens": 128000, - "input_cost_per_token": 1.25e-06, - "output_cost_per_token": 1e-05, - "cache_read_input_token_cost": 1.25e-07, - "litellm_provider": "azure", + "anthropic.claude-3-haiku-20240307-v1:0": { + "input_cost_per_token": 2.5e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", + "output_cost_per_token": 1.25e-06, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "anthropic.claude-3-opus-20240229-v1:0": { + "input_cost_per_token": 1.5e-05, + "litellm_provider": "bedrock", + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 7.5e-05, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "anthropic.claude-3-sonnet-20240229-v1:0": { + "input_cost_per_token": 3e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "anthropic.claude-instant-v1": { + "input_cost_per_token": 8e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 2.4e-06, + "supports_tool_choice": true + }, + "anthropic.claude-opus-4-1-20250805-v1:0": { + "cache_creation_input_token_cost": 1.875e-05, + "cache_read_input_token_cost": 1.5e-06, + "input_cost_per_token": 1.5e-05, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 200000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 7.5e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159 + }, + "anthropic.claude-opus-4-20250514-v1:0": { + "cache_creation_input_token_cost": 1.875e-05, + "cache_read_input_token_cost": 1.5e-06, + "input_cost_per_token": 1.5e-05, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 200000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 7.5e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159 + }, + "anthropic.claude-sonnet-4-20250514-v1:0": { + "cache_creation_input_token_cost": 3.75e-06, + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 3e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159 + }, + "anthropic.claude-v1": { + "input_cost_per_token": 8e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 2.4e-05 + }, + "anthropic.claude-v2:1": { + "input_cost_per_token": 8e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 2.4e-05, + "supports_tool_choice": true + }, + "anyscale/HuggingFaceH4/zephyr-7b-beta": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "anyscale", + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1.5e-07 + }, + "anyscale/codellama/CodeLlama-34b-Instruct-hf": { + "input_cost_per_token": 1e-06, + "litellm_provider": "anyscale", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1e-06 + }, + "anyscale/codellama/CodeLlama-70b-Instruct-hf": { + "input_cost_per_token": 1e-06, + "litellm_provider": "anyscale", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1e-06, + "source": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/codellama-CodeLlama-70b-Instruct-hf" + }, + "anyscale/google/gemma-7b-it": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "anyscale", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.5e-07, + "source": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/google-gemma-7b-it" + }, + "anyscale/meta-llama/Llama-2-13b-chat-hf": { + "input_cost_per_token": 2.5e-07, + "litellm_provider": "anyscale", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 2.5e-07 + }, + "anyscale/meta-llama/Llama-2-70b-chat-hf": { + "input_cost_per_token": 1e-06, + "litellm_provider": "anyscale", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1e-06 + }, + "anyscale/meta-llama/Llama-2-7b-chat-hf": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "anyscale", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.5e-07 + }, + "anyscale/meta-llama/Meta-Llama-3-70B-Instruct": { + "input_cost_per_token": 1e-06, + "litellm_provider": "anyscale", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1e-06, + "source": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/meta-llama-Meta-Llama-3-70B-Instruct" + }, + "anyscale/meta-llama/Meta-Llama-3-8B-Instruct": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "anyscale", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.5e-07, + "source": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/meta-llama-Meta-Llama-3-8B-Instruct" + }, + "anyscale/mistralai/Mistral-7B-Instruct-v0.1": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "anyscale", + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1.5e-07, + "source": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/mistralai-Mistral-7B-Instruct-v0.1", + "supports_function_calling": true + }, + "anyscale/mistralai/Mixtral-8x22B-Instruct-v0.1": { + "input_cost_per_token": 9e-07, + "litellm_provider": "anyscale", + "max_input_tokens": 65536, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 9e-07, + "source": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/mistralai-Mixtral-8x22B-Instruct-v0.1", + "supports_function_calling": true + }, + "anyscale/mistralai/Mixtral-8x7B-Instruct-v0.1": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "anyscale", + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1.5e-07, + "source": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/mistralai-Mixtral-8x7B-Instruct-v0.1", + "supports_function_calling": true + }, + "apac.amazon.nova-lite-v1:0": { + "input_cost_per_token": 6.3e-08, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 300000, + "max_output_tokens": 10000, + "max_tokens": 10000, + "mode": "chat", + "output_cost_per_token": 2.52e-07, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_vision": true + }, + "apac.amazon.nova-micro-v1:0": { + "input_cost_per_token": 3.7e-08, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 128000, + "max_output_tokens": 10000, + "max_tokens": 10000, + "mode": "chat", + "output_cost_per_token": 1.48e-07, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true + }, + "apac.amazon.nova-pro-v1:0": { + "input_cost_per_token": 8.4e-07, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 300000, + "max_output_tokens": 10000, + "max_tokens": 10000, + "mode": "chat", + "output_cost_per_token": 3.36e-06, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_vision": true + }, + "apac.anthropic.claude-3-5-sonnet-20240620-v1:0": { + "input_cost_per_token": 3e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "apac.anthropic.claude-3-5-sonnet-20241022-v2:0": { + "cache_creation_input_token_cost": 3.75e-06, + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 3e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "apac.anthropic.claude-3-haiku-20240307-v1:0": { + "input_cost_per_token": 2.5e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.25e-06, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "apac.anthropic.claude-3-sonnet-20240229-v1:0": { + "input_cost_per_token": 3e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "apac.anthropic.claude-sonnet-4-20250514-v1:0": { + "cache_creation_input_token_cost": 3.75e-06, + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 3e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159 + }, + "assemblyai/best": { + "input_cost_per_second": 3.333e-05, + "litellm_provider": "assemblyai", + "mode": "audio_transcription", + "output_cost_per_second": 0.0 + }, + "assemblyai/nano": { + "input_cost_per_second": 0.00010278, + "litellm_provider": "assemblyai", + "mode": "audio_transcription", + "output_cost_per_second": 0.0 + }, + "azure/ada": { + "input_cost_per_token": 1e-07, + "litellm_provider": "azure", + "max_input_tokens": 8191, + "max_tokens": 8191, + "mode": "embedding", + "output_cost_per_token": 0.0 + }, + "azure/codex-mini": { + "cache_read_input_token_cost": 3.75e-07, + "input_cost_per_token": 1.5e-06, + "litellm_provider": "azure", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "responses", + "output_cost_per_token": 6e-06, "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", "/v1/responses" ], "supported_modalities": [ @@ -2574,43 +825,34 @@ "supported_output_modalities": [ "text" ], - "supports_pdf_input": true, "supports_function_calling": true, "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, + "supports_pdf_input": true, "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, "supports_system_messages": true, - "supports_tool_choice": false, - "supports_native_streaming": true, - "supports_reasoning": true + "supports_tool_choice": true, + "supports_vision": true }, - "azure/gpt-4o-mini-tts": { - "mode": "audio_speech", - "input_cost_per_token": 2.5e-06, - "output_cost_per_token": 1e-05, - "output_cost_per_audio_token": 1.2e-05, - "output_cost_per_second": 0.00025, + "azure/command-r-plus": { + "input_cost_per_token": 3e-06, "litellm_provider": "azure", - "supported_modalities": [ - "text", - "audio" - ], - "supported_output_modalities": [ - "audio" - ], - "supported_endpoints": [ - "/v1/audio/speech" - ] + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "supports_function_calling": true }, "azure/computer-use-preview": { - "max_tokens": 1024, + "input_cost_per_token": 3e-06, + "litellm_provider": "azure", "max_input_tokens": 8192, "max_output_tokens": 1024, - "input_cost_per_token": 3e-06, + "max_tokens": 1024, + "mode": "chat", "output_cost_per_token": 1.2e-05, - "litellm_provider": "azure", - "mode": "chat", "supported_endpoints": [ "/v1/responses" ], @@ -2623,2209 +865,2284 @@ ], "supports_function_calling": true, "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_reasoning": true + "supports_vision": true }, - "azure/gpt-4o-audio-preview-2024-12-17": { - "max_tokens": 16384, + "azure/eu/gpt-4o-2024-08-06": { + "cache_read_input_token_cost": 1.375e-06, + "input_cost_per_token": 2.75e-06, + "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, - "input_cost_per_token": 2.5e-06, - "input_cost_per_audio_token": 4e-05, - "output_cost_per_token": 1e-05, - "output_cost_per_audio_token": 8e-05, - "litellm_provider": "azure", + "max_tokens": 16384, "mode": "chat", - "supported_endpoints": [ - "/v1/chat/completions" - ], - "supported_modalities": [ - "text", - "audio" - ], - "supported_output_modalities": [ - "text", - "audio" - ], + "output_cost_per_token": 1.1e-05, "supports_function_calling": true, "supports_parallel_function_calling": true, - "supports_response_schema": false, - "supports_vision": false, - "supports_prompt_caching": false, - "supports_system_messages": true, + "supports_prompt_caching": true, + "supports_response_schema": true, "supports_tool_choice": true, - "supports_native_streaming": true, - "supports_reasoning": false + "supports_vision": true }, - "azure/gpt-4o-mini-audio-preview-2024-12-17": { - "max_tokens": 16384, + "azure/eu/gpt-4o-2024-11-20": { + "cache_creation_input_token_cost": 1.38e-06, + "input_cost_per_token": 2.75e-06, + "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, - "input_cost_per_token": 2.5e-06, - "input_cost_per_audio_token": 4e-05, - "output_cost_per_token": 1e-05, - "output_cost_per_audio_token": 8e-05, - "litellm_provider": "azure", + "max_tokens": 16384, "mode": "chat", - "supported_endpoints": [ - "/v1/chat/completions" - ], - "supported_modalities": [ - "text", - "audio" - ], - "supported_output_modalities": [ - "text", - "audio" - ], - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": false, - "supports_vision": false, - "supports_prompt_caching": false, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_native_streaming": true, - "supports_reasoning": false - }, - "azure/gpt-4.1": { - "max_tokens": 32768, - "max_input_tokens": 1047576, - "max_output_tokens": 32768, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 8e-06, - "input_cost_per_token_batches": 1e-06, - "output_cost_per_token_batches": 4e-06, - "cache_read_input_token_cost": 5e-07, - "litellm_provider": "azure", - "mode": "chat", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], + "output_cost_per_token": 1.1e-05, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, "supports_tool_choice": true, - "supports_native_streaming": true, - "supports_web_search": false + "supports_vision": true }, - "azure/gpt-4.1-2025-04-14": { - "max_tokens": 32768, - "max_input_tokens": 1047576, - "max_output_tokens": 32768, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 8e-06, - "input_cost_per_token_batches": 1e-06, - "output_cost_per_token_batches": 4e-06, - "cache_read_input_token_cost": 5e-07, + "azure/eu/gpt-4o-mini-2024-07-18": { + "cache_read_input_token_cost": 8.3e-08, + "input_cost_per_token": 1.65e-07, "litellm_provider": "azure", - "mode": "chat", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_native_streaming": true, - "supports_web_search": false - }, - "azure/gpt-4.1-mini": { - "max_tokens": 32768, - "max_input_tokens": 1047576, - "max_output_tokens": 32768, - "input_cost_per_token": 4e-07, - "output_cost_per_token": 1.6e-06, - "input_cost_per_token_batches": 2e-07, - "output_cost_per_token_batches": 8e-07, - "cache_read_input_token_cost": 1e-07, - "litellm_provider": "azure", - "mode": "chat", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_native_streaming": true, - "supports_web_search": false - }, - "azure/gpt-4.1-mini-2025-04-14": { - "max_tokens": 32768, - "max_input_tokens": 1047576, - "max_output_tokens": 32768, - "input_cost_per_token": 4e-07, - "output_cost_per_token": 1.6e-06, - "input_cost_per_token_batches": 2e-07, - "output_cost_per_token_batches": 8e-07, - "cache_read_input_token_cost": 1e-07, - "litellm_provider": "azure", - "mode": "chat", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_native_streaming": true, - "supports_web_search": false - }, - "azure/gpt-4.1-nano": { - "max_tokens": 32768, - "max_input_tokens": 1047576, - "max_output_tokens": 32768, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 4e-07, - "input_cost_per_token_batches": 5e-08, - "output_cost_per_token_batches": 2e-07, - "cache_read_input_token_cost": 2.5e-08, - "litellm_provider": "azure", - "mode": "chat", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_native_streaming": true - }, - "azure/gpt-4.1-nano-2025-04-14": { - "max_tokens": 32768, - "max_input_tokens": 1047576, - "max_output_tokens": 32768, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 4e-07, - "input_cost_per_token_batches": 5e-08, - "output_cost_per_token_batches": 2e-07, - "cache_read_input_token_cost": 2.5e-08, - "litellm_provider": "azure", - "mode": "chat", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_native_streaming": true - }, - "azure/o3-pro": { - "max_tokens": 100000, - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "input_cost_per_token": 2e-05, - "output_cost_per_token": 8e-05, - "input_cost_per_token_batches": 1e-05, - "output_cost_per_token_batches": 4e-05, - "litellm_provider": "azure", - "mode": "responses", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": true, - "supports_parallel_function_calling": false, - "supports_vision": true, - "supports_prompt_caching": false, - "supports_response_schema": true, - "supports_reasoning": true, - "supports_tool_choice": true - }, - "azure/o3-pro-2025-06-10": { - "max_tokens": 100000, - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "input_cost_per_token": 2e-05, - "output_cost_per_token": 8e-05, - "input_cost_per_token_batches": 1e-05, - "output_cost_per_token_batches": 4e-05, - "litellm_provider": "azure", - "mode": "responses", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": true, - "supports_parallel_function_calling": false, - "supports_vision": true, - "supports_prompt_caching": false, - "supports_response_schema": true, - "supports_reasoning": true, - "supports_tool_choice": true - }, - "azure/o3": { - "max_tokens": 100000, - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 8e-06, - "cache_read_input_token_cost": 5e-07, - "litellm_provider": "azure", - "mode": "chat", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": true, - "supports_parallel_function_calling": false, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_reasoning": true, - "supports_tool_choice": true - }, - "azure/o3-2025-04-16": { - "max_tokens": 100000, - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "input_cost_per_token": 1e-05, - "output_cost_per_token": 4e-05, - "cache_read_input_token_cost": 2.5e-06, - "litellm_provider": "azure", - "mode": "chat", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": true, - "supports_parallel_function_calling": false, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_reasoning": true, - "supports_tool_choice": true - }, - "azure/o3-deep-research": { - "max_tokens": 100000, - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "input_cost_per_token": 1e-05, - "output_cost_per_token": 4e-05, - "cache_read_input_token_cost": 2.5e-06, - "litellm_provider": "azure", - "mode": "responses", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_pdf_input": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_web_search": true - }, - "azure/o4-mini": { - "max_tokens": 100000, - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "input_cost_per_token": 1.1e-06, - "output_cost_per_token": 4.4e-06, - "cache_read_input_token_cost": 2.75e-07, - "litellm_provider": "azure", - "mode": "chat", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": true, - "supports_parallel_function_calling": false, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_reasoning": true, - "supports_tool_choice": true - }, - "azure/gpt-4o-mini-realtime-preview-2024-12-17": { - "max_tokens": 4096, "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 6e-07, - "input_cost_per_audio_token": 1e-05, - "cache_read_input_token_cost": 3e-07, - "cache_creation_input_audio_token_cost": 3e-07, - "output_cost_per_token": 2.4e-06, - "output_cost_per_audio_token": 2e-05, - "litellm_provider": "azure", + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", + "output_cost_per_token": 6.6e-07, "supports_function_calling": true, "supports_parallel_function_calling": true, - "supports_audio_input": true, - "supports_audio_output": true, - "supports_system_messages": true, - "supports_tool_choice": true + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true }, "azure/eu/gpt-4o-mini-realtime-preview-2024-12-17": { - "max_tokens": 4096, - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 6.6e-07, - "input_cost_per_audio_token": 1.1e-05, - "cache_read_input_token_cost": 3.3e-07, "cache_creation_input_audio_token_cost": 3.3e-07, - "output_cost_per_token": 2.64e-06, - "output_cost_per_audio_token": 2.2e-05, - "litellm_provider": "azure", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_audio_input": true, - "supports_audio_output": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "azure/us/gpt-4o-mini-realtime-preview-2024-12-17": { - "max_tokens": 4096, - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 6.6e-07, - "input_cost_per_audio_token": 1.1e-05, "cache_read_input_token_cost": 3.3e-07, - "cache_creation_input_audio_token_cost": 3.3e-07, - "output_cost_per_token": 2.64e-06, + "input_cost_per_audio_token": 1.1e-05, + "input_cost_per_token": 6.6e-07, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", "output_cost_per_audio_token": 2.2e-05, - "litellm_provider": "azure", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, + "output_cost_per_token": 2.64e-06, "supports_audio_input": true, "supports_audio_output": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "azure/gpt-4o-realtime-preview-2024-12-17": { - "max_tokens": 4096, - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 5e-06, - "input_cost_per_audio_token": 4e-05, - "cache_read_input_token_cost": 2.5e-06, - "output_cost_per_token": 2e-05, - "output_cost_per_audio_token": 8e-05, - "litellm_provider": "azure", - "mode": "chat", - "supported_modalities": [ - "text", - "audio" - ], - "supported_output_modalities": [ - "text", - "audio" - ], "supports_function_calling": true, "supports_parallel_function_calling": true, - "supports_audio_input": true, - "supports_audio_output": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "azure/us/gpt-4o-realtime-preview-2024-12-17": { - "max_tokens": 4096, - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 5.5e-06, - "input_cost_per_audio_token": 4.4e-05, - "cache_read_input_token_cost": 2.75e-06, - "cache_read_input_audio_token_cost": 2.5e-06, - "output_cost_per_token": 2.2e-05, - "output_cost_per_audio_token": 8e-05, - "litellm_provider": "azure", - "mode": "chat", - "supported_modalities": [ - "text", - "audio" - ], - "supported_output_modalities": [ - "text", - "audio" - ], - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_audio_input": true, - "supports_audio_output": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "azure/eu/gpt-4o-realtime-preview-2024-12-17": { - "max_tokens": 4096, - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 5.5e-06, - "input_cost_per_audio_token": 4.4e-05, - "cache_read_input_token_cost": 2.75e-06, - "cache_read_input_audio_token_cost": 2.5e-06, - "output_cost_per_token": 2.2e-05, - "output_cost_per_audio_token": 8e-05, - "litellm_provider": "azure", - "mode": "chat", - "supported_modalities": [ - "text", - "audio" - ], - "supported_output_modalities": [ - "text", - "audio" - ], - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_audio_input": true, - "supports_audio_output": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "azure/gpt-4o-realtime-preview-2024-10-01": { - "max_tokens": 4096, - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 5e-06, - "input_cost_per_audio_token": 0.0001, - "cache_read_input_token_cost": 2.5e-06, - "cache_creation_input_audio_token_cost": 2e-05, - "output_cost_per_token": 2e-05, - "output_cost_per_audio_token": 0.0002, - "litellm_provider": "azure", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_audio_input": true, - "supports_audio_output": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "azure/us/gpt-4o-realtime-preview-2024-10-01": { - "max_tokens": 4096, - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 5.5e-06, - "input_cost_per_audio_token": 0.00011, - "cache_read_input_token_cost": 2.75e-06, - "cache_creation_input_audio_token_cost": 2.2e-05, - "output_cost_per_token": 2.2e-05, - "output_cost_per_audio_token": 0.00022, - "litellm_provider": "azure", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_audio_input": true, - "supports_audio_output": true, "supports_system_messages": true, "supports_tool_choice": true }, "azure/eu/gpt-4o-realtime-preview-2024-10-01": { - "max_tokens": 4096, + "cache_creation_input_audio_token_cost": 2.2e-05, + "cache_read_input_token_cost": 2.75e-06, + "input_cost_per_audio_token": 0.00011, + "input_cost_per_token": 5.5e-06, + "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 4096, - "input_cost_per_token": 5.5e-06, - "input_cost_per_audio_token": 0.00011, - "cache_read_input_token_cost": 2.75e-06, - "cache_creation_input_audio_token_cost": 2.2e-05, - "output_cost_per_token": 2.2e-05, - "output_cost_per_audio_token": 0.00022, - "litellm_provider": "azure", + "max_tokens": 4096, "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, + "output_cost_per_audio_token": 0.00022, + "output_cost_per_token": 2.2e-05, "supports_audio_input": true, "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true }, - "azure/o4-mini-2025-04-16": { - "max_tokens": 100000, - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "input_cost_per_token": 1.1e-06, - "output_cost_per_token": 4.4e-06, - "cache_read_input_token_cost": 2.75e-07, + "azure/eu/gpt-4o-realtime-preview-2024-12-17": { + "cache_read_input_audio_token_cost": 2.5e-06, + "cache_read_input_token_cost": 2.75e-06, + "input_cost_per_audio_token": 4.4e-05, + "input_cost_per_token": 5.5e-06, "litellm_provider": "azure", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": false, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_reasoning": true, - "supports_tool_choice": true - }, - "azure/o3-mini-2025-01-31": { - "max_tokens": 100000, - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "input_cost_per_token": 1.1e-06, - "output_cost_per_token": 4.4e-06, - "cache_read_input_token_cost": 5.5e-07, - "litellm_provider": "azure", - "mode": "chat", - "supports_reasoning": true, - "supports_vision": false, - "supports_prompt_caching": true, - "supports_tool_choice": true - }, - "azure/us/o3-mini-2025-01-31": { - "max_tokens": 100000, - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "input_cost_per_token": 1.21e-06, - "input_cost_per_token_batches": 6.05e-07, - "output_cost_per_token": 4.84e-06, - "output_cost_per_token_batches": 2.42e-06, - "cache_read_input_token_cost": 6.05e-07, - "litellm_provider": "azure", - "mode": "chat", - "supports_vision": false, - "supports_reasoning": true, - "supports_prompt_caching": true, - "supports_tool_choice": true - }, - "azure/eu/o3-mini-2025-01-31": { - "max_tokens": 100000, - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "input_cost_per_token": 1.21e-06, - "input_cost_per_token_batches": 6.05e-07, - "output_cost_per_token": 4.84e-06, - "output_cost_per_token_batches": 2.42e-06, - "cache_read_input_token_cost": 6.05e-07, - "litellm_provider": "azure", - "mode": "chat", - "supports_vision": false, - "supports_reasoning": true, - "supports_prompt_caching": true, - "supports_tool_choice": true - }, - "azure/tts-1": { - "mode": "audio_speech", - "input_cost_per_character": 1.5e-05, - "litellm_provider": "azure" - }, - "azure/tts-1-hd": { - "mode": "audio_speech", - "input_cost_per_character": 3e-05, - "litellm_provider": "azure" - }, - "azure/whisper-1": { - "mode": "audio_transcription", - "input_cost_per_second": 0.0001, - "output_cost_per_second": 0.0001, - "litellm_provider": "azure" - }, - "azure/gpt-4o-transcribe": { - "mode": "audio_transcription", - "max_input_tokens": 16000, - "max_output_tokens": 2000, - "input_cost_per_token": 2.5e-06, - "input_cost_per_audio_token": 6e-06, - "output_cost_per_token": 1e-05, - "litellm_provider": "azure", - "supported_endpoints": [ - "/v1/audio/transcriptions" - ] - }, - "azure/gpt-4o-mini-transcribe": { - "mode": "audio_transcription", - "max_input_tokens": 16000, - "max_output_tokens": 2000, - "input_cost_per_token": 1.25e-06, - "input_cost_per_audio_token": 3e-06, - "output_cost_per_token": 5e-06, - "litellm_provider": "azure", - "supported_endpoints": [ - "/v1/audio/transcriptions" - ] - }, - "azure/o3-mini": { - "max_tokens": 100000, - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "input_cost_per_token": 1.1e-06, - "output_cost_per_token": 4.4e-06, - "cache_read_input_token_cost": 5.5e-07, - "litellm_provider": "azure", - "mode": "chat", - "supports_vision": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "azure/o1-mini": { - "max_tokens": 65536, "max_input_tokens": 128000, - "max_output_tokens": 65536, - "input_cost_per_token": 1.21e-06, - "output_cost_per_token": 4.84e-06, - "cache_read_input_token_cost": 6.05e-07, - "litellm_provider": "azure", + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", + "output_cost_per_audio_token": 8e-05, + "output_cost_per_token": 2.2e-05, + "supported_modalities": [ + "text", + "audio" + ], + "supported_output_modalities": [ + "text", + "audio" + ], + "supports_audio_input": true, + "supports_audio_output": true, "supports_function_calling": true, "supports_parallel_function_calling": true, - "supports_vision": false, - "supports_reasoning": true, - "supports_prompt_caching": true - }, - "azure/o1-mini-2024-09-12": { - "max_tokens": 65536, - "max_input_tokens": 128000, - "max_output_tokens": 65536, - "input_cost_per_token": 1.1e-06, - "output_cost_per_token": 4.4e-06, - "cache_read_input_token_cost": 5.5e-07, - "litellm_provider": "azure", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_vision": false, - "supports_reasoning": true, - "supports_prompt_caching": true - }, - "azure/us/o1-mini-2024-09-12": { - "max_tokens": 65536, - "max_input_tokens": 128000, - "max_output_tokens": 65536, - "input_cost_per_token": 1.21e-06, - "input_cost_per_token_batches": 6.05e-07, - "output_cost_per_token": 4.84e-06, - "output_cost_per_token_batches": 2.42e-06, - "cache_read_input_token_cost": 6.05e-07, - "litellm_provider": "azure", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_vision": false, - "supports_prompt_caching": true - }, - "azure/eu/o1-mini-2024-09-12": { - "max_tokens": 65536, - "max_input_tokens": 128000, - "max_output_tokens": 65536, - "input_cost_per_token": 1.21e-06, - "input_cost_per_token_batches": 6.05e-07, - "output_cost_per_token": 4.84e-06, - "output_cost_per_token_batches": 2.42e-06, - "cache_read_input_token_cost": 6.05e-07, - "litellm_provider": "azure", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_vision": false, - "supports_prompt_caching": true - }, - "azure/o1": { - "max_tokens": 100000, - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "input_cost_per_token": 1.5e-05, - "output_cost_per_token": 6e-05, - "cache_read_input_token_cost": 7.5e-06, - "litellm_provider": "azure", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_vision": true, - "supports_reasoning": true, - "supports_prompt_caching": true, - "supports_tool_choice": true - }, - "azure/o1-2024-12-17": { - "max_tokens": 100000, - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "input_cost_per_token": 1.5e-05, - "output_cost_per_token": 6e-05, - "cache_read_input_token_cost": 7.5e-06, - "litellm_provider": "azure", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_vision": true, - "supports_reasoning": true, - "supports_prompt_caching": true, - "supports_tool_choice": true - }, - "azure/us/o1-2024-12-17": { - "max_tokens": 100000, - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "input_cost_per_token": 1.65e-05, - "output_cost_per_token": 6.6e-05, - "cache_read_input_token_cost": 8.25e-06, - "litellm_provider": "azure", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_vision": true, - "supports_prompt_caching": true, + "supports_system_messages": true, "supports_tool_choice": true }, "azure/eu/o1-2024-12-17": { - "max_tokens": 100000, - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "input_cost_per_token": 1.65e-05, - "output_cost_per_token": 6.6e-05, "cache_read_input_token_cost": 8.25e-06, + "input_cost_per_token": 1.65e-05, "litellm_provider": "azure", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_tool_choice": true - }, - "azure/codex-mini": { - "max_tokens": 100000, "max_input_tokens": 200000, "max_output_tokens": 100000, - "input_cost_per_token": 1.5e-06, - "output_cost_per_token": 6e-06, - "cache_read_input_token_cost": 3.75e-07, - "litellm_provider": "azure", - "mode": "responses", - "supports_pdf_input": true, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 6.6e-05, "supports_function_calling": true, "supports_parallel_function_calling": true, - "supports_vision": true, "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_response_schema": true, "supports_tool_choice": true, - "supports_reasoning": true, - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supported_endpoints": [ - "/v1/responses" - ] + "supports_vision": true }, - "azure/o1-preview": { - "max_tokens": 32768, - "max_input_tokens": 128000, - "max_output_tokens": 32768, - "input_cost_per_token": 1.5e-05, - "output_cost_per_token": 6e-05, - "cache_read_input_token_cost": 7.5e-06, + "azure/eu/o1-mini-2024-09-12": { + "cache_read_input_token_cost": 6.05e-07, + "input_cost_per_token": 1.21e-06, + "input_cost_per_token_batches": 6.05e-07, "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 65536, + "max_tokens": 65536, "mode": "chat", + "output_cost_per_token": 4.84e-06, + "output_cost_per_token_batches": 2.42e-06, "supports_function_calling": true, "supports_parallel_function_calling": true, - "supports_vision": false, - "supports_reasoning": true, - "supports_prompt_caching": true - }, - "azure/o1-preview-2024-09-12": { - "max_tokens": 32768, - "max_input_tokens": 128000, - "max_output_tokens": 32768, - "input_cost_per_token": 1.5e-05, - "output_cost_per_token": 6e-05, - "cache_read_input_token_cost": 7.5e-06, - "litellm_provider": "azure", - "mode": "chat", - "supports_pdf_input": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_vision": false, - "supports_reasoning": true, - "supports_prompt_caching": true - }, - "azure/us/o1-preview-2024-09-12": { - "max_tokens": 32768, - "max_input_tokens": 128000, - "max_output_tokens": 32768, - "input_cost_per_token": 1.65e-05, - "output_cost_per_token": 6.6e-05, - "cache_read_input_token_cost": 8.25e-06, - "litellm_provider": "azure", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_vision": false, - "supports_prompt_caching": true + "supports_prompt_caching": true, + "supports_vision": false }, "azure/eu/o1-preview-2024-09-12": { - "max_tokens": 32768, + "cache_read_input_token_cost": 8.25e-06, + "input_cost_per_token": 1.65e-05, + "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 32768, - "input_cost_per_token": 1.65e-05, + "max_tokens": 32768, + "mode": "chat", "output_cost_per_token": 6.6e-05, - "cache_read_input_token_cost": 8.25e-06, - "litellm_provider": "azure", - "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true, - "supports_vision": false, - "supports_prompt_caching": true - }, - "azure/gpt-4.5-preview": { - "max_tokens": 16384, - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "input_cost_per_token": 7.5e-05, - "output_cost_per_token": 0.00015, - "input_cost_per_token_batches": 3.75e-05, - "output_cost_per_token_batches": 7.5e-05, - "cache_read_input_token_cost": 3.75e-05, - "litellm_provider": "azure", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true + "supports_vision": false }, - "azure/gpt-4o": { - "max_tokens": 16384, - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "input_cost_per_token": 2.5e-06, - "output_cost_per_token": 1e-05, - "cache_read_input_token_cost": 1.25e-06, + "azure/eu/o3-mini-2025-01-31": { + "cache_read_input_token_cost": 6.05e-07, + "input_cost_per_token": 1.21e-06, + "input_cost_per_token_batches": 6.05e-07, "litellm_provider": "azure", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, + "output_cost_per_token": 4.84e-06, + "output_cost_per_token_batches": 2.42e-06, "supports_prompt_caching": true, - "supports_tool_choice": true - }, - "azure/global/gpt-4o-2024-11-20": { - "max_tokens": 16384, - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "input_cost_per_token": 2.5e-06, - "output_cost_per_token": 1e-05, - "cache_read_input_token_cost": 1.25e-06, - "litellm_provider": "azure", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_tool_choice": true - }, - "azure/gpt-4o-2024-08-06": { - "max_tokens": 16384, - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "input_cost_per_token": 2.5e-06, - "output_cost_per_token": 1e-05, - "cache_read_input_token_cost": 1.25e-06, - "litellm_provider": "azure", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_tool_choice": true - }, - "azure/global/gpt-4o-2024-08-06": { - "max_tokens": 16384, - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "input_cost_per_token": 2.5e-06, - "output_cost_per_token": 1e-05, - "cache_read_input_token_cost": 1.25e-06, - "litellm_provider": "azure", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_tool_choice": true - }, - "azure/gpt-4o-2024-11-20": { - "max_tokens": 16384, - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "input_cost_per_token": 2.75e-06, - "output_cost_per_token": 1.1e-05, - "cache_read_input_token_cost": 1.25e-06, - "litellm_provider": "azure", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_tool_choice": true - }, - "azure/us/gpt-4o-2024-11-20": { - "max_tokens": 16384, - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "input_cost_per_token": 2.75e-06, - "cache_creation_input_token_cost": 1.38e-06, - "output_cost_per_token": 1.1e-05, - "litellm_provider": "azure", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_tool_choice": true - }, - "azure/eu/gpt-4o-2024-11-20": { - "max_tokens": 16384, - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "input_cost_per_token": 2.75e-06, - "cache_creation_input_token_cost": 1.38e-06, - "output_cost_per_token": 1.1e-05, - "litellm_provider": "azure", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_tool_choice": true - }, - "azure/gpt-4o-2024-05-13": { - "max_tokens": 4096, - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 5e-06, - "output_cost_per_token": 1.5e-05, - "litellm_provider": "azure", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_tool_choice": true + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false }, "azure/global-standard/gpt-4o-2024-08-06": { - "max_tokens": 16384, - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "input_cost_per_token": 2.5e-06, - "output_cost_per_token": 1e-05, "cache_read_input_token_cost": 1.25e-06, + "deprecation_date": "2025-08-20", + "input_cost_per_token": 2.5e-06, "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", + "output_cost_per_token": 1e-05, "supports_function_calling": true, "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, "supports_prompt_caching": true, + "supports_response_schema": true, "supports_tool_choice": true, - "deprecation_date": "2025-08-20" - }, - "azure/us/gpt-4o-2024-08-06": { - "max_tokens": 16384, - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "input_cost_per_token": 2.75e-06, - "output_cost_per_token": 1.1e-05, - "cache_read_input_token_cost": 1.375e-06, - "litellm_provider": "azure", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_tool_choice": true - }, - "azure/eu/gpt-4o-2024-08-06": { - "max_tokens": 16384, - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "input_cost_per_token": 2.75e-06, - "output_cost_per_token": 1.1e-05, - "cache_read_input_token_cost": 1.375e-06, - "litellm_provider": "azure", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_tool_choice": true + "supports_vision": true }, "azure/global-standard/gpt-4o-2024-11-20": { - "max_tokens": 16384, + "cache_read_input_token_cost": 1.25e-06, + "deprecation_date": "2025-12-20", + "input_cost_per_token": 2.5e-06, + "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, - "input_cost_per_token": 2.5e-06, - "output_cost_per_token": 1e-05, - "cache_read_input_token_cost": 1.25e-06, - "litellm_provider": "azure", + "max_tokens": 16384, "mode": "chat", + "output_cost_per_token": 1e-05, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, - "supports_vision": true, "supports_tool_choice": true, - "deprecation_date": "2025-12-20" + "supports_vision": true }, "azure/global-standard/gpt-4o-mini": { - "max_tokens": 16384, - "max_input_tokens": 128000, - "max_output_tokens": 16384, "input_cost_per_token": 1.5e-07, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", "output_cost_per_token": 6e-07, - "litellm_provider": "azure", - "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, - "supports_vision": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_vision": true }, - "azure/gpt-4o-mini": { - "max_tokens": 16384, + "azure/global/gpt-4o-2024-08-06": { + "cache_read_input_token_cost": 1.25e-06, + "input_cost_per_token": 2.5e-06, + "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, - "input_cost_per_token": 1.65e-07, - "output_cost_per_token": 6.6e-07, - "cache_read_input_token_cost": 7.5e-08, - "litellm_provider": "azure", + "max_tokens": 16384, "mode": "chat", + "output_cost_per_token": 1e-05, "supports_function_calling": true, "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, "supports_prompt_caching": true, - "supports_tool_choice": true + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true }, - "azure/gpt-4o-mini-2024-07-18": { - "max_tokens": 16384, + "azure/global/gpt-4o-2024-11-20": { + "cache_read_input_token_cost": 1.25e-06, + "input_cost_per_token": 2.5e-06, + "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, - "input_cost_per_token": 1.65e-07, - "output_cost_per_token": 6.6e-07, - "cache_read_input_token_cost": 7.5e-08, - "litellm_provider": "azure", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_tool_choice": true - }, - "azure/us/gpt-4o-mini-2024-07-18": { "max_tokens": 16384, - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "input_cost_per_token": 1.65e-07, - "output_cost_per_token": 6.6e-07, - "cache_read_input_token_cost": 8.3e-08, - "litellm_provider": "azure", "mode": "chat", + "output_cost_per_token": 1e-05, "supports_function_calling": true, "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, "supports_prompt_caching": true, - "supports_tool_choice": true + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true }, - "azure/eu/gpt-4o-mini-2024-07-18": { - "max_tokens": 16384, - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "input_cost_per_token": 1.65e-07, - "output_cost_per_token": 6.6e-07, - "cache_read_input_token_cost": 8.3e-08, + "azure/gpt-3.5-turbo": { + "input_cost_per_token": 5e-07, "litellm_provider": "azure", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_tool_choice": true - }, - "azure/gpt-4-turbo-2024-04-09": { - "max_tokens": 4096, - "max_input_tokens": 128000, + "max_input_tokens": 4097, "max_output_tokens": 4096, - "input_cost_per_token": 1e-05, - "output_cost_per_token": 3e-05, - "litellm_provider": "azure", + "max_tokens": 4096, "mode": "chat", + "output_cost_per_token": 1.5e-06, + "supports_function_calling": true, + "supports_tool_choice": true + }, + "azure/gpt-3.5-turbo-0125": { + "deprecation_date": "2025-03-31", + "input_cost_per_token": 5e-07, + "litellm_provider": "azure", + "max_input_tokens": 16384, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.5e-06, "supports_function_calling": true, "supports_parallel_function_calling": true, - "supports_vision": true, + "supports_tool_choice": true + }, + "azure/gpt-3.5-turbo-instruct-0914": { + "input_cost_per_token": 1.5e-06, + "litellm_provider": "azure_text", + "max_input_tokens": 4097, + "max_tokens": 4097, + "mode": "completion", + "output_cost_per_token": 2e-06 + }, + "azure/gpt-35-turbo": { + "input_cost_per_token": 5e-07, + "litellm_provider": "azure", + "max_input_tokens": 4097, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.5e-06, + "supports_function_calling": true, + "supports_tool_choice": true + }, + "azure/gpt-35-turbo-0125": { + "deprecation_date": "2025-05-31", + "input_cost_per_token": 5e-07, + "litellm_provider": "azure", + "max_input_tokens": 16384, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.5e-06, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true + }, + "azure/gpt-35-turbo-0301": { + "deprecation_date": "2025-02-13", + "input_cost_per_token": 2e-07, + "litellm_provider": "azure", + "max_input_tokens": 4097, + "max_output_tokens": 4096, + "max_tokens": 4097, + "mode": "chat", + "output_cost_per_token": 2e-06, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true + }, + "azure/gpt-35-turbo-0613": { + "deprecation_date": "2025-02-13", + "input_cost_per_token": 1.5e-06, + "litellm_provider": "azure", + "max_input_tokens": 4097, + "max_output_tokens": 4096, + "max_tokens": 4097, + "mode": "chat", + "output_cost_per_token": 2e-06, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true + }, + "azure/gpt-35-turbo-1106": { + "deprecation_date": "2025-03-31", + "input_cost_per_token": 1e-06, + "litellm_provider": "azure", + "max_input_tokens": 16384, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 2e-06, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true + }, + "azure/gpt-35-turbo-16k": { + "input_cost_per_token": 3e-06, + "litellm_provider": "azure", + "max_input_tokens": 16385, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 4e-06, + "supports_tool_choice": true + }, + "azure/gpt-35-turbo-16k-0613": { + "input_cost_per_token": 3e-06, + "litellm_provider": "azure", + "max_input_tokens": 16385, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 4e-06, + "supports_function_calling": true, + "supports_tool_choice": true + }, + "azure/gpt-35-turbo-instruct": { + "input_cost_per_token": 1.5e-06, + "litellm_provider": "azure_text", + "max_input_tokens": 4097, + "max_tokens": 4097, + "mode": "completion", + "output_cost_per_token": 2e-06 + }, + "azure/gpt-35-turbo-instruct-0914": { + "input_cost_per_token": 1.5e-06, + "litellm_provider": "azure_text", + "max_input_tokens": 4097, + "max_tokens": 4097, + "mode": "completion", + "output_cost_per_token": 2e-06 + }, + "azure/gpt-4": { + "input_cost_per_token": 3e-05, + "litellm_provider": "azure", + "max_input_tokens": 8192, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 6e-05, + "supports_function_calling": true, "supports_tool_choice": true }, "azure/gpt-4-0125-preview": { - "max_tokens": 4096, + "input_cost_per_token": 1e-05, + "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 4096, - "input_cost_per_token": 1e-05, - "output_cost_per_token": 3e-05, - "litellm_provider": "azure", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_tool_choice": true - }, - "azure/gpt-4-1106-preview": { "max_tokens": 4096, - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 1e-05, - "output_cost_per_token": 3e-05, - "litellm_provider": "azure", "mode": "chat", + "output_cost_per_token": 3e-05, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true }, "azure/gpt-4-0613": { - "max_tokens": 4096, + "input_cost_per_token": 3e-05, + "litellm_provider": "azure", "max_input_tokens": 8192, "max_output_tokens": 4096, - "input_cost_per_token": 3e-05, - "output_cost_per_token": 6e-05, - "litellm_provider": "azure", + "max_tokens": 4096, "mode": "chat", + "output_cost_per_token": 6e-05, "supports_function_calling": true, "supports_tool_choice": true }, - "azure/gpt-4-32k-0613": { - "max_tokens": 4096, - "max_input_tokens": 32768, - "max_output_tokens": 4096, - "input_cost_per_token": 6e-05, - "output_cost_per_token": 0.00012, + "azure/gpt-4-1106-preview": { + "input_cost_per_token": 1e-05, "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", + "output_cost_per_token": 3e-05, + "supports_function_calling": true, + "supports_parallel_function_calling": true, "supports_tool_choice": true }, "azure/gpt-4-32k": { - "max_tokens": 4096, + "input_cost_per_token": 6e-05, + "litellm_provider": "azure", "max_input_tokens": 32768, "max_output_tokens": 4096, - "input_cost_per_token": 6e-05, - "output_cost_per_token": 0.00012, - "litellm_provider": "azure", + "max_tokens": 4096, "mode": "chat", + "output_cost_per_token": 0.00012, "supports_tool_choice": true }, - "azure/gpt-4": { - "max_tokens": 4096, - "max_input_tokens": 8192, - "max_output_tokens": 4096, - "input_cost_per_token": 3e-05, - "output_cost_per_token": 6e-05, + "azure/gpt-4-32k-0613": { + "input_cost_per_token": 6e-05, "litellm_provider": "azure", + "max_input_tokens": 32768, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", - "supports_function_calling": true, + "output_cost_per_token": 0.00012, "supports_tool_choice": true }, "azure/gpt-4-turbo": { - "max_tokens": 4096, + "input_cost_per_token": 1e-05, + "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 4096, - "input_cost_per_token": 1e-05, - "output_cost_per_token": 3e-05, - "litellm_provider": "azure", + "max_tokens": 4096, "mode": "chat", + "output_cost_per_token": 3e-05, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true }, + "azure/gpt-4-turbo-2024-04-09": { + "input_cost_per_token": 1e-05, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 3e-05, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true + }, "azure/gpt-4-turbo-vision-preview": { - "max_tokens": 4096, - "max_input_tokens": 128000, - "max_output_tokens": 4096, "input_cost_per_token": 1e-05, - "output_cost_per_token": 3e-05, "litellm_provider": "azure", - "mode": "chat", - "supports_vision": true, - "supports_tool_choice": true - }, - "azure/gpt-35-turbo-16k-0613": { - "max_tokens": 4096, - "max_input_tokens": 16385, - "max_output_tokens": 4096, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 4e-06, - "litellm_provider": "azure", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true - }, - "azure/gpt-35-turbo-1106": { - "max_tokens": 4096, - "max_input_tokens": 16384, - "max_output_tokens": 4096, - "input_cost_per_token": 1e-06, - "output_cost_per_token": 2e-06, - "litellm_provider": "azure", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "deprecation_date": "2025-03-31", - "supports_tool_choice": true - }, - "azure/gpt-35-turbo-0613": { - "max_tokens": 4097, - "max_input_tokens": 4097, - "max_output_tokens": 4096, - "input_cost_per_token": 1.5e-06, - "output_cost_per_token": 2e-06, - "litellm_provider": "azure", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "deprecation_date": "2025-02-13", - "supports_tool_choice": true - }, - "azure/gpt-35-turbo-0301": { - "max_tokens": 4097, - "max_input_tokens": 4097, - "max_output_tokens": 4096, - "input_cost_per_token": 2e-07, - "output_cost_per_token": 2e-06, - "litellm_provider": "azure", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "deprecation_date": "2025-02-13", - "supports_tool_choice": true - }, - "azure/gpt-35-turbo-0125": { - "max_tokens": 4096, - "max_input_tokens": 16384, - "max_output_tokens": 4096, - "input_cost_per_token": 5e-07, - "output_cost_per_token": 1.5e-06, - "litellm_provider": "azure", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "deprecation_date": "2025-05-31", - "supports_tool_choice": true - }, - "azure/gpt-3.5-turbo-0125": { - "max_tokens": 4096, - "max_input_tokens": 16384, - "max_output_tokens": 4096, - "input_cost_per_token": 5e-07, - "output_cost_per_token": 1.5e-06, - "litellm_provider": "azure", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "deprecation_date": "2025-03-31", - "supports_tool_choice": true - }, - "azure/gpt-35-turbo-16k": { - "max_tokens": 4096, - "max_input_tokens": 16385, - "max_output_tokens": 4096, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 4e-06, - "litellm_provider": "azure", - "mode": "chat", - "supports_tool_choice": true - }, - "azure/gpt-35-turbo": { - "max_tokens": 4096, - "max_input_tokens": 4097, - "max_output_tokens": 4096, - "input_cost_per_token": 5e-07, - "output_cost_per_token": 1.5e-06, - "litellm_provider": "azure", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true - }, - "azure/gpt-3.5-turbo": { - "max_tokens": 4096, - "max_input_tokens": 4097, - "max_output_tokens": 4096, - "input_cost_per_token": 5e-07, - "output_cost_per_token": 1.5e-06, - "litellm_provider": "azure", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true - }, - "azure/gpt-3.5-turbo-instruct-0914": { - "max_tokens": 4097, - "max_input_tokens": 4097, - "input_cost_per_token": 1.5e-06, - "output_cost_per_token": 2e-06, - "litellm_provider": "azure_text", - "mode": "completion" - }, - "azure/gpt-35-turbo-instruct": { - "max_tokens": 4097, - "max_input_tokens": 4097, - "input_cost_per_token": 1.5e-06, - "output_cost_per_token": 2e-06, - "litellm_provider": "azure_text", - "mode": "completion" - }, - "azure/gpt-35-turbo-instruct-0914": { - "max_tokens": 4097, - "max_input_tokens": 4097, - "input_cost_per_token": 1.5e-06, - "output_cost_per_token": 2e-06, - "litellm_provider": "azure_text", - "mode": "completion" - }, - "azure/mistral-large-latest": { - "max_tokens": 32000, - "max_input_tokens": 32000, - "input_cost_per_token": 8e-06, - "output_cost_per_token": 2.4e-05, - "litellm_provider": "azure", - "mode": "chat", - "supports_function_calling": true - }, - "azure/mistral-large-2402": { - "max_tokens": 32000, - "max_input_tokens": 32000, - "input_cost_per_token": 8e-06, - "output_cost_per_token": 2.4e-05, - "litellm_provider": "azure", - "mode": "chat", - "supports_function_calling": true - }, - "azure/command-r-plus": { - "max_tokens": 4096, "max_input_tokens": 128000, "max_output_tokens": 4096, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "litellm_provider": "azure", + "max_tokens": 4096, "mode": "chat", - "supports_function_calling": true + "output_cost_per_token": 3e-05, + "supports_tool_choice": true, + "supports_vision": true }, - "azure/ada": { - "max_tokens": 8191, - "max_input_tokens": 8191, + "azure/gpt-4.1": { + "cache_read_input_token_cost": 5e-07, + "input_cost_per_token": 2e-06, + "input_cost_per_token_batches": 1e-06, + "litellm_provider": "azure", + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 8e-06, + "output_cost_per_token_batches": 4e-06, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": false + }, + "azure/gpt-4.1-2025-04-14": { + "cache_read_input_token_cost": 5e-07, + "input_cost_per_token": 2e-06, + "input_cost_per_token_batches": 1e-06, + "litellm_provider": "azure", + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 8e-06, + "output_cost_per_token_batches": 4e-06, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": false + }, + "azure/gpt-4.1-mini": { + "cache_read_input_token_cost": 1e-07, + "input_cost_per_token": 4e-07, + "input_cost_per_token_batches": 2e-07, + "litellm_provider": "azure", + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 1.6e-06, + "output_cost_per_token_batches": 8e-07, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": false + }, + "azure/gpt-4.1-mini-2025-04-14": { + "cache_read_input_token_cost": 1e-07, + "input_cost_per_token": 4e-07, + "input_cost_per_token_batches": 2e-07, + "litellm_provider": "azure", + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 1.6e-06, + "output_cost_per_token_batches": 8e-07, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": false + }, + "azure/gpt-4.1-nano": { + "cache_read_input_token_cost": 2.5e-08, "input_cost_per_token": 1e-07, - "output_cost_per_token": 0.0, + "input_cost_per_token_batches": 5e-08, "litellm_provider": "azure", - "mode": "embedding" + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 4e-07, + "output_cost_per_token_batches": 2e-07, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true }, - "azure/text-embedding-ada-002": { - "max_tokens": 8191, - "max_input_tokens": 8191, + "azure/gpt-4.1-nano-2025-04-14": { + "cache_read_input_token_cost": 2.5e-08, "input_cost_per_token": 1e-07, - "output_cost_per_token": 0.0, + "input_cost_per_token_batches": 5e-08, "litellm_provider": "azure", - "mode": "embedding" + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 4e-07, + "output_cost_per_token_batches": 2e-07, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true }, - "azure/text-embedding-3-large": { - "max_tokens": 8191, - "max_input_tokens": 8191, - "input_cost_per_token": 1.3e-07, - "output_cost_per_token": 0.0, + "azure/gpt-4.5-preview": { + "cache_read_input_token_cost": 3.75e-05, + "input_cost_per_token": 7.5e-05, + "input_cost_per_token_batches": 3.75e-05, "litellm_provider": "azure", - "mode": "embedding" + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 0.00015, + "output_cost_per_token_batches": 7.5e-05, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true }, - "azure/text-embedding-3-small": { - "max_tokens": 8191, - "max_input_tokens": 8191, - "input_cost_per_token": 2e-08, - "output_cost_per_token": 0.0, + "azure/gpt-4o": { + "cache_read_input_token_cost": 1.25e-06, + "input_cost_per_token": 2.5e-06, "litellm_provider": "azure", - "mode": "embedding" + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1e-05, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "azure/gpt-4o-2024-05-13": { + "input_cost_per_token": 5e-06, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "azure/gpt-4o-2024-08-06": { + "cache_read_input_token_cost": 1.25e-06, + "input_cost_per_token": 2.5e-06, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1e-05, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "azure/gpt-4o-2024-11-20": { + "cache_read_input_token_cost": 1.25e-06, + "input_cost_per_token": 2.75e-06, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1.1e-05, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "azure/gpt-4o-audio-preview-2024-12-17": { + "input_cost_per_audio_token": 4e-05, + "input_cost_per_token": 2.5e-06, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_audio_token": 8e-05, + "output_cost_per_token": 1e-05, + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supported_modalities": [ + "text", + "audio" + ], + "supported_output_modalities": [ + "text", + "audio" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": false, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "azure/gpt-4o-mini": { + "cache_read_input_token_cost": 7.5e-08, + "input_cost_per_token": 1.65e-07, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 6.6e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "azure/gpt-4o-mini-2024-07-18": { + "cache_read_input_token_cost": 7.5e-08, + "input_cost_per_token": 1.65e-07, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 6.6e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "azure/gpt-4o-mini-audio-preview-2024-12-17": { + "input_cost_per_audio_token": 4e-05, + "input_cost_per_token": 2.5e-06, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_audio_token": 8e-05, + "output_cost_per_token": 1e-05, + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supported_modalities": [ + "text", + "audio" + ], + "supported_output_modalities": [ + "text", + "audio" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": false, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "azure/gpt-4o-mini-realtime-preview-2024-12-17": { + "cache_creation_input_audio_token_cost": 3e-07, + "cache_read_input_token_cost": 3e-07, + "input_cost_per_audio_token": 1e-05, + "input_cost_per_token": 6e-07, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_audio_token": 2e-05, + "output_cost_per_token": 2.4e-06, + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "azure/gpt-4o-mini-transcribe": { + "input_cost_per_audio_token": 3e-06, + "input_cost_per_token": 1.25e-06, + "litellm_provider": "azure", + "max_input_tokens": 16000, + "max_output_tokens": 2000, + "mode": "audio_transcription", + "output_cost_per_token": 5e-06, + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "azure/gpt-4o-mini-tts": { + "input_cost_per_token": 2.5e-06, + "litellm_provider": "azure", + "mode": "audio_speech", + "output_cost_per_audio_token": 1.2e-05, + "output_cost_per_second": 0.00025, + "output_cost_per_token": 1e-05, + "supported_endpoints": [ + "/v1/audio/speech" + ], + "supported_modalities": [ + "text", + "audio" + ], + "supported_output_modalities": [ + "audio" + ] + }, + "azure/gpt-4o-realtime-preview-2024-10-01": { + "cache_creation_input_audio_token_cost": 2e-05, + "cache_read_input_token_cost": 2.5e-06, + "input_cost_per_audio_token": 0.0001, + "input_cost_per_token": 5e-06, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_audio_token": 0.0002, + "output_cost_per_token": 2e-05, + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "azure/gpt-4o-realtime-preview-2024-12-17": { + "cache_read_input_token_cost": 2.5e-06, + "input_cost_per_audio_token": 4e-05, + "input_cost_per_token": 5e-06, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_audio_token": 8e-05, + "output_cost_per_token": 2e-05, + "supported_modalities": [ + "text", + "audio" + ], + "supported_output_modalities": [ + "text", + "audio" + ], + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "azure/gpt-4o-transcribe": { + "input_cost_per_audio_token": 6e-06, + "input_cost_per_token": 2.5e-06, + "litellm_provider": "azure", + "max_input_tokens": 16000, + "max_output_tokens": 2000, + "mode": "audio_transcription", + "output_cost_per_token": 1e-05, + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "azure/gpt-5": { + "cache_read_input_token_cost": 1.25e-07, + "input_cost_per_token": 1.25e-06, + "litellm_provider": "azure", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "azure/gpt-5-2025-08-07": { + "cache_read_input_token_cost": 1.25e-07, + "input_cost_per_token": 1.25e-06, + "litellm_provider": "azure", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "azure/gpt-5-chat": { + "cache_read_input_token_cost": 1.25e-07, + "input_cost_per_token": 1.25e-06, + "litellm_provider": "azure", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "source": "https://azure.microsoft.com/en-us/blog/gpt-5-in-azure-ai-foundry-the-future-of-ai-apps-and-agents-starts-here/", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": false, + "supports_vision": true + }, + "azure/gpt-5-chat-latest": { + "cache_read_input_token_cost": 1.25e-07, + "input_cost_per_token": 1.25e-06, + "litellm_provider": "azure", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": false, + "supports_vision": true + }, + "azure/gpt-5-mini": { + "cache_read_input_token_cost": 2.5e-08, + "input_cost_per_token": 2.5e-07, + "litellm_provider": "azure", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2e-06, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "azure/gpt-5-mini-2025-08-07": { + "cache_read_input_token_cost": 2.5e-08, + "input_cost_per_token": 2.5e-07, + "litellm_provider": "azure", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2e-06, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "azure/gpt-5-nano": { + "cache_read_input_token_cost": 5e-09, + "input_cost_per_token": 5e-08, + "litellm_provider": "azure", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4e-07, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "azure/gpt-5-nano-2025-08-07": { + "cache_read_input_token_cost": 5e-09, + "input_cost_per_token": 5e-08, + "litellm_provider": "azure", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4e-07, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true }, "azure/gpt-image-1": { - "mode": "image_generation", "input_cost_per_pixel": 4.0054321e-08, - "output_cost_per_pixel": 0.0, "litellm_provider": "azure", + "mode": "image_generation", + "output_cost_per_pixel": 0.0, "supported_endpoints": [ "/v1/images/generations" ] }, - "azure/low/1024-x-1024/gpt-image-1": { - "mode": "image_generation", - "input_cost_per_pixel": 1.0490417e-08, - "output_cost_per_pixel": 0.0, + "azure/hd/1024-x-1024/dall-e-3": { + "input_cost_per_pixel": 7.629e-08, "litellm_provider": "azure", - "supported_endpoints": [ - "/v1/images/generations" - ] + "mode": "image_generation", + "output_cost_per_token": 0.0 }, - "azure/medium/1024-x-1024/gpt-image-1": { - "mode": "image_generation", - "input_cost_per_pixel": 4.0054321e-08, - "output_cost_per_pixel": 0.0, + "azure/hd/1024-x-1792/dall-e-3": { + "input_cost_per_pixel": 6.539e-08, "litellm_provider": "azure", - "supported_endpoints": [ - "/v1/images/generations" - ] + "mode": "image_generation", + "output_cost_per_token": 0.0 + }, + "azure/hd/1792-x-1024/dall-e-3": { + "input_cost_per_pixel": 6.539e-08, + "litellm_provider": "azure", + "mode": "image_generation", + "output_cost_per_token": 0.0 }, "azure/high/1024-x-1024/gpt-image-1": { - "mode": "image_generation", "input_cost_per_pixel": 1.59263611e-07, - "output_cost_per_pixel": 0.0, "litellm_provider": "azure", - "supported_endpoints": [ - "/v1/images/generations" - ] - }, - "azure/low/1024-x-1536/gpt-image-1": { "mode": "image_generation", - "input_cost_per_pixel": 1.0172526e-08, "output_cost_per_pixel": 0.0, - "litellm_provider": "azure", - "supported_endpoints": [ - "/v1/images/generations" - ] - }, - "azure/medium/1024-x-1536/gpt-image-1": { - "mode": "image_generation", - "input_cost_per_pixel": 4.0054321e-08, - "output_cost_per_pixel": 0.0, - "litellm_provider": "azure", "supported_endpoints": [ "/v1/images/generations" ] }, "azure/high/1024-x-1536/gpt-image-1": { - "mode": "image_generation", "input_cost_per_pixel": 1.58945719e-07, - "output_cost_per_pixel": 0.0, "litellm_provider": "azure", - "supported_endpoints": [ - "/v1/images/generations" - ] - }, - "azure/low/1536-x-1024/gpt-image-1": { "mode": "image_generation", - "input_cost_per_pixel": 1.0172526e-08, "output_cost_per_pixel": 0.0, - "litellm_provider": "azure", - "supported_endpoints": [ - "/v1/images/generations" - ] - }, - "azure/medium/1536-x-1024/gpt-image-1": { - "mode": "image_generation", - "input_cost_per_pixel": 4.0054321e-08, - "output_cost_per_pixel": 0.0, - "litellm_provider": "azure", "supported_endpoints": [ "/v1/images/generations" ] }, "azure/high/1536-x-1024/gpt-image-1": { - "mode": "image_generation", "input_cost_per_pixel": 1.58945719e-07, - "output_cost_per_pixel": 0.0, "litellm_provider": "azure", + "mode": "image_generation", + "output_cost_per_pixel": 0.0, "supported_endpoints": [ "/v1/images/generations" ] }, - "azure/standard/1024-x-1024/dall-e-3": { - "input_cost_per_pixel": 3.81469e-08, - "output_cost_per_token": 0.0, + "azure/low/1024-x-1024/gpt-image-1": { + "input_cost_per_pixel": 1.0490417e-08, "litellm_provider": "azure", - "mode": "image_generation" + "mode": "image_generation", + "output_cost_per_pixel": 0.0, + "supported_endpoints": [ + "/v1/images/generations" + ] }, - "azure/hd/1024-x-1024/dall-e-3": { - "input_cost_per_pixel": 7.629e-08, - "output_cost_per_token": 0.0, + "azure/low/1024-x-1536/gpt-image-1": { + "input_cost_per_pixel": 1.0172526e-08, "litellm_provider": "azure", - "mode": "image_generation" + "mode": "image_generation", + "output_cost_per_pixel": 0.0, + "supported_endpoints": [ + "/v1/images/generations" + ] }, - "azure/standard/1024-x-1792/dall-e-3": { - "input_cost_per_pixel": 4.359e-08, - "output_cost_per_token": 0.0, + "azure/low/1536-x-1024/gpt-image-1": { + "input_cost_per_pixel": 1.0172526e-08, "litellm_provider": "azure", - "mode": "image_generation" + "mode": "image_generation", + "output_cost_per_pixel": 0.0, + "supported_endpoints": [ + "/v1/images/generations" + ] }, - "azure/standard/1792-x-1024/dall-e-3": { - "input_cost_per_pixel": 4.359e-08, - "output_cost_per_token": 0.0, + "azure/medium/1024-x-1024/gpt-image-1": { + "input_cost_per_pixel": 4.0054321e-08, "litellm_provider": "azure", - "mode": "image_generation" + "mode": "image_generation", + "output_cost_per_pixel": 0.0, + "supported_endpoints": [ + "/v1/images/generations" + ] }, - "azure/hd/1024-x-1792/dall-e-3": { - "input_cost_per_pixel": 6.539e-08, - "output_cost_per_token": 0.0, + "azure/medium/1024-x-1536/gpt-image-1": { + "input_cost_per_pixel": 4.0054321e-08, "litellm_provider": "azure", - "mode": "image_generation" + "mode": "image_generation", + "output_cost_per_pixel": 0.0, + "supported_endpoints": [ + "/v1/images/generations" + ] }, - "azure/hd/1792-x-1024/dall-e-3": { - "input_cost_per_pixel": 6.539e-08, - "output_cost_per_token": 0.0, + "azure/medium/1536-x-1024/gpt-image-1": { + "input_cost_per_pixel": 4.0054321e-08, "litellm_provider": "azure", - "mode": "image_generation" + "mode": "image_generation", + "output_cost_per_pixel": 0.0, + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "azure/mistral-large-2402": { + "input_cost_per_token": 8e-06, + "litellm_provider": "azure", + "max_input_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 2.4e-05, + "supports_function_calling": true + }, + "azure/mistral-large-latest": { + "input_cost_per_token": 8e-06, + "litellm_provider": "azure", + "max_input_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 2.4e-05, + "supports_function_calling": true + }, + "azure/o1": { + "cache_read_input_token_cost": 7.5e-06, + "input_cost_per_token": 1.5e-05, + "litellm_provider": "azure", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 6e-05, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "azure/o1-2024-12-17": { + "cache_read_input_token_cost": 7.5e-06, + "input_cost_per_token": 1.5e-05, + "litellm_provider": "azure", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 6e-05, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "azure/o1-mini": { + "cache_read_input_token_cost": 6.05e-07, + "input_cost_per_token": 1.21e-06, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 4.84e-06, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_vision": false + }, + "azure/o1-mini-2024-09-12": { + "cache_read_input_token_cost": 5.5e-07, + "input_cost_per_token": 1.1e-06, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_vision": false + }, + "azure/o1-preview": { + "cache_read_input_token_cost": 7.5e-06, + "input_cost_per_token": 1.5e-05, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 6e-05, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_vision": false + }, + "azure/o1-preview-2024-09-12": { + "cache_read_input_token_cost": 7.5e-06, + "input_cost_per_token": 1.5e-05, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 6e-05, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_vision": false + }, + "azure/o3": { + "cache_read_input_token_cost": 5e-07, + "input_cost_per_token": 2e-06, + "litellm_provider": "azure", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 8e-06, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "azure/o3-2025-04-16": { + "cache_read_input_token_cost": 2.5e-06, + "input_cost_per_token": 1e-05, + "litellm_provider": "azure", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 4e-05, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "azure/o3-deep-research": { + "cache_read_input_token_cost": 2.5e-06, + "input_cost_per_token": 1e-05, + "litellm_provider": "azure", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "responses", + "output_cost_per_token": 4e-05, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "azure/o3-mini": { + "cache_read_input_token_cost": 5.5e-07, + "input_cost_per_token": 1.1e-06, + "litellm_provider": "azure", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "azure/o3-mini-2025-01-31": { + "cache_read_input_token_cost": 5.5e-07, + "input_cost_per_token": 1.1e-06, + "litellm_provider": "azure", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "azure/o3-pro": { + "input_cost_per_token": 2e-05, + "input_cost_per_token_batches": 1e-05, + "litellm_provider": "azure", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "responses", + "output_cost_per_token": 8e-05, + "output_cost_per_token_batches": 4e-05, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": false, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "azure/o3-pro-2025-06-10": { + "input_cost_per_token": 2e-05, + "input_cost_per_token_batches": 1e-05, + "litellm_provider": "azure", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "responses", + "output_cost_per_token": 8e-05, + "output_cost_per_token_batches": 4e-05, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": false, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "azure/o4-mini": { + "cache_read_input_token_cost": 2.75e-07, + "input_cost_per_token": 1.1e-06, + "litellm_provider": "azure", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "azure/o4-mini-2025-04-16": { + "cache_read_input_token_cost": 2.75e-07, + "input_cost_per_token": 1.1e-06, + "litellm_provider": "azure", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "supports_function_calling": true, + "supports_parallel_function_calling": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true }, "azure/standard/1024-x-1024/dall-e-2": { "input_cost_per_pixel": 0.0, - "output_cost_per_token": 0.0, "litellm_provider": "azure", - "mode": "image_generation" + "mode": "image_generation", + "output_cost_per_token": 0.0 }, - "azure_ai/grok-3": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 3.3e-06, - "output_cost_per_token": 1.65e-05, - "litellm_provider": "azure_ai", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": false, - "source": "https://devblogs.microsoft.com/foundry/announcing-grok-3-and-grok-3-mini-on-azure-ai-foundry/", - "supports_web_search": true + "azure/standard/1024-x-1024/dall-e-3": { + "input_cost_per_pixel": 3.81469e-08, + "litellm_provider": "azure", + "mode": "image_generation", + "output_cost_per_token": 0.0 }, - "azure_ai/global/grok-3": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "litellm_provider": "azure_ai", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": false, - "source": "https://devblogs.microsoft.com/foundry/announcing-grok-3-and-grok-3-mini-on-azure-ai-foundry/", - "supports_web_search": true + "azure/standard/1024-x-1792/dall-e-3": { + "input_cost_per_pixel": 4.359e-08, + "litellm_provider": "azure", + "mode": "image_generation", + "output_cost_per_token": 0.0 }, - "azure_ai/global/grok-3-mini": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 2.5e-07, - "output_cost_per_token": 1.27e-06, - "litellm_provider": "azure_ai", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": false, - "source": "https://devblogs.microsoft.com/foundry/announcing-grok-3-and-grok-3-mini-on-azure-ai-foundry/", - "supports_web_search": true + "azure/standard/1792-x-1024/dall-e-3": { + "input_cost_per_pixel": 4.359e-08, + "litellm_provider": "azure", + "mode": "image_generation", + "output_cost_per_token": 0.0 }, - "azure_ai/grok-3-mini": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 2.75e-07, - "output_cost_per_token": 1.38e-06, - "litellm_provider": "azure_ai", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": false, - "source": "https://devblogs.microsoft.com/foundry/announcing-grok-3-and-grok-3-mini-on-azure-ai-foundry/", - "supports_web_search": true - }, - "azure_ai/deepseek-r1": { - "max_tokens": 8192, - "max_input_tokens": 128000, - "max_output_tokens": 8192, - "input_cost_per_token": 1.35e-06, - "output_cost_per_token": 5.4e-06, - "litellm_provider": "azure_ai", - "mode": "chat", - "supports_tool_choice": true, - "supports_reasoning": true, - "source": "https://techcommunity.microsoft.com/blog/machinelearningblog/deepseek-r1-improved-performance-higher-limits-and-transparent-pricing/4386367" - }, - "azure_ai/deepseek-v3": { - "max_tokens": 8192, - "max_input_tokens": 128000, - "max_output_tokens": 8192, - "input_cost_per_token": 1.14e-06, - "output_cost_per_token": 4.56e-06, - "litellm_provider": "azure_ai", - "mode": "chat", - "supports_tool_choice": true, - "source": "https://techcommunity.microsoft.com/blog/machinelearningblog/announcing-deepseek-v3-on-azure-ai-foundry-and-github/4390438" - }, - "azure_ai/deepseek-v3-0324": { - "max_tokens": 8192, - "max_input_tokens": 128000, - "max_output_tokens": 8192, - "input_cost_per_token": 1.14e-06, - "output_cost_per_token": 4.56e-06, - "litellm_provider": "azure_ai", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true, - "source": "https://techcommunity.microsoft.com/blog/machinelearningblog/announcing-deepseek-v3-on-azure-ai-foundry-and-github/4390438" - }, - "azure_ai/jamba-instruct": { - "max_tokens": 4096, - "max_input_tokens": 70000, - "max_output_tokens": 4096, - "input_cost_per_token": 5e-07, - "output_cost_per_token": 7e-07, - "litellm_provider": "azure_ai", - "mode": "chat", - "supports_tool_choice": true - }, - "azure_ai/jais-30b-chat": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 0.0032, - "output_cost_per_token": 0.00971, - "litellm_provider": "azure_ai", - "mode": "chat", - "source": "https://azure.microsoft.com/en-us/products/ai-services/ai-foundry/models/jais-30b-chat" - }, - "azure_ai/mistral-nemo": { - "max_tokens": 4096, - "max_input_tokens": 131072, - "max_output_tokens": 4096, - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 1.5e-07, - "litellm_provider": "azure_ai", - "mode": "chat", - "supports_function_calling": true, - "source": "https://azuremarketplace.microsoft.com/en/marketplace/apps/000-000.mistral-nemo-12b-2407?tab=PlansAndPrice" - }, - "azure_ai/mistral-medium-2505": { + "azure/text-embedding-3-large": { + "input_cost_per_token": 1.3e-07, + "litellm_provider": "azure", + "max_input_tokens": 8191, "max_tokens": 8191, - "max_input_tokens": 131072, - "max_output_tokens": 8191, - "input_cost_per_token": 4e-07, - "output_cost_per_token": 2e-06, - "litellm_provider": "azure_ai", - "mode": "chat", - "supports_function_calling": true, - "supports_assistant_prefill": true, - "supports_tool_choice": true + "mode": "embedding", + "output_cost_per_token": 0.0 }, - "azure_ai/mistral-large": { + "azure/text-embedding-3-small": { + "input_cost_per_token": 2e-08, + "litellm_provider": "azure", + "max_input_tokens": 8191, "max_tokens": 8191, - "max_input_tokens": 32000, - "max_output_tokens": 8191, - "input_cost_per_token": 4e-06, - "output_cost_per_token": 1.2e-05, - "litellm_provider": "azure_ai", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true + "mode": "embedding", + "output_cost_per_token": 0.0 }, - "azure_ai/mistral-small": { + "azure/text-embedding-ada-002": { + "input_cost_per_token": 1e-07, + "litellm_provider": "azure", + "max_input_tokens": 8191, "max_tokens": 8191, - "max_input_tokens": 32000, - "max_output_tokens": 8191, - "input_cost_per_token": 1e-06, - "output_cost_per_token": 3e-06, - "litellm_provider": "azure_ai", - "supports_function_calling": true, - "mode": "chat", - "supports_tool_choice": true + "mode": "embedding", + "output_cost_per_token": 0.0 }, - "azure_ai/mistral-small-2503": { - "max_tokens": 128000, + "azure/tts-1": { + "input_cost_per_character": 1.5e-05, + "litellm_provider": "azure", + "mode": "audio_speech" + }, + "azure/tts-1-hd": { + "input_cost_per_character": 3e-05, + "litellm_provider": "azure", + "mode": "audio_speech" + }, + "azure/us/gpt-4o-2024-08-06": { + "cache_read_input_token_cost": 1.375e-06, + "input_cost_per_token": 2.75e-06, + "litellm_provider": "azure", "max_input_tokens": 128000, - "max_output_tokens": 128000, - "input_cost_per_token": 1e-06, - "output_cost_per_token": 3e-06, - "litellm_provider": "azure_ai", + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", + "output_cost_per_token": 1.1e-05, "supports_function_calling": true, - "supports_vision": true, - "supports_tool_choice": true + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true }, - "azure_ai/mistral-large-2407": { - "max_tokens": 4096, + "azure/us/gpt-4o-2024-11-20": { + "cache_creation_input_token_cost": 1.38e-06, + "input_cost_per_token": 2.75e-06, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1.1e-05, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "azure/us/gpt-4o-mini-2024-07-18": { + "cache_read_input_token_cost": 8.3e-08, + "input_cost_per_token": 1.65e-07, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 6.6e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "azure/us/gpt-4o-mini-realtime-preview-2024-12-17": { + "cache_creation_input_audio_token_cost": 3.3e-07, + "cache_read_input_token_cost": 3.3e-07, + "input_cost_per_audio_token": 1.1e-05, + "input_cost_per_token": 6.6e-07, + "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 4096, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 6e-06, - "litellm_provider": "azure_ai", - "supports_function_calling": true, + "max_tokens": 4096, "mode": "chat", - "source": "https://azuremarketplace.microsoft.com/en/marketplace/apps/000-000.mistral-ai-large-2407-offer?tab=Overview", + "output_cost_per_audio_token": 2.2e-05, + "output_cost_per_token": 2.64e-06, + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, "supports_tool_choice": true }, - "azure_ai/mistral-large-latest": { - "max_tokens": 4096, + "azure/us/gpt-4o-realtime-preview-2024-10-01": { + "cache_creation_input_audio_token_cost": 2.2e-05, + "cache_read_input_token_cost": 2.75e-06, + "input_cost_per_audio_token": 0.00011, + "input_cost_per_token": 5.5e-06, + "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 4096, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 6e-06, - "litellm_provider": "azure_ai", - "supports_function_calling": true, + "max_tokens": 4096, "mode": "chat", - "source": "https://azuremarketplace.microsoft.com/en/marketplace/apps/000-000.mistral-ai-large-2407-offer?tab=Overview", + "output_cost_per_audio_token": 0.00022, + "output_cost_per_token": 2.2e-05, + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, "supports_tool_choice": true }, - "azure_ai/ministral-3b": { - "max_tokens": 4096, + "azure/us/gpt-4o-realtime-preview-2024-12-17": { + "cache_read_input_audio_token_cost": 2.5e-06, + "cache_read_input_token_cost": 2.75e-06, + "input_cost_per_audio_token": 4.4e-05, + "input_cost_per_token": 5.5e-06, + "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 4096, - "input_cost_per_token": 4e-08, - "output_cost_per_token": 4e-08, - "litellm_provider": "azure_ai", - "supports_function_calling": true, + "max_tokens": 4096, "mode": "chat", - "source": "https://azuremarketplace.microsoft.com/en/marketplace/apps/000-000.ministral-3b-2410-offer?tab=Overview", + "output_cost_per_audio_token": 8e-05, + "output_cost_per_token": 2.2e-05, + "supported_modalities": [ + "text", + "audio" + ], + "supported_output_modalities": [ + "text", + "audio" + ], + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, "supports_tool_choice": true }, + "azure/us/o1-2024-12-17": { + "cache_read_input_token_cost": 8.25e-06, + "input_cost_per_token": 1.65e-05, + "litellm_provider": "azure", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 6.6e-05, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "azure/us/o1-mini-2024-09-12": { + "cache_read_input_token_cost": 6.05e-07, + "input_cost_per_token": 1.21e-06, + "input_cost_per_token_batches": 6.05e-07, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 4.84e-06, + "output_cost_per_token_batches": 2.42e-06, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_vision": false + }, + "azure/us/o1-preview-2024-09-12": { + "cache_read_input_token_cost": 8.25e-06, + "input_cost_per_token": 1.65e-05, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 6.6e-05, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_vision": false + }, + "azure/us/o3-mini-2025-01-31": { + "cache_read_input_token_cost": 6.05e-07, + "input_cost_per_token": 1.21e-06, + "input_cost_per_token_batches": 6.05e-07, + "litellm_provider": "azure", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 4.84e-06, + "output_cost_per_token_batches": 2.42e-06, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "azure/whisper-1": { + "input_cost_per_second": 0.0001, + "litellm_provider": "azure", + "mode": "audio_transcription", + "output_cost_per_second": 0.0001 + }, + "azure_ai/Cohere-embed-v3-english": { + "input_cost_per_token": 1e-07, + "litellm_provider": "azure_ai", + "max_input_tokens": 512, + "max_tokens": 512, + "mode": "embedding", + "output_cost_per_token": 0.0, + "output_vector_size": 1024, + "source": "https://azuremarketplace.microsoft.com/en-us/marketplace/apps/cohere.cohere-embed-v3-english-offer?tab=PlansAndPrice", + "supports_embedding_image_input": true + }, + "azure_ai/Cohere-embed-v3-multilingual": { + "input_cost_per_token": 1e-07, + "litellm_provider": "azure_ai", + "max_input_tokens": 512, + "max_tokens": 512, + "mode": "embedding", + "output_cost_per_token": 0.0, + "output_vector_size": 1024, + "source": "https://azuremarketplace.microsoft.com/en-us/marketplace/apps/cohere.cohere-embed-v3-english-offer?tab=PlansAndPrice", + "supports_embedding_image_input": true + }, + "azure_ai/FLUX-1.1-pro": { + "litellm_provider": "azure_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/black-forest-labs-flux-1-kontext-pro-and-flux1-1-pro-now-available-in-azure-ai-f/4434659", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "azure_ai/FLUX.1-Kontext-pro": { + "litellm_provider": "azure_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://azuremarketplace.microsoft.com/pt-br/marketplace/apps/cohere.cohere-embed-4-offer?tab=PlansAndPrice", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, "azure_ai/Llama-3.2-11B-Vision-Instruct": { - "max_tokens": 2048, + "input_cost_per_token": 3.7e-07, + "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 2048, - "input_cost_per_token": 3.7e-07, - "output_cost_per_token": 3.7e-07, - "litellm_provider": "azure_ai", - "supports_function_calling": true, - "supports_vision": true, + "max_tokens": 2048, "mode": "chat", + "output_cost_per_token": 3.7e-07, "source": "https://azuremarketplace.microsoft.com/en/marketplace/apps/metagenai.meta-llama-3-2-11b-vision-instruct-offer?tab=Overview", - "supports_tool_choice": true + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "azure_ai/Llama-3.2-90B-Vision-Instruct": { + "input_cost_per_token": 2.04e-06, + "litellm_provider": "azure_ai", + "max_input_tokens": 128000, + "max_output_tokens": 2048, + "max_tokens": 2048, + "mode": "chat", + "output_cost_per_token": 2.04e-06, + "source": "https://azuremarketplace.microsoft.com/en/marketplace/apps/metagenai.meta-llama-3-2-90b-vision-instruct-offer?tab=Overview", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true }, "azure_ai/Llama-3.3-70B-Instruct": { - "max_tokens": 2048, + "input_cost_per_token": 7.1e-07, + "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 2048, - "input_cost_per_token": 7.1e-07, + "max_tokens": 2048, + "mode": "chat", "output_cost_per_token": 7.1e-07, - "litellm_provider": "azure_ai", - "supports_function_calling": true, - "mode": "chat", "source": "https://azuremarketplace.microsoft.com/en/marketplace/apps/metagenai.llama-3-3-70b-instruct-offer?tab=Overview", - "supports_tool_choice": true - }, - "azure_ai/Llama-4-Scout-17B-16E-Instruct": { - "max_tokens": 16384, - "max_input_tokens": 10000000, - "max_output_tokens": 16384, - "input_cost_per_token": 2e-07, - "output_cost_per_token": 7.8e-07, - "litellm_provider": "azure_ai", "supports_function_calling": true, - "supports_vision": true, - "mode": "chat", - "source": "https://azure.microsoft.com/en-us/blog/introducing-the-llama-4-herd-in-azure-ai-foundry-and-azure-databricks/", "supports_tool_choice": true }, "azure_ai/Llama-4-Maverick-17B-128E-Instruct-FP8": { - "max_tokens": 16384, + "input_cost_per_token": 1.41e-06, + "litellm_provider": "azure_ai", "max_input_tokens": 1000000, "max_output_tokens": 16384, - "input_cost_per_token": 1.41e-06, + "max_tokens": 16384, + "mode": "chat", "output_cost_per_token": 3.5e-07, - "litellm_provider": "azure_ai", - "supports_function_calling": true, - "supports_vision": true, - "mode": "chat", "source": "https://azure.microsoft.com/en-us/blog/introducing-the-llama-4-herd-in-azure-ai-foundry-and-azure-databricks/", - "supports_tool_choice": true - }, - "azure_ai/Llama-3.2-90B-Vision-Instruct": { - "max_tokens": 2048, - "max_input_tokens": 128000, - "max_output_tokens": 2048, - "input_cost_per_token": 2.04e-06, - "output_cost_per_token": 2.04e-06, - "litellm_provider": "azure_ai", "supports_function_calling": true, - "supports_vision": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "azure_ai/Llama-4-Scout-17B-16E-Instruct": { + "input_cost_per_token": 2e-07, + "litellm_provider": "azure_ai", + "max_input_tokens": 10000000, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", - "source": "https://azuremarketplace.microsoft.com/en/marketplace/apps/metagenai.meta-llama-3-2-90b-vision-instruct-offer?tab=Overview", - "supports_tool_choice": true + "output_cost_per_token": 7.8e-07, + "source": "https://azure.microsoft.com/en-us/blog/introducing-the-llama-4-herd-in-azure-ai-foundry-and-azure-databricks/", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true }, "azure_ai/Meta-Llama-3-70B-Instruct": { - "max_tokens": 2048, + "input_cost_per_token": 1.1e-06, + "litellm_provider": "azure_ai", "max_input_tokens": 8192, "max_output_tokens": 2048, - "input_cost_per_token": 1.1e-06, + "max_tokens": 2048, + "mode": "chat", "output_cost_per_token": 3.7e-07, - "litellm_provider": "azure_ai", - "mode": "chat", - "supports_tool_choice": true - }, - "azure_ai/Meta-Llama-3.1-8B-Instruct": { - "max_tokens": 2048, - "max_input_tokens": 128000, - "max_output_tokens": 2048, - "input_cost_per_token": 3e-07, - "output_cost_per_token": 6.1e-07, - "litellm_provider": "azure_ai", - "mode": "chat", - "source": "https://azuremarketplace.microsoft.com/en-us/marketplace/apps/metagenai.meta-llama-3-1-8b-instruct-offer?tab=PlansAndPrice", - "supports_tool_choice": true - }, - "azure_ai/Meta-Llama-3.1-70B-Instruct": { - "max_tokens": 2048, - "max_input_tokens": 128000, - "max_output_tokens": 2048, - "input_cost_per_token": 2.68e-06, - "output_cost_per_token": 3.54e-06, - "litellm_provider": "azure_ai", - "mode": "chat", - "source": "https://azuremarketplace.microsoft.com/en-us/marketplace/apps/metagenai.meta-llama-3-1-70b-instruct-offer?tab=PlansAndPrice", "supports_tool_choice": true }, "azure_ai/Meta-Llama-3.1-405B-Instruct": { - "max_tokens": 2048, + "input_cost_per_token": 5.33e-06, + "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 2048, - "input_cost_per_token": 5.33e-06, - "output_cost_per_token": 1.6e-05, - "litellm_provider": "azure_ai", + "max_tokens": 2048, "mode": "chat", + "output_cost_per_token": 1.6e-05, "source": "https://azuremarketplace.microsoft.com/en-us/marketplace/apps/metagenai.meta-llama-3-1-405b-instruct-offer?tab=PlansAndPrice", "supports_tool_choice": true }, - "azure_ai/Phi-4-mini-instruct": { - "max_tokens": 4096, - "max_input_tokens": 131072, - "max_output_tokens": 4096, - "input_cost_per_token": 7.5e-08, - "output_cost_per_token": 3e-07, + "azure_ai/Meta-Llama-3.1-70B-Instruct": { + "input_cost_per_token": 2.68e-06, "litellm_provider": "azure_ai", - "mode": "chat", - "supports_function_calling": true, - "source": "https://techcommunity.microsoft.com/blog/Azure-AI-Services-blog/announcing-new-phi-pricing-empowering-your-business-with-small-language-models/4395112" - }, - "azure_ai/Phi-4-multimodal-instruct": { - "max_tokens": 4096, - "max_input_tokens": 131072, - "max_output_tokens": 4096, - "input_cost_per_token": 8e-08, - "input_cost_per_audio_token": 4e-06, - "output_cost_per_token": 3.2e-07, - "litellm_provider": "azure_ai", - "mode": "chat", - "supports_audio_input": true, - "supports_function_calling": true, - "supports_vision": true, - "source": "https://techcommunity.microsoft.com/blog/Azure-AI-Services-blog/announcing-new-phi-pricing-empowering-your-business-with-small-language-models/4395112" - }, - "azure_ai/Phi-4": { - "max_tokens": 16384, - "max_input_tokens": 16384, - "max_output_tokens": 16384, - "input_cost_per_token": 1.25e-07, - "output_cost_per_token": 5e-07, - "litellm_provider": "azure_ai", - "mode": "chat", - "supports_vision": false, - "source": "https://techcommunity.microsoft.com/blog/machinelearningblog/affordable-innovation-unveiling-the-pricing-of-phi-3-slms-on-models-as-a-service/4156495", - "supports_function_calling": true, - "supports_tool_choice": true - }, - "azure_ai/Phi-3.5-mini-instruct": { - "max_tokens": 4096, "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 1.3e-07, - "output_cost_per_token": 5.2e-07, - "litellm_provider": "azure_ai", + "max_output_tokens": 2048, + "max_tokens": 2048, "mode": "chat", - "supports_vision": false, - "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", + "output_cost_per_token": 3.54e-06, + "source": "https://azuremarketplace.microsoft.com/en-us/marketplace/apps/metagenai.meta-llama-3-1-70b-instruct-offer?tab=PlansAndPrice", "supports_tool_choice": true }, - "azure_ai/Phi-3.5-vision-instruct": { - "max_tokens": 4096, + "azure_ai/Meta-Llama-3.1-8B-Instruct": { + "input_cost_per_token": 3e-07, + "litellm_provider": "azure_ai", "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 1.3e-07, - "output_cost_per_token": 5.2e-07, - "litellm_provider": "azure_ai", + "max_output_tokens": 2048, + "max_tokens": 2048, "mode": "chat", - "supports_vision": true, - "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", - "supports_tool_choice": true - }, - "azure_ai/Phi-3.5-MoE-instruct": { - "max_tokens": 4096, - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 1.6e-07, - "output_cost_per_token": 6.4e-07, - "litellm_provider": "azure_ai", - "mode": "chat", - "supports_vision": false, - "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", - "supports_tool_choice": true - }, - "azure_ai/Phi-3-mini-4k-instruct": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 1.3e-07, - "output_cost_per_token": 5.2e-07, - "litellm_provider": "azure_ai", - "mode": "chat", - "supports_vision": false, - "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", - "supports_tool_choice": true - }, - "azure_ai/Phi-3-mini-128k-instruct": { - "max_tokens": 4096, - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 1.3e-07, - "output_cost_per_token": 5.2e-07, - "litellm_provider": "azure_ai", - "mode": "chat", - "supports_vision": false, - "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", - "supports_tool_choice": true - }, - "azure_ai/Phi-3-small-8k-instruct": { - "max_tokens": 4096, - "max_input_tokens": 8192, - "max_output_tokens": 4096, - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 6e-07, - "litellm_provider": "azure_ai", - "mode": "chat", - "supports_vision": false, - "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", - "supports_tool_choice": true - }, - "azure_ai/Phi-3-small-128k-instruct": { - "max_tokens": 4096, - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 6e-07, - "litellm_provider": "azure_ai", - "mode": "chat", - "supports_vision": false, - "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", - "supports_tool_choice": true - }, - "azure_ai/Phi-3-medium-4k-instruct": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 1.7e-07, - "output_cost_per_token": 6.8e-07, - "litellm_provider": "azure_ai", - "mode": "chat", - "supports_vision": false, - "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", + "output_cost_per_token": 6.1e-07, + "source": "https://azuremarketplace.microsoft.com/en-us/marketplace/apps/metagenai.meta-llama-3-1-8b-instruct-offer?tab=PlansAndPrice", "supports_tool_choice": true }, "azure_ai/Phi-3-medium-128k-instruct": { - "max_tokens": 4096, + "input_cost_per_token": 1.7e-07, + "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 4096, - "input_cost_per_token": 1.7e-07, - "output_cost_per_token": 6.8e-07, - "litellm_provider": "azure_ai", + "max_tokens": 4096, "mode": "chat", - "supports_vision": false, + "output_cost_per_token": 6.8e-07, "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_vision": false }, - "azure_ai/cohere-rerank-v3.5": { - "max_tokens": 4096, + "azure_ai/Phi-3-medium-4k-instruct": { + "input_cost_per_token": 1.7e-07, + "litellm_provider": "azure_ai", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_query_tokens": 2048, - "input_cost_per_token": 0.0, - "input_cost_per_query": 0.002, - "output_cost_per_token": 0.0, - "litellm_provider": "azure_ai", - "mode": "rerank" - }, - "azure_ai/cohere-rerank-v3-multilingual": { "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 6.8e-07, + "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", + "supports_tool_choice": true, + "supports_vision": false + }, + "azure_ai/Phi-3-mini-128k-instruct": { + "input_cost_per_token": 1.3e-07, + "litellm_provider": "azure_ai", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 5.2e-07, + "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", + "supports_tool_choice": true, + "supports_vision": false + }, + "azure_ai/Phi-3-mini-4k-instruct": { + "input_cost_per_token": 1.3e-07, + "litellm_provider": "azure_ai", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_query_tokens": 2048, - "input_cost_per_token": 0.0, - "input_cost_per_query": 0.002, - "output_cost_per_token": 0.0, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 5.2e-07, + "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", + "supports_tool_choice": true, + "supports_vision": false + }, + "azure_ai/Phi-3-small-128k-instruct": { + "input_cost_per_token": 1.5e-07, "litellm_provider": "azure_ai", - "mode": "rerank" + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 6e-07, + "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", + "supports_tool_choice": true, + "supports_vision": false + }, + "azure_ai/Phi-3-small-8k-instruct": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "azure_ai", + "max_input_tokens": 8192, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 6e-07, + "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", + "supports_tool_choice": true, + "supports_vision": false + }, + "azure_ai/Phi-3.5-MoE-instruct": { + "input_cost_per_token": 1.6e-07, + "litellm_provider": "azure_ai", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 6.4e-07, + "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", + "supports_tool_choice": true, + "supports_vision": false + }, + "azure_ai/Phi-3.5-mini-instruct": { + "input_cost_per_token": 1.3e-07, + "litellm_provider": "azure_ai", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 5.2e-07, + "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", + "supports_tool_choice": true, + "supports_vision": false + }, + "azure_ai/Phi-3.5-vision-instruct": { + "input_cost_per_token": 1.3e-07, + "litellm_provider": "azure_ai", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 5.2e-07, + "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", + "supports_tool_choice": true, + "supports_vision": true + }, + "azure_ai/Phi-4": { + "input_cost_per_token": 1.25e-07, + "litellm_provider": "azure_ai", + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 5e-07, + "source": "https://techcommunity.microsoft.com/blog/machinelearningblog/affordable-innovation-unveiling-the-pricing-of-phi-3-slms-on-models-as-a-service/4156495", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "azure_ai/Phi-4-mini-instruct": { + "input_cost_per_token": 7.5e-08, + "litellm_provider": "azure_ai", + "max_input_tokens": 131072, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 3e-07, + "source": "https://techcommunity.microsoft.com/blog/Azure-AI-Services-blog/announcing-new-phi-pricing-empowering-your-business-with-small-language-models/4395112", + "supports_function_calling": true + }, + "azure_ai/Phi-4-multimodal-instruct": { + "input_cost_per_audio_token": 4e-06, + "input_cost_per_token": 8e-08, + "litellm_provider": "azure_ai", + "max_input_tokens": 131072, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 3.2e-07, + "source": "https://techcommunity.microsoft.com/blog/Azure-AI-Services-blog/announcing-new-phi-pricing-empowering-your-business-with-small-language-models/4395112", + "supports_audio_input": true, + "supports_function_calling": true, + "supports_vision": true }, "azure_ai/cohere-rerank-v3-english": { - "max_tokens": 4096, + "input_cost_per_query": 0.002, + "input_cost_per_token": 0.0, + "litellm_provider": "azure_ai", "max_input_tokens": 4096, "max_output_tokens": 4096, "max_query_tokens": 2048, - "input_cost_per_token": 0.0, + "max_tokens": 4096, + "mode": "rerank", + "output_cost_per_token": 0.0 + }, + "azure_ai/cohere-rerank-v3-multilingual": { "input_cost_per_query": 0.002, - "output_cost_per_token": 0.0, + "input_cost_per_token": 0.0, "litellm_provider": "azure_ai", - "mode": "rerank" + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_query_tokens": 2048, + "max_tokens": 4096, + "mode": "rerank", + "output_cost_per_token": 0.0 }, - "azure_ai/Cohere-embed-v3-english": { - "max_tokens": 512, - "max_input_tokens": 512, - "output_vector_size": 1024, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 0.0, + "azure_ai/cohere-rerank-v3.5": { + "input_cost_per_query": 0.002, + "input_cost_per_token": 0.0, "litellm_provider": "azure_ai", - "mode": "embedding", - "supports_embedding_image_input": true, - "source": "https://azuremarketplace.microsoft.com/en-us/marketplace/apps/cohere.cohere-embed-v3-english-offer?tab=PlansAndPrice" + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_query_tokens": 2048, + "max_tokens": 4096, + "mode": "rerank", + "output_cost_per_token": 0.0 }, - "azure_ai/Cohere-embed-v3-multilingual": { - "max_tokens": 512, - "max_input_tokens": 512, - "output_vector_size": 1024, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 0.0, + "azure_ai/deepseek-r1": { + "input_cost_per_token": 1.35e-06, "litellm_provider": "azure_ai", - "mode": "embedding", - "supports_embedding_image_input": true, - "source": "https://azuremarketplace.microsoft.com/en-us/marketplace/apps/cohere.cohere-embed-v3-english-offer?tab=PlansAndPrice" + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 5.4e-06, + "source": "https://techcommunity.microsoft.com/blog/machinelearningblog/deepseek-r1-improved-performance-higher-limits-and-transparent-pricing/4386367", + "supports_reasoning": true, + "supports_tool_choice": true + }, + "azure_ai/deepseek-v3": { + "input_cost_per_token": 1.14e-06, + "litellm_provider": "azure_ai", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 4.56e-06, + "source": "https://techcommunity.microsoft.com/blog/machinelearningblog/announcing-deepseek-v3-on-azure-ai-foundry-and-github/4390438", + "supports_tool_choice": true + }, + "azure_ai/deepseek-v3-0324": { + "input_cost_per_token": 1.14e-06, + "litellm_provider": "azure_ai", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 4.56e-06, + "source": "https://techcommunity.microsoft.com/blog/machinelearningblog/announcing-deepseek-v3-on-azure-ai-foundry-and-github/4390438", + "supports_function_calling": true, + "supports_tool_choice": true }, "azure_ai/embed-v-4-0": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "output_vector_size": 3072, "input_cost_per_token": 1.2e-07, - "output_cost_per_token": 0.0, "litellm_provider": "azure_ai", + "max_input_tokens": 128000, + "max_tokens": 128000, "mode": "embedding", - "supports_embedding_image_input": true, + "output_cost_per_token": 0.0, + "output_vector_size": 3072, + "source": "https://azuremarketplace.microsoft.com/pt-br/marketplace/apps/cohere.cohere-embed-4-offer?tab=PlansAndPrice", "supported_endpoints": [ "/v1/embeddings" ], @@ -4833,3767 +3150,5449 @@ "text", "image" ], - "source": "https://azuremarketplace.microsoft.com/pt-br/marketplace/apps/cohere.cohere-embed-4-offer?tab=PlansAndPrice" + "supports_embedding_image_input": true }, - "azure_ai/FLUX-1.1-pro": { - "output_cost_per_image": 0.04, + "azure_ai/global/grok-3": { + "input_cost_per_token": 3e-06, "litellm_provider": "azure_ai", - "mode": "image_generation", - "supported_endpoints": [ - "/v1/images/generations" - ], - "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/black-forest-labs-flux-1-kontext-pro-and-flux1-1-pro-now-available-in-azure-ai-f/4434659" + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "source": "https://devblogs.microsoft.com/foundry/announcing-grok-3-and-grok-3-mini-on-azure-ai-foundry/", + "supports_function_calling": true, + "supports_response_schema": false, + "supports_tool_choice": true, + "supports_web_search": true }, - "azure_ai/FLUX.1-Kontext-pro": { - "output_cost_per_image": 0.04, + "azure_ai/global/grok-3-mini": { + "input_cost_per_token": 2.5e-07, "litellm_provider": "azure_ai", - "mode": "image_generation", - "supported_endpoints": [ - "/v1/images/generations" - ], - "source": "https://azuremarketplace.microsoft.com/pt-br/marketplace/apps/cohere.cohere-embed-4-offer?tab=PlansAndPrice" + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.27e-06, + "source": "https://devblogs.microsoft.com/foundry/announcing-grok-3-and-grok-3-mini-on-azure-ai-foundry/", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": false, + "supports_tool_choice": true, + "supports_web_search": true + }, + "azure_ai/grok-3": { + "input_cost_per_token": 3.3e-06, + "litellm_provider": "azure_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.65e-05, + "source": "https://devblogs.microsoft.com/foundry/announcing-grok-3-and-grok-3-mini-on-azure-ai-foundry/", + "supports_function_calling": true, + "supports_response_schema": false, + "supports_tool_choice": true, + "supports_web_search": true + }, + "azure_ai/grok-3-mini": { + "input_cost_per_token": 2.75e-07, + "litellm_provider": "azure_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.38e-06, + "source": "https://devblogs.microsoft.com/foundry/announcing-grok-3-and-grok-3-mini-on-azure-ai-foundry/", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": false, + "supports_tool_choice": true, + "supports_web_search": true + }, + "azure_ai/jais-30b-chat": { + "input_cost_per_token": 0.0032, + "litellm_provider": "azure_ai", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.00971, + "source": "https://azure.microsoft.com/en-us/products/ai-services/ai-foundry/models/jais-30b-chat" + }, + "azure_ai/jamba-instruct": { + "input_cost_per_token": 5e-07, + "litellm_provider": "azure_ai", + "max_input_tokens": 70000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 7e-07, + "supports_tool_choice": true + }, + "azure_ai/ministral-3b": { + "input_cost_per_token": 4e-08, + "litellm_provider": "azure_ai", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 4e-08, + "source": "https://azuremarketplace.microsoft.com/en/marketplace/apps/000-000.ministral-3b-2410-offer?tab=Overview", + "supports_function_calling": true, + "supports_tool_choice": true + }, + "azure_ai/mistral-large": { + "input_cost_per_token": 4e-06, + "litellm_provider": "azure_ai", + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 1.2e-05, + "supports_function_calling": true, + "supports_tool_choice": true + }, + "azure_ai/mistral-large-2407": { + "input_cost_per_token": 2e-06, + "litellm_provider": "azure_ai", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 6e-06, + "source": "https://azuremarketplace.microsoft.com/en/marketplace/apps/000-000.mistral-ai-large-2407-offer?tab=Overview", + "supports_function_calling": true, + "supports_tool_choice": true + }, + "azure_ai/mistral-large-latest": { + "input_cost_per_token": 2e-06, + "litellm_provider": "azure_ai", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 6e-06, + "source": "https://azuremarketplace.microsoft.com/en/marketplace/apps/000-000.mistral-ai-large-2407-offer?tab=Overview", + "supports_function_calling": true, + "supports_tool_choice": true + }, + "azure_ai/mistral-medium-2505": { + "input_cost_per_token": 4e-07, + "litellm_provider": "azure_ai", + "max_input_tokens": 131072, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 2e-06, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_tool_choice": true + }, + "azure_ai/mistral-nemo": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "azure_ai", + "max_input_tokens": 131072, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.5e-07, + "source": "https://azuremarketplace.microsoft.com/en/marketplace/apps/000-000.mistral-nemo-12b-2407?tab=PlansAndPrice", + "supports_function_calling": true + }, + "azure_ai/mistral-small": { + "input_cost_per_token": 1e-06, + "litellm_provider": "azure_ai", + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 3e-06, + "supports_function_calling": true, + "supports_tool_choice": true + }, + "azure_ai/mistral-small-2503": { + "input_cost_per_token": 1e-06, + "litellm_provider": "azure_ai", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 3e-06, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true }, "babbage-002": { - "max_tokens": 16384, + "input_cost_per_token": 4e-07, + "litellm_provider": "text-completion-openai", "max_input_tokens": 16384, "max_output_tokens": 4096, - "input_cost_per_token": 4e-07, - "output_cost_per_token": 4e-07, - "litellm_provider": "text-completion-openai", - "mode": "completion" - }, - "davinci-002": { "max_tokens": 16384, - "max_input_tokens": 16384, - "max_output_tokens": 4096, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 2e-06, - "litellm_provider": "text-completion-openai", - "mode": "completion" - }, - "gpt-3.5-turbo-instruct": { - "max_tokens": 4096, - "max_input_tokens": 8192, - "max_output_tokens": 4096, - "input_cost_per_token": 1.5e-06, - "output_cost_per_token": 2e-06, - "litellm_provider": "text-completion-openai", - "mode": "completion" - }, - "gpt-3.5-turbo-instruct-0914": { - "max_tokens": 4097, - "max_input_tokens": 8192, - "max_output_tokens": 4097, - "input_cost_per_token": 1.5e-06, - "output_cost_per_token": 2e-06, - "litellm_provider": "text-completion-openai", - "mode": "completion" - }, - "mistral/mistral-tiny": { - "max_tokens": 8191, - "max_input_tokens": 32000, - "max_output_tokens": 8191, - "input_cost_per_token": 2.5e-07, - "output_cost_per_token": 2.5e-07, - "litellm_provider": "mistral", - "mode": "chat", - "supports_assistant_prefill": true, - "supports_tool_choice": true, - "supports_response_schema": true - }, - "mistral/mistral-small": { - "max_tokens": 8191, - "max_input_tokens": 32000, - "max_output_tokens": 8191, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 3e-07, - "litellm_provider": "mistral", - "supports_function_calling": true, - "mode": "chat", - "supports_assistant_prefill": true, - "supports_tool_choice": true, - "supports_response_schema": true - }, - "mistral/mistral-small-latest": { - "max_tokens": 8191, - "max_input_tokens": 32000, - "max_output_tokens": 8191, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 3e-07, - "litellm_provider": "mistral", - "supports_function_calling": true, - "mode": "chat", - "supports_assistant_prefill": true, - "supports_tool_choice": true, - "supports_response_schema": true - }, - "mistral/mistral-medium": { - "max_tokens": 8191, - "max_input_tokens": 32000, - "max_output_tokens": 8191, - "input_cost_per_token": 2.7e-06, - "output_cost_per_token": 8.1e-06, - "litellm_provider": "mistral", - "mode": "chat", - "supports_assistant_prefill": true, - "supports_tool_choice": true, - "supports_response_schema": true - }, - "mistral/mistral-medium-latest": { - "max_tokens": 8191, - "max_input_tokens": 131072, - "max_output_tokens": 8191, - "input_cost_per_token": 4e-07, - "output_cost_per_token": 2e-06, - "litellm_provider": "mistral", - "mode": "chat", - "supports_function_calling": true, - "supports_assistant_prefill": true, - "supports_tool_choice": true, - "supports_response_schema": true - }, - "mistral/mistral-medium-2505": { - "max_tokens": 8191, - "max_input_tokens": 131072, - "max_output_tokens": 8191, - "input_cost_per_token": 4e-07, - "output_cost_per_token": 2e-06, - "litellm_provider": "mistral", - "mode": "chat", - "supports_function_calling": true, - "supports_assistant_prefill": true, - "supports_tool_choice": true, - "supports_response_schema": true - }, - "mistral/mistral-medium-2312": { - "max_tokens": 8191, - "max_input_tokens": 32000, - "max_output_tokens": 8191, - "input_cost_per_token": 2.7e-06, - "output_cost_per_token": 8.1e-06, - "litellm_provider": "mistral", - "mode": "chat", - "supports_assistant_prefill": true, - "supports_tool_choice": true, - "supports_response_schema": true - }, - "mistral/mistral-large-latest": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 6e-06, - "litellm_provider": "mistral", - "mode": "chat", - "supports_function_calling": true, - "supports_assistant_prefill": true, - "supports_tool_choice": true, - "supports_response_schema": true - }, - "mistral/mistral-large-2411": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 6e-06, - "litellm_provider": "mistral", - "mode": "chat", - "supports_function_calling": true, - "supports_assistant_prefill": true, - "supports_tool_choice": true, - "supports_response_schema": true - }, - "mistral/mistral-large-2402": { - "max_tokens": 8191, - "max_input_tokens": 32000, - "max_output_tokens": 8191, - "input_cost_per_token": 4e-06, - "output_cost_per_token": 1.2e-05, - "litellm_provider": "mistral", - "mode": "chat", - "supports_function_calling": true, - "supports_assistant_prefill": true, - "supports_tool_choice": true, - "supports_response_schema": true - }, - "mistral/mistral-large-2407": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 9e-06, - "litellm_provider": "mistral", - "mode": "chat", - "supports_function_calling": true, - "supports_assistant_prefill": true, - "supports_tool_choice": true, - "supports_response_schema": true - }, - "mistral/pixtral-large-latest": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 6e-06, - "litellm_provider": "mistral", - "mode": "chat", - "supports_function_calling": true, - "supports_assistant_prefill": true, - "supports_vision": true, - "supports_tool_choice": true, - "supports_response_schema": true - }, - "mistral/pixtral-large-2411": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 6e-06, - "litellm_provider": "mistral", - "mode": "chat", - "supports_function_calling": true, - "supports_assistant_prefill": true, - "supports_vision": true, - "supports_tool_choice": true, - "supports_response_schema": true - }, - "mistral/pixtral-12b-2409": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 1.5e-07, - "litellm_provider": "mistral", - "mode": "chat", - "supports_function_calling": true, - "supports_assistant_prefill": true, - "supports_vision": true, - "supports_tool_choice": true, - "supports_response_schema": true - }, - "mistral/open-mistral-7b": { - "max_tokens": 8191, - "max_input_tokens": 32000, - "max_output_tokens": 8191, - "input_cost_per_token": 2.5e-07, - "output_cost_per_token": 2.5e-07, - "litellm_provider": "mistral", - "mode": "chat", - "supports_assistant_prefill": true, - "supports_tool_choice": true, - "supports_response_schema": true - }, - "mistral/open-mixtral-8x7b": { - "max_tokens": 8191, - "max_input_tokens": 32000, - "max_output_tokens": 8191, - "input_cost_per_token": 7e-07, - "output_cost_per_token": 7e-07, - "litellm_provider": "mistral", - "mode": "chat", - "supports_function_calling": true, - "supports_assistant_prefill": true, - "supports_tool_choice": true, - "supports_response_schema": true - }, - "mistral/open-mixtral-8x22b": { - "max_tokens": 8191, - "max_input_tokens": 65336, - "max_output_tokens": 8191, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 6e-06, - "litellm_provider": "mistral", - "mode": "chat", - "supports_function_calling": true, - "supports_assistant_prefill": true, - "supports_tool_choice": true, - "supports_response_schema": true - }, - "mistral/codestral-latest": { - "max_tokens": 8191, - "max_input_tokens": 32000, - "max_output_tokens": 8191, - "input_cost_per_token": 1e-06, - "output_cost_per_token": 3e-06, - "litellm_provider": "mistral", - "mode": "chat", - "supports_assistant_prefill": true, - "supports_tool_choice": true, - "supports_response_schema": true - }, - "mistral/codestral-2405": { - "max_tokens": 8191, - "max_input_tokens": 32000, - "max_output_tokens": 8191, - "input_cost_per_token": 1e-06, - "output_cost_per_token": 3e-06, - "litellm_provider": "mistral", - "mode": "chat", - "supports_assistant_prefill": true, - "supports_tool_choice": true, - "supports_response_schema": true - }, - "mistral/open-mistral-nemo": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "input_cost_per_token": 3e-07, - "output_cost_per_token": 3e-07, - "litellm_provider": "mistral", - "mode": "chat", - "source": "https://mistral.ai/technology/", - "supports_assistant_prefill": true, - "supports_tool_choice": true, - "supports_response_schema": true - }, - "mistral/open-mistral-nemo-2407": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "input_cost_per_token": 3e-07, - "output_cost_per_token": 3e-07, - "litellm_provider": "mistral", - "mode": "chat", - "source": "https://mistral.ai/technology/", - "supports_assistant_prefill": true, - "supports_tool_choice": true, - "supports_response_schema": true - }, - "mistral/open-codestral-mamba": { - "max_tokens": 256000, - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "input_cost_per_token": 2.5e-07, - "output_cost_per_token": 2.5e-07, - "litellm_provider": "mistral", - "mode": "chat", - "source": "https://mistral.ai/technology/", - "supports_assistant_prefill": true, - "supports_tool_choice": true - }, - "mistral/codestral-mamba-latest": { - "max_tokens": 256000, - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "input_cost_per_token": 2.5e-07, - "output_cost_per_token": 2.5e-07, - "litellm_provider": "mistral", - "mode": "chat", - "source": "https://mistral.ai/technology/", - "supports_assistant_prefill": true, - "supports_tool_choice": true - }, - "mistral/devstral-small-2505": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 3e-07, - "litellm_provider": "mistral", - "mode": "chat", - "source": "https://mistral.ai/news/devstral", - "supports_function_calling": true, - "supports_assistant_prefill": true, - "supports_tool_choice": true, - "supports_response_schema": true - }, - "mistral/devstral-small-2507": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 3e-07, - "litellm_provider": "mistral", - "mode": "chat", - "source": "https://mistral.ai/news/devstral", - "supports_function_calling": true, - "supports_assistant_prefill": true, - "supports_tool_choice": true, - "supports_response_schema": true - }, - "mistral/devstral-medium-2507": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "input_cost_per_token": 4e-07, - "output_cost_per_token": 2e-06, - "litellm_provider": "mistral", - "mode": "chat", - "source": "https://mistral.ai/news/devstral", - "supports_function_calling": true, - "supports_assistant_prefill": true, - "supports_tool_choice": true, - "supports_response_schema": true - }, - "mistral/magistral-medium-latest": { - "max_tokens": 40000, - "max_input_tokens": 40000, - "max_output_tokens": 40000, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 5e-06, - "litellm_provider": "mistral", - "mode": "chat", - "source": "https://mistral.ai/news/magistral", - "supports_function_calling": true, - "supports_assistant_prefill": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true - }, - "mistral/magistral-medium-2506": { - "max_tokens": 40000, - "max_input_tokens": 40000, - "max_output_tokens": 40000, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 5e-06, - "litellm_provider": "mistral", - "mode": "chat", - "source": "https://mistral.ai/news/magistral", - "supports_function_calling": true, - "supports_assistant_prefill": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true - }, - "mistral/magistral-small-latest": { - "max_tokens": 40000, - "max_input_tokens": 40000, - "max_output_tokens": 40000, - "input_cost_per_token": 5e-07, - "output_cost_per_token": 1.5e-06, - "litellm_provider": "mistral", - "mode": "chat", - "source": "https://mistral.ai/pricing#api-pricing", - "supports_function_calling": true, - "supports_assistant_prefill": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true - }, - "mistral/magistral-small-2506": { - "max_tokens": 40000, - "max_input_tokens": 40000, - "max_output_tokens": 40000, - "input_cost_per_token": 5e-07, - "output_cost_per_token": 1.5e-06, - "litellm_provider": "mistral", - "mode": "chat", - "source": "https://mistral.ai/pricing#api-pricing", - "supports_function_calling": true, - "supports_assistant_prefill": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true - }, - "mistral/mistral-embed": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "input_cost_per_token": 1e-07, - "litellm_provider": "mistral", - "mode": "embedding" - }, - "deepseek/deepseek-reasoner": { - "max_tokens": 8192, - "max_input_tokens": 65536, - "max_output_tokens": 8192, - "input_cost_per_token": 5.5e-07, - "input_cost_per_token_cache_hit": 1.4e-07, - "output_cost_per_token": 2.19e-06, - "litellm_provider": "deepseek", - "mode": "chat", - "supports_function_calling": true, - "supports_assistant_prefill": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_prompt_caching": true - }, - "deepseek/deepseek-chat": { - "max_tokens": 8192, - "max_input_tokens": 65536, - "max_output_tokens": 8192, - "input_cost_per_token": 2.7e-07, - "input_cost_per_token_cache_hit": 7e-08, - "cache_read_input_token_cost": 7e-08, - "cache_creation_input_token_cost": 0.0, - "output_cost_per_token": 1.1e-06, - "litellm_provider": "deepseek", - "mode": "chat", - "supports_function_calling": true, - "supports_assistant_prefill": true, - "supports_tool_choice": true, - "supports_prompt_caching": true - }, - "deepseek/deepseek-r1": { - "max_tokens": 8192, - "max_input_tokens": 65536, - "max_output_tokens": 8192, - "input_cost_per_token": 5.5e-07, - "input_cost_per_token_cache_hit": 1.4e-07, - "output_cost_per_token": 2.19e-06, - "litellm_provider": "deepseek", - "mode": "chat", - "supports_function_calling": true, - "supports_assistant_prefill": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_prompt_caching": true - }, - "deepseek/deepseek-v3": { - "max_tokens": 8192, - "max_input_tokens": 65536, - "max_output_tokens": 8192, - "input_cost_per_token": 2.7e-07, - "input_cost_per_token_cache_hit": 7e-08, - "cache_read_input_token_cost": 7e-08, - "cache_creation_input_token_cost": 0.0, - "output_cost_per_token": 1.1e-06, - "litellm_provider": "deepseek", - "mode": "chat", - "supports_function_calling": true, - "supports_assistant_prefill": true, - "supports_tool_choice": true, - "supports_prompt_caching": true - }, - "codestral/codestral-latest": { - "max_tokens": 8191, - "max_input_tokens": 32000, - "max_output_tokens": 8191, - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "codestral", - "mode": "chat", - "source": "https://docs.mistral.ai/capabilities/code_generation/", - "supports_assistant_prefill": true, - "supports_tool_choice": true - }, - "codestral/codestral-2405": { - "max_tokens": 8191, - "max_input_tokens": 32000, - "max_output_tokens": 8191, - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "codestral", - "mode": "chat", - "source": "https://docs.mistral.ai/capabilities/code_generation/", - "supports_assistant_prefill": true, - "supports_tool_choice": true - }, - "text-completion-codestral/codestral-latest": { - "max_tokens": 8191, - "max_input_tokens": 32000, - "max_output_tokens": 8191, - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "text-completion-codestral", "mode": "completion", - "source": "https://docs.mistral.ai/capabilities/code_generation/" + "output_cost_per_token": 4e-07 }, - "text-completion-codestral/codestral-2405": { - "max_tokens": 8191, - "max_input_tokens": 32000, - "max_output_tokens": 8191, - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "text-completion-codestral", - "mode": "completion", - "source": "https://docs.mistral.ai/capabilities/code_generation/" - }, - "xai/grok-beta": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 5e-06, - "output_cost_per_token": 1.5e-05, - "litellm_provider": "xai", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "supports_tool_choice": true, - "supports_web_search": true - }, - "xai/grok-2-vision-1212": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "input_cost_per_token": 2e-06, - "input_cost_per_image": 2e-06, - "output_cost_per_token": 1e-05, - "litellm_provider": "xai", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "supports_tool_choice": true, - "supports_web_search": true - }, - "xai/grok-2-vision-latest": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "input_cost_per_token": 2e-06, - "input_cost_per_image": 2e-06, - "output_cost_per_token": 1e-05, - "litellm_provider": "xai", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "supports_tool_choice": true, - "supports_web_search": true - }, - "xai/grok-2-vision": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "input_cost_per_token": 2e-06, - "input_cost_per_image": 2e-06, - "output_cost_per_token": 1e-05, - "litellm_provider": "xai", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "supports_tool_choice": true, - "supports_web_search": true - }, - "xai/grok-3": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "litellm_provider": "xai", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": false, - "source": "https://x.ai/api#pricing", - "supports_web_search": true - }, - "xai/grok-3-latest": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "litellm_provider": "xai", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": false, - "source": "https://x.ai/api#pricing", - "supports_web_search": true - }, - "xai/grok-3-beta": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "litellm_provider": "xai", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": false, - "source": "https://x.ai/api#pricing", - "supports_web_search": true - }, - "xai/grok-3-fast-beta": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 5e-06, - "output_cost_per_token": 2.5e-05, - "litellm_provider": "xai", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": false, - "source": "https://x.ai/api#pricing", - "supports_web_search": true - }, - "xai/grok-3-fast-latest": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 5e-06, - "output_cost_per_token": 2.5e-05, - "litellm_provider": "xai", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": false, - "source": "https://x.ai/api#pricing", - "supports_web_search": true - }, - "xai/grok-3-mini": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 3e-07, - "output_cost_per_token": 5e-07, - "litellm_provider": "xai", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": false, - "source": "https://x.ai/api#pricing", - "supports_web_search": true - }, - "xai/grok-3-mini-latest": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 3e-07, - "output_cost_per_token": 5e-07, - "litellm_provider": "xai", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": false, - "source": "https://x.ai/api#pricing", - "supports_web_search": true - }, - "xai/grok-3-mini-fast": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 6e-07, - "output_cost_per_token": 4e-06, - "litellm_provider": "xai", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": false, - "source": "https://x.ai/api#pricing", - "supports_web_search": true - }, - "xai/grok-3-mini-fast-latest": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 6e-07, - "output_cost_per_token": 4e-06, - "litellm_provider": "xai", - "mode": "chat", - "supports_reasoning": true, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": false, - "source": "https://x.ai/api#pricing", - "supports_web_search": true - }, - "xai/grok-3-mini-beta": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 3e-07, - "output_cost_per_token": 5e-07, - "litellm_provider": "xai", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": false, - "source": "https://x.ai/api#pricing", - "supports_web_search": true - }, - "xai/grok-3-mini-fast-beta": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 6e-07, - "output_cost_per_token": 4e-06, - "litellm_provider": "xai", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": false, - "source": "https://x.ai/api#pricing", - "supports_web_search": true - }, - "xai/grok-vision-beta": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 5e-06, - "input_cost_per_image": 5e-06, - "output_cost_per_token": 1.5e-05, - "litellm_provider": "xai", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "supports_tool_choice": true, - "supports_web_search": true - }, - "xai/grok-2-1212": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 1e-05, - "litellm_provider": "xai", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_web_search": true - }, - "xai/grok-2": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 1e-05, - "litellm_provider": "xai", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_web_search": true - }, - "xai/grok-2-latest": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 1e-05, - "litellm_provider": "xai", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_web_search": true - }, - "xai/grok-code-fast-1": { - "max_tokens": 256000, - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "input_cost_per_token": 0.2e-06, - "output_cost_per_token": 1.5e-06, - "cache_read_input_token_cost": 0.02e-06, - "litellm_provider": "xai", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "source": "https://docs.x.ai/docs/models" - }, - "xai/grok-code-fast": { - "max_tokens": 256000, - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "input_cost_per_token": 0.2e-06, - "output_cost_per_token": 1.5e-06, - "cache_read_input_token_cost": 0.02e-06, - "litellm_provider": "xai", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "source": "https://docs.x.ai/docs/models" - }, - "xai/grok-code-fast-1-0825": { - "max_tokens": 256000, - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "input_cost_per_token": 0.2e-06, - "output_cost_per_token": 1.5e-06, - "cache_read_input_token_cost": 0.02e-06, - "litellm_provider": "xai", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "source": "https://docs.x.ai/docs/models" - }, - "xai/grok-4": { - "max_tokens": 256000, - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "litellm_provider": "xai", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "source": "https://docs.x.ai/docs/models", - "supports_web_search": true - }, - "xai/grok-4-0709": { - "max_tokens": 256000, - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "litellm_provider": "xai", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "source": "https://docs.x.ai/docs/models", - "supports_web_search": true - }, - "xai/grok-4-latest": { - "max_tokens": 256000, - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "litellm_provider": "xai", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "source": "https://docs.x.ai/docs/models", - "supports_web_search": true - }, - "deepseek/deepseek-coder": { - "max_tokens": 4096, - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 1.4e-07, - "input_cost_per_token_cache_hit": 1.4e-08, - "output_cost_per_token": 2.8e-07, - "litellm_provider": "deepseek", - "mode": "chat", - "supports_function_calling": true, - "supports_assistant_prefill": true, - "supports_tool_choice": true, - "supports_prompt_caching": true - }, - "groq/deepseek-r1-distill-llama-70b": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "input_cost_per_token": 7.5e-07, - "output_cost_per_token": 9.9e-07, - "litellm_provider": "groq", - "mode": "chat", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_reasoning": true, - "supports_tool_choice": true - }, - "groq/llama-3.3-70b-versatile": { - "max_tokens": 32768, - "max_input_tokens": 128000, - "max_output_tokens": 32768, - "input_cost_per_token": 5.9e-07, - "output_cost_per_token": 7.9e-07, - "litellm_provider": "groq", - "mode": "chat", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "groq/llama-3.3-70b-specdec": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 5.9e-07, - "output_cost_per_token": 9.9e-07, - "litellm_provider": "groq", - "mode": "chat", - "supports_tool_choice": true, - "deprecation_date": "2025-04-14" - }, - "groq/llama-guard-3-8b": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 2e-07, - "output_cost_per_token": 2e-07, - "litellm_provider": "groq", - "mode": "chat" - }, - "groq/llama2-70b-4096": { - "max_tokens": 4096, + "bedrock/*/1-month-commitment/cohere.command-light-text-v14": { + "input_cost_per_second": 0.001902, + "litellm_provider": "bedrock", "max_input_tokens": 4096, "max_output_tokens": 4096, - "input_cost_per_token": 7e-07, - "output_cost_per_token": 8e-07, - "litellm_provider": "groq", + "max_tokens": 4096, "mode": "chat", - "supports_function_calling": true, - "supports_response_schema": true, + "output_cost_per_second": 0.001902, "supports_tool_choice": true }, - "groq/llama-3.2-1b-preview": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 4e-08, - "output_cost_per_token": 4e-08, - "litellm_provider": "groq", + "bedrock/*/1-month-commitment/cohere.command-text-v14": { + "input_cost_per_second": 0.011, + "litellm_provider": "bedrock", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "deprecation_date": "2025-04-14" - }, - "groq/llama-3.2-3b-preview": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 6e-08, - "output_cost_per_token": 6e-08, - "litellm_provider": "groq", - "mode": "chat", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "deprecation_date": "2025-04-14" - }, - "groq/llama-3.2-11b-text-preview": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 1.8e-07, - "output_cost_per_token": 1.8e-07, - "litellm_provider": "groq", - "mode": "chat", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "deprecation_date": "2024-10-28" - }, - "groq/llama-3.2-11b-vision-preview": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 1.8e-07, - "output_cost_per_token": 1.8e-07, - "litellm_provider": "groq", - "mode": "chat", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_tool_choice": true, - "deprecation_date": "2025-04-14" - }, - "groq/llama-3.2-90b-text-preview": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 9e-07, - "output_cost_per_token": 9e-07, - "litellm_provider": "groq", - "mode": "chat", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "deprecation_date": "2024-11-25" - }, - "groq/llama-3.2-90b-vision-preview": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 9e-07, - "output_cost_per_token": 9e-07, - "litellm_provider": "groq", - "mode": "chat", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_tool_choice": true, - "deprecation_date": "2025-04-14" - }, - "groq/llama-3.1-8b-instant": { - "max_tokens": 8192, - "max_input_tokens": 128000, - "max_output_tokens": 8192, - "input_cost_per_token": 5e-08, - "output_cost_per_token": 8e-08, - "litellm_provider": "groq", - "mode": "chat", - "supports_function_calling": true, - "supports_response_schema": true, + "output_cost_per_second": 0.011, "supports_tool_choice": true }, - "groq/llama-3.1-70b-versatile": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 5.9e-07, - "output_cost_per_token": 7.9e-07, - "litellm_provider": "groq", + "bedrock/*/6-month-commitment/cohere.command-light-text-v14": { + "input_cost_per_second": 0.0011416, + "litellm_provider": "bedrock", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "deprecation_date": "2025-01-24" - }, - "groq/llama-3.1-405b-reasoning": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 5.9e-07, - "output_cost_per_token": 7.9e-07, - "litellm_provider": "groq", - "mode": "chat", - "supports_function_calling": true, - "supports_response_schema": true, + "output_cost_per_second": 0.0011416, "supports_tool_choice": true }, - "groq/meta-llama/llama-4-scout-17b-16e-instruct": { - "max_tokens": 8192, - "max_input_tokens": 131072, - "max_output_tokens": 8192, - "input_cost_per_token": 1.1e-07, - "output_cost_per_token": 3.4e-07, - "litellm_provider": "groq", + "bedrock/*/6-month-commitment/cohere.command-text-v14": { + "input_cost_per_second": 0.0066027, + "litellm_provider": "bedrock", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", - "supports_function_calling": true, - "supports_response_schema": true, + "output_cost_per_second": 0.0066027, "supports_tool_choice": true }, - "groq/meta-llama/llama-4-maverick-17b-128e-instruct": { - "max_tokens": 8192, - "max_input_tokens": 131072, + "bedrock/ap-northeast-1/1-month-commitment/anthropic.claude-instant-v1": { + "input_cost_per_second": 0.01475, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_second": 0.01475, + "supports_tool_choice": true + }, + "bedrock/ap-northeast-1/1-month-commitment/anthropic.claude-v1": { + "input_cost_per_second": 0.0455, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_second": 0.0455 + }, + "bedrock/ap-northeast-1/1-month-commitment/anthropic.claude-v2:1": { + "input_cost_per_second": 0.0455, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_second": 0.0455, + "supports_tool_choice": true + }, + "bedrock/ap-northeast-1/6-month-commitment/anthropic.claude-instant-v1": { + "input_cost_per_second": 0.008194, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_second": 0.008194, + "supports_tool_choice": true + }, + "bedrock/ap-northeast-1/6-month-commitment/anthropic.claude-v1": { + "input_cost_per_second": 0.02527, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_second": 0.02527 + }, + "bedrock/ap-northeast-1/6-month-commitment/anthropic.claude-v2:1": { + "input_cost_per_second": 0.02527, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_second": 0.02527, + "supports_tool_choice": true + }, + "bedrock/ap-northeast-1/anthropic.claude-instant-v1": { + "input_cost_per_token": 2.23e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 7.55e-06, + "supports_tool_choice": true + }, + "bedrock/ap-northeast-1/anthropic.claude-v1": { + "input_cost_per_token": 8e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 2.4e-05, + "supports_tool_choice": true + }, + "bedrock/ap-northeast-1/anthropic.claude-v2:1": { + "input_cost_per_token": 8e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 2.4e-05, + "supports_tool_choice": true + }, + "bedrock/ap-south-1/meta.llama3-70b-instruct-v1:0": { + "input_cost_per_token": 3.18e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 8192, "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 4.2e-06 + }, + "bedrock/ap-south-1/meta.llama3-8b-instruct-v1:0": { + "input_cost_per_token": 3.6e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 7.2e-07 + }, + "bedrock/ca-central-1/meta.llama3-70b-instruct-v1:0": { + "input_cost_per_token": 3.05e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 4.03e-06 + }, + "bedrock/ca-central-1/meta.llama3-8b-instruct-v1:0": { + "input_cost_per_token": 3.5e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 6.9e-07 + }, + "bedrock/eu-central-1/1-month-commitment/anthropic.claude-instant-v1": { + "input_cost_per_second": 0.01635, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_second": 0.01635, + "supports_tool_choice": true + }, + "bedrock/eu-central-1/1-month-commitment/anthropic.claude-v1": { + "input_cost_per_second": 0.0415, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_second": 0.0415 + }, + "bedrock/eu-central-1/1-month-commitment/anthropic.claude-v2:1": { + "input_cost_per_second": 0.0415, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_second": 0.0415, + "supports_tool_choice": true + }, + "bedrock/eu-central-1/6-month-commitment/anthropic.claude-instant-v1": { + "input_cost_per_second": 0.009083, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_second": 0.009083, + "supports_tool_choice": true + }, + "bedrock/eu-central-1/6-month-commitment/anthropic.claude-v1": { + "input_cost_per_second": 0.02305, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_second": 0.02305 + }, + "bedrock/eu-central-1/6-month-commitment/anthropic.claude-v2:1": { + "input_cost_per_second": 0.02305, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_second": 0.02305, + "supports_tool_choice": true + }, + "bedrock/eu-central-1/anthropic.claude-instant-v1": { + "input_cost_per_token": 2.48e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 8.38e-06, + "supports_tool_choice": true + }, + "bedrock/eu-central-1/anthropic.claude-v1": { + "input_cost_per_token": 8e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 2.4e-05 + }, + "bedrock/eu-central-1/anthropic.claude-v2:1": { + "input_cost_per_token": 8e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 2.4e-05, + "supports_tool_choice": true + }, + "bedrock/eu-west-1/meta.llama3-70b-instruct-v1:0": { + "input_cost_per_token": 2.86e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 3.78e-06 + }, + "bedrock/eu-west-1/meta.llama3-8b-instruct-v1:0": { + "input_cost_per_token": 3.2e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 6.5e-07 + }, + "bedrock/eu-west-2/meta.llama3-70b-instruct-v1:0": { + "input_cost_per_token": 3.45e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 4.55e-06 + }, + "bedrock/eu-west-2/meta.llama3-8b-instruct-v1:0": { + "input_cost_per_token": 3.9e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 7.8e-07 + }, + "bedrock/eu-west-3/mistral.mistral-7b-instruct-v0:2": { "input_cost_per_token": 2e-07, - "output_cost_per_token": 6e-07, - "litellm_provider": "groq", - "mode": "chat", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "groq/mistral-saba-24b": { - "max_tokens": 32000, + "litellm_provider": "bedrock", "max_input_tokens": 32000, - "max_output_tokens": 32000, - "input_cost_per_token": 7.9e-07, - "output_cost_per_token": 7.9e-07, - "litellm_provider": "groq", - "mode": "chat" - }, - "groq/mixtral-8x7b-32768": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "input_cost_per_token": 2.4e-07, - "output_cost_per_token": 2.4e-07, - "litellm_provider": "groq", + "max_output_tokens": 8191, + "max_tokens": 8191, "mode": "chat", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "deprecation_date": "2025-03-20" - }, - "groq/gemma-7b-it": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 7e-08, - "output_cost_per_token": 7e-08, - "litellm_provider": "groq", - "mode": "chat", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "deprecation_date": "2024-12-18" - }, - "groq/gemma2-9b-it": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 2e-07, - "output_cost_per_token": 2e-07, - "litellm_provider": "groq", - "mode": "chat", - "supports_function_calling": false, - "supports_response_schema": true, - "supports_tool_choice": false - }, - "groq/llama3-groq-70b-8192-tool-use-preview": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 8.9e-07, - "output_cost_per_token": 8.9e-07, - "litellm_provider": "groq", - "mode": "chat", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "deprecation_date": "2025-01-06" - }, - "groq/llama3-groq-8b-8192-tool-use-preview": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 1.9e-07, - "output_cost_per_token": 1.9e-07, - "litellm_provider": "groq", - "mode": "chat", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "deprecation_date": "2025-01-06" - }, - "groq/qwen/qwen3-32b": { - "max_tokens": 131000, - "max_input_tokens": 131000, - "max_output_tokens": 131000, - "input_cost_per_token": 2.9e-07, - "output_cost_per_token": 5.9e-07, - "litellm_provider": "groq", - "mode": "chat", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_reasoning": true, + "output_cost_per_token": 2.6e-07, "supports_tool_choice": true }, - "groq/moonshotai/kimi-k2-instruct": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 16384, - "input_cost_per_token": 1e-06, - "output_cost_per_token": 3e-06, - "litellm_provider": "groq", + "bedrock/eu-west-3/mistral.mistral-large-2402-v1:0": { + "input_cost_per_token": 1.04e-05, + "litellm_provider": "bedrock", + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, "mode": "chat", - "supports_function_calling": true, - "supports_response_schema": true, + "output_cost_per_token": 3.12e-05, + "supports_function_calling": true + }, + "bedrock/eu-west-3/mistral.mixtral-8x7b-instruct-v0:1": { + "input_cost_per_token": 5.9e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 9.1e-07, "supports_tool_choice": true }, - "groq/playai-tts": { - "max_tokens": 10000, - "max_input_tokens": 10000, - "max_output_tokens": 10000, - "input_cost_per_character": 5e-05, - "litellm_provider": "groq", - "mode": "audio_speech" - }, - "groq/whisper-large-v3": { - "input_cost_per_second": 3.083e-05, - "output_cost_per_second": 0.0, - "litellm_provider": "groq", - "mode": "audio_transcription" - }, - "groq/whisper-large-v3-turbo": { - "input_cost_per_second": 1.111e-05, - "output_cost_per_second": 0.0, - "litellm_provider": "groq", - "mode": "audio_transcription" - }, - "groq/distil-whisper-large-v3-en": { - "input_cost_per_second": 5.56e-06, - "output_cost_per_second": 0.0, - "litellm_provider": "groq", - "mode": "audio_transcription" - }, - "groq/openai/gpt-oss-20b": { - "max_tokens": 32768, - "max_input_tokens": 131072, - "max_output_tokens": 32768, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 5e-07, - "litellm_provider": "groq", + "bedrock/invoke/anthropic.claude-3-5-sonnet-20240620-v1:0": { + "input_cost_per_token": 3e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "metadata": { + "notes": "Anthropic via Invoke route does not currently support pdf input." + }, "mode": "chat", + "output_cost_per_token": 1.5e-05, "supports_function_calling": true, - "supports_parallel_function_calling": true, "supports_response_schema": true, - "supports_reasoning": true, "supports_tool_choice": true, - "supports_web_search": true + "supports_vision": true }, - "groq/openai/gpt-oss-120b": { - "max_tokens": 32766, - "max_input_tokens": 131072, - "max_output_tokens": 32766, + "bedrock/sa-east-1/meta.llama3-70b-instruct-v1:0": { + "input_cost_per_token": 4.45e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 5.88e-06 + }, + "bedrock/sa-east-1/meta.llama3-8b-instruct-v1:0": { + "input_cost_per_token": 5e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.01e-06 + }, + "bedrock/us-east-1/1-month-commitment/anthropic.claude-instant-v1": { + "input_cost_per_second": 0.011, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_second": 0.011, + "supports_tool_choice": true + }, + "bedrock/us-east-1/1-month-commitment/anthropic.claude-v1": { + "input_cost_per_second": 0.0175, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_second": 0.0175 + }, + "bedrock/us-east-1/1-month-commitment/anthropic.claude-v2:1": { + "input_cost_per_second": 0.0175, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_second": 0.0175, + "supports_tool_choice": true + }, + "bedrock/us-east-1/6-month-commitment/anthropic.claude-instant-v1": { + "input_cost_per_second": 0.00611, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_second": 0.00611, + "supports_tool_choice": true + }, + "bedrock/us-east-1/6-month-commitment/anthropic.claude-v1": { + "input_cost_per_second": 0.00972, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_second": 0.00972 + }, + "bedrock/us-east-1/6-month-commitment/anthropic.claude-v2:1": { + "input_cost_per_second": 0.00972, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_second": 0.00972, + "supports_tool_choice": true + }, + "bedrock/us-east-1/anthropic.claude-instant-v1": { + "input_cost_per_token": 8e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 2.4e-06, + "supports_tool_choice": true + }, + "bedrock/us-east-1/anthropic.claude-v1": { + "input_cost_per_token": 8e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 2.4e-05, + "supports_tool_choice": true + }, + "bedrock/us-east-1/anthropic.claude-v2:1": { + "input_cost_per_token": 8e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 2.4e-05, + "supports_tool_choice": true + }, + "bedrock/us-east-1/meta.llama3-70b-instruct-v1:0": { + "input_cost_per_token": 2.65e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 3.5e-06 + }, + "bedrock/us-east-1/meta.llama3-8b-instruct-v1:0": { + "input_cost_per_token": 3e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 6e-07 + }, + "bedrock/us-east-1/mistral.mistral-7b-instruct-v0:2": { "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 7.5e-07, - "litellm_provider": "groq", + "litellm_provider": "bedrock", + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_reasoning": true, - "supports_tool_choice": true, - "supports_web_search": true + "output_cost_per_token": 2e-07, + "supports_tool_choice": true }, - "cerebras/llama3.1-8b": { - "max_tokens": 128000, + "bedrock/us-east-1/mistral.mistral-large-2402-v1:0": { + "input_cost_per_token": 8e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 2.4e-05, + "supports_function_calling": true + }, + "bedrock/us-east-1/mistral.mixtral-8x7b-instruct-v0:1": { + "input_cost_per_token": 4.5e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 7e-07, + "supports_tool_choice": true + }, + "bedrock/us-gov-east-1/amazon.nova-pro-v1:0": { + "input_cost_per_token": 9.6e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 300000, + "max_output_tokens": 10000, + "max_tokens": 10000, + "mode": "chat", + "output_cost_per_token": 3.84e-06, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_vision": true + }, + "bedrock/us-gov-east-1/amazon.titan-embed-text-v1": { + "input_cost_per_token": 1e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 8192, + "max_tokens": 8192, + "mode": "embedding", + "output_cost_per_token": 0.0, + "output_vector_size": 1536 + }, + "bedrock/us-gov-east-1/amazon.titan-embed-text-v2:0": { + "input_cost_per_token": 2e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 8192, + "max_tokens": 8192, + "mode": "embedding", + "output_cost_per_token": 0.0, + "output_vector_size": 1024 + }, + "bedrock/us-gov-east-1/amazon.titan-text-express-v1": { + "input_cost_per_token": 1.3e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 42000, + "max_output_tokens": 8000, + "max_tokens": 8000, + "mode": "chat", + "output_cost_per_token": 1.7e-06 + }, + "bedrock/us-gov-east-1/amazon.titan-text-lite-v1": { + "input_cost_per_token": 3e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 42000, + "max_output_tokens": 4000, + "max_tokens": 4000, + "mode": "chat", + "output_cost_per_token": 4e-07 + }, + "bedrock/us-gov-east-1/amazon.titan-text-premier-v1:0": { + "input_cost_per_token": 5e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 42000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 1.5e-06 + }, + "bedrock/us-gov-east-1/anthropic.claude-3-5-sonnet-20240620-v1:0": { + "input_cost_per_token": 3.6e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.8e-05, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "bedrock/us-gov-east-1/anthropic.claude-3-haiku-20240307-v1:0": { + "input_cost_per_token": 3e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.5e-06, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "bedrock/us-gov-east-1/meta.llama3-70b-instruct-v1:0": { + "input_cost_per_token": 2.65e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 8000, + "max_output_tokens": 2048, + "max_tokens": 2048, + "mode": "chat", + "output_cost_per_token": 3.5e-06, + "supports_pdf_input": true + }, + "bedrock/us-gov-east-1/meta.llama3-8b-instruct-v1:0": { + "input_cost_per_token": 3e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 8000, + "max_output_tokens": 2048, + "max_tokens": 2048, + "mode": "chat", + "output_cost_per_token": 2.65e-06, + "supports_pdf_input": true + }, + "bedrock/us-gov-west-1/amazon.nova-pro-v1:0": { + "input_cost_per_token": 9.6e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 300000, + "max_output_tokens": 10000, + "max_tokens": 10000, + "mode": "chat", + "output_cost_per_token": 3.84e-06, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_vision": true + }, + "bedrock/us-gov-west-1/amazon.titan-embed-text-v1": { + "input_cost_per_token": 1e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 8192, + "max_tokens": 8192, + "mode": "embedding", + "output_cost_per_token": 0.0, + "output_vector_size": 1536 + }, + "bedrock/us-gov-west-1/amazon.titan-embed-text-v2:0": { + "input_cost_per_token": 2e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 8192, + "max_tokens": 8192, + "mode": "embedding", + "output_cost_per_token": 0.0, + "output_vector_size": 1024 + }, + "bedrock/us-gov-west-1/amazon.titan-text-express-v1": { + "input_cost_per_token": 1.3e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 42000, + "max_output_tokens": 8000, + "max_tokens": 8000, + "mode": "chat", + "output_cost_per_token": 1.7e-06 + }, + "bedrock/us-gov-west-1/amazon.titan-text-lite-v1": { + "input_cost_per_token": 3e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 42000, + "max_output_tokens": 4000, + "max_tokens": 4000, + "mode": "chat", + "output_cost_per_token": 4e-07 + }, + "bedrock/us-gov-west-1/amazon.titan-text-premier-v1:0": { + "input_cost_per_token": 5e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 42000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 1.5e-06 + }, + "bedrock/us-gov-west-1/anthropic.claude-3-5-sonnet-20240620-v1:0": { + "input_cost_per_token": 3.6e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.8e-05, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "bedrock/us-gov-west-1/anthropic.claude-3-haiku-20240307-v1:0": { + "input_cost_per_token": 3e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.5e-06, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "bedrock/us-gov-west-1/meta.llama3-70b-instruct-v1:0": { + "input_cost_per_token": 2.65e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 8000, + "max_output_tokens": 2048, + "max_tokens": 2048, + "mode": "chat", + "output_cost_per_token": 3.5e-06, + "supports_pdf_input": true + }, + "bedrock/us-gov-west-1/meta.llama3-8b-instruct-v1:0": { + "input_cost_per_token": 3e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 8000, + "max_output_tokens": 2048, + "max_tokens": 2048, + "mode": "chat", + "output_cost_per_token": 2.65e-06, + "supports_pdf_input": true + }, + "bedrock/us-west-1/meta.llama3-70b-instruct-v1:0": { + "input_cost_per_token": 2.65e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 3.5e-06 + }, + "bedrock/us-west-1/meta.llama3-8b-instruct-v1:0": { + "input_cost_per_token": 3e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 6e-07 + }, + "bedrock/us-west-2/1-month-commitment/anthropic.claude-instant-v1": { + "input_cost_per_second": 0.011, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_second": 0.011, + "supports_tool_choice": true + }, + "bedrock/us-west-2/1-month-commitment/anthropic.claude-v1": { + "input_cost_per_second": 0.0175, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_second": 0.0175 + }, + "bedrock/us-west-2/1-month-commitment/anthropic.claude-v2:1": { + "input_cost_per_second": 0.0175, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_second": 0.0175, + "supports_tool_choice": true + }, + "bedrock/us-west-2/6-month-commitment/anthropic.claude-instant-v1": { + "input_cost_per_second": 0.00611, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_second": 0.00611, + "supports_tool_choice": true + }, + "bedrock/us-west-2/6-month-commitment/anthropic.claude-v1": { + "input_cost_per_second": 0.00972, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_second": 0.00972 + }, + "bedrock/us-west-2/6-month-commitment/anthropic.claude-v2:1": { + "input_cost_per_second": 0.00972, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_second": 0.00972, + "supports_tool_choice": true + }, + "bedrock/us-west-2/anthropic.claude-instant-v1": { + "input_cost_per_token": 8e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 2.4e-06, + "supports_tool_choice": true + }, + "bedrock/us-west-2/anthropic.claude-v1": { + "input_cost_per_token": 8e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 2.4e-05, + "supports_tool_choice": true + }, + "bedrock/us-west-2/anthropic.claude-v2:1": { + "input_cost_per_token": 8e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 2.4e-05, + "supports_tool_choice": true + }, + "bedrock/us-west-2/mistral.mistral-7b-instruct-v0:2": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 2e-07, + "supports_tool_choice": true + }, + "bedrock/us-west-2/mistral.mistral-large-2402-v1:0": { + "input_cost_per_token": 8e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 2.4e-05, + "supports_function_calling": true + }, + "bedrock/us-west-2/mistral.mixtral-8x7b-instruct-v0:1": { + "input_cost_per_token": 4.5e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 7e-07, + "supports_tool_choice": true + }, + "bedrock/us.anthropic.claude-3-5-haiku-20241022-v1:0": { + "cache_creation_input_token_cost": 1e-06, + "cache_read_input_token_cost": 8e-08, + "input_cost_per_token": 8e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 4e-06, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "cerebras/llama-3.3-70b": { + "input_cost_per_token": 8.5e-07, + "litellm_provider": "cerebras", "max_input_tokens": 128000, "max_output_tokens": 128000, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 1e-07, - "litellm_provider": "cerebras", + "max_tokens": 128000, "mode": "chat", + "output_cost_per_token": 1.2e-06, "supports_function_calling": true, "supports_tool_choice": true }, "cerebras/llama3.1-70b": { - "max_tokens": 128000, + "input_cost_per_token": 6e-07, + "litellm_provider": "cerebras", "max_input_tokens": 128000, "max_output_tokens": 128000, - "input_cost_per_token": 6e-07, - "output_cost_per_token": 6e-07, - "litellm_provider": "cerebras", + "max_tokens": 128000, "mode": "chat", + "output_cost_per_token": 6e-07, "supports_function_calling": true, "supports_tool_choice": true }, - "cerebras/llama-3.3-70b": { - "max_tokens": 128000, + "cerebras/llama3.1-8b": { + "input_cost_per_token": 1e-07, + "litellm_provider": "cerebras", "max_input_tokens": 128000, "max_output_tokens": 128000, - "input_cost_per_token": 8.5e-07, - "output_cost_per_token": 1.2e-06, - "litellm_provider": "cerebras", + "max_tokens": 128000, "mode": "chat", + "output_cost_per_token": 1e-07, "supports_function_calling": true, "supports_tool_choice": true }, + "cerebras/openai/gpt-oss-120b": { + "input_cost_per_token": 2.5e-07, + "litellm_provider": "cerebras", + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 6.9e-07, + "source": "https://www.cerebras.ai/blog/openai-gpt-oss-120b-runs-fastest-on-cerebras", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, "cerebras/qwen-3-32b": { - "max_tokens": 128000, + "input_cost_per_token": 4e-07, + "litellm_provider": "cerebras", "max_input_tokens": 128000, "max_output_tokens": 128000, - "input_cost_per_token": 4e-07, + "max_tokens": 128000, + "mode": "chat", "output_cost_per_token": 8e-07, - "litellm_provider": "cerebras", - "mode": "chat", + "source": "https://inference-docs.cerebras.ai/support/pricing", "supports_function_calling": true, - "supports_tool_choice": true, - "source": "https://inference-docs.cerebras.ai/support/pricing" - }, - - "cerebras/openai/gpt-oss-120b": { - "max_tokens": 32768, - "max_input_tokens": 131072, - "max_output_tokens": 32768, - "input_cost_per_token": 2.5e-07, - "output_cost_per_token": 6.9e-07, - "litellm_provider": "cerebras", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_reasoning": true, - "supports_tool_choice": true, - "source": "https://www.cerebras.ai/blog/openai-gpt-oss-120b-runs-fastest-on-cerebras" - }, - "friendliai/meta-llama-3.1-8b-instruct": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 1e-07, - "litellm_provider": "friendliai", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_response_schema": true, "supports_tool_choice": true }, - "friendliai/meta-llama-3.1-70b-instruct": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 6e-07, - "output_cost_per_token": 6e-07, - "litellm_provider": "friendliai", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "claude-3-haiku-20240307": { - "max_tokens": 4096, - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "input_cost_per_token": 2.5e-07, - "output_cost_per_token": 1.25e-06, - "cache_creation_input_token_cost": 3e-07, - "cache_read_input_token_cost": 3e-08, - "litellm_provider": "anthropic", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 264, - "supports_assistant_prefill": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "deprecation_date": "2025-03-01", - "supports_tool_choice": true - }, - "claude-3-5-haiku-20241022": { - "max_tokens": 8192, - "max_input_tokens": 200000, - "max_output_tokens": 8192, - "input_cost_per_token": 8e-07, - "output_cost_per_token": 4e-06, - "cache_creation_input_token_cost": 1e-06, - "cache_creation_input_token_cost_above_1hr": 1.6e-06, - "cache_read_input_token_cost": 8e-08, - "search_context_cost_per_query": { - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01, - "search_context_size_high": 0.01 - }, - "litellm_provider": "anthropic", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 264, - "supports_assistant_prefill": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "deprecation_date": "2025-10-01", - "supports_tool_choice": true, - "supports_web_search": true - }, - "claude-3-5-haiku-latest": { - "max_tokens": 8192, - "max_input_tokens": 200000, - "max_output_tokens": 8192, - "input_cost_per_token": 1e-06, - "output_cost_per_token": 5e-06, - "cache_creation_input_token_cost": 1.25e-06, - "cache_read_input_token_cost": 1e-07, - "search_context_cost_per_query": { - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01, - "search_context_size_high": 0.01 - }, - "litellm_provider": "anthropic", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 264, - "supports_assistant_prefill": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "deprecation_date": "2025-10-01", - "supports_tool_choice": true, - "supports_web_search": true - }, - "claude-3-opus-latest": { - "max_tokens": 4096, - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "input_cost_per_token": 1.5e-05, - "output_cost_per_token": 7.5e-05, - "cache_creation_input_token_cost": 1.875e-05, - "cache_read_input_token_cost": 1.5e-06, - "litellm_provider": "anthropic", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 395, - "supports_assistant_prefill": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "deprecation_date": "2025-03-01", - "supports_tool_choice": true - }, - "claude-3-opus-20240229": { - "max_tokens": 4096, - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "input_cost_per_token": 1.5e-05, - "output_cost_per_token": 7.5e-05, - "cache_creation_input_token_cost": 1.875e-05, - "cache_read_input_token_cost": 1.5e-06, - "litellm_provider": "anthropic", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 395, - "supports_assistant_prefill": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "deprecation_date": "2025-03-01", - "supports_tool_choice": true - }, - "claude-3-5-sonnet-latest": { - "supports_computer_use": true, - "max_tokens": 8192, - "max_input_tokens": 200000, - "max_output_tokens": 8192, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "cache_creation_input_token_cost": 3.75e-06, - "cache_read_input_token_cost": 3e-07, - "search_context_cost_per_query": { - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01, - "search_context_size_high": 0.01 - }, - "litellm_provider": "anthropic", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 159, - "supports_assistant_prefill": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "deprecation_date": "2025-06-01", - "supports_tool_choice": true, - "supports_web_search": true - }, - "claude-3-5-sonnet-20240620": { - "max_tokens": 8192, - "max_input_tokens": 200000, - "max_output_tokens": 8192, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "cache_creation_input_token_cost": 3.75e-06, - "cache_read_input_token_cost": 3e-07, - "litellm_provider": "anthropic", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 159, - "supports_assistant_prefill": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "deprecation_date": "2025-06-01", - "supports_tool_choice": true - }, - "claude-opus-4-20250514": { - "max_tokens": 32000, - "max_input_tokens": 200000, - "max_output_tokens": 32000, - "input_cost_per_token": 1.5e-05, - "output_cost_per_token": 7.5e-05, - "search_context_cost_per_query": { - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01, - "search_context_size_high": 0.01 - }, - "cache_creation_input_token_cost": 1.875e-05, - "cache_read_input_token_cost": 1.5e-06, - "litellm_provider": "anthropic", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 159, - "supports_assistant_prefill": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_computer_use": true - }, - "claude-opus-4-1": { - "max_tokens": 32000, - "max_input_tokens": 200000, - "max_output_tokens": 32000, - "input_cost_per_token": 1.5e-05, - "output_cost_per_token": 7.5e-05, - "search_context_cost_per_query": { - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01, - "search_context_size_high": 0.01 - }, - "cache_creation_input_token_cost": 1.875e-05, - "cache_read_input_token_cost": 1.5e-06, - "litellm_provider": "anthropic", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 159, - "supports_assistant_prefill": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_computer_use": true - }, - "claude-opus-4-1-20250805": { - "max_tokens": 32000, - "max_input_tokens": 200000, - "max_output_tokens": 32000, - "input_cost_per_token": 1.5e-05, - "output_cost_per_token": 7.5e-05, - "search_context_cost_per_query": { - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01, - "search_context_size_high": 0.01 - }, - "cache_creation_input_token_cost": 1.875e-05, - "cache_read_input_token_cost": 1.5e-06, - "litellm_provider": "anthropic", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 159, - "supports_assistant_prefill": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_computer_use": true - }, - "claude-sonnet-4-20250514": { - "max_tokens": 64000, - "max_input_tokens": 200000, - "max_output_tokens": 64000, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "search_context_cost_per_query": { - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01, - "search_context_size_high": 0.01 - }, - "cache_creation_input_token_cost": 3.75e-06, - "cache_read_input_token_cost": 3e-07, - "litellm_provider": "anthropic", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 159, - "supports_assistant_prefill": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_computer_use": true - }, - "claude-4-opus-20250514": { - "max_tokens": 32000, - "max_input_tokens": 200000, - "max_output_tokens": 32000, - "input_cost_per_token": 1.5e-05, - "output_cost_per_token": 7.5e-05, - "search_context_cost_per_query": { - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01, - "search_context_size_high": 0.01 - }, - "cache_creation_input_token_cost": 1.875e-05, - "cache_read_input_token_cost": 1.5e-06, - "litellm_provider": "anthropic", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 159, - "supports_assistant_prefill": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_computer_use": true - }, - "claude-4-sonnet-20250514": { - "max_tokens": 1000000, - "max_input_tokens": 1000000, - "max_output_tokens": 1000000, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "input_cost_per_token_above_200k_tokens": 6e-06, - "output_cost_per_token_above_200k_tokens": 2.25e-05, - "search_context_cost_per_query": { - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01, - "search_context_size_high": 0.01 - }, - "cache_creation_input_token_cost": 3.75e-06, - "cache_read_input_token_cost": 3e-07, - "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, - "cache_read_input_token_cost_above_200k_tokens": 6e-07, - "litellm_provider": "anthropic", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 159, - "supports_assistant_prefill": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_computer_use": true - }, - "claude-3-7-sonnet-latest": { - "supports_computer_use": true, - "max_tokens": 128000, - "max_input_tokens": 200000, - "max_output_tokens": 128000, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "search_context_cost_per_query": { - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01, - "search_context_size_high": 0.01 - }, - "cache_creation_input_token_cost": 3.75e-06, - "cache_read_input_token_cost": 3e-07, - "litellm_provider": "anthropic", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 159, - "supports_assistant_prefill": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "deprecation_date": "2025-06-01", - "supports_tool_choice": true, - "supports_reasoning": true - }, - "claude-3-7-sonnet-20250219": { - "supports_computer_use": true, - "max_tokens": 128000, - "max_input_tokens": 200000, - "max_output_tokens": 128000, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "cache_creation_input_token_cost": 3.75e-06, - "cache_read_input_token_cost": 3e-07, - "search_context_cost_per_query": { - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01, - "search_context_size_high": 0.01 - }, - "litellm_provider": "anthropic", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 159, - "supports_assistant_prefill": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "deprecation_date": "2026-02-01", - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_web_search": true - }, - "claude-3-5-sonnet-20241022": { - "supports_computer_use": true, - "max_tokens": 8192, - "max_input_tokens": 200000, - "max_output_tokens": 8192, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "cache_creation_input_token_cost": 3.75e-06, - "cache_read_input_token_cost": 3e-07, - "search_context_cost_per_query": { - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01, - "search_context_size_high": 0.01 - }, - "litellm_provider": "anthropic", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 159, - "supports_assistant_prefill": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "deprecation_date": "2025-10-01", - "supports_tool_choice": true, - "supports_web_search": true - }, - "text-bison": { - "max_tokens": 2048, - "max_input_tokens": 8192, - "max_output_tokens": 2048, - "input_cost_per_character": 2.5e-07, - "output_cost_per_character": 5e-07, - "litellm_provider": "vertex_ai-text-models", - "mode": "completion", - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" - }, - "text-bison@001": { - "max_tokens": 1024, - "max_input_tokens": 8192, - "max_output_tokens": 1024, - "input_cost_per_character": 2.5e-07, - "output_cost_per_character": 5e-07, - "litellm_provider": "vertex_ai-text-models", - "mode": "completion", - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" - }, - "text-bison@002": { - "max_tokens": 1024, - "max_input_tokens": 8192, - "max_output_tokens": 1024, - "input_cost_per_character": 2.5e-07, - "output_cost_per_character": 5e-07, - "litellm_provider": "vertex_ai-text-models", - "mode": "completion", - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" - }, - "text-bison32k": { - "max_tokens": 1024, - "max_input_tokens": 8192, - "max_output_tokens": 1024, - "input_cost_per_token": 1.25e-07, - "output_cost_per_token": 1.25e-07, - "input_cost_per_character": 2.5e-07, - "output_cost_per_character": 5e-07, - "litellm_provider": "vertex_ai-text-models", - "mode": "completion", - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" - }, - "text-bison32k@002": { - "max_tokens": 1024, - "max_input_tokens": 8192, - "max_output_tokens": 1024, - "input_cost_per_token": 1.25e-07, - "output_cost_per_token": 1.25e-07, - "input_cost_per_character": 2.5e-07, - "output_cost_per_character": 5e-07, - "litellm_provider": "vertex_ai-text-models", - "mode": "completion", - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" - }, - "text-unicorn": { - "max_tokens": 1024, - "max_input_tokens": 8192, - "max_output_tokens": 1024, - "input_cost_per_token": 1e-05, - "output_cost_per_token": 2.8e-05, - "litellm_provider": "vertex_ai-text-models", - "mode": "completion", - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" - }, - "text-unicorn@001": { - "max_tokens": 1024, - "max_input_tokens": 8192, - "max_output_tokens": 1024, - "input_cost_per_token": 1e-05, - "output_cost_per_token": 2.8e-05, - "litellm_provider": "vertex_ai-text-models", - "mode": "completion", - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" - }, "chat-bison": { - "max_tokens": 4096, + "input_cost_per_character": 2.5e-07, + "input_cost_per_token": 1.25e-07, + "litellm_provider": "vertex_ai-chat-models", "max_input_tokens": 8192, "max_output_tokens": 4096, - "input_cost_per_token": 1.25e-07, - "output_cost_per_token": 1.25e-07, - "input_cost_per_character": 2.5e-07, - "output_cost_per_character": 5e-07, - "litellm_provider": "vertex_ai-chat-models", - "mode": "chat", - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", - "supports_tool_choice": true - }, - "chat-bison@001": { "max_tokens": 4096, - "max_input_tokens": 8192, - "max_output_tokens": 4096, - "input_cost_per_token": 1.25e-07, - "output_cost_per_token": 1.25e-07, - "input_cost_per_character": 2.5e-07, - "output_cost_per_character": 5e-07, - "litellm_provider": "vertex_ai-chat-models", "mode": "chat", - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", - "supports_tool_choice": true - }, - "chat-bison@002": { - "max_tokens": 4096, - "max_input_tokens": 8192, - "max_output_tokens": 4096, - "input_cost_per_token": 1.25e-07, - "output_cost_per_token": 1.25e-07, - "input_cost_per_character": 2.5e-07, "output_cost_per_character": 5e-07, - "litellm_provider": "vertex_ai-chat-models", - "mode": "chat", + "output_cost_per_token": 1.25e-07, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", - "deprecation_date": "2025-04-09", "supports_tool_choice": true }, "chat-bison-32k": { - "max_tokens": 8192, + "input_cost_per_character": 2.5e-07, + "input_cost_per_token": 1.25e-07, + "litellm_provider": "vertex_ai-chat-models", "max_input_tokens": 32000, "max_output_tokens": 8192, - "input_cost_per_token": 1.25e-07, - "output_cost_per_token": 1.25e-07, - "input_cost_per_character": 2.5e-07, - "output_cost_per_character": 5e-07, - "litellm_provider": "vertex_ai-chat-models", + "max_tokens": 8192, "mode": "chat", + "output_cost_per_character": 5e-07, + "output_cost_per_token": 1.25e-07, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", "supports_tool_choice": true }, "chat-bison-32k@002": { - "max_tokens": 8192, + "input_cost_per_character": 2.5e-07, + "input_cost_per_token": 1.25e-07, + "litellm_provider": "vertex_ai-chat-models", "max_input_tokens": 32000, "max_output_tokens": 8192, - "input_cost_per_token": 1.25e-07, - "output_cost_per_token": 1.25e-07, - "input_cost_per_character": 2.5e-07, - "output_cost_per_character": 5e-07, - "litellm_provider": "vertex_ai-chat-models", + "max_tokens": 8192, "mode": "chat", + "output_cost_per_character": 5e-07, + "output_cost_per_token": 1.25e-07, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", "supports_tool_choice": true }, + "chat-bison@001": { + "input_cost_per_character": 2.5e-07, + "input_cost_per_token": 1.25e-07, + "litellm_provider": "vertex_ai-chat-models", + "max_input_tokens": 8192, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_character": 5e-07, + "output_cost_per_token": 1.25e-07, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "supports_tool_choice": true + }, + "chat-bison@002": { + "deprecation_date": "2025-04-09", + "input_cost_per_character": 2.5e-07, + "input_cost_per_token": 1.25e-07, + "litellm_provider": "vertex_ai-chat-models", + "max_input_tokens": 8192, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_character": 5e-07, + "output_cost_per_token": 1.25e-07, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "supports_tool_choice": true + }, + "chatdolphin": { + "input_cost_per_token": 5e-07, + "litellm_provider": "nlp_cloud", + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 5e-07 + }, + "chatgpt-4o-latest": { + "input_cost_per_token": 5e-06, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "claude-3-5-haiku-20241022": { + "cache_creation_input_token_cost": 1e-06, + "cache_creation_input_token_cost_above_1hr": 1.6e-06, + "cache_read_input_token_cost": 8e-08, + "deprecation_date": "2025-10-01", + "input_cost_per_token": 8e-07, + "litellm_provider": "anthropic", + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 4e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "tool_use_system_prompt_tokens": 264 + }, + "claude-3-5-haiku-latest": { + "cache_creation_input_token_cost": 1.25e-06, + "cache_read_input_token_cost": 1e-07, + "deprecation_date": "2025-10-01", + "input_cost_per_token": 1e-06, + "litellm_provider": "anthropic", + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 5e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "tool_use_system_prompt_tokens": 264 + }, + "claude-3-5-sonnet-20240620": { + "cache_creation_input_token_cost": 3.75e-06, + "cache_creation_input_token_cost_above_1hr": 1.6e-06, + "cache_read_input_token_cost": 3e-07, + "deprecation_date": "2025-06-01", + "input_cost_per_token": 3e-06, + "litellm_provider": "anthropic", + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159 + }, + "claude-3-5-sonnet-20241022": { + "cache_creation_input_token_cost": 3.75e-06, + "cache_creation_input_token_cost_above_1hr": 1.6e-06, + "cache_read_input_token_cost": 3e-07, + "deprecation_date": "2025-10-01", + "input_cost_per_token": 3e-06, + "litellm_provider": "anthropic", + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "tool_use_system_prompt_tokens": 159 + }, + "claude-3-5-sonnet-latest": { + "cache_creation_input_token_cost": 3.75e-06, + "cache_creation_input_token_cost_above_1hr": 1.6e-06, + "cache_read_input_token_cost": 3e-07, + "deprecation_date": "2025-06-01", + "input_cost_per_token": 3e-06, + "litellm_provider": "anthropic", + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "tool_use_system_prompt_tokens": 159 + }, + "claude-3-7-sonnet-20250219": { + "cache_creation_input_token_cost": 3.75e-06, + "cache_read_input_token_cost": 3e-07, + "deprecation_date": "2026-02-01", + "input_cost_per_token": 3e-06, + "litellm_provider": "anthropic", + "max_input_tokens": 200000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "tool_use_system_prompt_tokens": 159 + }, + "claude-3-7-sonnet-latest": { + "cache_creation_input_token_cost": 3.75e-06, + "cache_read_input_token_cost": 3e-07, + "deprecation_date": "2025-06-01", + "input_cost_per_token": 3e-06, + "litellm_provider": "anthropic", + "max_input_tokens": 200000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159 + }, + "claude-3-haiku-20240307": { + "cache_creation_input_token_cost": 3e-07, + "cache_read_input_token_cost": 3e-08, + "deprecation_date": "2025-03-01", + "input_cost_per_token": 2.5e-07, + "litellm_provider": "anthropic", + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.25e-06, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 264 + }, + "claude-3-opus-20240229": { + "cache_creation_input_token_cost": 1.875e-05, + "cache_read_input_token_cost": 1.5e-06, + "deprecation_date": "2025-03-01", + "input_cost_per_token": 1.5e-05, + "litellm_provider": "anthropic", + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 7.5e-05, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 395 + }, + "claude-3-opus-latest": { + "cache_creation_input_token_cost": 1.875e-05, + "cache_read_input_token_cost": 1.5e-06, + "deprecation_date": "2025-03-01", + "input_cost_per_token": 1.5e-05, + "litellm_provider": "anthropic", + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 7.5e-05, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 395 + }, + "claude-4-opus-20250514": { + "cache_creation_input_token_cost": 1.875e-05, + "cache_read_input_token_cost": 1.5e-06, + "input_cost_per_token": 1.5e-05, + "litellm_provider": "anthropic", + "max_input_tokens": 200000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 7.5e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159 + }, + "claude-4-sonnet-20250514": { + "cache_creation_input_token_cost": 3.75e-06, + "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, + "cache_read_input_token_cost": 3e-07, + "cache_read_input_token_cost_above_200k_tokens": 6e-07, + "input_cost_per_token": 3e-06, + "input_cost_per_token_above_200k_tokens": 6e-06, + "litellm_provider": "anthropic", + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "max_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "output_cost_per_token_above_200k_tokens": 2.25e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159 + }, + "claude-opus-4-1": { + "cache_creation_input_token_cost": 1.875e-05, + "cache_read_input_token_cost": 1.5e-06, + "input_cost_per_token": 1.5e-05, + "litellm_provider": "anthropic", + "max_input_tokens": 200000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 7.5e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159 + }, + "claude-opus-4-1-20250805": { + "cache_creation_input_token_cost": 1.875e-05, + "cache_read_input_token_cost": 1.5e-06, + "input_cost_per_token": 1.5e-05, + "litellm_provider": "anthropic", + "max_input_tokens": 200000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 7.5e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159 + }, + "claude-opus-4-20250514": { + "cache_creation_input_token_cost": 1.875e-05, + "cache_read_input_token_cost": 1.5e-06, + "input_cost_per_token": 1.5e-05, + "litellm_provider": "anthropic", + "max_input_tokens": 200000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 7.5e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159 + }, + "claude-sonnet-4-20250514": { + "cache_creation_input_token_cost": 3.75e-06, + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 3e-06, + "litellm_provider": "anthropic", + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159 + }, + "cloudflare/@cf/meta/llama-2-7b-chat-fp16": { + "input_cost_per_token": 1.923e-06, + "litellm_provider": "cloudflare", + "max_input_tokens": 3072, + "max_output_tokens": 3072, + "max_tokens": 3072, + "mode": "chat", + "output_cost_per_token": 1.923e-06 + }, + "cloudflare/@cf/meta/llama-2-7b-chat-int8": { + "input_cost_per_token": 1.923e-06, + "litellm_provider": "cloudflare", + "max_input_tokens": 2048, + "max_output_tokens": 2048, + "max_tokens": 2048, + "mode": "chat", + "output_cost_per_token": 1.923e-06 + }, + "cloudflare/@cf/mistral/mistral-7b-instruct-v0.1": { + "input_cost_per_token": 1.923e-06, + "litellm_provider": "cloudflare", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.923e-06 + }, + "cloudflare/@hf/thebloke/codellama-7b-instruct-awq": { + "input_cost_per_token": 1.923e-06, + "litellm_provider": "cloudflare", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.923e-06 + }, "code-bison": { - "max_tokens": 1024, + "input_cost_per_character": 2.5e-07, + "input_cost_per_token": 1.25e-07, + "litellm_provider": "vertex_ai-code-text-models", "max_input_tokens": 6144, "max_output_tokens": 1024, - "input_cost_per_token": 1.25e-07, - "output_cost_per_token": 1.25e-07, - "input_cost_per_character": 2.5e-07, - "output_cost_per_character": 5e-07, - "litellm_provider": "vertex_ai-code-text-models", + "max_tokens": 1024, "mode": "chat", + "output_cost_per_character": 5e-07, + "output_cost_per_token": 1.25e-07, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", "supports_tool_choice": true }, - "code-bison@001": { - "max_tokens": 1024, + "code-bison-32k@002": { + "input_cost_per_character": 2.5e-07, + "input_cost_per_token": 1.25e-07, + "litellm_provider": "vertex_ai-code-text-models", "max_input_tokens": 6144, "max_output_tokens": 1024, - "input_cost_per_token": 1.25e-07, - "output_cost_per_token": 1.25e-07, - "input_cost_per_character": 2.5e-07, - "output_cost_per_character": 5e-07, - "litellm_provider": "vertex_ai-code-text-models", - "mode": "completion", - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" - }, - "code-bison@002": { "max_tokens": 1024, - "max_input_tokens": 6144, - "max_output_tokens": 1024, - "input_cost_per_token": 1.25e-07, - "output_cost_per_token": 1.25e-07, - "input_cost_per_character": 2.5e-07, - "output_cost_per_character": 5e-07, - "litellm_provider": "vertex_ai-code-text-models", "mode": "completion", + "output_cost_per_character": 5e-07, + "output_cost_per_token": 1.25e-07, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" }, "code-bison32k": { - "max_tokens": 1024, + "input_cost_per_character": 2.5e-07, + "input_cost_per_token": 1.25e-07, + "litellm_provider": "vertex_ai-code-text-models", "max_input_tokens": 6144, "max_output_tokens": 1024, - "input_cost_per_token": 1.25e-07, - "output_cost_per_token": 1.25e-07, - "input_cost_per_character": 2.5e-07, - "output_cost_per_character": 5e-07, - "litellm_provider": "vertex_ai-code-text-models", + "max_tokens": 1024, "mode": "completion", + "output_cost_per_character": 5e-07, + "output_cost_per_token": 1.25e-07, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" }, - "code-bison-32k@002": { - "max_tokens": 1024, + "code-bison@001": { + "input_cost_per_character": 2.5e-07, + "input_cost_per_token": 1.25e-07, + "litellm_provider": "vertex_ai-code-text-models", "max_input_tokens": 6144, "max_output_tokens": 1024, - "input_cost_per_token": 1.25e-07, - "output_cost_per_token": 1.25e-07, - "input_cost_per_character": 2.5e-07, + "max_tokens": 1024, + "mode": "completion", "output_cost_per_character": 5e-07, - "litellm_provider": "vertex_ai-code-text-models", - "mode": "completion", + "output_cost_per_token": 1.25e-07, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" }, - "code-gecko@001": { - "max_tokens": 64, - "max_input_tokens": 2048, - "max_output_tokens": 64, + "code-bison@002": { + "input_cost_per_character": 2.5e-07, "input_cost_per_token": 1.25e-07, - "output_cost_per_token": 1.25e-07, "litellm_provider": "vertex_ai-code-text-models", + "max_input_tokens": 6144, + "max_output_tokens": 1024, + "max_tokens": 1024, "mode": "completion", - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" - }, - "code-gecko@002": { - "max_tokens": 64, - "max_input_tokens": 2048, - "max_output_tokens": 64, - "input_cost_per_token": 1.25e-07, + "output_cost_per_character": 5e-07, "output_cost_per_token": 1.25e-07, - "litellm_provider": "vertex_ai-code-text-models", - "mode": "completion", "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" }, "code-gecko": { - "max_tokens": 64, + "input_cost_per_token": 1.25e-07, + "litellm_provider": "vertex_ai-code-text-models", "max_input_tokens": 2048, "max_output_tokens": 64, - "input_cost_per_token": 1.25e-07, - "output_cost_per_token": 1.25e-07, - "litellm_provider": "vertex_ai-code-text-models", + "max_tokens": 64, "mode": "completion", + "output_cost_per_token": 1.25e-07, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" }, "code-gecko-latest": { - "max_tokens": 64, + "input_cost_per_token": 1.25e-07, + "litellm_provider": "vertex_ai-code-text-models", "max_input_tokens": 2048, "max_output_tokens": 64, - "input_cost_per_token": 1.25e-07, - "output_cost_per_token": 1.25e-07, - "litellm_provider": "vertex_ai-code-text-models", + "max_tokens": 64, "mode": "completion", + "output_cost_per_token": 1.25e-07, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" }, - "codechat-bison@latest": { - "max_tokens": 1024, - "max_input_tokens": 6144, - "max_output_tokens": 1024, + "code-gecko@001": { "input_cost_per_token": 1.25e-07, + "litellm_provider": "vertex_ai-code-text-models", + "max_input_tokens": 2048, + "max_output_tokens": 64, + "max_tokens": 64, + "mode": "completion", "output_cost_per_token": 1.25e-07, - "input_cost_per_character": 2.5e-07, - "output_cost_per_character": 5e-07, - "litellm_provider": "vertex_ai-code-chat-models", - "mode": "chat", - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", - "supports_tool_choice": true + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" + }, + "code-gecko@002": { + "input_cost_per_token": 1.25e-07, + "litellm_provider": "vertex_ai-code-text-models", + "max_input_tokens": 2048, + "max_output_tokens": 64, + "max_tokens": 64, + "mode": "completion", + "output_cost_per_token": 1.25e-07, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" }, "codechat-bison": { - "max_tokens": 1024, + "input_cost_per_character": 2.5e-07, + "input_cost_per_token": 1.25e-07, + "litellm_provider": "vertex_ai-code-chat-models", "max_input_tokens": 6144, "max_output_tokens": 1024, - "input_cost_per_token": 1.25e-07, - "output_cost_per_token": 1.25e-07, - "input_cost_per_character": 2.5e-07, - "output_cost_per_character": 5e-07, - "litellm_provider": "vertex_ai-code-chat-models", - "mode": "chat", - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", - "supports_tool_choice": true - }, - "codechat-bison@001": { "max_tokens": 1024, - "max_input_tokens": 6144, - "max_output_tokens": 1024, - "input_cost_per_token": 1.25e-07, - "output_cost_per_token": 1.25e-07, - "input_cost_per_character": 2.5e-07, - "output_cost_per_character": 5e-07, - "litellm_provider": "vertex_ai-code-chat-models", "mode": "chat", - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", - "supports_tool_choice": true - }, - "codechat-bison@002": { - "max_tokens": 1024, - "max_input_tokens": 6144, - "max_output_tokens": 1024, - "input_cost_per_token": 1.25e-07, - "output_cost_per_token": 1.25e-07, - "input_cost_per_character": 2.5e-07, "output_cost_per_character": 5e-07, - "litellm_provider": "vertex_ai-code-chat-models", - "mode": "chat", + "output_cost_per_token": 1.25e-07, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", "supports_tool_choice": true }, "codechat-bison-32k": { - "max_tokens": 8192, + "input_cost_per_character": 2.5e-07, + "input_cost_per_token": 1.25e-07, + "litellm_provider": "vertex_ai-code-chat-models", "max_input_tokens": 32000, "max_output_tokens": 8192, - "input_cost_per_token": 1.25e-07, - "output_cost_per_token": 1.25e-07, - "input_cost_per_character": 2.5e-07, - "output_cost_per_character": 5e-07, - "litellm_provider": "vertex_ai-code-chat-models", + "max_tokens": 8192, "mode": "chat", + "output_cost_per_character": 5e-07, + "output_cost_per_token": 1.25e-07, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", "supports_tool_choice": true }, "codechat-bison-32k@002": { - "max_tokens": 8192, + "input_cost_per_character": 2.5e-07, + "input_cost_per_token": 1.25e-07, + "litellm_provider": "vertex_ai-code-chat-models", "max_input_tokens": 32000, "max_output_tokens": 8192, - "input_cost_per_token": 1.25e-07, - "output_cost_per_token": 1.25e-07, - "input_cost_per_character": 2.5e-07, - "output_cost_per_character": 5e-07, - "litellm_provider": "vertex_ai-code-chat-models", + "max_tokens": 8192, "mode": "chat", + "output_cost_per_character": 5e-07, + "output_cost_per_token": 1.25e-07, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", "supports_tool_choice": true }, - "meta_llama/Llama-4-Scout-17B-16E-Instruct-FP8": { - "max_tokens": 128000, - "max_input_tokens": 10000000, - "max_output_tokens": 4028, - "litellm_provider": "meta_llama", + "codechat-bison@001": { + "input_cost_per_character": 2.5e-07, + "input_cost_per_token": 1.25e-07, + "litellm_provider": "vertex_ai-code-chat-models", + "max_input_tokens": 6144, + "max_output_tokens": 1024, + "max_tokens": 1024, "mode": "chat", - "supports_function_calling": true, - "source": "https://llama.developer.meta.com/docs/models", - "supports_tool_choice": true, - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ] - }, - "meta_llama/Llama-4-Maverick-17B-128E-Instruct-FP8": { - "max_tokens": 128000, - "max_input_tokens": 1000000, - "max_output_tokens": 4028, - "litellm_provider": "meta_llama", - "mode": "chat", - "supports_function_calling": true, - "source": "https://llama.developer.meta.com/docs/models", - "supports_tool_choice": true, - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ] - }, - "meta_llama/Llama-3.3-70B-Instruct": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 4028, - "litellm_provider": "meta_llama", - "mode": "chat", - "supports_function_calling": true, - "source": "https://llama.developer.meta.com/docs/models", - "supports_tool_choice": true, - "supported_modalities": [ - "text" - ], - "supported_output_modalities": [ - "text" - ] - }, - "meta_llama/Llama-3.3-8B-Instruct": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 4028, - "litellm_provider": "meta_llama", - "mode": "chat", - "supports_function_calling": true, - "source": "https://llama.developer.meta.com/docs/models", - "supports_tool_choice": true, - "supported_modalities": [ - "text" - ], - "supported_output_modalities": [ - "text" - ] - }, - "gemini-pro": { - "max_tokens": 8192, - "max_input_tokens": 32760, - "max_output_tokens": 8192, - "input_cost_per_image": 0.0025, - "input_cost_per_video_per_second": 0.002, - "input_cost_per_token": 5e-07, - "input_cost_per_character": 1.25e-07, - "output_cost_per_token": 1.5e-06, - "output_cost_per_character": 3.75e-07, - "litellm_provider": "vertex_ai-language-models", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "output_cost_per_character": 5e-07, + "output_cost_per_token": 1.25e-07, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", "supports_tool_choice": true }, - "gemini-1.0-pro": { - "max_tokens": 8192, - "max_input_tokens": 32760, - "max_output_tokens": 8192, - "input_cost_per_image": 0.0025, - "input_cost_per_video_per_second": 0.002, - "input_cost_per_token": 5e-07, - "input_cost_per_character": 1.25e-07, - "output_cost_per_token": 1.5e-06, - "output_cost_per_character": 3.75e-07, - "litellm_provider": "vertex_ai-language-models", + "codechat-bison@002": { + "input_cost_per_character": 2.5e-07, + "input_cost_per_token": 1.25e-07, + "litellm_provider": "vertex_ai-code-chat-models", + "max_input_tokens": 6144, + "max_output_tokens": 1024, + "max_tokens": 1024, "mode": "chat", + "output_cost_per_character": 5e-07, + "output_cost_per_token": 1.25e-07, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "supports_tool_choice": true + }, + "codechat-bison@latest": { + "input_cost_per_character": 2.5e-07, + "input_cost_per_token": 1.25e-07, + "litellm_provider": "vertex_ai-code-chat-models", + "max_input_tokens": 6144, + "max_output_tokens": 1024, + "max_tokens": 1024, + "mode": "chat", + "output_cost_per_character": 5e-07, + "output_cost_per_token": 1.25e-07, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "supports_tool_choice": true + }, + "codestral/codestral-2405": { + "input_cost_per_token": 0.0, + "litellm_provider": "codestral", + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 0.0, + "source": "https://docs.mistral.ai/capabilities/code_generation/", + "supports_assistant_prefill": true, + "supports_tool_choice": true + }, + "codestral/codestral-latest": { + "input_cost_per_token": 0.0, + "litellm_provider": "codestral", + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 0.0, + "source": "https://docs.mistral.ai/capabilities/code_generation/", + "supports_assistant_prefill": true, + "supports_tool_choice": true + }, + "codex-mini-latest": { + "cache_read_input_token_cost": 3.75e-07, + "input_cost_per_token": 1.5e-06, + "litellm_provider": "openai", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "responses", + "output_cost_per_token": 6e-06, + "supported_endpoints": [ + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], "supports_function_calling": true, "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "cohere.command-light-text-v14": { + "input_cost_per_token": 3e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 6e-07, + "supports_tool_choice": true + }, + "cohere.command-r-plus-v1:0": { + "input_cost_per_token": 3e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "supports_tool_choice": true + }, + "cohere.command-r-v1:0": { + "input_cost_per_token": 5e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.5e-06, + "supports_tool_choice": true + }, + "cohere.command-text-v14": { + "input_cost_per_token": 1.5e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 2e-06, + "supports_tool_choice": true + }, + "cohere.embed-english-v3": { + "input_cost_per_token": 1e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 512, + "max_tokens": 512, + "mode": "embedding", + "output_cost_per_token": 0.0, + "supports_embedding_image_input": true + }, + "cohere.embed-multilingual-v3": { + "input_cost_per_token": 1e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 512, + "max_tokens": 512, + "mode": "embedding", + "output_cost_per_token": 0.0, + "supports_embedding_image_input": true + }, + "cohere.rerank-v3-5:0": { + "input_cost_per_query": 0.002, + "input_cost_per_token": 0.0, + "litellm_provider": "bedrock", + "max_document_chunks_per_query": 100, + "max_input_tokens": 32000, + "max_output_tokens": 32000, + "max_query_tokens": 32000, + "max_tokens": 32000, + "max_tokens_per_document_chunk": 512, + "mode": "rerank", + "output_cost_per_token": 0.0 + }, + "command": { + "input_cost_per_token": 1e-06, + "litellm_provider": "cohere", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "completion", + "output_cost_per_token": 2e-06 + }, + "command-a-03-2025": { + "input_cost_per_token": 2.5e-06, + "litellm_provider": "cohere_chat", + "max_input_tokens": 256000, + "max_output_tokens": 8000, + "max_tokens": 8000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "supports_function_calling": true, + "supports_tool_choice": true + }, + "command-light": { + "input_cost_per_token": 3e-07, + "litellm_provider": "cohere_chat", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 6e-07, + "supports_tool_choice": true + }, + "command-nightly": { + "input_cost_per_token": 1e-06, + "litellm_provider": "cohere", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "completion", + "output_cost_per_token": 2e-06 + }, + "command-r": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "cohere_chat", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 6e-07, + "supports_function_calling": true, + "supports_tool_choice": true + }, + "command-r-08-2024": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "cohere_chat", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 6e-07, + "supports_function_calling": true, + "supports_tool_choice": true + }, + "command-r-plus": { + "input_cost_per_token": 2.5e-06, + "litellm_provider": "cohere_chat", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1e-05, + "supports_function_calling": true, + "supports_tool_choice": true + }, + "command-r-plus-08-2024": { + "input_cost_per_token": 2.5e-06, + "litellm_provider": "cohere_chat", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1e-05, + "supports_function_calling": true, + "supports_tool_choice": true + }, + "command-r7b-12-2024": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "cohere_chat", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 3.75e-08, + "source": "https://docs.cohere.com/v2/docs/command-r7b", + "supports_function_calling": true, + "supports_tool_choice": true + }, + "computer-use-preview": { + "input_cost_per_token": 3e-06, + "litellm_provider": "azure", + "max_input_tokens": 8192, + "max_output_tokens": 1024, + "max_tokens": 1024, + "mode": "chat", + "output_cost_per_token": 1.2e-05, + "supported_endpoints": [ + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "dashscope/qwen-coder": { + "input_cost_per_token": 3e-07, + "litellm_provider": "dashscope", + "max_input_tokens": 1000000, + "max_output_tokens": 16384, + "max_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 1.5e-06, + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "dashscope/qwen-flash": { + "litellm_provider": "dashscope", + "max_input_tokens": 997952, + "max_output_tokens": 32768, + "max_tokens": 1000000, + "mode": "chat", + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "tiered_pricing": [ + { + "input_cost_per_token": 5e-08, + "output_cost_per_token": 4e-07, + "range": [ + 0, + 256000.0 + ] + }, + { + "input_cost_per_token": 2.5e-07, + "output_cost_per_token": 2e-06, + "range": [ + 256000.0, + 1000000.0 + ] + } + ] + }, + "dashscope/qwen-flash-2025-07-28": { + "litellm_provider": "dashscope", + "max_input_tokens": 997952, + "max_output_tokens": 32768, + "max_tokens": 1000000, + "mode": "chat", + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "tiered_pricing": [ + { + "input_cost_per_token": 5e-08, + "output_cost_per_token": 4e-07, + "range": [ + 0, + 256000.0 + ] + }, + { + "input_cost_per_token": 2.5e-07, + "output_cost_per_token": 2e-06, + "range": [ + 256000.0, + 1000000.0 + ] + } + ] + }, + "dashscope/qwen-max": { + "input_cost_per_token": 1.6e-06, + "litellm_provider": "dashscope", + "max_input_tokens": 30720, + "max_output_tokens": 8192, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 6.4e-06, + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "dashscope/qwen-plus": { + "input_cost_per_token": 4e-07, + "litellm_provider": "dashscope", + "max_input_tokens": 129024, + "max_output_tokens": 16384, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "dashscope/qwen-plus-2025-01-25": { + "input_cost_per_token": 4e-07, + "litellm_provider": "dashscope", + "max_input_tokens": 129024, + "max_output_tokens": 8192, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "dashscope/qwen-plus-2025-04-28": { + "input_cost_per_token": 4e-07, + "litellm_provider": "dashscope", + "max_input_tokens": 129024, + "max_output_tokens": 16384, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_reasoning_token": 4e-06, + "output_cost_per_token": 1.2e-06, + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "dashscope/qwen-plus-2025-07-14": { + "input_cost_per_token": 4e-07, + "litellm_provider": "dashscope", + "max_input_tokens": 129024, + "max_output_tokens": 16384, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_reasoning_token": 4e-06, + "output_cost_per_token": 1.2e-06, + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "dashscope/qwen-plus-2025-07-28": { + "litellm_provider": "dashscope", + "max_input_tokens": 997952, + "max_output_tokens": 32768, + "max_tokens": 1000000, + "mode": "chat", + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "tiered_pricing": [ + { + "input_cost_per_token": 4e-07, + "output_cost_per_reasoning_token": 4e-06, + "output_cost_per_token": 1.2e-06, + "range": [ + 0, + 256000.0 + ] + }, + { + "input_cost_per_token": 1.2e-06, + "output_cost_per_reasoning_token": 1.2e-05, + "output_cost_per_token": 3.6e-06, + "range": [ + 256000.0, + 1000000.0 + ] + } + ] + }, + "dashscope/qwen-plus-2025-09-11": { + "litellm_provider": "dashscope", + "max_input_tokens": 997952, + "max_output_tokens": 32768, + "max_tokens": 1000000, + "mode": "chat", + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "tiered_pricing": [ + { + "input_cost_per_token": 4e-07, + "output_cost_per_reasoning_token": 4e-06, + "output_cost_per_token": 1.2e-06, + "range": [ + 0, + 256000.0 + ] + }, + { + "input_cost_per_token": 1.2e-06, + "output_cost_per_reasoning_token": 1.2e-05, + "output_cost_per_token": 3.6e-06, + "range": [ + 256000.0, + 1000000.0 + ] + } + ] + }, + "dashscope/qwen-plus-latest": { + "litellm_provider": "dashscope", + "max_input_tokens": 997952, + "max_output_tokens": 32768, + "max_tokens": 1000000, + "mode": "chat", + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "tiered_pricing": [ + { + "input_cost_per_token": 4e-07, + "output_cost_per_reasoning_token": 4e-06, + "output_cost_per_token": 1.2e-06, + "range": [ + 0, + 256000.0 + ] + }, + { + "input_cost_per_token": 1.2e-06, + "output_cost_per_reasoning_token": 1.2e-05, + "output_cost_per_token": 3.6e-06, + "range": [ + 256000.0, + 1000000.0 + ] + } + ] + }, + "dashscope/qwen-turbo": { + "input_cost_per_token": 5e-08, + "litellm_provider": "dashscope", + "max_input_tokens": 129024, + "max_output_tokens": 16384, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_reasoning_token": 5e-07, + "output_cost_per_token": 2e-07, + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "dashscope/qwen-turbo-2024-11-01": { + "input_cost_per_token": 5e-08, + "litellm_provider": "dashscope", + "max_input_tokens": 1000000, + "max_output_tokens": 8192, + "max_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 2e-07, + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "dashscope/qwen-turbo-2025-04-28": { + "input_cost_per_token": 5e-08, + "litellm_provider": "dashscope", + "max_input_tokens": 1000000, + "max_output_tokens": 16384, + "max_tokens": 1000000, + "mode": "chat", + "output_cost_per_reasoning_token": 5e-07, + "output_cost_per_token": 2e-07, + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "dashscope/qwen-turbo-latest": { + "input_cost_per_token": 5e-08, + "litellm_provider": "dashscope", + "max_input_tokens": 1000000, + "max_output_tokens": 16384, + "max_tokens": 1000000, + "mode": "chat", + "output_cost_per_reasoning_token": 5e-07, + "output_cost_per_token": 2e-07, + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "dashscope/qwen3-30b-a3b": { + "litellm_provider": "dashscope", + "max_input_tokens": 129024, + "max_output_tokens": 16384, + "max_tokens": 131072, + "mode": "chat", + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "dashscope/qwen3-coder-flash": { + "litellm_provider": "dashscope", + "max_input_tokens": 997952, + "max_output_tokens": 65536, + "max_tokens": 1000000, + "mode": "chat", + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "tiered_pricing": [ + { + "cache_read_input_token_cost": 8e-08, + "input_cost_per_token": 3e-07, + "output_cost_per_token": 1.5e-06, + "range": [ + 0, + 32000.0 + ] + }, + { + "cache_read_input_token_cost": 1.2e-07, + "input_cost_per_token": 5e-07, + "output_cost_per_token": 2.5e-06, + "range": [ + 32000.0, + 128000.0 + ] + }, + { + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 8e-07, + "output_cost_per_token": 4e-06, + "range": [ + 128000.0, + 256000.0 + ] + }, + { + "cache_read_input_token_cost": 4e-07, + "input_cost_per_token": 1.6e-06, + "output_cost_per_token": 9.6e-06, + "range": [ + 256000.0, + 1000000.0 + ] + } + ] + }, + "dashscope/qwen3-coder-flash-2025-07-28": { + "litellm_provider": "dashscope", + "max_input_tokens": 997952, + "max_output_tokens": 65536, + "max_tokens": 1000000, + "mode": "chat", + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "tiered_pricing": [ + { + "input_cost_per_token": 3e-07, + "output_cost_per_token": 1.5e-06, + "range": [ + 0, + 32000.0 + ] + }, + { + "input_cost_per_token": 5e-07, + "output_cost_per_token": 2.5e-06, + "range": [ + 32000.0, + 128000.0 + ] + }, + { + "input_cost_per_token": 8e-07, + "output_cost_per_token": 4e-06, + "range": [ + 128000.0, + 256000.0 + ] + }, + { + "input_cost_per_token": 1.6e-06, + "output_cost_per_token": 9.6e-06, + "range": [ + 256000.0, + 1000000.0 + ] + } + ] + }, + "dashscope/qwen3-coder-plus": { + "litellm_provider": "dashscope", + "max_input_tokens": 997952, + "max_output_tokens": 65536, + "max_tokens": 1000000, + "mode": "chat", + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "tiered_pricing": [ + { + "cache_read_input_token_cost": 1e-07, + "input_cost_per_token": 1e-06, + "output_cost_per_token": 5e-06, + "range": [ + 0, + 32000.0 + ] + }, + { + "cache_read_input_token_cost": 1.8e-07, + "input_cost_per_token": 1.8e-06, + "output_cost_per_token": 9e-06, + "range": [ + 32000.0, + 128000.0 + ] + }, + { + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 3e-06, + "output_cost_per_token": 1.5e-05, + "range": [ + 128000.0, + 256000.0 + ] + }, + { + "cache_read_input_token_cost": 6e-07, + "input_cost_per_token": 6e-06, + "output_cost_per_token": 6e-05, + "range": [ + 256000.0, + 1000000.0 + ] + } + ] + }, + "dashscope/qwen3-coder-plus-2025-07-22": { + "litellm_provider": "dashscope", + "max_input_tokens": 997952, + "max_output_tokens": 65536, + "max_tokens": 1000000, + "mode": "chat", + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "tiered_pricing": [ + { + "input_cost_per_token": 1e-06, + "output_cost_per_token": 5e-06, + "range": [ + 0, + 32000.0 + ] + }, + { + "input_cost_per_token": 1.8e-06, + "output_cost_per_token": 9e-06, + "range": [ + 32000.0, + 128000.0 + ] + }, + { + "input_cost_per_token": 3e-06, + "output_cost_per_token": 1.5e-05, + "range": [ + 128000.0, + 256000.0 + ] + }, + { + "input_cost_per_token": 6e-06, + "output_cost_per_token": 6e-05, + "range": [ + 256000.0, + 1000000.0 + ] + } + ] + }, + "dashscope/qwen3-max-preview": { + "litellm_provider": "dashscope", + "max_input_tokens": 258048, + "max_output_tokens": 65536, + "max_tokens": 262144, + "mode": "chat", + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "tiered_pricing": [ + { + "input_cost_per_token": 1.2e-06, + "output_cost_per_token": 6e-06, + "range": [ + 0, + 32000.0 + ] + }, + { + "input_cost_per_token": 2.4e-06, + "output_cost_per_token": 1.2e-05, + "range": [ + 32000.0, + 128000.0 + ] + }, + { + "input_cost_per_token": 3e-06, + "output_cost_per_token": 1.5e-05, + "range": [ + 128000.0, + 252000.0 + ] + } + ] + }, + "dashscope/qwq-plus": { + "input_cost_per_token": 8e-07, + "litellm_provider": "dashscope", + "max_input_tokens": 98304, + "max_output_tokens": 8192, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2.4e-06, + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "databricks/databricks-bge-large-en": { + "input_cost_per_token": 1.0003e-07, + "input_dbu_cost_per_token": 1.429e-06, + "litellm_provider": "databricks", + "max_input_tokens": 512, + "max_tokens": 512, + "metadata": { + "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." + }, + "mode": "embedding", + "output_cost_per_token": 0.0, + "output_dbu_cost_per_token": 0.0, + "output_vector_size": 1024, + "source": "https://www.databricks.com/product/pricing/foundation-model-serving" + }, + "databricks/databricks-claude-3-7-sonnet": { + "input_cost_per_token": 2.5e-06, + "input_dbu_cost_per_token": 3.571e-05, + "litellm_provider": "databricks", + "max_input_tokens": 200000, + "max_output_tokens": 128000, + "max_tokens": 200000, + "metadata": { + "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Claude 3.7 conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." + }, + "mode": "chat", + "output_cost_per_token": 1.7857e-05, + "output_db_cost_per_token": 0.000214286, + "source": "https://www.databricks.com/product/pricing/foundation-model-serving", + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "databricks/databricks-gte-large-en": { + "input_cost_per_token": 1.2999e-07, + "input_dbu_cost_per_token": 1.857e-06, + "litellm_provider": "databricks", + "max_input_tokens": 8192, + "max_tokens": 8192, + "metadata": { + "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." + }, + "mode": "embedding", + "output_cost_per_token": 0.0, + "output_dbu_cost_per_token": 0.0, + "output_vector_size": 1024, + "source": "https://www.databricks.com/product/pricing/foundation-model-serving" + }, + "databricks/databricks-llama-2-70b-chat": { + "input_cost_per_token": 5.0001e-07, + "input_dbu_cost_per_token": 7.143e-06, + "litellm_provider": "databricks", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "metadata": { + "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." + }, + "mode": "chat", + "output_cost_per_token": 1.5e-06, + "output_dbu_cost_per_token": 2.1429e-05, + "source": "https://www.databricks.com/product/pricing/foundation-model-serving", + "supports_tool_choice": true + }, + "databricks/databricks-llama-4-maverick": { + "input_cost_per_token": 5e-06, + "input_dbu_cost_per_token": 7.143e-05, + "litellm_provider": "databricks", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "metadata": { + "notes": "Databricks documentation now provides both DBU costs (_dbu_cost_per_token) and dollar costs(_cost_per_token)." + }, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "output_dbu_cost_per_token": 0.00021429, + "source": "https://www.databricks.com/product/pricing/foundation-model-serving", + "supports_tool_choice": true + }, + "databricks/databricks-meta-llama-3-1-405b-instruct": { + "input_cost_per_token": 5e-06, + "input_dbu_cost_per_token": 7.1429e-05, + "litellm_provider": "databricks", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "metadata": { + "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." + }, + "mode": "chat", + "output_cost_per_token": 1.500002e-05, + "output_db_cost_per_token": 0.000214286, + "source": "https://www.databricks.com/product/pricing/foundation-model-serving", + "supports_tool_choice": true + }, + "databricks/databricks-meta-llama-3-3-70b-instruct": { + "input_cost_per_token": 1.00002e-06, + "input_dbu_cost_per_token": 1.4286e-05, + "litellm_provider": "databricks", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "metadata": { + "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." + }, + "mode": "chat", + "output_cost_per_token": 2.99999e-06, + "output_dbu_cost_per_token": 4.2857e-05, + "source": "https://www.databricks.com/product/pricing/foundation-model-serving", + "supports_tool_choice": true + }, + "databricks/databricks-meta-llama-3-70b-instruct": { + "input_cost_per_token": 1.00002e-06, + "input_dbu_cost_per_token": 1.4286e-05, + "litellm_provider": "databricks", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "metadata": { + "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." + }, + "mode": "chat", + "output_cost_per_token": 2.99999e-06, + "output_dbu_cost_per_token": 4.2857e-05, + "source": "https://www.databricks.com/product/pricing/foundation-model-serving", + "supports_tool_choice": true + }, + "databricks/databricks-mixtral-8x7b-instruct": { + "input_cost_per_token": 5.0001e-07, + "input_dbu_cost_per_token": 7.143e-06, + "litellm_provider": "databricks", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "metadata": { + "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." + }, + "mode": "chat", + "output_cost_per_token": 9.9902e-07, + "output_dbu_cost_per_token": 1.4286e-05, + "source": "https://www.databricks.com/product/pricing/foundation-model-serving", + "supports_tool_choice": true + }, + "databricks/databricks-mpt-30b-instruct": { + "input_cost_per_token": 9.9902e-07, + "input_dbu_cost_per_token": 1.4286e-05, + "litellm_provider": "databricks", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "metadata": { + "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." + }, + "mode": "chat", + "output_cost_per_token": 9.9902e-07, + "output_dbu_cost_per_token": 1.4286e-05, + "source": "https://www.databricks.com/product/pricing/foundation-model-serving", + "supports_tool_choice": true + }, + "databricks/databricks-mpt-7b-instruct": { + "input_cost_per_token": 5.0001e-07, + "input_dbu_cost_per_token": 7.143e-06, + "litellm_provider": "databricks", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "metadata": { + "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." + }, + "mode": "chat", + "output_cost_per_token": 0.0, + "output_dbu_cost_per_token": 0.0, + "source": "https://www.databricks.com/product/pricing/foundation-model-serving", + "supports_tool_choice": true + }, + "davinci-002": { + "input_cost_per_token": 2e-06, + "litellm_provider": "text-completion-openai", + "max_input_tokens": 16384, + "max_output_tokens": 4096, + "max_tokens": 16384, + "mode": "completion", + "output_cost_per_token": 2e-06 + }, + "deepgram/base": { + "input_cost_per_second": 0.00020833, + "litellm_provider": "deepgram", + "metadata": { + "calculation": "$0.0125/60 seconds = $0.00020833 per second", + "original_pricing_per_minute": 0.0125 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "deepgram/base-conversationalai": { + "input_cost_per_second": 0.00020833, + "litellm_provider": "deepgram", + "metadata": { + "calculation": "$0.0125/60 seconds = $0.00020833 per second", + "original_pricing_per_minute": 0.0125 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "deepgram/base-finance": { + "input_cost_per_second": 0.00020833, + "litellm_provider": "deepgram", + "metadata": { + "calculation": "$0.0125/60 seconds = $0.00020833 per second", + "original_pricing_per_minute": 0.0125 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "deepgram/base-general": { + "input_cost_per_second": 0.00020833, + "litellm_provider": "deepgram", + "metadata": { + "calculation": "$0.0125/60 seconds = $0.00020833 per second", + "original_pricing_per_minute": 0.0125 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "deepgram/base-meeting": { + "input_cost_per_second": 0.00020833, + "litellm_provider": "deepgram", + "metadata": { + "calculation": "$0.0125/60 seconds = $0.00020833 per second", + "original_pricing_per_minute": 0.0125 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "deepgram/base-phonecall": { + "input_cost_per_second": 0.00020833, + "litellm_provider": "deepgram", + "metadata": { + "calculation": "$0.0125/60 seconds = $0.00020833 per second", + "original_pricing_per_minute": 0.0125 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "deepgram/base-video": { + "input_cost_per_second": 0.00020833, + "litellm_provider": "deepgram", + "metadata": { + "calculation": "$0.0125/60 seconds = $0.00020833 per second", + "original_pricing_per_minute": 0.0125 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "deepgram/base-voicemail": { + "input_cost_per_second": 0.00020833, + "litellm_provider": "deepgram", + "metadata": { + "calculation": "$0.0125/60 seconds = $0.00020833 per second", + "original_pricing_per_minute": 0.0125 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "deepgram/enhanced": { + "input_cost_per_second": 0.00024167, + "litellm_provider": "deepgram", + "metadata": { + "calculation": "$0.0145/60 seconds = $0.00024167 per second", + "original_pricing_per_minute": 0.0145 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "deepgram/enhanced-finance": { + "input_cost_per_second": 0.00024167, + "litellm_provider": "deepgram", + "metadata": { + "calculation": "$0.0145/60 seconds = $0.00024167 per second", + "original_pricing_per_minute": 0.0145 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "deepgram/enhanced-general": { + "input_cost_per_second": 0.00024167, + "litellm_provider": "deepgram", + "metadata": { + "calculation": "$0.0145/60 seconds = $0.00024167 per second", + "original_pricing_per_minute": 0.0145 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "deepgram/enhanced-meeting": { + "input_cost_per_second": 0.00024167, + "litellm_provider": "deepgram", + "metadata": { + "calculation": "$0.0145/60 seconds = $0.00024167 per second", + "original_pricing_per_minute": 0.0145 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "deepgram/enhanced-phonecall": { + "input_cost_per_second": 0.00024167, + "litellm_provider": "deepgram", + "metadata": { + "calculation": "$0.0145/60 seconds = $0.00024167 per second", + "original_pricing_per_minute": 0.0145 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "deepgram/nova": { + "input_cost_per_second": 7.167e-05, + "litellm_provider": "deepgram", + "metadata": { + "calculation": "$0.0043/60 seconds = $0.00007167 per second", + "original_pricing_per_minute": 0.0043 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "deepgram/nova-2": { + "input_cost_per_second": 7.167e-05, + "litellm_provider": "deepgram", + "metadata": { + "calculation": "$0.0043/60 seconds = $0.00007167 per second", + "original_pricing_per_minute": 0.0043 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "deepgram/nova-2-atc": { + "input_cost_per_second": 7.167e-05, + "litellm_provider": "deepgram", + "metadata": { + "calculation": "$0.0043/60 seconds = $0.00007167 per second", + "original_pricing_per_minute": 0.0043 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "deepgram/nova-2-automotive": { + "input_cost_per_second": 7.167e-05, + "litellm_provider": "deepgram", + "metadata": { + "calculation": "$0.0043/60 seconds = $0.00007167 per second", + "original_pricing_per_minute": 0.0043 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "deepgram/nova-2-conversationalai": { + "input_cost_per_second": 7.167e-05, + "litellm_provider": "deepgram", + "metadata": { + "calculation": "$0.0043/60 seconds = $0.00007167 per second", + "original_pricing_per_minute": 0.0043 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "deepgram/nova-2-drivethru": { + "input_cost_per_second": 7.167e-05, + "litellm_provider": "deepgram", + "metadata": { + "calculation": "$0.0043/60 seconds = $0.00007167 per second", + "original_pricing_per_minute": 0.0043 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "deepgram/nova-2-finance": { + "input_cost_per_second": 7.167e-05, + "litellm_provider": "deepgram", + "metadata": { + "calculation": "$0.0043/60 seconds = $0.00007167 per second", + "original_pricing_per_minute": 0.0043 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "deepgram/nova-2-general": { + "input_cost_per_second": 7.167e-05, + "litellm_provider": "deepgram", + "metadata": { + "calculation": "$0.0043/60 seconds = $0.00007167 per second", + "original_pricing_per_minute": 0.0043 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "deepgram/nova-2-meeting": { + "input_cost_per_second": 7.167e-05, + "litellm_provider": "deepgram", + "metadata": { + "calculation": "$0.0043/60 seconds = $0.00007167 per second", + "original_pricing_per_minute": 0.0043 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "deepgram/nova-2-phonecall": { + "input_cost_per_second": 7.167e-05, + "litellm_provider": "deepgram", + "metadata": { + "calculation": "$0.0043/60 seconds = $0.00007167 per second", + "original_pricing_per_minute": 0.0043 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "deepgram/nova-2-video": { + "input_cost_per_second": 7.167e-05, + "litellm_provider": "deepgram", + "metadata": { + "calculation": "$0.0043/60 seconds = $0.00007167 per second", + "original_pricing_per_minute": 0.0043 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "deepgram/nova-2-voicemail": { + "input_cost_per_second": 7.167e-05, + "litellm_provider": "deepgram", + "metadata": { + "calculation": "$0.0043/60 seconds = $0.00007167 per second", + "original_pricing_per_minute": 0.0043 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "deepgram/nova-3": { + "input_cost_per_second": 7.167e-05, + "litellm_provider": "deepgram", + "metadata": { + "calculation": "$0.0043/60 seconds = $0.00007167 per second", + "original_pricing_per_minute": 0.0043 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "deepgram/nova-3-general": { + "input_cost_per_second": 7.167e-05, + "litellm_provider": "deepgram", + "metadata": { + "calculation": "$0.0043/60 seconds = $0.00007167 per second", + "original_pricing_per_minute": 0.0043 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "deepgram/nova-3-medical": { + "input_cost_per_second": 8.667e-05, + "litellm_provider": "deepgram", + "metadata": { + "calculation": "$0.0052/60 seconds = $0.00008667 per second (multilingual)", + "original_pricing_per_minute": 0.0052 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "deepgram/nova-general": { + "input_cost_per_second": 7.167e-05, + "litellm_provider": "deepgram", + "metadata": { + "calculation": "$0.0043/60 seconds = $0.00007167 per second", + "original_pricing_per_minute": 0.0043 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "deepgram/nova-phonecall": { + "input_cost_per_second": 7.167e-05, + "litellm_provider": "deepgram", + "metadata": { + "calculation": "$0.0043/60 seconds = $0.00007167 per second", + "original_pricing_per_minute": 0.0043 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "deepgram/whisper": { + "input_cost_per_second": 0.0001, + "litellm_provider": "deepgram", + "metadata": { + "notes": "Deepgram's hosted OpenAI Whisper models - pricing may differ from native Deepgram models" + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "deepgram/whisper-base": { + "input_cost_per_second": 0.0001, + "litellm_provider": "deepgram", + "metadata": { + "notes": "Deepgram's hosted OpenAI Whisper models - pricing may differ from native Deepgram models" + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "deepgram/whisper-large": { + "input_cost_per_second": 0.0001, + "litellm_provider": "deepgram", + "metadata": { + "notes": "Deepgram's hosted OpenAI Whisper models - pricing may differ from native Deepgram models" + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "deepgram/whisper-medium": { + "input_cost_per_second": 0.0001, + "litellm_provider": "deepgram", + "metadata": { + "notes": "Deepgram's hosted OpenAI Whisper models - pricing may differ from native Deepgram models" + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "deepgram/whisper-small": { + "input_cost_per_second": 0.0001, + "litellm_provider": "deepgram", + "metadata": { + "notes": "Deepgram's hosted OpenAI Whisper models - pricing may differ from native Deepgram models" + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "deepgram/whisper-tiny": { + "input_cost_per_second": 0.0001, + "litellm_provider": "deepgram", + "metadata": { + "notes": "Deepgram's hosted OpenAI Whisper models - pricing may differ from native Deepgram models" + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "deepinfra/Gryphe/MythoMax-L2-13b": { + "input_cost_per_token": 7.2e-08, + "litellm_provider": "deepinfra", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 7.2e-08, + "supports_tool_choice": true + }, + "deepinfra/NousResearch/Hermes-3-Llama-3.1-405B": { + "input_cost_per_token": 7e-07, + "litellm_provider": "deepinfra", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 8e-07, + "supports_tool_choice": true + }, + "deepinfra/NousResearch/Hermes-3-Llama-3.1-70B": { + "input_cost_per_token": 1e-07, + "litellm_provider": "deepinfra", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2.8e-07, + "supports_tool_choice": false + }, + "deepinfra/Qwen/QwQ-32B": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "deepinfra", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4e-07, + "supports_tool_choice": true + }, + "deepinfra/Qwen/Qwen2.5-72B-Instruct": { + "input_cost_per_token": 1.2e-07, + "litellm_provider": "deepinfra", + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 3.9e-07, + "supports_tool_choice": true + }, + "deepinfra/Qwen/Qwen2.5-7B-Instruct": { + "input_cost_per_token": 4e-08, + "litellm_provider": "deepinfra", + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 1e-07, + "supports_tool_choice": false + }, + "deepinfra/Qwen/Qwen2.5-VL-32B-Instruct": { + "input_cost_per_token": 2e-07, + "litellm_provider": "deepinfra", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 6e-07, + "supports_tool_choice": true + }, + "deepinfra/Qwen/Qwen3-14B": { + "input_cost_per_token": 6e-08, + "litellm_provider": "deepinfra", + "max_input_tokens": 40960, + "max_output_tokens": 40960, + "max_tokens": 40960, + "mode": "chat", + "output_cost_per_token": 2.4e-07, + "supports_tool_choice": true + }, + "deepinfra/Qwen/Qwen3-235B-A22B": { + "input_cost_per_token": 1.3e-07, + "litellm_provider": "deepinfra", + "max_input_tokens": 40960, + "max_output_tokens": 40960, + "max_tokens": 40960, + "mode": "chat", + "output_cost_per_token": 6e-07, + "supports_tool_choice": true + }, + "deepinfra/Qwen/Qwen3-235B-A22B-Instruct-2507": { + "input_cost_per_token": 1.3e-07, + "litellm_provider": "deepinfra", + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 6e-07, + "supports_tool_choice": true + }, + "deepinfra/Qwen/Qwen3-235B-A22B-Thinking-2507": { + "input_cost_per_token": 1.3e-07, + "litellm_provider": "deepinfra", + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 6e-07, + "supports_tool_choice": true + }, + "deepinfra/Qwen/Qwen3-30B-A3B": { + "input_cost_per_token": 8e-08, + "litellm_provider": "deepinfra", + "max_input_tokens": 40960, + "max_output_tokens": 40960, + "max_tokens": 40960, + "mode": "chat", + "output_cost_per_token": 2.9e-07, + "supports_tool_choice": true + }, + "deepinfra/Qwen/Qwen3-32B": { + "input_cost_per_token": 1e-07, + "litellm_provider": "deepinfra", + "max_input_tokens": 40960, + "max_output_tokens": 40960, + "max_tokens": 40960, + "mode": "chat", + "output_cost_per_token": 3e-07, + "supports_tool_choice": true + }, + "deepinfra/Qwen/Qwen3-Coder-480B-A35B-Instruct": { + "input_cost_per_token": 4e-07, + "litellm_provider": "deepinfra", + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 1.6e-06, + "supports_tool_choice": true + }, + "deepinfra/Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo": { + "cache_read_input_token_cost": 2.4e-07, + "input_cost_per_token": 3e-07, + "litellm_provider": "deepinfra", + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "supports_tool_choice": true + }, + "deepinfra/Sao10K/L3-8B-Lunaris-v1-Turbo": { + "input_cost_per_token": 2e-08, + "litellm_provider": "deepinfra", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 5e-08, + "supports_tool_choice": false + }, + "deepinfra/Sao10K/L3.1-70B-Euryale-v2.2": { + "input_cost_per_token": 6.5e-07, + "litellm_provider": "deepinfra", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 7.5e-07, + "supports_tool_choice": false + }, + "deepinfra/Sao10K/L3.3-70B-Euryale-v2.3": { + "input_cost_per_token": 6.5e-07, + "litellm_provider": "deepinfra", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 7.5e-07, + "supports_tool_choice": false + }, + "deepinfra/allenai/olmOCR-7B-0725-FP8": { + "input_cost_per_token": 2.7e-07, + "litellm_provider": "deepinfra", + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1.5e-06, + "supports_tool_choice": false + }, + "deepinfra/anthropic/claude-3-7-sonnet-latest": { + "cache_read_input_token_cost": 3.3e-07, + "input_cost_per_token": 3.3e-06, + "litellm_provider": "deepinfra", + "max_input_tokens": 200000, + "max_output_tokens": 200000, + "max_tokens": 200000, + "mode": "chat", + "output_cost_per_token": 1.65e-05, + "supports_tool_choice": true + }, + "deepinfra/anthropic/claude-4-opus": { + "input_cost_per_token": 1.65e-05, + "litellm_provider": "deepinfra", + "max_input_tokens": 200000, + "max_output_tokens": 200000, + "max_tokens": 200000, + "mode": "chat", + "output_cost_per_token": 8.25e-05, + "supports_tool_choice": true + }, + "deepinfra/anthropic/claude-4-sonnet": { + "input_cost_per_token": 3.3e-06, + "litellm_provider": "deepinfra", + "max_input_tokens": 200000, + "max_output_tokens": 200000, + "max_tokens": 200000, + "mode": "chat", + "output_cost_per_token": 1.65e-05, + "supports_tool_choice": true + }, + "deepinfra/deepseek-ai/DeepSeek-R1": { + "input_cost_per_token": 7e-07, + "litellm_provider": "deepinfra", + "max_input_tokens": 163840, + "max_output_tokens": 163840, + "max_tokens": 163840, + "mode": "chat", + "output_cost_per_token": 2.4e-06, + "supports_tool_choice": true + }, + "deepinfra/deepseek-ai/DeepSeek-R1-0528": { + "cache_read_input_token_cost": 4e-07, + "input_cost_per_token": 5e-07, + "litellm_provider": "deepinfra", + "max_input_tokens": 163840, + "max_output_tokens": 163840, + "max_tokens": 163840, + "mode": "chat", + "output_cost_per_token": 2.15e-06, + "supports_tool_choice": true + }, + "deepinfra/deepseek-ai/DeepSeek-R1-0528-Turbo": { + "input_cost_per_token": 1e-06, + "litellm_provider": "deepinfra", + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 3e-06, + "supports_tool_choice": true + }, + "deepinfra/deepseek-ai/DeepSeek-R1-Distill-Llama-70B": { + "input_cost_per_token": 1e-07, + "litellm_provider": "deepinfra", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4e-07, + "supports_tool_choice": false + }, + "deepinfra/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B": { + "input_cost_per_token": 7.5e-08, + "litellm_provider": "deepinfra", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.5e-07, + "supports_tool_choice": true + }, + "deepinfra/deepseek-ai/DeepSeek-R1-Turbo": { + "input_cost_per_token": 1e-06, + "litellm_provider": "deepinfra", + "max_input_tokens": 40960, + "max_output_tokens": 40960, + "max_tokens": 40960, + "mode": "chat", + "output_cost_per_token": 3e-06, + "supports_tool_choice": true + }, + "deepinfra/deepseek-ai/DeepSeek-V3": { + "input_cost_per_token": 3.8e-07, + "litellm_provider": "deepinfra", + "max_input_tokens": 163840, + "max_output_tokens": 163840, + "max_tokens": 163840, + "mode": "chat", + "output_cost_per_token": 8.9e-07, + "supports_tool_choice": true + }, + "deepinfra/deepseek-ai/DeepSeek-V3-0324": { + "cache_read_input_token_cost": 2.24e-07, + "input_cost_per_token": 2.8e-07, + "litellm_provider": "deepinfra", + "max_input_tokens": 163840, + "max_output_tokens": 163840, + "max_tokens": 163840, + "mode": "chat", + "output_cost_per_token": 8.8e-07, + "supports_tool_choice": true + }, + "deepinfra/deepseek-ai/DeepSeek-V3.1": { + "cache_read_input_token_cost": 2.16e-07, + "input_cost_per_token": 2.7e-07, + "litellm_provider": "deepinfra", + "max_input_tokens": 163840, + "max_output_tokens": 163840, + "max_tokens": 163840, + "mode": "chat", + "output_cost_per_token": 1e-06, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "deepinfra/google/gemini-2.0-flash-001": { + "input_cost_per_token": 1e-07, + "litellm_provider": "deepinfra", + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "max_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 4e-07, + "supports_tool_choice": true + }, + "deepinfra/google/gemini-2.5-flash": { + "input_cost_per_token": 2.1e-07, + "litellm_provider": "deepinfra", + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "max_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 1.75e-06, + "supports_tool_choice": true + }, + "deepinfra/google/gemini-2.5-pro": { + "input_cost_per_token": 8.75e-07, + "litellm_provider": "deepinfra", + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "max_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 7e-06, + "supports_tool_choice": true + }, + "deepinfra/google/gemma-3-12b-it": { + "input_cost_per_token": 5e-08, + "litellm_provider": "deepinfra", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1e-07, + "supports_tool_choice": true + }, + "deepinfra/google/gemma-3-27b-it": { + "input_cost_per_token": 9e-08, + "litellm_provider": "deepinfra", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.7e-07, + "supports_tool_choice": true + }, + "deepinfra/google/gemma-3-4b-it": { + "input_cost_per_token": 4e-08, + "litellm_provider": "deepinfra", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 8e-08, + "supports_tool_choice": true + }, + "deepinfra/meta-llama/Llama-3.2-11B-Vision-Instruct": { + "input_cost_per_token": 4.9e-08, + "litellm_provider": "deepinfra", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4.9e-08, + "supports_tool_choice": false + }, + "deepinfra/meta-llama/Llama-3.2-3B-Instruct": { + "input_cost_per_token": 1.2e-08, + "litellm_provider": "deepinfra", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2.4e-08, + "supports_tool_choice": true + }, + "deepinfra/meta-llama/Llama-3.3-70B-Instruct": { + "input_cost_per_token": 2.3e-07, + "litellm_provider": "deepinfra", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4e-07, + "supports_tool_choice": true + }, + "deepinfra/meta-llama/Llama-3.3-70B-Instruct-Turbo": { + "input_cost_per_token": 3.8e-08, + "litellm_provider": "deepinfra", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.2e-07, + "supports_tool_choice": true + }, + "deepinfra/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "deepinfra", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 6e-07, + "supports_tool_choice": true + }, + "deepinfra/meta-llama/Llama-4-Scout-17B-16E-Instruct": { + "input_cost_per_token": 8e-08, + "litellm_provider": "deepinfra", + "max_input_tokens": 327680, + "max_output_tokens": 327680, + "max_tokens": 327680, + "mode": "chat", + "output_cost_per_token": 3e-07, + "supports_tool_choice": true + }, + "deepinfra/meta-llama/Llama-Guard-3-8B": { + "input_cost_per_token": 5.5e-08, + "litellm_provider": "deepinfra", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 5.5e-08, + "supports_tool_choice": false + }, + "deepinfra/meta-llama/Llama-Guard-4-12B": { + "input_cost_per_token": 1.8e-07, + "litellm_provider": "deepinfra", + "max_input_tokens": 163840, + "max_output_tokens": 163840, + "max_tokens": 163840, + "mode": "chat", + "output_cost_per_token": 1.8e-07, + "supports_tool_choice": false + }, + "deepinfra/meta-llama/Meta-Llama-3-8B-Instruct": { + "input_cost_per_token": 3e-08, + "litellm_provider": "deepinfra", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 6e-08, + "supports_tool_choice": true + }, + "deepinfra/meta-llama/Meta-Llama-3.1-70B-Instruct": { + "input_cost_per_token": 2.3e-07, + "litellm_provider": "deepinfra", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4e-07, + "supports_tool_choice": true + }, + "deepinfra/meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo": { + "input_cost_per_token": 1e-07, + "litellm_provider": "deepinfra", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2.8e-07, + "supports_tool_choice": true + }, + "deepinfra/meta-llama/Meta-Llama-3.1-8B-Instruct": { + "input_cost_per_token": 3e-08, + "litellm_provider": "deepinfra", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 5e-08, + "supports_tool_choice": true + }, + "deepinfra/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo": { + "input_cost_per_token": 1.5e-08, + "litellm_provider": "deepinfra", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2e-08, + "supports_tool_choice": true + }, + "deepinfra/microsoft/WizardLM-2-8x22B": { + "input_cost_per_token": 4.8e-07, + "litellm_provider": "deepinfra", + "max_input_tokens": 65536, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 4.8e-07, + "supports_tool_choice": false + }, + "deepinfra/microsoft/phi-4": { + "input_cost_per_token": 7e-08, + "litellm_provider": "deepinfra", + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1.4e-07, + "supports_tool_choice": true + }, + "deepinfra/mistralai/Mistral-Nemo-Instruct-2407": { + "input_cost_per_token": 2e-08, + "litellm_provider": "deepinfra", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4e-08, + "supports_tool_choice": true + }, + "deepinfra/mistralai/Mistral-Small-24B-Instruct-2501": { + "input_cost_per_token": 5e-08, + "litellm_provider": "deepinfra", + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 8e-08, + "supports_tool_choice": true + }, + "deepinfra/mistralai/Mistral-Small-3.2-24B-Instruct-2506": { + "input_cost_per_token": 5e-08, + "litellm_provider": "deepinfra", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-07, + "supports_tool_choice": true + }, + "deepinfra/mistralai/Mixtral-8x7B-Instruct-v0.1": { + "input_cost_per_token": 8e-08, + "litellm_provider": "deepinfra", + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 2.4e-07, + "supports_tool_choice": true + }, + "deepinfra/moonshotai/Kimi-K2-Instruct": { + "input_cost_per_token": 5e-07, + "litellm_provider": "deepinfra", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2e-06, + "supports_tool_choice": true + }, + "deepinfra/nvidia/Llama-3.1-Nemotron-70B-Instruct": { + "input_cost_per_token": 1.2e-07, + "litellm_provider": "deepinfra", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 3e-07, + "supports_tool_choice": true + }, + "deepinfra/openai/gpt-oss-120b": { + "input_cost_per_token": 9e-08, + "litellm_provider": "deepinfra", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4.5e-07, + "supports_tool_choice": true + }, + "deepinfra/openai/gpt-oss-20b": { + "input_cost_per_token": 4e-08, + "litellm_provider": "deepinfra", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.6e-07, + "supports_tool_choice": true + }, + "deepinfra/zai-org/GLM-4.5": { + "input_cost_per_token": 5.5e-07, + "litellm_provider": "deepinfra", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2e-06, + "supports_tool_choice": true + }, + "deepinfra/zai-org/GLM-4.5-Air": { + "input_cost_per_token": 2e-07, + "litellm_provider": "deepinfra", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.1e-06, + "supports_tool_choice": true + }, + "deepseek/deepseek-chat": { + "cache_creation_input_token_cost": 0.0, + "cache_read_input_token_cost": 7e-08, + "input_cost_per_token": 2.7e-07, + "input_cost_per_token_cache_hit": 7e-08, + "litellm_provider": "deepseek", + "max_input_tokens": 65536, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.1e-06, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_tool_choice": true + }, + "deepseek/deepseek-coder": { + "input_cost_per_token": 1.4e-07, + "input_cost_per_token_cache_hit": 1.4e-08, + "litellm_provider": "deepseek", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 2.8e-07, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_tool_choice": true + }, + "deepseek/deepseek-r1": { + "input_cost_per_token": 5.5e-07, + "input_cost_per_token_cache_hit": 1.4e-07, + "litellm_provider": "deepseek", + "max_input_tokens": 65536, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 2.19e-06, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "deepseek/deepseek-reasoner": { + "input_cost_per_token": 5.5e-07, + "input_cost_per_token_cache_hit": 1.4e-07, + "litellm_provider": "deepseek", + "max_input_tokens": 65536, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 2.19e-06, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "deepseek/deepseek-v3": { + "cache_creation_input_token_cost": 0.0, + "cache_read_input_token_cost": 7e-08, + "input_cost_per_token": 2.7e-07, + "input_cost_per_token_cache_hit": 7e-08, + "litellm_provider": "deepseek", + "max_input_tokens": 65536, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.1e-06, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_tool_choice": true + }, + "dolphin": { + "input_cost_per_token": 5e-07, + "litellm_provider": "nlp_cloud", + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "completion", + "output_cost_per_token": 5e-07 + }, + "doubao-embedding": { + "input_cost_per_token": 0.0, + "litellm_provider": "volcengine", + "max_input_tokens": 4096, + "max_tokens": 4096, + "metadata": { + "notes": "Volcengine Doubao embedding model - standard version with 2560 dimensions" + }, + "mode": "embedding", + "output_cost_per_token": 0.0, + "output_vector_size": 2560 + }, + "doubao-embedding-large": { + "input_cost_per_token": 0.0, + "litellm_provider": "volcengine", + "max_input_tokens": 4096, + "max_tokens": 4096, + "metadata": { + "notes": "Volcengine Doubao embedding model - large version with 2048 dimensions" + }, + "mode": "embedding", + "output_cost_per_token": 0.0, + "output_vector_size": 2048 + }, + "doubao-embedding-large-text-240915": { + "input_cost_per_token": 0.0, + "litellm_provider": "volcengine", + "max_input_tokens": 4096, + "max_tokens": 4096, + "metadata": { + "notes": "Volcengine Doubao embedding model - text-240915 version with 4096 dimensions" + }, + "mode": "embedding", + "output_cost_per_token": 0.0, + "output_vector_size": 4096 + }, + "doubao-embedding-large-text-250515": { + "input_cost_per_token": 0.0, + "litellm_provider": "volcengine", + "max_input_tokens": 4096, + "max_tokens": 4096, + "metadata": { + "notes": "Volcengine Doubao embedding model - text-250515 version with 2048 dimensions" + }, + "mode": "embedding", + "output_cost_per_token": 0.0, + "output_vector_size": 2048 + }, + "doubao-embedding-text-240715": { + "input_cost_per_token": 0.0, + "litellm_provider": "volcengine", + "max_input_tokens": 4096, + "max_tokens": 4096, + "metadata": { + "notes": "Volcengine Doubao embedding model - text-240715 version with 2560 dimensions" + }, + "mode": "embedding", + "output_cost_per_token": 0.0, + "output_vector_size": 2560 + }, + "elevenlabs/scribe_v1": { + "input_cost_per_second": 6.11e-05, + "litellm_provider": "elevenlabs", + "metadata": { + "calculation": "$0.22/hour = $0.00366/minute = $0.0000611 per second (enterprise pricing)", + "notes": "ElevenLabs Scribe v1 - state-of-the-art speech recognition model with 99 language support", + "original_pricing_per_hour": 0.22 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://elevenlabs.io/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "elevenlabs/scribe_v1_experimental": { + "input_cost_per_second": 6.11e-05, + "litellm_provider": "elevenlabs", + "metadata": { + "calculation": "$0.22/hour = $0.00366/minute = $0.0000611 per second (enterprise pricing)", + "notes": "ElevenLabs Scribe v1 experimental - enhanced version of the main Scribe model", + "original_pricing_per_hour": 0.22 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://elevenlabs.io/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "embed-english-light-v2.0": { + "input_cost_per_token": 1e-07, + "litellm_provider": "cohere", + "max_input_tokens": 1024, + "max_tokens": 1024, + "mode": "embedding", + "output_cost_per_token": 0.0 + }, + "embed-english-light-v3.0": { + "input_cost_per_token": 1e-07, + "litellm_provider": "cohere", + "max_input_tokens": 1024, + "max_tokens": 1024, + "mode": "embedding", + "output_cost_per_token": 0.0 + }, + "embed-english-v2.0": { + "input_cost_per_token": 1e-07, + "litellm_provider": "cohere", + "max_input_tokens": 4096, + "max_tokens": 4096, + "mode": "embedding", + "output_cost_per_token": 0.0 + }, + "embed-english-v3.0": { + "input_cost_per_image": 0.0001, + "input_cost_per_token": 1e-07, + "litellm_provider": "cohere", + "max_input_tokens": 1024, + "max_tokens": 1024, + "metadata": { + "notes": "'supports_image_input' is a deprecated field. Use 'supports_embedding_image_input' instead." + }, + "mode": "embedding", + "output_cost_per_token": 0.0, + "supports_embedding_image_input": true, + "supports_image_input": true + }, + "embed-multilingual-v2.0": { + "input_cost_per_token": 1e-07, + "litellm_provider": "cohere", + "max_input_tokens": 768, + "max_tokens": 768, + "mode": "embedding", + "output_cost_per_token": 0.0 + }, + "embed-multilingual-v3.0": { + "input_cost_per_token": 1e-07, + "litellm_provider": "cohere", + "max_input_tokens": 1024, + "max_tokens": 1024, + "mode": "embedding", + "output_cost_per_token": 0.0, + "supports_embedding_image_input": true + }, + "eu.amazon.nova-lite-v1:0": { + "input_cost_per_token": 7.8e-08, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 300000, + "max_output_tokens": 10000, + "max_tokens": 10000, + "mode": "chat", + "output_cost_per_token": 3.12e-07, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_vision": true + }, + "eu.amazon.nova-micro-v1:0": { + "input_cost_per_token": 4.6e-08, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 128000, + "max_output_tokens": 10000, + "max_tokens": 10000, + "mode": "chat", + "output_cost_per_token": 1.84e-07, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true + }, + "eu.amazon.nova-pro-v1:0": { + "input_cost_per_token": 1.05e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 300000, + "max_output_tokens": 10000, + "max_tokens": 10000, + "mode": "chat", + "output_cost_per_token": 4.2e-06, + "source": "https://aws.amazon.com/bedrock/pricing/", + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_vision": true + }, + "eu.anthropic.claude-3-5-haiku-20241022-v1:0": { + "input_cost_per_token": 2.5e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.25e-06, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "eu.anthropic.claude-3-5-sonnet-20240620-v1:0": { + "input_cost_per_token": 3e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "eu.anthropic.claude-3-5-sonnet-20241022-v2:0": { + "input_cost_per_token": 3e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "eu.anthropic.claude-3-7-sonnet-20250219-v1:0": { + "input_cost_per_token": 3e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "eu.anthropic.claude-3-haiku-20240307-v1:0": { + "input_cost_per_token": 2.5e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.25e-06, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "eu.anthropic.claude-3-opus-20240229-v1:0": { + "input_cost_per_token": 1.5e-05, + "litellm_provider": "bedrock", + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 7.5e-05, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "eu.anthropic.claude-3-sonnet-20240229-v1:0": { + "input_cost_per_token": 3e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "eu.anthropic.claude-opus-4-1-20250805-v1:0": { + "cache_creation_input_token_cost": 1.875e-05, + "cache_read_input_token_cost": 1.5e-06, + "input_cost_per_token": 1.5e-05, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 200000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 7.5e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159 + }, + "eu.anthropic.claude-opus-4-20250514-v1:0": { + "cache_creation_input_token_cost": 1.875e-05, + "cache_read_input_token_cost": 1.5e-06, + "input_cost_per_token": 1.5e-05, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 200000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 7.5e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159 + }, + "eu.anthropic.claude-sonnet-4-20250514-v1:0": { + "cache_creation_input_token_cost": 3.75e-06, + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 3e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159 + }, + "eu.meta.llama3-2-1b-instruct-v1:0": { + "input_cost_per_token": 1.3e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.3e-07, + "supports_function_calling": true, + "supports_tool_choice": false + }, + "eu.meta.llama3-2-3b-instruct-v1:0": { + "input_cost_per_token": 1.9e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.9e-07, + "supports_function_calling": true, + "supports_tool_choice": false + }, + "eu.mistral.pixtral-large-2502-v1:0": { + "input_cost_per_token": 2e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 6e-06, + "supports_function_calling": true, + "supports_tool_choice": false + }, + "featherless_ai/featherless-ai/Qwerky-72B": { + "litellm_provider": "featherless_ai", + "max_input_tokens": 32768, + "max_output_tokens": 4096, + "max_tokens": 32768, + "mode": "chat" + }, + "featherless_ai/featherless-ai/Qwerky-QwQ-32B": { + "litellm_provider": "featherless_ai", + "max_input_tokens": 32768, + "max_output_tokens": 4096, + "max_tokens": 32768, + "mode": "chat" + }, + "fireworks-ai-4.1b-to-16b": { + "input_cost_per_token": 2e-07, + "litellm_provider": "fireworks_ai", + "output_cost_per_token": 2e-07 + }, + "fireworks-ai-56b-to-176b": { + "input_cost_per_token": 1.2e-06, + "litellm_provider": "fireworks_ai", + "output_cost_per_token": 1.2e-06 + }, + "fireworks-ai-above-16b": { + "input_cost_per_token": 9e-07, + "litellm_provider": "fireworks_ai", + "output_cost_per_token": 9e-07 + }, + "fireworks-ai-default": { + "input_cost_per_token": 0.0, + "litellm_provider": "fireworks_ai", + "output_cost_per_token": 0.0 + }, + "fireworks-ai-embedding-150m-to-350m": { + "input_cost_per_token": 1.6e-08, + "litellm_provider": "fireworks_ai-embedding-models", + "output_cost_per_token": 0.0 + }, + "fireworks-ai-embedding-up-to-150m": { + "input_cost_per_token": 8e-09, + "litellm_provider": "fireworks_ai-embedding-models", + "output_cost_per_token": 0.0 + }, + "fireworks-ai-moe-up-to-56b": { + "input_cost_per_token": 5e-07, + "litellm_provider": "fireworks_ai", + "output_cost_per_token": 5e-07 + }, + "fireworks-ai-up-to-4b": { + "input_cost_per_token": 2e-07, + "litellm_provider": "fireworks_ai", + "output_cost_per_token": 2e-07 + }, + "fireworks_ai/WhereIsAI/UAE-Large-V1": { + "input_cost_per_token": 1.6e-08, + "litellm_provider": "fireworks_ai-embedding-models", + "max_input_tokens": 512, + "max_tokens": 512, + "mode": "embedding", + "output_cost_per_token": 0.0, + "source": "https://fireworks.ai/pricing" + }, + "fireworks_ai/accounts/fireworks/models/deepseek-coder-v2-instruct": { + "input_cost_per_token": 1.2e-06, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 65536, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://fireworks.ai/pricing", + "supports_function_calling": false, + "supports_response_schema": true, + "supports_tool_choice": false + }, + "fireworks_ai/accounts/fireworks/models/deepseek-r1": { + "input_cost_per_token": 3e-06, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 128000, + "max_output_tokens": 20480, + "max_tokens": 20480, + "mode": "chat", + "output_cost_per_token": 8e-06, + "source": "https://fireworks.ai/pricing", + "supports_response_schema": true, + "supports_tool_choice": false + }, + "fireworks_ai/accounts/fireworks/models/deepseek-r1-0528": { + "input_cost_per_token": 3e-06, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 160000, + "max_output_tokens": 160000, + "max_tokens": 160000, + "mode": "chat", + "output_cost_per_token": 8e-06, + "source": "https://fireworks.ai/pricing", + "supports_response_schema": true, + "supports_tool_choice": false + }, + "fireworks_ai/accounts/fireworks/models/deepseek-r1-basic": { + "input_cost_per_token": 5.5e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 128000, + "max_output_tokens": 20480, + "max_tokens": 20480, + "mode": "chat", + "output_cost_per_token": 2.19e-06, + "source": "https://fireworks.ai/pricing", + "supports_response_schema": true, + "supports_tool_choice": false + }, + "fireworks_ai/accounts/fireworks/models/deepseek-v3": { + "input_cost_per_token": 9e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 9e-07, + "source": "https://fireworks.ai/pricing", + "supports_response_schema": true, + "supports_tool_choice": false + }, + "fireworks_ai/accounts/fireworks/models/deepseek-v3-0324": { + "input_cost_per_token": 9e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 163840, + "max_output_tokens": 163840, + "max_tokens": 163840, + "mode": "chat", + "output_cost_per_token": 9e-07, + "source": "https://fireworks.ai/models/fireworks/deepseek-v3-0324", + "supports_response_schema": true, + "supports_tool_choice": false + }, + "fireworks_ai/accounts/fireworks/models/deepseek-v3p1": { + "input_cost_per_token": 5.6e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.68e-06, + "source": "https://fireworks.ai/pricing", + "supports_response_schema": true, + "supports_tool_choice": true + }, + "fireworks_ai/accounts/fireworks/models/firefunction-v2": { + "input_cost_per_token": 9e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 9e-07, + "source": "https://fireworks.ai/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "fireworks_ai/accounts/fireworks/models/glm-4p5": { + "input_cost_per_token": 5.5e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 128000, + "max_output_tokens": 96000, + "max_tokens": 96000, + "mode": "chat", + "output_cost_per_token": 2.19e-06, + "source": "https://fireworks.ai/models/fireworks/glm-4p5", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "fireworks_ai/accounts/fireworks/models/glm-4p5-air": { + "input_cost_per_token": 2.2e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 128000, + "max_output_tokens": 96000, + "max_tokens": 96000, + "mode": "chat", + "output_cost_per_token": 8.8e-07, + "source": "https://artificialanalysis.ai/models/glm-4-5-air", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "fireworks_ai/accounts/fireworks/models/gpt-oss-120b": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 6e-07, + "source": "https://fireworks.ai/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "fireworks_ai/accounts/fireworks/models/gpt-oss-20b": { + "input_cost_per_token": 5e-08, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2e-07, + "source": "https://fireworks.ai/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "fireworks_ai/accounts/fireworks/models/kimi-k2-instruct": { + "input_cost_per_token": 6e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 131072, + "max_output_tokens": 16384, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2.5e-06, + "source": "https://fireworks.ai/models/fireworks/kimi-k2-instruct", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "fireworks_ai/accounts/fireworks/models/llama-v3p1-405b-instruct": { + "input_cost_per_token": 3e-06, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 3e-06, + "source": "https://fireworks.ai/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "fireworks_ai/accounts/fireworks/models/llama-v3p1-8b-instruct": { + "input_cost_per_token": 1e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1e-07, + "source": "https://fireworks.ai/pricing", + "supports_function_calling": false, + "supports_response_schema": true, + "supports_tool_choice": false + }, + "fireworks_ai/accounts/fireworks/models/llama-v3p2-11b-vision-instruct": { + "input_cost_per_token": 2e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 2e-07, + "source": "https://fireworks.ai/pricing", + "supports_function_calling": false, + "supports_response_schema": true, + "supports_tool_choice": false, + "supports_vision": true + }, + "fireworks_ai/accounts/fireworks/models/llama-v3p2-1b-instruct": { + "input_cost_per_token": 1e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1e-07, + "source": "https://fireworks.ai/pricing", + "supports_function_calling": false, + "supports_response_schema": true, + "supports_tool_choice": false + }, + "fireworks_ai/accounts/fireworks/models/llama-v3p2-3b-instruct": { + "input_cost_per_token": 1e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1e-07, + "source": "https://fireworks.ai/pricing", + "supports_function_calling": false, + "supports_response_schema": true, + "supports_tool_choice": false + }, + "fireworks_ai/accounts/fireworks/models/llama-v3p2-90b-vision-instruct": { + "input_cost_per_token": 9e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 9e-07, + "source": "https://fireworks.ai/pricing", + "supports_response_schema": true, + "supports_tool_choice": false, + "supports_vision": true + }, + "fireworks_ai/accounts/fireworks/models/llama4-maverick-instruct-basic": { + "input_cost_per_token": 2.2e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 8.8e-07, + "source": "https://fireworks.ai/pricing", + "supports_response_schema": true, + "supports_tool_choice": false + }, + "fireworks_ai/accounts/fireworks/models/llama4-scout-instruct-basic": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 6e-07, + "source": "https://fireworks.ai/pricing", + "supports_response_schema": true, + "supports_tool_choice": false + }, + "fireworks_ai/accounts/fireworks/models/mixtral-8x22b-instruct-hf": { + "input_cost_per_token": 1.2e-06, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 65536, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://fireworks.ai/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "fireworks_ai/accounts/fireworks/models/qwen2-72b-instruct": { + "input_cost_per_token": 9e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 9e-07, + "source": "https://fireworks.ai/pricing", + "supports_function_calling": false, + "supports_response_schema": true, + "supports_tool_choice": false + }, + "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-32b-instruct": { + "input_cost_per_token": 9e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 9e-07, + "source": "https://fireworks.ai/pricing", + "supports_function_calling": false, + "supports_response_schema": true, + "supports_tool_choice": false + }, + "fireworks_ai/accounts/fireworks/models/yi-large": { + "input_cost_per_token": 3e-06, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 3e-06, + "source": "https://fireworks.ai/pricing", + "supports_function_calling": false, + "supports_response_schema": true, + "supports_tool_choice": false + }, + "fireworks_ai/nomic-ai/nomic-embed-text-v1": { + "input_cost_per_token": 8e-09, + "litellm_provider": "fireworks_ai-embedding-models", + "max_input_tokens": 8192, + "max_tokens": 8192, + "mode": "embedding", + "output_cost_per_token": 0.0, + "source": "https://fireworks.ai/pricing" + }, + "fireworks_ai/nomic-ai/nomic-embed-text-v1.5": { + "input_cost_per_token": 8e-09, + "litellm_provider": "fireworks_ai-embedding-models", + "max_input_tokens": 8192, + "max_tokens": 8192, + "mode": "embedding", + "output_cost_per_token": 0.0, + "source": "https://fireworks.ai/pricing" + }, + "fireworks_ai/thenlper/gte-base": { + "input_cost_per_token": 8e-09, + "litellm_provider": "fireworks_ai-embedding-models", + "max_input_tokens": 512, + "max_tokens": 512, + "mode": "embedding", + "output_cost_per_token": 0.0, + "source": "https://fireworks.ai/pricing" + }, + "fireworks_ai/thenlper/gte-large": { + "input_cost_per_token": 1.6e-08, + "litellm_provider": "fireworks_ai-embedding-models", + "max_input_tokens": 512, + "max_tokens": 512, + "mode": "embedding", + "output_cost_per_token": 0.0, + "source": "https://fireworks.ai/pricing" + }, + "friendliai/meta-llama-3.1-70b-instruct": { + "input_cost_per_token": 6e-07, + "litellm_provider": "friendliai", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 6e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "friendliai/meta-llama-3.1-8b-instruct": { + "input_cost_per_token": 1e-07, + "litellm_provider": "friendliai", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "ft:babbage-002": { + "input_cost_per_token": 4e-07, + "input_cost_per_token_batches": 2e-07, + "litellm_provider": "text-completion-openai", + "max_input_tokens": 16384, + "max_output_tokens": 4096, + "max_tokens": 16384, + "mode": "completion", + "output_cost_per_token": 4e-07, + "output_cost_per_token_batches": 2e-07 + }, + "ft:davinci-002": { + "input_cost_per_token": 2e-06, + "input_cost_per_token_batches": 1e-06, + "litellm_provider": "text-completion-openai", + "max_input_tokens": 16384, + "max_output_tokens": 4096, + "max_tokens": 16384, + "mode": "completion", + "output_cost_per_token": 2e-06, + "output_cost_per_token_batches": 1e-06 + }, + "ft:gpt-3.5-turbo": { + "input_cost_per_token": 3e-06, + "input_cost_per_token_batches": 1.5e-06, + "litellm_provider": "openai", + "max_input_tokens": 16385, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 6e-06, + "output_cost_per_token_batches": 3e-06, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "ft:gpt-3.5-turbo-0125": { + "input_cost_per_token": 3e-06, + "litellm_provider": "openai", + "max_input_tokens": 16385, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 6e-06, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "ft:gpt-3.5-turbo-0613": { + "input_cost_per_token": 3e-06, + "litellm_provider": "openai", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 6e-06, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "ft:gpt-3.5-turbo-1106": { + "input_cost_per_token": 3e-06, + "litellm_provider": "openai", + "max_input_tokens": 16385, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 6e-06, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "ft:gpt-4-0613": { + "input_cost_per_token": 3e-05, + "litellm_provider": "openai", + "max_input_tokens": 8192, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 6e-05, + "source": "OpenAI needs to add pricing for this ft model, will be updated when added by OpenAI. Defaulting to base model pricing", + "supports_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "ft:gpt-4o-2024-08-06": { + "input_cost_per_token": 3.75e-06, + "input_cost_per_token_batches": 1.875e-06, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "output_cost_per_token_batches": 7.5e-06, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "ft:gpt-4o-2024-11-20": { + "cache_creation_input_token_cost": 1.875e-06, + "input_cost_per_token": 3.75e-06, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "ft:gpt-4o-mini-2024-07-18": { + "cache_read_input_token_cost": 1.5e-07, + "input_cost_per_token": 3e-07, + "input_cost_per_token_batches": 1.5e-07, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "output_cost_per_token_batches": 6e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "gemini-1.0-pro": { + "input_cost_per_character": 1.25e-07, + "input_cost_per_image": 0.0025, + "input_cost_per_token": 5e-07, + "input_cost_per_video_per_second": 0.002, + "litellm_provider": "vertex_ai-language-models", + "max_input_tokens": 32760, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_character": 3.75e-07, + "output_cost_per_token": 1.5e-06, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#google_models", + "supports_function_calling": true, + "supports_parallel_function_calling": true, "supports_tool_choice": true }, "gemini-1.0-pro-001": { - "max_tokens": 8192, + "deprecation_date": "2025-04-09", + "input_cost_per_character": 1.25e-07, + "input_cost_per_image": 0.0025, + "input_cost_per_token": 5e-07, + "input_cost_per_video_per_second": 0.002, + "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 32760, "max_output_tokens": 8192, - "input_cost_per_image": 0.0025, - "input_cost_per_video_per_second": 0.002, - "input_cost_per_token": 5e-07, - "input_cost_per_character": 1.25e-07, - "output_cost_per_token": 1.5e-06, - "output_cost_per_character": 3.75e-07, - "litellm_provider": "vertex_ai-language-models", + "max_tokens": 8192, "mode": "chat", - "supports_function_calling": true, + "output_cost_per_character": 3.75e-07, + "output_cost_per_token": 1.5e-06, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", - "deprecation_date": "2025-04-09", - "supports_tool_choice": true, - "supports_parallel_function_calling": true - }, - "gemini-1.0-ultra": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 2048, - "input_cost_per_image": 0.0025, - "input_cost_per_video_per_second": 0.002, - "input_cost_per_token": 5e-07, - "input_cost_per_character": 1.25e-07, - "output_cost_per_token": 1.5e-06, - "output_cost_per_character": 3.75e-07, - "litellm_provider": "vertex_ai-language-models", - "mode": "chat", "supports_function_calling": true, - "source": "As of Jun, 2024. There is no available doc on vertex ai pricing gemini-1.0-ultra-001. Using gemini-1.0-pro pricing. Got max_tokens info here: https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", - "supports_tool_choice": true, - "supports_parallel_function_calling": true - }, - "gemini-1.0-ultra-001": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 2048, - "input_cost_per_image": 0.0025, - "input_cost_per_video_per_second": 0.002, - "input_cost_per_token": 5e-07, - "input_cost_per_character": 1.25e-07, - "output_cost_per_token": 1.5e-06, - "output_cost_per_character": 3.75e-07, - "litellm_provider": "vertex_ai-language-models", - "mode": "chat", - "supports_function_calling": true, - "source": "As of Jun, 2024. There is no available doc on vertex ai pricing gemini-1.0-ultra-001. Using gemini-1.0-pro pricing. Got max_tokens info here: https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", - "supports_tool_choice": true, - "supports_parallel_function_calling": true + "supports_parallel_function_calling": true, + "supports_tool_choice": true }, "gemini-1.0-pro-002": { - "max_tokens": 8192, + "deprecation_date": "2025-04-09", + "input_cost_per_character": 1.25e-07, + "input_cost_per_image": 0.0025, + "input_cost_per_token": 5e-07, + "input_cost_per_video_per_second": 0.002, + "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 32760, "max_output_tokens": 8192, - "input_cost_per_image": 0.0025, - "input_cost_per_video_per_second": 0.002, - "input_cost_per_token": 5e-07, - "input_cost_per_character": 1.25e-07, - "output_cost_per_token": 1.5e-06, + "max_tokens": 8192, + "mode": "chat", "output_cost_per_character": 3.75e-07, - "litellm_provider": "vertex_ai-language-models", - "mode": "chat", - "supports_function_calling": true, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", - "deprecation_date": "2025-04-09", - "supports_tool_choice": true, - "supports_parallel_function_calling": true - }, - "gemini-1.5-pro": { - "max_tokens": 8192, - "max_input_tokens": 2097152, - "max_output_tokens": 8192, - "input_cost_per_image": 0.00032875, - "input_cost_per_audio_per_second": 3.125e-05, - "input_cost_per_video_per_second": 0.00032875, - "input_cost_per_token": 1.25e-06, - "input_cost_per_character": 3.125e-07, - "input_cost_per_image_above_128k_tokens": 0.0006575, - "input_cost_per_video_per_second_above_128k_tokens": 0.0006575, - "input_cost_per_audio_per_second_above_128k_tokens": 6.25e-05, - "input_cost_per_token_above_128k_tokens": 2.5e-06, - "input_cost_per_character_above_128k_tokens": 6.25e-07, - "output_cost_per_token": 5e-06, - "output_cost_per_character": 1.25e-06, - "output_cost_per_token_above_128k_tokens": 1e-05, - "output_cost_per_character_above_128k_tokens": 2.5e-06, - "litellm_provider": "vertex_ai-language-models", - "mode": "chat", - "supports_vision": true, - "supports_pdf_input": true, - "supports_system_messages": true, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": true, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", - "supports_parallel_function_calling": true - }, - "gemini-1.5-pro-002": { - "max_tokens": 8192, - "max_input_tokens": 2097152, - "max_output_tokens": 8192, - "input_cost_per_image": 0.00032875, - "input_cost_per_audio_per_second": 3.125e-05, - "input_cost_per_video_per_second": 0.00032875, - "input_cost_per_token": 1.25e-06, - "input_cost_per_character": 3.125e-07, - "input_cost_per_image_above_128k_tokens": 0.0006575, - "input_cost_per_video_per_second_above_128k_tokens": 0.0006575, - "input_cost_per_audio_per_second_above_128k_tokens": 6.25e-05, - "input_cost_per_token_above_128k_tokens": 2.5e-06, - "input_cost_per_character_above_128k_tokens": 6.25e-07, - "output_cost_per_token": 5e-06, - "output_cost_per_character": 1.25e-06, - "output_cost_per_token_above_128k_tokens": 1e-05, - "output_cost_per_character_above_128k_tokens": 2.5e-06, - "litellm_provider": "vertex_ai-language-models", - "mode": "chat", - "supports_vision": true, - "supports_system_messages": true, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": true, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-1.5-pro", - "deprecation_date": "2025-09-24", - "supports_parallel_function_calling": true - }, - "gemini-1.5-pro-001": { - "max_tokens": 8192, - "max_input_tokens": 1000000, - "max_output_tokens": 8192, - "input_cost_per_image": 0.00032875, - "input_cost_per_audio_per_second": 3.125e-05, - "input_cost_per_video_per_second": 0.00032875, - "input_cost_per_token": 1.25e-06, - "input_cost_per_character": 3.125e-07, - "input_cost_per_image_above_128k_tokens": 0.0006575, - "input_cost_per_video_per_second_above_128k_tokens": 0.0006575, - "input_cost_per_audio_per_second_above_128k_tokens": 6.25e-05, - "input_cost_per_token_above_128k_tokens": 2.5e-06, - "input_cost_per_character_above_128k_tokens": 6.25e-07, - "output_cost_per_token": 5e-06, - "output_cost_per_character": 1.25e-06, - "output_cost_per_token_above_128k_tokens": 1e-05, - "output_cost_per_character_above_128k_tokens": 2.5e-06, - "litellm_provider": "vertex_ai-language-models", - "mode": "chat", - "supports_vision": true, - "supports_system_messages": true, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": true, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", - "deprecation_date": "2025-05-24", - "supports_parallel_function_calling": true - }, - "gemini-1.5-pro-preview-0514": { - "max_tokens": 8192, - "max_input_tokens": 1000000, - "max_output_tokens": 8192, - "input_cost_per_image": 0.00032875, - "input_cost_per_audio_per_second": 3.125e-05, - "input_cost_per_video_per_second": 0.00032875, - "input_cost_per_token": 7.8125e-08, - "input_cost_per_character": 3.125e-07, - "input_cost_per_image_above_128k_tokens": 0.0006575, - "input_cost_per_video_per_second_above_128k_tokens": 0.0006575, - "input_cost_per_audio_per_second_above_128k_tokens": 6.25e-05, - "input_cost_per_token_above_128k_tokens": 1.5625e-07, - "input_cost_per_character_above_128k_tokens": 6.25e-07, - "output_cost_per_token": 3.125e-07, - "output_cost_per_character": 1.25e-06, - "output_cost_per_token_above_128k_tokens": 6.25e-07, - "output_cost_per_character_above_128k_tokens": 2.5e-06, - "litellm_provider": "vertex_ai-language-models", - "mode": "chat", - "supports_system_messages": true, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": true, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", - "supports_parallel_function_calling": true - }, - "gemini-1.5-pro-preview-0215": { - "max_tokens": 8192, - "max_input_tokens": 1000000, - "max_output_tokens": 8192, - "input_cost_per_image": 0.00032875, - "input_cost_per_audio_per_second": 3.125e-05, - "input_cost_per_video_per_second": 0.00032875, - "input_cost_per_token": 7.8125e-08, - "input_cost_per_character": 3.125e-07, - "input_cost_per_image_above_128k_tokens": 0.0006575, - "input_cost_per_video_per_second_above_128k_tokens": 0.0006575, - "input_cost_per_audio_per_second_above_128k_tokens": 6.25e-05, - "input_cost_per_token_above_128k_tokens": 1.5625e-07, - "input_cost_per_character_above_128k_tokens": 6.25e-07, - "output_cost_per_token": 3.125e-07, - "output_cost_per_character": 1.25e-06, - "output_cost_per_token_above_128k_tokens": 6.25e-07, - "output_cost_per_character_above_128k_tokens": 2.5e-06, - "litellm_provider": "vertex_ai-language-models", - "mode": "chat", - "supports_system_messages": true, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": true, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", - "supports_parallel_function_calling": true - }, - "gemini-1.5-pro-preview-0409": { - "max_tokens": 8192, - "max_input_tokens": 1000000, - "max_output_tokens": 8192, - "input_cost_per_image": 0.00032875, - "input_cost_per_audio_per_second": 3.125e-05, - "input_cost_per_video_per_second": 0.00032875, - "input_cost_per_token": 7.8125e-08, - "input_cost_per_character": 3.125e-07, - "input_cost_per_image_above_128k_tokens": 0.0006575, - "input_cost_per_video_per_second_above_128k_tokens": 0.0006575, - "input_cost_per_audio_per_second_above_128k_tokens": 6.25e-05, - "input_cost_per_token_above_128k_tokens": 1.5625e-07, - "input_cost_per_character_above_128k_tokens": 6.25e-07, - "output_cost_per_token": 3.125e-07, - "output_cost_per_character": 1.25e-06, - "output_cost_per_token_above_128k_tokens": 6.25e-07, - "output_cost_per_character_above_128k_tokens": 2.5e-06, - "litellm_provider": "vertex_ai-language-models", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": true, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", - "supports_parallel_function_calling": true - }, - "gemini-1.5-flash": { - "max_tokens": 8192, - "max_input_tokens": 1000000, - "max_output_tokens": 8192, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_pdf_size_mb": 30, - "input_cost_per_image": 2e-05, - "input_cost_per_video_per_second": 2e-05, - "input_cost_per_audio_per_second": 2e-06, - "input_cost_per_token": 7.5e-08, - "input_cost_per_character": 1.875e-08, - "input_cost_per_token_above_128k_tokens": 1e-06, - "input_cost_per_character_above_128k_tokens": 2.5e-07, - "input_cost_per_image_above_128k_tokens": 4e-05, - "input_cost_per_video_per_second_above_128k_tokens": 4e-05, - "input_cost_per_audio_per_second_above_128k_tokens": 4e-06, - "output_cost_per_token": 3e-07, - "output_cost_per_character": 7.5e-08, - "output_cost_per_token_above_128k_tokens": 6e-07, - "output_cost_per_character_above_128k_tokens": 1.5e-07, - "litellm_provider": "vertex_ai-language-models", - "mode": "chat", - "supports_system_messages": true, - "supports_function_calling": true, - "supports_vision": true, - "supports_response_schema": true, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", - "supports_tool_choice": true, - "supports_parallel_function_calling": true - }, - "gemini-1.5-flash-exp-0827": { - "max_tokens": 8192, - "max_input_tokens": 1000000, - "max_output_tokens": 8192, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_pdf_size_mb": 30, - "input_cost_per_image": 2e-05, - "input_cost_per_video_per_second": 2e-05, - "input_cost_per_audio_per_second": 2e-06, - "input_cost_per_token": 4.688e-09, - "input_cost_per_character": 1.875e-08, - "input_cost_per_token_above_128k_tokens": 1e-06, - "input_cost_per_character_above_128k_tokens": 2.5e-07, - "input_cost_per_image_above_128k_tokens": 4e-05, - "input_cost_per_video_per_second_above_128k_tokens": 4e-05, - "input_cost_per_audio_per_second_above_128k_tokens": 4e-06, - "output_cost_per_token": 4.6875e-09, - "output_cost_per_character": 1.875e-08, - "output_cost_per_token_above_128k_tokens": 9.375e-09, - "output_cost_per_character_above_128k_tokens": 3.75e-08, - "litellm_provider": "vertex_ai-language-models", - "mode": "chat", - "supports_system_messages": true, - "supports_function_calling": true, - "supports_vision": true, - "supports_response_schema": true, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", - "supports_tool_choice": true, - "supports_parallel_function_calling": true - }, - "gemini-1.5-flash-002": { - "max_tokens": 8192, - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_pdf_size_mb": 30, - "input_cost_per_image": 2e-05, - "input_cost_per_video_per_second": 2e-05, - "input_cost_per_audio_per_second": 2e-06, - "input_cost_per_token": 7.5e-08, - "input_cost_per_character": 1.875e-08, - "input_cost_per_token_above_128k_tokens": 1e-06, - "input_cost_per_character_above_128k_tokens": 2.5e-07, - "input_cost_per_image_above_128k_tokens": 4e-05, - "input_cost_per_video_per_second_above_128k_tokens": 4e-05, - "input_cost_per_audio_per_second_above_128k_tokens": 4e-06, - "output_cost_per_token": 3e-07, - "output_cost_per_character": 7.5e-08, - "output_cost_per_token_above_128k_tokens": 6e-07, - "output_cost_per_character_above_128k_tokens": 1.5e-07, - "litellm_provider": "vertex_ai-language-models", - "mode": "chat", - "supports_system_messages": true, - "supports_function_calling": true, - "supports_vision": true, - "supports_response_schema": true, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-1.5-flash", - "deprecation_date": "2025-09-24", - "supports_tool_choice": true, - "supports_parallel_function_calling": true - }, - "gemini-1.5-flash-001": { - "max_tokens": 8192, - "max_input_tokens": 1000000, - "max_output_tokens": 8192, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_pdf_size_mb": 30, - "input_cost_per_image": 2e-05, - "input_cost_per_video_per_second": 2e-05, - "input_cost_per_audio_per_second": 2e-06, - "input_cost_per_token": 7.5e-08, - "input_cost_per_character": 1.875e-08, - "input_cost_per_token_above_128k_tokens": 1e-06, - "input_cost_per_character_above_128k_tokens": 2.5e-07, - "input_cost_per_image_above_128k_tokens": 4e-05, - "input_cost_per_video_per_second_above_128k_tokens": 4e-05, - "input_cost_per_audio_per_second_above_128k_tokens": 4e-06, - "output_cost_per_token": 3e-07, - "output_cost_per_character": 7.5e-08, - "output_cost_per_token_above_128k_tokens": 6e-07, - "output_cost_per_character_above_128k_tokens": 1.5e-07, - "litellm_provider": "vertex_ai-language-models", - "mode": "chat", - "supports_system_messages": true, - "supports_function_calling": true, - "supports_vision": true, - "supports_response_schema": true, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", - "deprecation_date": "2025-05-24", - "supports_tool_choice": true, - "supports_parallel_function_calling": true - }, - "gemini-1.5-flash-preview-0514": { - "max_tokens": 8192, - "max_input_tokens": 1000000, - "max_output_tokens": 8192, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_pdf_size_mb": 30, - "input_cost_per_image": 2e-05, - "input_cost_per_video_per_second": 2e-05, - "input_cost_per_audio_per_second": 2e-06, - "input_cost_per_token": 7.5e-08, - "input_cost_per_character": 1.875e-08, - "input_cost_per_token_above_128k_tokens": 1e-06, - "input_cost_per_character_above_128k_tokens": 2.5e-07, - "input_cost_per_image_above_128k_tokens": 4e-05, - "input_cost_per_video_per_second_above_128k_tokens": 4e-05, - "input_cost_per_audio_per_second_above_128k_tokens": 4e-06, - "output_cost_per_token": 4.6875e-09, - "output_cost_per_character": 1.875e-08, - "output_cost_per_token_above_128k_tokens": 9.375e-09, - "output_cost_per_character_above_128k_tokens": 3.75e-08, - "litellm_provider": "vertex_ai-language-models", - "mode": "chat", - "supports_system_messages": true, - "supports_function_calling": true, - "supports_vision": true, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", - "supports_tool_choice": true, - "supports_parallel_function_calling": true - }, - "gemini-pro-experimental": { - "max_tokens": 8192, - "max_input_tokens": 1000000, - "max_output_tokens": 8192, - "input_cost_per_token": 0, - "output_cost_per_token": 0, - "input_cost_per_character": 0, - "output_cost_per_character": 0, - "litellm_provider": "vertex_ai-language-models", - "mode": "chat", - "supports_function_calling": false, - "supports_tool_choice": true, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/multimodal/gemini-experimental", - "supports_parallel_function_calling": true - }, - "gemini-flash-experimental": { - "max_tokens": 8192, - "max_input_tokens": 1000000, - "max_output_tokens": 8192, - "input_cost_per_token": 0, - "output_cost_per_token": 0, - "input_cost_per_character": 0, - "output_cost_per_character": 0, - "litellm_provider": "vertex_ai-language-models", - "mode": "chat", - "supports_function_calling": false, - "supports_tool_choice": true, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/multimodal/gemini-experimental", - "supports_parallel_function_calling": true - }, - "gemini-pro-vision": { - "max_tokens": 2048, - "max_input_tokens": 16384, - "max_output_tokens": 2048, - "max_images_per_prompt": 16, - "max_videos_per_prompt": 1, - "max_video_length": 2, - "input_cost_per_token": 5e-07, "output_cost_per_token": 1.5e-06, - "input_cost_per_image": 0.0025, - "litellm_provider": "vertex_ai-vision-models", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", - "supports_tool_choice": true, - "supports_parallel_function_calling": true + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true }, "gemini-1.0-pro-vision": { - "max_tokens": 2048, + "input_cost_per_image": 0.0025, + "input_cost_per_token": 5e-07, + "litellm_provider": "vertex_ai-vision-models", + "max_images_per_prompt": 16, "max_input_tokens": 16384, "max_output_tokens": 2048, - "max_images_per_prompt": 16, - "max_videos_per_prompt": 1, + "max_tokens": 2048, "max_video_length": 2, - "input_cost_per_token": 5e-07, - "output_cost_per_token": 1.5e-06, - "input_cost_per_image": 0.0025, - "litellm_provider": "vertex_ai-vision-models", + "max_videos_per_prompt": 1, "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, + "output_cost_per_token": 1.5e-06, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "supports_function_calling": true, + "supports_parallel_function_calling": true, "supports_tool_choice": true, - "supports_parallel_function_calling": true + "supports_vision": true }, "gemini-1.0-pro-vision-001": { - "max_tokens": 2048, + "deprecation_date": "2025-04-09", + "input_cost_per_image": 0.0025, + "input_cost_per_token": 5e-07, + "litellm_provider": "vertex_ai-vision-models", + "max_images_per_prompt": 16, "max_input_tokens": 16384, "max_output_tokens": 2048, - "max_images_per_prompt": 16, - "max_videos_per_prompt": 1, + "max_tokens": 2048, "max_video_length": 2, - "input_cost_per_token": 5e-07, + "max_videos_per_prompt": 1, + "mode": "chat", "output_cost_per_token": 1.5e-06, - "input_cost_per_image": 0.0025, - "litellm_provider": "vertex_ai-vision-models", - "mode": "chat", + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", "supports_function_calling": true, - "supports_vision": true, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", - "deprecation_date": "2025-04-09", + "supports_parallel_function_calling": true, "supports_tool_choice": true, - "supports_parallel_function_calling": true + "supports_vision": true }, - "medlm-medium": { - "max_tokens": 8192, - "max_input_tokens": 32768, - "max_output_tokens": 8192, - "input_cost_per_character": 5e-07, - "output_cost_per_character": 1e-06, + "gemini-1.0-ultra": { + "input_cost_per_character": 1.25e-07, + "input_cost_per_image": 0.0025, + "input_cost_per_token": 5e-07, + "input_cost_per_video_per_second": 0.002, "litellm_provider": "vertex_ai-language-models", - "mode": "chat", - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", - "supports_tool_choice": true - }, - "medlm-large": { - "max_tokens": 1024, "max_input_tokens": 8192, - "max_output_tokens": 1024, - "input_cost_per_character": 5e-06, - "output_cost_per_character": 1.5e-05, - "litellm_provider": "vertex_ai-language-models", + "max_output_tokens": 2048, + "max_tokens": 8192, "mode": "chat", - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "output_cost_per_character": 3.75e-07, + "output_cost_per_token": 1.5e-06, + "source": "As of Jun, 2024. There is no available doc on vertex ai pricing gemini-1.0-ultra-001. Using gemini-1.0-pro pricing. Got max_tokens info here: https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "supports_function_calling": true, + "supports_parallel_function_calling": true, "supports_tool_choice": true }, - "gemini-2.5-pro-exp-03-25": { - "max_tokens": 65535, - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, + "gemini-1.0-ultra-001": { + "input_cost_per_character": 1.25e-07, + "input_cost_per_image": 0.0025, + "input_cost_per_token": 5e-07, + "input_cost_per_video_per_second": 0.002, + "litellm_provider": "vertex_ai-language-models", + "max_input_tokens": 8192, + "max_output_tokens": 2048, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_character": 3.75e-07, + "output_cost_per_token": 1.5e-06, + "source": "As of Jun, 2024. There is no available doc on vertex ai pricing gemini-1.0-ultra-001. Using gemini-1.0-pro pricing. Got max_tokens info here: https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true + }, + "gemini-1.5-flash": { + "input_cost_per_audio_per_second": 2e-06, + "input_cost_per_audio_per_second_above_128k_tokens": 4e-06, + "input_cost_per_character": 1.875e-08, + "input_cost_per_character_above_128k_tokens": 2.5e-07, + "input_cost_per_image": 2e-05, + "input_cost_per_image_above_128k_tokens": 4e-05, + "input_cost_per_token": 7.5e-08, + "input_cost_per_token_above_128k_tokens": 1e-06, + "input_cost_per_video_per_second": 2e-05, + "input_cost_per_video_per_second_above_128k_tokens": 4e-05, + "litellm_provider": "vertex_ai-language-models", "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1000000, + "max_output_tokens": 8192, "max_pdf_size_mb": 30, - "input_cost_per_token": 1.25e-06, - "input_cost_per_token_above_200k_tokens": 2.5e-06, - "output_cost_per_token": 1e-05, - "output_cost_per_token_above_200k_tokens": 1.5e-05, - "litellm_provider": "vertex_ai-language-models", - "mode": "chat", - "supports_system_messages": true, - "supports_function_calling": true, - "supports_vision": true, - "supports_audio_input": true, - "supports_video_input": true, - "supports_pdf_input": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", - "supports_parallel_function_calling": true, - "supports_web_search": true, - "cache_read_input_token_cost": 3.125e-07, - "supports_prompt_caching": true - }, - "gemini-2.0-pro-exp-02-05": { "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_character": 7.5e-08, + "output_cost_per_character_above_128k_tokens": 1.5e-07, + "output_cost_per_token": 3e-07, + "output_cost_per_token_above_128k_tokens": 6e-07, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "gemini-1.5-flash-001": { + "deprecation_date": "2025-05-24", + "input_cost_per_audio_per_second": 2e-06, + "input_cost_per_audio_per_second_above_128k_tokens": 4e-06, + "input_cost_per_character": 1.875e-08, + "input_cost_per_character_above_128k_tokens": 2.5e-07, + "input_cost_per_image": 2e-05, + "input_cost_per_image_above_128k_tokens": 4e-05, + "input_cost_per_token": 7.5e-08, + "input_cost_per_token_above_128k_tokens": 1e-06, + "input_cost_per_video_per_second": 2e-05, + "input_cost_per_video_per_second_above_128k_tokens": 4e-05, + "litellm_provider": "vertex_ai-language-models", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1000000, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_character": 7.5e-08, + "output_cost_per_character_above_128k_tokens": 1.5e-07, + "output_cost_per_token": 3e-07, + "output_cost_per_token_above_128k_tokens": 6e-07, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "gemini-1.5-flash-002": { + "deprecation_date": "2025-09-24", + "input_cost_per_audio_per_second": 2e-06, + "input_cost_per_audio_per_second_above_128k_tokens": 4e-06, + "input_cost_per_character": 1.875e-08, + "input_cost_per_character_above_128k_tokens": 2.5e-07, + "input_cost_per_image": 2e-05, + "input_cost_per_image_above_128k_tokens": 4e-05, + "input_cost_per_token": 7.5e-08, + "input_cost_per_token_above_128k_tokens": 1e-06, + "input_cost_per_video_per_second": 2e-05, + "input_cost_per_video_per_second_above_128k_tokens": 4e-05, + "litellm_provider": "vertex_ai-language-models", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_character": 7.5e-08, + "output_cost_per_character_above_128k_tokens": 1.5e-07, + "output_cost_per_token": 3e-07, + "output_cost_per_token_above_128k_tokens": 6e-07, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-1.5-flash", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "gemini-1.5-flash-exp-0827": { + "input_cost_per_audio_per_second": 2e-06, + "input_cost_per_audio_per_second_above_128k_tokens": 4e-06, + "input_cost_per_character": 1.875e-08, + "input_cost_per_character_above_128k_tokens": 2.5e-07, + "input_cost_per_image": 2e-05, + "input_cost_per_image_above_128k_tokens": 4e-05, + "input_cost_per_token": 4.688e-09, + "input_cost_per_token_above_128k_tokens": 1e-06, + "input_cost_per_video_per_second": 2e-05, + "input_cost_per_video_per_second_above_128k_tokens": 4e-05, + "litellm_provider": "vertex_ai-language-models", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1000000, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_character": 1.875e-08, + "output_cost_per_character_above_128k_tokens": 3.75e-08, + "output_cost_per_token": 4.6875e-09, + "output_cost_per_token_above_128k_tokens": 9.375e-09, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "gemini-1.5-flash-preview-0514": { + "input_cost_per_audio_per_second": 2e-06, + "input_cost_per_audio_per_second_above_128k_tokens": 4e-06, + "input_cost_per_character": 1.875e-08, + "input_cost_per_character_above_128k_tokens": 2.5e-07, + "input_cost_per_image": 2e-05, + "input_cost_per_image_above_128k_tokens": 4e-05, + "input_cost_per_token": 7.5e-08, + "input_cost_per_token_above_128k_tokens": 1e-06, + "input_cost_per_video_per_second": 2e-05, + "input_cost_per_video_per_second_above_128k_tokens": 4e-05, + "litellm_provider": "vertex_ai-language-models", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1000000, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_character": 1.875e-08, + "output_cost_per_character_above_128k_tokens": 3.75e-08, + "output_cost_per_token": 4.6875e-09, + "output_cost_per_token_above_128k_tokens": 9.375e-09, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "gemini-1.5-pro": { + "input_cost_per_audio_per_second": 3.125e-05, + "input_cost_per_audio_per_second_above_128k_tokens": 6.25e-05, + "input_cost_per_character": 3.125e-07, + "input_cost_per_character_above_128k_tokens": 6.25e-07, + "input_cost_per_image": 0.00032875, + "input_cost_per_image_above_128k_tokens": 0.0006575, + "input_cost_per_token": 1.25e-06, + "input_cost_per_token_above_128k_tokens": 2.5e-06, + "input_cost_per_video_per_second": 0.00032875, + "input_cost_per_video_per_second_above_128k_tokens": 0.0006575, + "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 2097152, "max_output_tokens": 8192, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_pdf_size_mb": 30, - "input_cost_per_token": 1.25e-06, - "input_cost_per_token_above_200k_tokens": 2.5e-06, - "output_cost_per_token": 1e-05, - "output_cost_per_token_above_200k_tokens": 1.5e-05, - "litellm_provider": "vertex_ai-language-models", - "mode": "chat", - "supports_system_messages": true, - "supports_function_calling": true, - "supports_vision": true, - "supports_audio_input": true, - "supports_video_input": true, - "supports_pdf_input": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", - "supports_parallel_function_calling": true, - "supports_web_search": true, - "cache_read_input_token_cost": 3.125e-07, - "supports_prompt_caching": true - }, - "gemini-2.0-flash-exp": { "max_tokens": 8192, - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_pdf_size_mb": 30, - "input_cost_per_image": 0, - "input_cost_per_video_per_second": 0, - "input_cost_per_audio_per_second": 0, - "input_cost_per_token": 1.5e-07, - "input_cost_per_character": 0, - "input_cost_per_token_above_128k_tokens": 0, - "input_cost_per_character_above_128k_tokens": 0, - "input_cost_per_image_above_128k_tokens": 0, - "input_cost_per_video_per_second_above_128k_tokens": 0, - "input_cost_per_audio_per_second_above_128k_tokens": 0, - "output_cost_per_token": 6e-07, - "output_cost_per_character": 0, - "output_cost_per_token_above_128k_tokens": 0, - "output_cost_per_character_above_128k_tokens": 0, - "litellm_provider": "vertex_ai-language-models", "mode": "chat", - "supports_system_messages": true, + "output_cost_per_character": 1.25e-06, + "output_cost_per_character_above_128k_tokens": 2.5e-06, + "output_cost_per_token": 5e-06, + "output_cost_per_token_above_128k_tokens": 1e-05, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", "supports_function_calling": true, - "supports_vision": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, "supports_response_schema": true, - "supports_audio_output": true, - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text", - "image" - ], - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", - "supports_tool_choice": true, - "supports_parallel_function_calling": true, - "supports_web_search": true, - "cache_read_input_token_cost": 3.75e-08, - "supports_prompt_caching": true - }, - "gemini-2.0-flash-001": { - "max_tokens": 8192, - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_pdf_size_mb": 30, - "input_cost_per_audio_token": 1e-06, - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 6e-07, - "litellm_provider": "vertex_ai-language-models", - "mode": "chat", "supports_system_messages": true, - "supports_function_calling": true, - "supports_vision": true, - "supports_response_schema": true, - "supports_audio_output": true, "supports_tool_choice": true, - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text", - "image" - ], - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", - "deprecation_date": "2026-02-05", - "supports_parallel_function_calling": true, - "supports_web_search": true, - "cache_read_input_token_cost": 3.75e-08, - "supports_prompt_caching": true + "supports_vision": true }, - "gemini-2.0-flash-thinking-exp": { - "max_tokens": 8192, - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_pdf_size_mb": 30, - "input_cost_per_image": 0, - "input_cost_per_video_per_second": 0, - "input_cost_per_audio_per_second": 0, - "input_cost_per_token": 0, - "input_cost_per_character": 0, - "input_cost_per_token_above_128k_tokens": 0, - "input_cost_per_character_above_128k_tokens": 0, - "input_cost_per_image_above_128k_tokens": 0, - "input_cost_per_video_per_second_above_128k_tokens": 0, - "input_cost_per_audio_per_second_above_128k_tokens": 0, - "output_cost_per_token": 0, - "output_cost_per_character": 0, - "output_cost_per_token_above_128k_tokens": 0, - "output_cost_per_character_above_128k_tokens": 0, - "litellm_provider": "vertex_ai-language-models", - "mode": "chat", - "supports_system_messages": true, - "supports_function_calling": true, - "supports_vision": true, - "supports_response_schema": true, - "supports_audio_output": true, - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text", - "image" - ], - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-2.0-flash", - "supports_tool_choice": true, - "supports_parallel_function_calling": true, - "supports_web_search": true, - "cache_read_input_token_cost": 0.0, - "supports_prompt_caching": true - }, - "gemini-2.0-flash-thinking-exp-01-21": { - "max_tokens": 65536, - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_pdf_size_mb": 30, - "input_cost_per_image": 0, - "input_cost_per_video_per_second": 0, - "input_cost_per_audio_per_second": 0, - "input_cost_per_token": 0, - "input_cost_per_character": 0, - "input_cost_per_token_above_128k_tokens": 0, - "input_cost_per_character_above_128k_tokens": 0, - "input_cost_per_image_above_128k_tokens": 0, - "input_cost_per_video_per_second_above_128k_tokens": 0, - "input_cost_per_audio_per_second_above_128k_tokens": 0, - "output_cost_per_token": 0, - "output_cost_per_character": 0, - "output_cost_per_token_above_128k_tokens": 0, - "output_cost_per_character_above_128k_tokens": 0, - "litellm_provider": "vertex_ai-language-models", - "mode": "chat", - "supports_system_messages": true, - "supports_function_calling": false, - "supports_vision": true, - "supports_response_schema": false, - "supports_audio_output": false, - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text", - "image" - ], - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-2.0-flash", - "supports_tool_choice": true, - "supports_parallel_function_calling": true, - "supports_web_search": true, - "cache_read_input_token_cost": 0.0, - "supports_prompt_caching": true - }, - "gemini-2.5-pro": { - "max_tokens": 65535, - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_pdf_size_mb": 30, + "gemini-1.5-pro-001": { + "deprecation_date": "2025-05-24", + "input_cost_per_audio_per_second": 3.125e-05, + "input_cost_per_audio_per_second_above_128k_tokens": 6.25e-05, + "input_cost_per_character": 3.125e-07, + "input_cost_per_character_above_128k_tokens": 6.25e-07, + "input_cost_per_image": 0.00032875, + "input_cost_per_image_above_128k_tokens": 0.0006575, "input_cost_per_token": 1.25e-06, - "input_cost_per_token_above_200k_tokens": 2.5e-06, - "output_cost_per_token": 1e-05, - "output_cost_per_token_above_200k_tokens": 1.5e-05, + "input_cost_per_token_above_128k_tokens": 2.5e-06, + "input_cost_per_video_per_second": 0.00032875, + "input_cost_per_video_per_second_above_128k_tokens": 0.0006575, "litellm_provider": "vertex_ai-language-models", + "max_input_tokens": 1000000, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", - "supports_system_messages": true, + "output_cost_per_character": 1.25e-06, + "output_cost_per_character_above_128k_tokens": 2.5e-06, + "output_cost_per_token": 5e-06, + "output_cost_per_token_above_128k_tokens": 1e-05, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", "supports_function_calling": true, - "supports_vision": true, - "supports_audio_input": true, - "supports_video_input": true, - "supports_pdf_input": true, + "supports_parallel_function_calling": true, "supports_response_schema": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", - "supports_web_search": true, - "cache_read_input_token_cost": 3.125e-07, - "supports_prompt_caching": true - }, - "gemini/gemini-2.5-pro-exp-03-25": { - "max_tokens": 65535, - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_pdf_size_mb": 30, - "input_cost_per_token": 0.0, - "input_cost_per_token_above_200k_tokens": 0.0, - "output_cost_per_token": 0.0, - "output_cost_per_token_above_200k_tokens": 0.0, - "litellm_provider": "gemini", - "mode": "chat", - "rpm": 5, - "tpm": 250000, "supports_system_messages": true, - "supports_function_calling": true, - "supports_vision": true, - "supports_audio_input": true, - "supports_video_input": true, - "supports_pdf_input": true, - "supports_response_schema": true, "supports_tool_choice": true, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", - "supports_web_search": true, - "cache_read_input_token_cost": 0.0, - "supports_prompt_caching": true + "supports_vision": true }, - "gemini/gemini-2.5-pro": { - "max_tokens": 65535, - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_pdf_size_mb": 30, + "gemini-1.5-pro-002": { + "deprecation_date": "2025-09-24", + "input_cost_per_audio_per_second": 3.125e-05, + "input_cost_per_audio_per_second_above_128k_tokens": 6.25e-05, + "input_cost_per_character": 3.125e-07, + "input_cost_per_character_above_128k_tokens": 6.25e-07, + "input_cost_per_image": 0.00032875, + "input_cost_per_image_above_128k_tokens": 0.0006575, "input_cost_per_token": 1.25e-06, - "input_cost_per_token_above_200k_tokens": 2.5e-06, - "output_cost_per_token": 1e-05, - "output_cost_per_token_above_200k_tokens": 1.5e-05, - "litellm_provider": "gemini", - "mode": "chat", - "rpm": 2000, - "tpm": 800000, - "supports_system_messages": true, - "supports_function_calling": true, - "supports_vision": true, - "supports_audio_input": true, - "supports_video_input": true, - "supports_pdf_input": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", - "supports_web_search": true, - "cache_read_input_token_cost": 3.125e-07, - "supports_prompt_caching": true - }, - "gemini/gemini-2.5-flash": { - "max_tokens": 65535, - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_pdf_size_mb": 30, - "input_cost_per_audio_token": 1e-06, - "input_cost_per_token": 3e-07, - "output_cost_per_token": 2.5e-06, - "output_cost_per_reasoning_token": 2.5e-06, - "litellm_provider": "gemini", - "mode": "chat", - "supports_reasoning": true, - "supports_system_messages": true, - "supports_function_calling": true, - "supports_vision": true, - "supports_response_schema": true, - "supports_audio_output": false, - "supports_tool_choice": true, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", - "supports_parallel_function_calling": true, - "supports_web_search": true, - "supports_url_context": true, - "tpm": 8000000, - "rpm": 100000, - "supports_pdf_input": true, - "cache_read_input_token_cost": 7.5e-08, - "supports_prompt_caching": true - }, - "gemini/gemini-2.5-flash-image-preview": { - "max_tokens": 65535, - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_pdf_size_mb": 30, - "input_cost_per_audio_token": 1e-06, - "input_cost_per_token": 3e-07, - "output_cost_per_token": 3e-05, - "output_cost_per_reasoning_token": 3e-05, - "output_cost_per_image": 0.039, - "litellm_provider": "gemini", - "mode": "chat", - "supports_system_messages": true, - "supports_function_calling": true, - "supports_vision": true, - "supports_response_schema": true, - "supports_audio_output": false, - "supports_tool_choice": true, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text", - "image" - ], - "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", - "supports_parallel_function_calling": true, - "supports_web_search": true, - "supports_url_context": true, - "tpm": 8000000, - "rpm": 100000, - "supports_pdf_input": true, - "cache_read_input_token_cost": 7.5e-08, - "supports_prompt_caching": true - }, - "gemini-2.5-flash": { - "max_tokens": 65535, - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_pdf_size_mb": 30, - "input_cost_per_audio_token": 1e-06, - "input_cost_per_token": 3e-07, - "output_cost_per_token": 2.5e-06, - "output_cost_per_reasoning_token": 2.5e-06, + "input_cost_per_token_above_128k_tokens": 2.5e-06, + "input_cost_per_video_per_second": 0.00032875, + "input_cost_per_video_per_second_above_128k_tokens": 0.0006575, "litellm_provider": "vertex_ai-language-models", + "max_input_tokens": 2097152, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", - "supports_reasoning": true, - "supports_system_messages": true, + "output_cost_per_character": 1.25e-06, + "output_cost_per_character_above_128k_tokens": 2.5e-06, + "output_cost_per_token": 5e-06, + "output_cost_per_token_above_128k_tokens": 1e-05, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-1.5-pro", "supports_function_calling": true, - "supports_vision": true, - "supports_response_schema": true, - "supports_audio_output": false, - "supports_tool_choice": true, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", "supports_parallel_function_calling": true, - "supports_web_search": true, - "supports_url_context": true, - "supports_pdf_input": true, - "cache_read_input_token_cost": 7.5e-08, - "supports_prompt_caching": true - }, - "gemini/gemini-2.0-flash-live-001": { - "max_tokens": 65535, - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_pdf_size_mb": 30, - "input_cost_per_token": 3.5e-07, - "input_cost_per_audio_token": 2.1e-06, - "input_cost_per_image": 2.1e-06, - "input_cost_per_video_per_second": 2.1e-06, - "output_cost_per_token": 1.5e-06, - "output_cost_per_audio_token": 8.5e-06, - "litellm_provider": "gemini", - "mode": "chat", - "rpm": 10, - "tpm": 250000, - "supports_system_messages": true, - "supports_function_calling": true, - "supports_vision": true, - "supports_reasoning": true, "supports_response_schema": true, - "supports_audio_output": true, - "supports_tool_choice": true, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text", - "audio" - ], - "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2-0-flash-live-001", - "supports_web_search": true, - "supports_url_context": true, - "supports_pdf_input": true, - "cache_read_input_token_cost": 7.5e-08, - "supports_prompt_caching": true - }, - "gemini/gemini-2.5-flash-preview-tts": { - "max_tokens": 65535, - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_pdf_size_mb": 30, - "input_cost_per_audio_token": 1e-06, - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 6e-07, - "output_cost_per_reasoning_token": 3.5e-06, - "litellm_provider": "gemini", - "mode": "chat", - "rpm": 10, - "tpm": 250000, "supports_system_messages": true, - "supports_function_calling": true, - "supports_vision": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_audio_output": false, "supports_tool_choice": true, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions" - ], - "supported_modalities": [ - "text" - ], - "supported_output_modalities": [ - "audio" - ], - "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", - "supports_web_search": true, - "cache_read_input_token_cost": 3.75e-08, - "supports_prompt_caching": true + "supports_vision": true }, - "gemini/gemini-2.5-flash-preview-05-20": { - "max_tokens": 65535, - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_pdf_size_mb": 30, - "input_cost_per_audio_token": 1e-06, - "input_cost_per_token": 3e-07, - "output_cost_per_token": 2.5e-06, - "output_cost_per_reasoning_token": 2.5e-06, - "litellm_provider": "gemini", - "mode": "chat", - "rpm": 10, - "tpm": 250000, - "supports_system_messages": true, - "supports_function_calling": true, - "supports_vision": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_audio_output": false, - "supports_tool_choice": true, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", - "supports_web_search": true, - "supports_url_context": true, - "supports_pdf_input": true, - "cache_read_input_token_cost": 7.5e-08, - "supports_prompt_caching": true - }, - "gemini/gemini-2.5-flash-preview-04-17": { - "max_tokens": 65535, - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_pdf_size_mb": 30, - "input_cost_per_audio_token": 1e-06, - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 6e-07, - "output_cost_per_reasoning_token": 3.5e-06, - "litellm_provider": "gemini", - "mode": "chat", - "rpm": 10, - "tpm": 250000, - "supports_system_messages": true, - "supports_function_calling": true, - "supports_vision": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_audio_output": false, - "supports_tool_choice": true, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", - "supports_web_search": true, - "supports_pdf_input": true, - "cache_read_input_token_cost": 3.75e-08, - "supports_prompt_caching": true - }, - "gemini/gemini-2.5-flash-lite-preview-06-17": { - "max_tokens": 65535, - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_pdf_size_mb": 30, - "input_cost_per_audio_token": 5e-07, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 4e-07, - "output_cost_per_reasoning_token": 4e-07, - "litellm_provider": "gemini", - "mode": "chat", - "rpm": 15, - "tpm": 250000, - "supports_reasoning": true, - "supports_system_messages": true, - "supports_function_calling": true, - "supports_vision": true, - "supports_response_schema": true, - "supports_audio_output": false, - "supports_tool_choice": true, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-lite", - "supports_parallel_function_calling": true, - "supports_web_search": true, - "supports_url_context": true, - "supports_pdf_input": true, - "cache_read_input_token_cost": 2.5e-08, - "supports_prompt_caching": true - }, - "gemini/gemini-2.5-flash-lite": { - "max_tokens": 65535, - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_pdf_size_mb": 30, - "input_cost_per_audio_token": 5e-07, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 4e-07, - "output_cost_per_reasoning_token": 4e-07, - "litellm_provider": "gemini", - "mode": "chat", - "rpm": 15, - "tpm": 250000, - "supports_reasoning": true, - "supports_system_messages": true, - "supports_function_calling": true, - "supports_vision": true, - "supports_response_schema": true, - "supports_audio_output": false, - "supports_tool_choice": true, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-lite", - "supports_parallel_function_calling": true, - "supports_web_search": true, - "supports_url_context": true, - "supports_pdf_input": true, - "cache_read_input_token_cost": 2.5e-08, - "supports_prompt_caching": true - }, - "gemini-2.5-flash-image-preview": { - "max_tokens": 65535, - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_pdf_size_mb": 30, - "input_cost_per_audio_token": 1e-06, - "input_cost_per_token": 3e-07, - "output_cost_per_token": 3e-05, - "output_cost_per_reasoning_token": 3e-05, - "output_cost_per_image": 0.039, + "gemini-1.5-pro-preview-0215": { + "input_cost_per_audio_per_second": 3.125e-05, + "input_cost_per_audio_per_second_above_128k_tokens": 6.25e-05, + "input_cost_per_character": 3.125e-07, + "input_cost_per_character_above_128k_tokens": 6.25e-07, + "input_cost_per_image": 0.00032875, + "input_cost_per_image_above_128k_tokens": 0.0006575, + "input_cost_per_token": 7.8125e-08, + "input_cost_per_token_above_128k_tokens": 1.5625e-07, + "input_cost_per_video_per_second": 0.00032875, + "input_cost_per_video_per_second_above_128k_tokens": 0.0006575, "litellm_provider": "vertex_ai-language-models", + "max_input_tokens": 1000000, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", - "supports_system_messages": true, + "output_cost_per_character": 1.25e-06, + "output_cost_per_character_above_128k_tokens": 2.5e-06, + "output_cost_per_token": 3.125e-07, + "output_cost_per_token_above_128k_tokens": 6.25e-07, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", "supports_function_calling": true, - "supports_vision": true, - "supports_response_schema": true, - "supports_audio_output": false, - "supports_tool_choice": true, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text", - "image" - ], - "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", "supports_parallel_function_calling": true, - "supports_web_search": true, - "supports_url_context": true, - "tpm": 8000000, - "rpm": 100000, - "supports_pdf_input": true, - "cache_read_input_token_cost": 7.5e-08, - "supports_prompt_caching": true + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true }, - "gemini-2.5-flash-preview-05-20": { - "max_tokens": 65535, - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_pdf_size_mb": 30, - "input_cost_per_audio_token": 1e-06, - "input_cost_per_token": 3e-07, - "output_cost_per_token": 2.5e-06, - "output_cost_per_reasoning_token": 2.5e-06, + "gemini-1.5-pro-preview-0409": { + "input_cost_per_audio_per_second": 3.125e-05, + "input_cost_per_audio_per_second_above_128k_tokens": 6.25e-05, + "input_cost_per_character": 3.125e-07, + "input_cost_per_character_above_128k_tokens": 6.25e-07, + "input_cost_per_image": 0.00032875, + "input_cost_per_image_above_128k_tokens": 0.0006575, + "input_cost_per_token": 7.8125e-08, + "input_cost_per_token_above_128k_tokens": 1.5625e-07, + "input_cost_per_video_per_second": 0.00032875, + "input_cost_per_video_per_second_above_128k_tokens": 0.0006575, "litellm_provider": "vertex_ai-language-models", + "max_input_tokens": 1000000, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", - "supports_reasoning": true, - "supports_system_messages": true, + "output_cost_per_character": 1.25e-06, + "output_cost_per_character_above_128k_tokens": 2.5e-06, + "output_cost_per_token": 3.125e-07, + "output_cost_per_token_above_128k_tokens": 6.25e-07, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", "supports_function_calling": true, - "supports_vision": true, - "supports_response_schema": true, - "supports_audio_output": false, - "supports_tool_choice": true, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", "supports_parallel_function_calling": true, - "supports_web_search": true, - "supports_url_context": true, - "supports_pdf_input": true, - "cache_read_input_token_cost": 7.5e-08, - "supports_prompt_caching": true + "supports_response_schema": true, + "supports_tool_choice": true }, - "gemini-2.5-flash-preview-04-17": { - "max_tokens": 65535, - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_pdf_size_mb": 30, - "input_cost_per_audio_token": 1e-06, - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 6e-07, - "output_cost_per_reasoning_token": 3.5e-06, + "gemini-1.5-pro-preview-0514": { + "input_cost_per_audio_per_second": 3.125e-05, + "input_cost_per_audio_per_second_above_128k_tokens": 6.25e-05, + "input_cost_per_character": 3.125e-07, + "input_cost_per_character_above_128k_tokens": 6.25e-07, + "input_cost_per_image": 0.00032875, + "input_cost_per_image_above_128k_tokens": 0.0006575, + "input_cost_per_token": 7.8125e-08, + "input_cost_per_token_above_128k_tokens": 1.5625e-07, + "input_cost_per_video_per_second": 0.00032875, + "input_cost_per_video_per_second_above_128k_tokens": 0.0006575, "litellm_provider": "vertex_ai-language-models", + "max_input_tokens": 1000000, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", - "supports_reasoning": true, - "supports_system_messages": true, + "output_cost_per_character": 1.25e-06, + "output_cost_per_character_above_128k_tokens": 2.5e-06, + "output_cost_per_token": 3.125e-07, + "output_cost_per_token_above_128k_tokens": 6.25e-07, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", "supports_function_calling": true, - "supports_vision": true, - "supports_response_schema": true, - "supports_audio_output": false, - "supports_tool_choice": true, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", "supports_parallel_function_calling": true, - "supports_web_search": true, - "supports_pdf_input": true, - "cache_read_input_token_cost": 3.75e-08, - "supports_prompt_caching": true - }, - "gemini-2.5-flash-lite-preview-06-17": { - "max_tokens": 65535, - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_pdf_size_mb": 30, - "input_cost_per_audio_token": 5e-07, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 4e-07, - "output_cost_per_reasoning_token": 4e-07, - "litellm_provider": "vertex_ai-language-models", - "mode": "chat", - "supports_reasoning": true, + "supports_response_schema": true, "supports_system_messages": true, - "supports_function_calling": true, - "supports_vision": true, - "supports_response_schema": true, - "supports_audio_output": false, - "supports_tool_choice": true, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", - "supports_parallel_function_calling": true, - "supports_web_search": true, - "supports_url_context": true, - "supports_pdf_input": true, - "cache_read_input_token_cost": 2.5e-08, - "supports_prompt_caching": true - }, - "gemini-2.5-flash-lite": { - "max_tokens": 65535, - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_pdf_size_mb": 30, - "input_cost_per_audio_token": 5e-07, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 4e-07, - "output_cost_per_reasoning_token": 4e-07, - "litellm_provider": "vertex_ai-language-models", - "mode": "chat", - "supports_reasoning": true, - "supports_system_messages": true, - "supports_function_calling": true, - "supports_vision": true, - "supports_response_schema": true, - "supports_audio_output": false, - "supports_tool_choice": true, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", - "supports_parallel_function_calling": true, - "supports_web_search": true, - "supports_url_context": true, - "supports_pdf_input": true, - "cache_read_input_token_cost": 2.5e-08, - "supports_prompt_caching": true + "supports_tool_choice": true }, "gemini-2.0-flash": { - "max_tokens": 8192, - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_pdf_size_mb": 30, + "cache_read_input_token_cost": 2.5e-08, "input_cost_per_audio_token": 7e-07, "input_cost_per_token": 1e-07, - "output_cost_per_token": 4e-07, "litellm_provider": "vertex_ai-language-models", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, "mode": "chat", - "supports_system_messages": true, - "supports_function_calling": true, - "supports_vision": true, - "supports_response_schema": true, - "supports_audio_output": true, - "supports_audio_input": true, + "output_cost_per_token": 4e-07, + "source": "https://ai.google.dev/pricing#2_0flash", "supported_modalities": [ "text", "image", @@ -8604,33 +8603,120 @@ "text", "image" ], - "supports_tool_choice": true, - "source": "https://ai.google.dev/pricing#2_0flash", + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, "supports_parallel_function_calling": true, - "supports_web_search": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, "supports_url_context": true, - "cache_read_input_token_cost": 2.5e-08, - "supports_prompt_caching": true + "supports_vision": true, + "supports_web_search": true + }, + "gemini-2.0-flash-001": { + "cache_read_input_token_cost": 3.75e-08, + "deprecation_date": "2026-02-05", + "input_cost_per_audio_token": 1e-06, + "input_cost_per_token": 1.5e-07, + "litellm_provider": "vertex_ai-language-models", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_token": 6e-07, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text", + "image" + ], + "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "gemini-2.0-flash-exp": { + "cache_read_input_token_cost": 3.75e-08, + "input_cost_per_audio_per_second": 0, + "input_cost_per_audio_per_second_above_128k_tokens": 0, + "input_cost_per_character": 0, + "input_cost_per_character_above_128k_tokens": 0, + "input_cost_per_image": 0, + "input_cost_per_image_above_128k_tokens": 0, + "input_cost_per_token": 1.5e-07, + "input_cost_per_token_above_128k_tokens": 0, + "input_cost_per_video_per_second": 0, + "input_cost_per_video_per_second_above_128k_tokens": 0, + "litellm_provider": "vertex_ai-language-models", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_character": 0, + "output_cost_per_character_above_128k_tokens": 0, + "output_cost_per_token": 6e-07, + "output_cost_per_token_above_128k_tokens": 0, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text", + "image" + ], + "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true }, "gemini-2.0-flash-lite": { - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_pdf_size_mb": 50, + "cache_read_input_token_cost": 1.875e-08, "input_cost_per_audio_token": 7.5e-08, "input_cost_per_token": 7.5e-08, - "output_cost_per_token": 3e-07, "litellm_provider": "vertex_ai-language-models", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_pdf_size_mb": 50, + "max_video_length": 1, + "max_videos_per_prompt": 10, "mode": "chat", - "supports_system_messages": true, - "supports_function_calling": true, - "supports_vision": true, - "supports_response_schema": true, - "supports_audio_output": true, + "output_cost_per_token": 3e-07, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-2.0-flash", "supported_modalities": [ "text", "image", @@ -8640,32 +8726,33 @@ "supported_output_modalities": [ "text" ], - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-2.0-flash", - "supports_tool_choice": true, + "supports_audio_output": true, + "supports_function_calling": true, "supports_parallel_function_calling": true, - "supports_web_search": true, - "cache_read_input_token_cost": 1.875e-08, - "supports_prompt_caching": true + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true }, "gemini-2.0-flash-lite-001": { - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_pdf_size_mb": 50, + "cache_read_input_token_cost": 1.875e-08, + "deprecation_date": "2026-02-25", "input_cost_per_audio_token": 7.5e-08, "input_cost_per_token": 7.5e-08, - "output_cost_per_token": 3e-07, "litellm_provider": "vertex_ai-language-models", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_pdf_size_mb": 50, + "max_video_length": 1, + "max_videos_per_prompt": 10, "mode": "chat", - "supports_system_messages": true, - "supports_function_calling": true, - "supports_vision": true, - "supports_response_schema": true, - "supports_audio_output": true, + "output_cost_per_token": 3e-07, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-2.0-flash", "supported_modalities": [ "text", "image", @@ -8675,38 +8762,259 @@ "supported_output_modalities": [ "text" ], - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-2.0-flash", - "supports_tool_choice": true, - "deprecation_date": "2026-02-25", + "supports_audio_output": true, + "supports_function_calling": true, "supports_parallel_function_calling": true, - "supports_web_search": true, - "cache_read_input_token_cost": 1.875e-08, - "supports_prompt_caching": true + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true }, - "gemini-2.5-pro-preview-06-05": { - "max_tokens": 65535, - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, + "gemini-2.0-flash-live-preview-04-09": { + "cache_read_input_token_cost": 7.5e-08, + "input_cost_per_audio_token": 3e-06, + "input_cost_per_image": 3e-06, + "input_cost_per_token": 5e-07, + "input_cost_per_video_per_second": 3e-06, + "litellm_provider": "vertex_ai-language-models", "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, "max_pdf_size_mb": 30, - "input_cost_per_audio_token": 1.25e-06, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_audio_token": 1.2e-05, + "output_cost_per_token": 2e-06, + "rpm": 10, + "source": "https://cloud.google.com/vertex-ai/docs/generative-ai/model-reference/gemini#gemini-2-0-flash-live-preview-04-09", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text", + "audio" + ], + "supports_audio_output": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 250000 + }, + "gemini-2.0-flash-preview-image-generation": { + "cache_read_input_token_cost": 2.5e-08, + "input_cost_per_audio_token": 7e-07, + "input_cost_per_token": 1e-07, + "litellm_provider": "vertex_ai-language-models", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_token": 4e-07, + "source": "https://ai.google.dev/pricing#2_0flash", + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text", + "image" + ], + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "gemini-2.0-flash-thinking-exp": { + "cache_read_input_token_cost": 0.0, + "input_cost_per_audio_per_second": 0, + "input_cost_per_audio_per_second_above_128k_tokens": 0, + "input_cost_per_character": 0, + "input_cost_per_character_above_128k_tokens": 0, + "input_cost_per_image": 0, + "input_cost_per_image_above_128k_tokens": 0, + "input_cost_per_token": 0, + "input_cost_per_token_above_128k_tokens": 0, + "input_cost_per_video_per_second": 0, + "input_cost_per_video_per_second_above_128k_tokens": 0, + "litellm_provider": "vertex_ai-language-models", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_character": 0, + "output_cost_per_character_above_128k_tokens": 0, + "output_cost_per_token": 0, + "output_cost_per_token_above_128k_tokens": 0, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-2.0-flash", + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text", + "image" + ], + "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "gemini-2.0-flash-thinking-exp-01-21": { + "cache_read_input_token_cost": 0.0, + "input_cost_per_audio_per_second": 0, + "input_cost_per_audio_per_second_above_128k_tokens": 0, + "input_cost_per_character": 0, + "input_cost_per_character_above_128k_tokens": 0, + "input_cost_per_image": 0, + "input_cost_per_image_above_128k_tokens": 0, + "input_cost_per_token": 0, + "input_cost_per_token_above_128k_tokens": 0, + "input_cost_per_video_per_second": 0, + "input_cost_per_video_per_second_above_128k_tokens": 0, + "litellm_provider": "vertex_ai-language-models", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_pdf_size_mb": 30, + "max_tokens": 65536, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_character": 0, + "output_cost_per_character_above_128k_tokens": 0, + "output_cost_per_token": 0, + "output_cost_per_token_above_128k_tokens": 0, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-2.0-flash", + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text", + "image" + ], + "supports_audio_output": false, + "supports_function_calling": false, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": false, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "gemini-2.0-pro-exp-02-05": { + "cache_read_input_token_cost": 3.125e-07, "input_cost_per_token": 1.25e-06, "input_cost_per_token_above_200k_tokens": 2.5e-06, + "litellm_provider": "vertex_ai-language-models", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 2097152, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_above_200k_tokens": 1.5e-05, - "litellm_provider": "vertex_ai-language-models", - "mode": "chat", - "supports_reasoning": true, - "supports_system_messages": true, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true, "supports_function_calling": true, - "supports_vision": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, "supports_response_schema": true, - "supports_audio_output": false, + "supports_system_messages": true, "supports_tool_choice": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true + }, + "gemini-2.5-flash": { + "cache_read_input_token_cost": 7.5e-08, + "input_cost_per_audio_token": 1e-06, + "input_cost_per_token": 3e-07, + "litellm_provider": "vertex_ai-language-models", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_reasoning_token": 2.5e-06, + "output_cost_per_token": 2.5e-06, + "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -8721,37 +9029,396 @@ "supported_output_modalities": [ "text" ], - "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", + "supports_audio_output": false, + "supports_function_calling": true, "supports_parallel_function_calling": true, - "supports_web_search": true, "supports_pdf_input": true, - "cache_read_input_token_cost": 3.125e-07, - "supports_prompt_caching": true + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_vision": true, + "supports_web_search": true }, - "gemini-2.5-pro-preview-05-06": { - "max_tokens": 65535, - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, + "gemini-2.5-flash-image-preview": { + "cache_read_input_token_cost": 7.5e-08, + "input_cost_per_audio_token": 1e-06, + "input_cost_per_token": 3e-07, + "litellm_provider": "vertex_ai-language-models", "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_image": 0.039, + "output_cost_per_reasoning_token": 3e-05, + "output_cost_per_token": 3e-05, + "rpm": 100000, + "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text", + "image" + ], + "supports_audio_output": false, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 8000000 + }, + "gemini-2.5-flash-lite": { + "cache_read_input_token_cost": 2.5e-08, + "input_cost_per_audio_token": 5e-07, + "input_cost_per_token": 1e-07, + "litellm_provider": "vertex_ai-language-models", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_reasoning_token": 4e-07, + "output_cost_per_token": 4e-07, + "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_output": false, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_vision": true, + "supports_web_search": true + }, + "gemini-2.5-flash-lite-preview-06-17": { + "cache_read_input_token_cost": 2.5e-08, + "input_cost_per_audio_token": 5e-07, + "input_cost_per_token": 1e-07, + "litellm_provider": "vertex_ai-language-models", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_reasoning_token": 4e-07, + "output_cost_per_token": 4e-07, + "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_output": false, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_vision": true, + "supports_web_search": true + }, + "gemini-2.5-flash-preview-04-17": { + "cache_read_input_token_cost": 3.75e-08, + "input_cost_per_audio_token": 1e-06, + "input_cost_per_token": 1.5e-07, + "litellm_provider": "vertex_ai-language-models", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_reasoning_token": 3.5e-06, + "output_cost_per_token": 6e-07, + "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_output": false, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "gemini-2.5-flash-preview-05-20": { + "cache_read_input_token_cost": 7.5e-08, + "input_cost_per_audio_token": 1e-06, + "input_cost_per_token": 3e-07, + "litellm_provider": "vertex_ai-language-models", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_reasoning_token": 2.5e-06, + "output_cost_per_token": 2.5e-06, + "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_output": false, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_vision": true, + "supports_web_search": true + }, + "gemini-2.5-pro": { + "cache_read_input_token_cost": 3.125e-07, + "input_cost_per_token": 1.25e-06, + "input_cost_per_token_above_200k_tokens": 2.5e-06, + "litellm_provider": "vertex_ai-language-models", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_token": 1e-05, + "output_cost_per_token_above_200k_tokens": 1.5e-05, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true + }, + "gemini-2.5-pro-exp-03-25": { + "cache_read_input_token_cost": 3.125e-07, + "input_cost_per_token": 1.25e-06, + "input_cost_per_token_above_200k_tokens": 2.5e-06, + "litellm_provider": "vertex_ai-language-models", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_token": 1e-05, + "output_cost_per_token_above_200k_tokens": 1.5e-05, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true + }, + "gemini-2.5-pro-preview-03-25": { + "cache_read_input_token_cost": 3.125e-07, "input_cost_per_audio_token": 1.25e-06, "input_cost_per_token": 1.25e-06, "input_cost_per_token_above_200k_tokens": 2.5e-06, + "litellm_provider": "vertex_ai-language-models", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_above_200k_tokens": 1.5e-05, - "litellm_provider": "vertex_ai-language-models", - "mode": "chat", - "supports_reasoning": true, - "supports_system_messages": true, - "supports_function_calling": true, - "supports_vision": true, - "supports_response_schema": true, + "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], "supports_audio_output": false, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "gemini-2.5-pro-preview-05-06": { + "cache_read_input_token_cost": 3.125e-07, + "input_cost_per_audio_token": 1.25e-06, + "input_cost_per_token": 1.25e-06, + "input_cost_per_token_above_200k_tokens": 2.5e-06, + "litellm_provider": "vertex_ai-language-models", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_token": 1e-05, + "output_cost_per_token_above_200k_tokens": 1.5e-05, + "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -8769,37 +9436,37 @@ "supported_regions": [ "global" ], - "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", + "supports_audio_output": false, + "supports_function_calling": true, "supports_parallel_function_calling": true, - "supports_web_search": true, "supports_pdf_input": true, - "cache_read_input_token_cost": 3.125e-07, - "supports_prompt_caching": true + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true }, - "gemini-2.5-pro-preview-03-25": { - "max_tokens": 65535, - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_pdf_size_mb": 30, + "gemini-2.5-pro-preview-06-05": { + "cache_read_input_token_cost": 3.125e-07, "input_cost_per_audio_token": 1.25e-06, "input_cost_per_token": 1.25e-06, "input_cost_per_token_above_200k_tokens": 2.5e-06, + "litellm_provider": "vertex_ai-language-models", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_above_200k_tokens": 1.5e-05, - "litellm_provider": "vertex_ai-language-models", - "mode": "chat", - "supports_reasoning": true, - "supports_system_messages": true, - "supports_function_calling": true, - "supports_vision": true, - "supports_response_schema": true, - "supports_audio_output": false, - "supports_tool_choice": true, + "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -8814,794 +9481,678 @@ "supported_output_modalities": [ "text" ], - "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", + "supports_audio_output": false, + "supports_function_calling": true, "supports_parallel_function_calling": true, - "supports_web_search": true, "supports_pdf_input": true, - "cache_read_input_token_cost": 3.125e-07, - "supports_prompt_caching": true - }, - "gemini-2.0-flash-preview-image-generation": { - "max_tokens": 8192, - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_pdf_size_mb": 30, - "input_cost_per_audio_token": 7e-07, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 4e-07, - "litellm_provider": "vertex_ai-language-models", - "mode": "chat", - "supports_system_messages": true, - "supports_function_calling": true, - "supports_vision": true, - "supports_response_schema": true, - "supports_audio_output": true, - "supports_audio_input": true, - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text", - "image" - ], - "supports_tool_choice": true, - "source": "https://ai.google.dev/pricing#2_0flash", - "supports_parallel_function_calling": true, - "supports_web_search": true, - "cache_read_input_token_cost": 2.5e-08, - "supports_prompt_caching": true - }, - "gemini-2.5-pro-preview-tts": { - "max_tokens": 65535, - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_pdf_size_mb": 30, - "input_cost_per_audio_token": 7e-07, - "input_cost_per_token": 1.25e-06, - "input_cost_per_token_above_200k_tokens": 2.5e-06, - "output_cost_per_token": 1e-05, - "output_cost_per_token_above_200k_tokens": 1.5e-05, - "litellm_provider": "vertex_ai-language-models", - "mode": "chat", - "supports_system_messages": true, - "supports_function_calling": true, - "supports_vision": true, - "supports_response_schema": true, - "supports_audio_output": false, - "supports_tool_choice": true, - "supported_modalities": [ - "text" - ], - "supported_output_modalities": [ - "audio" - ], - "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-pro-preview", - "supports_parallel_function_calling": true, - "supports_web_search": true, - "cache_read_input_token_cost": 3.125e-07, - "supports_prompt_caching": true - }, - "gemini/gemini-2.0-pro-exp-02-05": { - "max_tokens": 8192, - "max_input_tokens": 2097152, - "max_output_tokens": 8192, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_pdf_size_mb": 30, - "input_cost_per_image": 0, - "input_cost_per_video_per_second": 0, - "input_cost_per_audio_per_second": 0, - "input_cost_per_token": 0, - "input_cost_per_character": 0, - "input_cost_per_token_above_128k_tokens": 0, - "input_cost_per_character_above_128k_tokens": 0, - "input_cost_per_image_above_128k_tokens": 0, - "input_cost_per_video_per_second_above_128k_tokens": 0, - "input_cost_per_audio_per_second_above_128k_tokens": 0, - "output_cost_per_token": 0, - "output_cost_per_character": 0, - "output_cost_per_token_above_128k_tokens": 0, - "output_cost_per_character_above_128k_tokens": 0, - "litellm_provider": "gemini", - "mode": "chat", - "rpm": 2, - "tpm": 1000000, - "supports_system_messages": true, - "supports_function_calling": true, - "supports_vision": true, - "supports_audio_input": true, - "supports_video_input": true, - "supports_pdf_input": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", - "supports_web_search": true, - "cache_read_input_token_cost": 0.0, - "supports_prompt_caching": true - }, - "gemini/gemini-2.0-flash-preview-image-generation": { - "max_tokens": 8192, - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_pdf_size_mb": 30, - "input_cost_per_audio_token": 7e-07, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 4e-07, - "litellm_provider": "gemini", - "mode": "chat", - "rpm": 10000, - "tpm": 10000000, - "supports_system_messages": true, - "supports_function_calling": true, - "supports_vision": true, - "supports_response_schema": true, - "supports_audio_output": true, - "supports_audio_input": true, - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text", - "image" - ], - "supports_tool_choice": true, - "source": "https://ai.google.dev/pricing#2_0flash", - "supports_web_search": true, - "cache_read_input_token_cost": 2.5e-08, - "supports_prompt_caching": true - }, - "gemini/gemini-2.0-flash": { - "max_tokens": 8192, - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_pdf_size_mb": 30, - "input_cost_per_audio_token": 7e-07, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 4e-07, - "litellm_provider": "gemini", - "mode": "chat", - "rpm": 10000, - "tpm": 10000000, - "supports_system_messages": true, - "supports_function_calling": true, - "supports_vision": true, - "supports_response_schema": true, - "supports_audio_output": true, - "supports_audio_input": true, - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text", - "image" - ], - "supports_tool_choice": true, - "source": "https://ai.google.dev/pricing#2_0flash", - "supports_web_search": true, - "supports_url_context": true, - "cache_read_input_token_cost": 2.5e-08, - "supports_prompt_caching": true - }, - "gemini/gemini-2.0-flash-lite": { - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_pdf_size_mb": 50, - "input_cost_per_audio_token": 7.5e-08, - "input_cost_per_token": 7.5e-08, - "output_cost_per_token": 3e-07, - "litellm_provider": "gemini", - "mode": "chat", - "tpm": 4000000, - "rpm": 4000, - "supports_system_messages": true, - "supports_function_calling": true, - "supports_vision": true, - "supports_response_schema": true, - "supports_audio_output": true, - "supports_tool_choice": true, - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.0-flash-lite", - "supports_web_search": true, - "cache_read_input_token_cost": 1.875e-08, - "supports_prompt_caching": true - }, - "gemini/gemini-2.0-flash-001": { - "max_tokens": 8192, - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_pdf_size_mb": 30, - "input_cost_per_audio_token": 7e-07, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 4e-07, - "litellm_provider": "gemini", - "mode": "chat", - "rpm": 10000, - "tpm": 10000000, - "supports_system_messages": true, - "supports_function_calling": true, - "supports_vision": true, - "supports_response_schema": true, - "supports_audio_output": false, - "supports_tool_choice": true, - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text", - "image" - ], - "source": "https://ai.google.dev/pricing#2_0flash", - "supports_web_search": true, - "cache_read_input_token_cost": 2.5e-08, - "supports_prompt_caching": true - }, - "gemini/gemini-2.5-pro-preview-tts": { - "max_tokens": 65535, - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_pdf_size_mb": 30, - "input_cost_per_audio_token": 7e-07, - "input_cost_per_token": 1.25e-06, - "input_cost_per_token_above_200k_tokens": 2.5e-06, - "output_cost_per_token": 1e-05, - "output_cost_per_token_above_200k_tokens": 1.5e-05, - "litellm_provider": "gemini", - "mode": "chat", - "rpm": 10000, - "tpm": 10000000, - "supports_system_messages": true, - "supports_function_calling": true, - "supports_vision": true, - "supports_response_schema": true, - "supports_audio_output": false, - "supports_tool_choice": true, - "supported_modalities": [ - "text" - ], - "supported_output_modalities": [ - "audio" - ], - "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-pro-preview", - "supports_web_search": true, - "cache_read_input_token_cost": 3.125e-07, - "supports_prompt_caching": true - }, - "gemini/gemini-2.5-pro-preview-06-05": { - "max_tokens": 65535, - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_pdf_size_mb": 30, - "input_cost_per_audio_token": 7e-07, - "input_cost_per_token": 1.25e-06, - "input_cost_per_token_above_200k_tokens": 2.5e-06, - "output_cost_per_token": 1e-05, - "output_cost_per_token_above_200k_tokens": 1.5e-05, - "litellm_provider": "gemini", - "mode": "chat", - "rpm": 10000, - "tpm": 10000000, - "supports_system_messages": true, - "supports_function_calling": true, - "supports_vision": true, - "supports_response_schema": true, - "supports_audio_output": false, - "supports_tool_choice": true, - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-pro-preview", - "supports_web_search": true, - "supports_url_context": true, - "supports_pdf_input": true, - "cache_read_input_token_cost": 3.125e-07, - "supports_prompt_caching": true - }, - "gemini/gemini-2.5-pro-preview-05-06": { - "max_tokens": 65535, - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_pdf_size_mb": 30, - "input_cost_per_audio_token": 7e-07, - "input_cost_per_token": 1.25e-06, - "input_cost_per_token_above_200k_tokens": 2.5e-06, - "output_cost_per_token": 1e-05, - "output_cost_per_token_above_200k_tokens": 1.5e-05, - "litellm_provider": "gemini", - "mode": "chat", - "rpm": 10000, - "tpm": 10000000, - "supports_system_messages": true, - "supports_function_calling": true, - "supports_vision": true, - "supports_response_schema": true, - "supports_audio_output": false, - "supports_tool_choice": true, - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-pro-preview", - "supports_web_search": true, - "supports_url_context": true, - "supports_pdf_input": true, - "cache_read_input_token_cost": 3.125e-07, - "supports_prompt_caching": true - }, - "gemini/gemini-2.5-pro-preview-03-25": { - "max_tokens": 65535, - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_pdf_size_mb": 30, - "input_cost_per_audio_token": 7e-07, - "input_cost_per_token": 1.25e-06, - "input_cost_per_token_above_200k_tokens": 2.5e-06, - "output_cost_per_token": 1e-05, - "output_cost_per_token_above_200k_tokens": 1.5e-05, - "litellm_provider": "gemini", - "mode": "chat", - "rpm": 10000, - "tpm": 10000000, - "supports_system_messages": true, - "supports_function_calling": true, - "supports_vision": true, - "supports_response_schema": true, - "supports_audio_output": false, - "supports_tool_choice": true, - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-pro-preview", - "supports_web_search": true, - "supports_pdf_input": true, - "cache_read_input_token_cost": 3.125e-07, - "supports_prompt_caching": true - }, - "gemini/gemini-2.0-flash-exp": { - "max_tokens": 8192, - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_pdf_size_mb": 30, - "input_cost_per_image": 0, - "input_cost_per_video_per_second": 0, - "input_cost_per_audio_per_second": 0, - "input_cost_per_token": 0, - "input_cost_per_character": 0, - "input_cost_per_token_above_128k_tokens": 0, - "input_cost_per_character_above_128k_tokens": 0, - "input_cost_per_image_above_128k_tokens": 0, - "input_cost_per_video_per_second_above_128k_tokens": 0, - "input_cost_per_audio_per_second_above_128k_tokens": 0, - "output_cost_per_token": 0, - "output_cost_per_character": 0, - "output_cost_per_token_above_128k_tokens": 0, - "output_cost_per_character_above_128k_tokens": 0, - "litellm_provider": "gemini", - "mode": "chat", - "supports_system_messages": true, - "supports_function_calling": true, - "supports_vision": true, - "supports_response_schema": true, - "supports_audio_output": true, - "tpm": 4000000, - "rpm": 10, - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text", - "image" - ], - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-2.0-flash", - "supports_tool_choice": true, - "supports_web_search": true, - "cache_read_input_token_cost": 0.0, - "supports_prompt_caching": true - }, - "gemini/gemini-2.0-flash-lite-preview-02-05": { - "max_tokens": 8192, - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_pdf_size_mb": 30, - "input_cost_per_audio_token": 7.5e-08, - "input_cost_per_token": 7.5e-08, - "output_cost_per_token": 3e-07, - "litellm_provider": "gemini", - "mode": "chat", - "rpm": 60000, - "tpm": 10000000, - "supports_system_messages": true, - "supports_function_calling": true, - "supports_vision": true, - "supports_response_schema": true, - "supports_audio_output": false, - "supports_tool_choice": true, - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-2.0-flash-lite", - "supports_web_search": true, - "cache_read_input_token_cost": 1.875e-08, - "supports_prompt_caching": true - }, - "gemini/gemini-2.0-flash-thinking-exp": { - "max_tokens": 8192, - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_pdf_size_mb": 30, - "input_cost_per_image": 0, - "input_cost_per_video_per_second": 0, - "input_cost_per_audio_per_second": 0, - "input_cost_per_token": 0, - "input_cost_per_character": 0, - "input_cost_per_token_above_128k_tokens": 0, - "input_cost_per_character_above_128k_tokens": 0, - "input_cost_per_image_above_128k_tokens": 0, - "input_cost_per_video_per_second_above_128k_tokens": 0, - "input_cost_per_audio_per_second_above_128k_tokens": 0, - "output_cost_per_token": 0, - "output_cost_per_character": 0, - "output_cost_per_token_above_128k_tokens": 0, - "output_cost_per_character_above_128k_tokens": 0, - "litellm_provider": "gemini", - "mode": "chat", - "supports_system_messages": true, - "supports_function_calling": true, - "supports_vision": true, - "supports_response_schema": true, - "supports_audio_output": true, - "tpm": 4000000, - "rpm": 10, - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text", - "image" - ], - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-2.0-flash", - "supports_tool_choice": true, - "supports_web_search": true, - "cache_read_input_token_cost": 0.0, - "supports_prompt_caching": true - }, - "gemini/gemini-2.0-flash-thinking-exp-01-21": { - "max_tokens": 8192, - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_pdf_size_mb": 30, - "input_cost_per_image": 0, - "input_cost_per_video_per_second": 0, - "input_cost_per_audio_per_second": 0, - "input_cost_per_token": 0, - "input_cost_per_character": 0, - "input_cost_per_token_above_128k_tokens": 0, - "input_cost_per_character_above_128k_tokens": 0, - "input_cost_per_image_above_128k_tokens": 0, - "input_cost_per_video_per_second_above_128k_tokens": 0, - "input_cost_per_audio_per_second_above_128k_tokens": 0, - "output_cost_per_token": 0, - "output_cost_per_character": 0, - "output_cost_per_token_above_128k_tokens": 0, - "output_cost_per_character_above_128k_tokens": 0, - "litellm_provider": "gemini", - "mode": "chat", - "supports_system_messages": true, - "supports_function_calling": true, - "supports_vision": true, - "supports_response_schema": true, - "supports_audio_output": true, - "tpm": 4000000, - "rpm": 10, - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text", - "image" - ], - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-2.0-flash", - "supports_tool_choice": true, - "supports_web_search": true, - "cache_read_input_token_cost": 0.0, - "supports_prompt_caching": true - }, - "gemini/gemma-3-27b-it": { - "max_tokens": 8192, - "max_input_tokens": 131072, - "max_output_tokens": 8192, - "input_cost_per_image": 0, - "input_cost_per_video_per_second": 0, - "input_cost_per_audio_per_second": 0, - "input_cost_per_token": 0, - "input_cost_per_character": 0, - "input_cost_per_token_above_128k_tokens": 0, - "input_cost_per_character_above_128k_tokens": 0, - "input_cost_per_image_above_128k_tokens": 0, - "input_cost_per_video_per_second_above_128k_tokens": 0, - "input_cost_per_audio_per_second_above_128k_tokens": 0, - "output_cost_per_token": 0, - "output_cost_per_character": 0, - "output_cost_per_token_above_128k_tokens": 0, - "output_cost_per_character_above_128k_tokens": 0, - "litellm_provider": "gemini", - "mode": "chat", - "supports_system_messages": true, - "supports_function_calling": true, - "supports_vision": true, - "supports_response_schema": true, - "supports_audio_output": false, - "source": "https://aistudio.google.com", - "supports_tool_choice": true - }, - "gemini/learnlm-1.5-pro-experimental": { - "max_tokens": 8192, - "max_input_tokens": 32767, - "max_output_tokens": 8192, - "input_cost_per_image": 0, - "input_cost_per_video_per_second": 0, - "input_cost_per_audio_per_second": 0, - "input_cost_per_token": 0, - "input_cost_per_character": 0, - "input_cost_per_token_above_128k_tokens": 0, - "input_cost_per_character_above_128k_tokens": 0, - "input_cost_per_image_above_128k_tokens": 0, - "input_cost_per_video_per_second_above_128k_tokens": 0, - "input_cost_per_audio_per_second_above_128k_tokens": 0, - "output_cost_per_token": 0, - "output_cost_per_character": 0, - "output_cost_per_token_above_128k_tokens": 0, - "output_cost_per_character_above_128k_tokens": 0, - "litellm_provider": "gemini", - "mode": "chat", - "supports_system_messages": true, - "supports_function_calling": true, - "supports_vision": true, - "supports_response_schema": true, - "supports_audio_output": false, - "source": "https://aistudio.google.com", - "supports_tool_choice": true - }, - "gemini/veo-3.0-generate-preview": { - "max_tokens": 1024, - "max_input_tokens": 1024, - "output_cost_per_second": 0.75, - "litellm_provider": "gemini", - "mode": "video_generation", - "supported_modalities": [ - "text" - ], - "supported_output_modalities": [ - "video" - ], - "source": "https://ai.google.dev/gemini-api/docs/video" - }, - "gemini/veo-3.0-fast-generate-preview": { - "max_tokens": 1024, - "max_input_tokens": 1024, - "output_cost_per_second": 0.40, - "litellm_provider": "gemini", - "mode": "video_generation", - "supported_modalities": [ - "text" - ], - "supported_output_modalities": [ - "video" - ], - "source": "https://ai.google.dev/gemini-api/docs/video" - }, - "gemini/veo-2.0-generate-001": { - "max_tokens": 1024, - "max_input_tokens": 1024, - "output_cost_per_second": 0.35, - "litellm_provider": "gemini", - "mode": "video_generation", - "supported_modalities": [ - "text" - ], - "supported_output_modalities": [ - "video" - ], - "source": "https://ai.google.dev/gemini-api/docs/video" - }, - "vertex_ai/claude-opus-4-1": { - "max_tokens": 4096, - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "input_cost_per_token": 15e-06, - "output_cost_per_token": 75e-06, - "input_cost_per_token_batches": 7.5e-06, - "output_cost_per_token_batches": 37.5e-06, - "cache_creation_input_token_cost": 1.875e-05, - "cache_read_input_token_cost": 1.5e-06, - "litellm_provider": "vertex_ai-anthropic_models", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "supports_assistant_prefill": true, - "supports_tool_choice": true - }, - "vertex_ai/claude-opus-4-1@20250805": { - "max_tokens": 4096, - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "input_cost_per_token": 15e-06, - "output_cost_per_token": 75e-06, - "input_cost_per_token_batches": 7.5e-06, - "output_cost_per_token_batches": 37.5e-06, - "cache_creation_input_token_cost": 1.875e-05, - "cache_read_input_token_cost": 1.5e-06, - "litellm_provider": "vertex_ai-anthropic_models", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "supports_assistant_prefill": true, - "supports_tool_choice": true - }, - "vertex_ai/claude-3-sonnet": { - "max_tokens": 4096, - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "litellm_provider": "vertex_ai-anthropic_models", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "supports_assistant_prefill": true, - "supports_tool_choice": true - }, - "gemini-2.0-flash-live-preview-04-09": { - "max_tokens": 65535, - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_pdf_size_mb": 30, - "input_cost_per_token": 5e-07, - "input_cost_per_audio_token": 3e-06, - "input_cost_per_image": 3e-06, - "input_cost_per_video_per_second": 3e-06, - "output_cost_per_token": 2e-06, - "output_cost_per_audio_token": 1.2e-05, - "litellm_provider": "vertex_ai-language-models", - "mode": "chat", - "rpm": 10, - "tpm": 250000, - "supports_system_messages": true, - "supports_function_calling": true, - "supports_vision": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_audio_output": true, + "supports_system_messages": true, "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "gemini-2.5-pro-preview-tts": { + "cache_read_input_token_cost": 3.125e-07, + "input_cost_per_audio_token": 7e-07, + "input_cost_per_token": 1.25e-06, + "input_cost_per_token_above_200k_tokens": 2.5e-06, + "litellm_provider": "vertex_ai-language-models", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_token": 1e-05, + "output_cost_per_token_above_200k_tokens": 1.5e-05, + "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-pro-preview", + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "audio" + ], + "supports_audio_output": false, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "gemini-embedding-001": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "vertex_ai-embedding-models", + "max_input_tokens": 2048, + "max_tokens": 2048, + "mode": "embedding", + "output_cost_per_token": 0, + "output_vector_size": 3072, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models" + }, + "gemini-flash-experimental": { + "input_cost_per_character": 0, + "input_cost_per_token": 0, + "litellm_provider": "vertex_ai-language-models", + "max_input_tokens": 1000000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_character": 0, + "output_cost_per_token": 0, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/multimodal/gemini-experimental", + "supports_function_calling": false, + "supports_parallel_function_calling": true, + "supports_tool_choice": true + }, + "gemini-pro": { + "input_cost_per_character": 1.25e-07, + "input_cost_per_image": 0.0025, + "input_cost_per_token": 5e-07, + "input_cost_per_video_per_second": 0.002, + "litellm_provider": "vertex_ai-language-models", + "max_input_tokens": 32760, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_character": 3.75e-07, + "output_cost_per_token": 1.5e-06, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true + }, + "gemini-pro-experimental": { + "input_cost_per_character": 0, + "input_cost_per_token": 0, + "litellm_provider": "vertex_ai-language-models", + "max_input_tokens": 1000000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_character": 0, + "output_cost_per_token": 0, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/multimodal/gemini-experimental", + "supports_function_calling": false, + "supports_parallel_function_calling": true, + "supports_tool_choice": true + }, + "gemini-pro-vision": { + "input_cost_per_image": 0.0025, + "input_cost_per_token": 5e-07, + "litellm_provider": "vertex_ai-vision-models", + "max_images_per_prompt": 16, + "max_input_tokens": 16384, + "max_output_tokens": 2048, + "max_tokens": 2048, + "max_video_length": 2, + "max_videos_per_prompt": 1, + "mode": "chat", + "output_cost_per_token": 1.5e-06, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "gemini/gemini-1.5-flash": { + "input_cost_per_token": 7.5e-08, + "input_cost_per_token_above_128k_tokens": 1.5e-07, + "litellm_provider": "gemini", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_token": 3e-07, + "output_cost_per_token_above_128k_tokens": 6e-07, + "rpm": 2000, + "source": "https://ai.google.dev/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "tpm": 4000000 + }, + "gemini/gemini-1.5-flash-001": { + "cache_creation_input_token_cost": 1e-06, + "cache_read_input_token_cost": 1.875e-08, + "deprecation_date": "2025-05-24", + "input_cost_per_token": 7.5e-08, + "input_cost_per_token_above_128k_tokens": 1.5e-07, + "litellm_provider": "gemini", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_token": 3e-07, + "output_cost_per_token_above_128k_tokens": 6e-07, + "rpm": 2000, + "source": "https://ai.google.dev/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "tpm": 4000000 + }, + "gemini/gemini-1.5-flash-002": { + "cache_creation_input_token_cost": 1e-06, + "cache_read_input_token_cost": 1.875e-08, + "deprecation_date": "2025-09-24", + "input_cost_per_token": 7.5e-08, + "input_cost_per_token_above_128k_tokens": 1.5e-07, + "litellm_provider": "gemini", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_token": 3e-07, + "output_cost_per_token_above_128k_tokens": 6e-07, + "rpm": 2000, + "source": "https://ai.google.dev/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "tpm": 4000000 + }, + "gemini/gemini-1.5-flash-8b": { + "input_cost_per_token": 0, + "input_cost_per_token_above_128k_tokens": 0, + "litellm_provider": "gemini", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_token": 0, + "output_cost_per_token_above_128k_tokens": 0, + "rpm": 4000, + "source": "https://ai.google.dev/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "tpm": 4000000 + }, + "gemini/gemini-1.5-flash-8b-exp-0827": { + "input_cost_per_token": 0, + "input_cost_per_token_above_128k_tokens": 0, + "litellm_provider": "gemini", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1000000, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_token": 0, + "output_cost_per_token_above_128k_tokens": 0, + "rpm": 4000, + "source": "https://ai.google.dev/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "tpm": 4000000 + }, + "gemini/gemini-1.5-flash-8b-exp-0924": { + "input_cost_per_token": 0, + "input_cost_per_token_above_128k_tokens": 0, + "litellm_provider": "gemini", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_token": 0, + "output_cost_per_token_above_128k_tokens": 0, + "rpm": 4000, + "source": "https://ai.google.dev/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "tpm": 4000000 + }, + "gemini/gemini-1.5-flash-exp-0827": { + "input_cost_per_token": 0, + "input_cost_per_token_above_128k_tokens": 0, + "litellm_provider": "gemini", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_token": 0, + "output_cost_per_token_above_128k_tokens": 0, + "rpm": 2000, + "source": "https://ai.google.dev/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "tpm": 4000000 + }, + "gemini/gemini-1.5-flash-latest": { + "input_cost_per_token": 7.5e-08, + "input_cost_per_token_above_128k_tokens": 1.5e-07, + "litellm_provider": "gemini", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_token": 3e-07, + "output_cost_per_token_above_128k_tokens": 6e-07, + "rpm": 2000, + "source": "https://ai.google.dev/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "tpm": 4000000 + }, + "gemini/gemini-1.5-pro": { + "input_cost_per_token": 3.5e-06, + "input_cost_per_token_above_128k_tokens": 7e-06, + "litellm_provider": "gemini", + "max_input_tokens": 2097152, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.05e-05, + "output_cost_per_token_above_128k_tokens": 2.1e-05, + "rpm": 1000, + "source": "https://ai.google.dev/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "tpm": 4000000 + }, + "gemini/gemini-1.5-pro-001": { + "deprecation_date": "2025-05-24", + "input_cost_per_token": 3.5e-06, + "input_cost_per_token_above_128k_tokens": 7e-06, + "litellm_provider": "gemini", + "max_input_tokens": 2097152, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.05e-05, + "output_cost_per_token_above_128k_tokens": 2.1e-05, + "rpm": 1000, + "source": "https://ai.google.dev/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "tpm": 4000000 + }, + "gemini/gemini-1.5-pro-002": { + "deprecation_date": "2025-09-24", + "input_cost_per_token": 3.5e-06, + "input_cost_per_token_above_128k_tokens": 7e-06, + "litellm_provider": "gemini", + "max_input_tokens": 2097152, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.05e-05, + "output_cost_per_token_above_128k_tokens": 2.1e-05, + "rpm": 1000, + "source": "https://ai.google.dev/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "tpm": 4000000 + }, + "gemini/gemini-1.5-pro-exp-0801": { + "input_cost_per_token": 3.5e-06, + "input_cost_per_token_above_128k_tokens": 7e-06, + "litellm_provider": "gemini", + "max_input_tokens": 2097152, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.05e-05, + "output_cost_per_token_above_128k_tokens": 2.1e-05, + "rpm": 1000, + "source": "https://ai.google.dev/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "tpm": 4000000 + }, + "gemini/gemini-1.5-pro-exp-0827": { + "input_cost_per_token": 0, + "input_cost_per_token_above_128k_tokens": 0, + "litellm_provider": "gemini", + "max_input_tokens": 2097152, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0, + "output_cost_per_token_above_128k_tokens": 0, + "rpm": 1000, + "source": "https://ai.google.dev/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "tpm": 4000000 + }, + "gemini/gemini-1.5-pro-latest": { + "input_cost_per_token": 3.5e-06, + "input_cost_per_token_above_128k_tokens": 7e-06, + "litellm_provider": "gemini", + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.05e-06, + "output_cost_per_token_above_128k_tokens": 2.1e-05, + "rpm": 1000, + "source": "https://ai.google.dev/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "tpm": 4000000 + }, + "gemini/gemini-2.0-flash": { + "cache_read_input_token_cost": 2.5e-08, + "input_cost_per_audio_token": 7e-07, + "input_cost_per_token": 1e-07, + "litellm_provider": "gemini", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_token": 4e-07, + "rpm": 10000, + "source": "https://ai.google.dev/pricing#2_0flash", + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text", + "image" + ], + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 10000000 + }, + "gemini/gemini-2.0-flash-001": { + "cache_read_input_token_cost": 2.5e-08, + "input_cost_per_audio_token": 7e-07, + "input_cost_per_token": 1e-07, + "litellm_provider": "gemini", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_token": 4e-07, + "rpm": 10000, + "source": "https://ai.google.dev/pricing#2_0flash", + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text", + "image" + ], + "supports_audio_output": false, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 10000000 + }, + "gemini/gemini-2.0-flash-exp": { + "cache_read_input_token_cost": 0.0, + "input_cost_per_audio_per_second": 0, + "input_cost_per_audio_per_second_above_128k_tokens": 0, + "input_cost_per_character": 0, + "input_cost_per_character_above_128k_tokens": 0, + "input_cost_per_image": 0, + "input_cost_per_image_above_128k_tokens": 0, + "input_cost_per_token": 0, + "input_cost_per_token_above_128k_tokens": 0, + "input_cost_per_video_per_second": 0, + "input_cost_per_video_per_second_above_128k_tokens": 0, + "litellm_provider": "gemini", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_character": 0, + "output_cost_per_character_above_128k_tokens": 0, + "output_cost_per_token": 0, + "output_cost_per_token_above_128k_tokens": 0, + "rpm": 10, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-2.0-flash", + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text", + "image" + ], + "supports_audio_output": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 4000000 + }, + "gemini/gemini-2.0-flash-lite": { + "cache_read_input_token_cost": 1.875e-08, + "input_cost_per_audio_token": 7.5e-08, + "input_cost_per_token": 7.5e-08, + "litellm_provider": "gemini", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_pdf_size_mb": 50, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_token": 3e-07, + "rpm": 4000, + "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.0-flash-lite", + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_output": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 4000000 + }, + "gemini/gemini-2.0-flash-lite-preview-02-05": { + "cache_read_input_token_cost": 1.875e-08, + "input_cost_per_audio_token": 7.5e-08, + "input_cost_per_token": 7.5e-08, + "litellm_provider": "gemini", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_token": 3e-07, + "rpm": 60000, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-2.0-flash-lite", + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_output": false, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 10000000 + }, + "gemini/gemini-2.0-flash-live-001": { + "cache_read_input_token_cost": 7.5e-08, + "input_cost_per_audio_token": 2.1e-06, + "input_cost_per_image": 2.1e-06, + "input_cost_per_token": 3.5e-07, + "input_cost_per_video_per_second": 2.1e-06, + "litellm_provider": "gemini", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_audio_token": 8.5e-06, + "output_cost_per_token": 1.5e-06, + "rpm": 10, + "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2-0-flash-live-001", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions" @@ -9616,11386 +10167,11104 @@ "text", "audio" ], - "source": "https://cloud.google.com/vertex-ai/docs/generative-ai/model-reference/gemini#gemini-2-0-flash-live-preview-04-09", - "supports_web_search": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, "supports_url_context": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 250000 + }, + "gemini/gemini-2.0-flash-preview-image-generation": { + "cache_read_input_token_cost": 2.5e-08, + "input_cost_per_audio_token": 7e-07, + "input_cost_per_token": 1e-07, + "litellm_provider": "gemini", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_token": 4e-07, + "rpm": 10000, + "source": "https://ai.google.dev/pricing#2_0flash", + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text", + "image" + ], + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 10000000 + }, + "gemini/gemini-2.0-flash-thinking-exp": { + "cache_read_input_token_cost": 0.0, + "input_cost_per_audio_per_second": 0, + "input_cost_per_audio_per_second_above_128k_tokens": 0, + "input_cost_per_character": 0, + "input_cost_per_character_above_128k_tokens": 0, + "input_cost_per_image": 0, + "input_cost_per_image_above_128k_tokens": 0, + "input_cost_per_token": 0, + "input_cost_per_token_above_128k_tokens": 0, + "input_cost_per_video_per_second": 0, + "input_cost_per_video_per_second_above_128k_tokens": 0, + "litellm_provider": "gemini", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_character": 0, + "output_cost_per_character_above_128k_tokens": 0, + "output_cost_per_token": 0, + "output_cost_per_token_above_128k_tokens": 0, + "rpm": 10, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-2.0-flash", + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text", + "image" + ], + "supports_audio_output": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 4000000 + }, + "gemini/gemini-2.0-flash-thinking-exp-01-21": { + "cache_read_input_token_cost": 0.0, + "input_cost_per_audio_per_second": 0, + "input_cost_per_audio_per_second_above_128k_tokens": 0, + "input_cost_per_character": 0, + "input_cost_per_character_above_128k_tokens": 0, + "input_cost_per_image": 0, + "input_cost_per_image_above_128k_tokens": 0, + "input_cost_per_token": 0, + "input_cost_per_token_above_128k_tokens": 0, + "input_cost_per_video_per_second": 0, + "input_cost_per_video_per_second_above_128k_tokens": 0, + "litellm_provider": "gemini", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_character": 0, + "output_cost_per_character_above_128k_tokens": 0, + "output_cost_per_token": 0, + "output_cost_per_token_above_128k_tokens": 0, + "rpm": 10, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-2.0-flash", + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text", + "image" + ], + "supports_audio_output": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 4000000 + }, + "gemini/gemini-2.0-pro-exp-02-05": { + "cache_read_input_token_cost": 0.0, + "input_cost_per_audio_per_second": 0, + "input_cost_per_audio_per_second_above_128k_tokens": 0, + "input_cost_per_character": 0, + "input_cost_per_character_above_128k_tokens": 0, + "input_cost_per_image": 0, + "input_cost_per_image_above_128k_tokens": 0, + "input_cost_per_token": 0, + "input_cost_per_token_above_128k_tokens": 0, + "input_cost_per_video_per_second": 0, + "input_cost_per_video_per_second_above_128k_tokens": 0, + "litellm_provider": "gemini", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 2097152, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_character": 0, + "output_cost_per_character_above_128k_tokens": 0, + "output_cost_per_token": 0, + "output_cost_per_token_above_128k_tokens": 0, + "rpm": 2, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "supports_audio_input": true, + "supports_function_calling": true, "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 1000000 + }, + "gemini/gemini-2.5-flash": { "cache_read_input_token_cost": 7.5e-08, - "supports_prompt_caching": true - }, - "vertex_ai/claude-3-sonnet@20240229": { - "max_tokens": 4096, - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "litellm_provider": "vertex_ai-anthropic_models", + "input_cost_per_audio_token": 1e-06, + "input_cost_per_token": 3e-07, + "litellm_provider": "gemini", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "supports_assistant_prefill": true, - "supports_tool_choice": true - }, - "vertex_ai/claude-3-5-sonnet": { - "supports_computer_use": true, - "max_tokens": 8192, - "max_input_tokens": 200000, - "max_output_tokens": 8192, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "litellm_provider": "vertex_ai-anthropic_models", - "mode": "chat", - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_vision": true, - "supports_assistant_prefill": true, - "supports_tool_choice": true - }, - "vertex_ai/claude-3-5-sonnet@20240620": { - "max_tokens": 8192, - "max_input_tokens": 200000, - "max_output_tokens": 8192, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "litellm_provider": "vertex_ai-anthropic_models", - "mode": "chat", - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_vision": true, - "supports_assistant_prefill": true, - "supports_tool_choice": true - }, - "vertex_ai/claude-3-5-sonnet-v2": { - "supports_computer_use": true, - "max_tokens": 8192, - "max_input_tokens": 200000, - "max_output_tokens": 8192, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "litellm_provider": "vertex_ai-anthropic_models", - "mode": "chat", - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_vision": true, - "supports_assistant_prefill": true, - "supports_tool_choice": true - }, - "vertex_ai/claude-3-5-sonnet-v2@20241022": { - "supports_computer_use": true, - "max_tokens": 8192, - "max_input_tokens": 200000, - "max_output_tokens": 8192, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "litellm_provider": "vertex_ai-anthropic_models", - "mode": "chat", - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_vision": true, - "supports_assistant_prefill": true, - "supports_tool_choice": true - }, - "vertex_ai/claude-3-7-sonnet@20250219": { - "supports_computer_use": true, - "max_tokens": 8192, - "max_input_tokens": 200000, - "max_output_tokens": 8192, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "cache_creation_input_token_cost": 3.75e-06, - "cache_read_input_token_cost": 3e-07, - "litellm_provider": "vertex_ai-anthropic_models", - "mode": "chat", - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 159, - "supports_assistant_prefill": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "deprecation_date": "2025-06-01", - "supports_reasoning": true, - "supports_tool_choice": true - }, - "vertex_ai/claude-opus-4": { - "max_tokens": 32000, - "max_input_tokens": 200000, - "max_output_tokens": 32000, - "input_cost_per_token": 1.5e-05, - "output_cost_per_token": 7.5e-05, - "search_context_cost_per_query": { - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01, - "search_context_size_high": 0.01 - }, - "cache_creation_input_token_cost": 1.875e-05, - "cache_read_input_token_cost": 1.5e-06, - "litellm_provider": "vertex_ai-anthropic_models", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 159, - "supports_assistant_prefill": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_computer_use": true - }, - "vertex_ai/claude-opus-4@20250514": { - "max_tokens": 32000, - "max_input_tokens": 200000, - "max_output_tokens": 32000, - "input_cost_per_token": 1.5e-05, - "output_cost_per_token": 7.5e-05, - "search_context_cost_per_query": { - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01, - "search_context_size_high": 0.01 - }, - "cache_creation_input_token_cost": 1.875e-05, - "cache_read_input_token_cost": 1.5e-06, - "litellm_provider": "vertex_ai-anthropic_models", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 159, - "supports_assistant_prefill": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_computer_use": true - }, - "vertex_ai/claude-sonnet-4": { - "max_tokens": 64000, - "max_input_tokens": 200000, - "max_output_tokens": 64000, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "search_context_cost_per_query": { - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01, - "search_context_size_high": 0.01 - }, - "cache_creation_input_token_cost": 3.75e-06, - "cache_read_input_token_cost": 3e-07, - "litellm_provider": "vertex_ai-anthropic_models", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 159, - "supports_assistant_prefill": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_computer_use": true - }, - "vertex_ai/claude-sonnet-4@20250514": { - "max_tokens": 64000, - "max_input_tokens": 200000, - "max_output_tokens": 64000, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "search_context_cost_per_query": { - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01, - "search_context_size_high": 0.01 - }, - "cache_creation_input_token_cost": 3.75e-06, - "cache_read_input_token_cost": 3e-07, - "litellm_provider": "vertex_ai-anthropic_models", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 159, - "supports_assistant_prefill": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_computer_use": true - }, - "vertex_ai/claude-3-haiku": { - "max_tokens": 4096, - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "input_cost_per_token": 2.5e-07, - "output_cost_per_token": 1.25e-06, - "litellm_provider": "vertex_ai-anthropic_models", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "supports_assistant_prefill": true, - "supports_tool_choice": true - }, - "vertex_ai/claude-3-haiku@20240307": { - "max_tokens": 4096, - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "input_cost_per_token": 2.5e-07, - "output_cost_per_token": 1.25e-06, - "litellm_provider": "vertex_ai-anthropic_models", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "supports_assistant_prefill": true, - "supports_tool_choice": true - }, - "vertex_ai/claude-3-5-haiku": { - "max_tokens": 8192, - "max_input_tokens": 200000, - "max_output_tokens": 8192, - "input_cost_per_token": 1e-06, - "output_cost_per_token": 5e-06, - "litellm_provider": "vertex_ai-anthropic_models", - "mode": "chat", - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_assistant_prefill": true, - "supports_tool_choice": true - }, - "vertex_ai/claude-3-5-haiku@20241022": { - "max_tokens": 8192, - "max_input_tokens": 200000, - "max_output_tokens": 8192, - "input_cost_per_token": 1e-06, - "output_cost_per_token": 5e-06, - "litellm_provider": "vertex_ai-anthropic_models", - "mode": "chat", - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_assistant_prefill": true, - "supports_tool_choice": true - }, - "vertex_ai/claude-3-opus": { - "max_tokens": 4096, - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "input_cost_per_token": 1.5e-05, - "output_cost_per_token": 7.5e-05, - "litellm_provider": "vertex_ai-anthropic_models", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "supports_assistant_prefill": true, - "supports_tool_choice": true - }, - "vertex_ai/claude-3-opus@20240229": { - "max_tokens": 4096, - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "input_cost_per_token": 1.5e-05, - "output_cost_per_token": 7.5e-05, - "litellm_provider": "vertex_ai-anthropic_models", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "supports_assistant_prefill": true, - "supports_tool_choice": true - }, - "vertex_ai/deepseek-ai/deepseek-r1-0528-maas": { - "max_tokens": 8192, - "max_input_tokens": 65336, - "max_output_tokens": 8192, - "input_cost_per_token": 1.35e-06, - "output_cost_per_token": 5.4e-06, - "litellm_provider": "vertex_ai-deepseek_models", - "mode": "chat", - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", - "supports_function_calling": true, - "supports_assistant_prefill": true, - "supports_reasoning": true, - "supports_tool_choice": true, - "supports_prompt_caching": true - }, - "vertex_ai/openai/gpt-oss-20b-maas": { - "max_tokens": 32768, - "max_input_tokens": 131072, - "max_output_tokens": 32768, - "input_cost_per_token": 0.075e-06, - "output_cost_per_token": 0.30e-06, - "litellm_provider": "vertex_ai-openai_models", - "mode": "chat", - "supports_reasoning": true, - "source": "https://console.cloud.google.com/vertex-ai/publishers/openai/model-garden/gpt-oss-120b-maas" - }, - "vertex_ai/openai/gpt-oss-120b-maas": { - "max_tokens": 32768, - "max_input_tokens": 131072, - "max_output_tokens": 32768, - "input_cost_per_token": 0.15e-06, - "output_cost_per_token": 0.60e-06, - "litellm_provider": "vertex_ai-openai_models", - "mode": "chat", - "supports_reasoning": true, - "source": "https://console.cloud.google.com/vertex-ai/publishers/openai/model-garden/gpt-oss-120b-maas" - }, - "vertex_ai/qwen/qwen3-coder-480b-a35b-instruct-maas": { - "max_tokens": 32768, - "max_input_tokens": 262144, - "max_output_tokens": 32768, - "input_cost_per_token": 1e-06, - "output_cost_per_token": 4e-06, - "litellm_provider": "vertex_ai-qwen_models", - "mode": "chat", - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", - "supports_function_calling": true, - "supports_tool_choice": true - }, - "vertex_ai/qwen/qwen3-235b-a22b-instruct-2507-maas": { - "max_tokens": 16384, - "max_input_tokens": 262144, - "max_output_tokens": 16384, - "input_cost_per_token": 0.25e-06, - "output_cost_per_token": 1e-06, - "litellm_provider": "vertex_ai-qwen_models", - "mode": "chat", - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", - "supports_function_calling": true, - "supports_tool_choice": true - }, - "vertex_ai/meta/llama3-405b-instruct-maas": { - "max_tokens": 32000, - "max_input_tokens": 32000, - "max_output_tokens": 32000, - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "vertex_ai-llama_models", - "mode": "chat", - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", - "supports_tool_choice": true - }, - "vertex_ai/meta/llama-4-scout-17b-16e-instruct-maas": { - "max_tokens": 10000000, - "max_input_tokens": 10000000, - "max_output_tokens": 10000000, - "input_cost_per_token": 2.5e-07, - "output_cost_per_token": 7e-07, - "litellm_provider": "vertex_ai-llama_models", - "mode": "chat", - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", - "supports_tool_choice": true, - "supports_function_calling": true, - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text", - "code" - ] - }, - "vertex_ai/meta/llama-4-scout-17b-128e-instruct-maas": { - "max_tokens": 10000000, - "max_input_tokens": 10000000, - "max_output_tokens": 10000000, - "input_cost_per_token": 2.5e-07, - "output_cost_per_token": 7e-07, - "litellm_provider": "vertex_ai-llama_models", - "mode": "chat", - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", - "supports_tool_choice": true, - "supports_function_calling": true, - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text", - "code" - ] - }, - "vertex_ai/meta/llama-4-maverick-17b-128e-instruct-maas": { - "max_tokens": 1000000, - "max_input_tokens": 1000000, - "max_output_tokens": 1000000, - "input_cost_per_token": 3.5e-07, - "output_cost_per_token": 1.15e-06, - "litellm_provider": "vertex_ai-llama_models", - "mode": "chat", - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", - "supports_tool_choice": true, - "supports_function_calling": true, - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text", - "code" - ] - }, - "vertex_ai/meta/llama-4-maverick-17b-16e-instruct-maas": { - "max_tokens": 1000000, - "max_input_tokens": 1000000, - "max_output_tokens": 1000000, - "input_cost_per_token": 3.5e-07, - "output_cost_per_token": 1.15e-06, - "litellm_provider": "vertex_ai-llama_models", - "mode": "chat", - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", - "supports_tool_choice": true, - "supports_function_calling": true, - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text", - "code" - ] - }, - "vertex_ai/meta/llama3-70b-instruct-maas": { - "max_tokens": 32000, - "max_input_tokens": 32000, - "max_output_tokens": 32000, - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "vertex_ai-llama_models", - "mode": "chat", - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", - "supports_tool_choice": true - }, - "vertex_ai/meta/llama3-8b-instruct-maas": { - "max_tokens": 32000, - "max_input_tokens": 32000, - "max_output_tokens": 32000, - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "vertex_ai-llama_models", - "mode": "chat", - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", - "supports_tool_choice": true - }, - "vertex_ai/meta/llama-3.1-8b-instruct-maas": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 2048, - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "vertex_ai-llama_models", - "mode": "chat", - "supports_system_messages": true, - "supports_vision": true, - "source": "https://console.cloud.google.com/vertex-ai/publishers/meta/model-garden/llama-3.2-90b-vision-instruct-maas", - "supports_tool_choice": true, - "metadata": { - "notes": "VertexAI states that The Llama 3.1 API service for llama-3.1-70b-instruct-maas and llama-3.1-8b-instruct-maas are in public preview and at no cost." - } - }, - "vertex_ai/meta/llama-3.1-70b-instruct-maas": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 2048, - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "vertex_ai-llama_models", - "mode": "chat", - "supports_system_messages": true, - "supports_vision": true, - "source": "https://console.cloud.google.com/vertex-ai/publishers/meta/model-garden/llama-3.2-90b-vision-instruct-maas", - "supports_tool_choice": true - }, - "vertex_ai/meta/llama-3.1-405b-instruct-maas": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 2048, - "input_cost_per_token": 5e-06, - "output_cost_per_token": 1.6e-05, - "litellm_provider": "vertex_ai-llama_models", - "mode": "chat", - "supports_system_messages": true, - "supports_vision": true, - "source": "https://console.cloud.google.com/vertex-ai/publishers/meta/model-garden/llama-3.2-90b-vision-instruct-maas", - "supports_tool_choice": true - }, - "vertex_ai/meta/llama-3.2-90b-vision-instruct-maas": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 2048, - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "vertex_ai-llama_models", - "mode": "chat", - "supports_system_messages": true, - "supports_vision": true, - "source": "https://console.cloud.google.com/vertex-ai/publishers/meta/model-garden/llama-3.2-90b-vision-instruct-maas", - "supports_tool_choice": true, - "metadata": { - "notes": "VertexAI states that The Llama 3.2 API service is at no cost during public preview, and will be priced as per dollar-per-1M-tokens at GA." - } - }, - "vertex_ai/mistral-large@latest": { - "max_tokens": 8191, - "max_input_tokens": 128000, - "max_output_tokens": 8191, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 6e-06, - "litellm_provider": "vertex_ai-mistral_models", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true - }, - "vertex_ai/mistral-large@2411-001": { - "max_tokens": 8191, - "max_input_tokens": 128000, - "max_output_tokens": 8191, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 6e-06, - "litellm_provider": "vertex_ai-mistral_models", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true - }, - "vertex_ai/mistral-large-2411": { - "max_tokens": 8191, - "max_input_tokens": 128000, - "max_output_tokens": 8191, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 6e-06, - "litellm_provider": "vertex_ai-mistral_models", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true - }, - "vertex_ai/mistral-large@2407": { - "max_tokens": 8191, - "max_input_tokens": 128000, - "max_output_tokens": 8191, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 6e-06, - "litellm_provider": "vertex_ai-mistral_models", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true - }, - "vertex_ai/mistral-nemo@latest": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 1.5e-07, - "litellm_provider": "vertex_ai-mistral_models", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true - }, - "vertex_ai/mistral-small-2503@001": { - "max_tokens": 8191, - "max_input_tokens": 32000, - "max_output_tokens": 8191, - "input_cost_per_token": 1e-06, - "output_cost_per_token": 3e-06, - "litellm_provider": "vertex_ai-mistral_models", - "supports_function_calling": true, - "mode": "chat", - "supports_tool_choice": true - }, - "vertex_ai/mistral-small-2503": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "input_cost_per_token": 1e-06, - "output_cost_per_token": 3e-06, - "litellm_provider": "vertex_ai-mistral_models", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "supports_tool_choice": true - }, - "vertex_ai/jamba-1.5-mini@001": { - "max_tokens": 256000, - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "input_cost_per_token": 2e-07, - "output_cost_per_token": 4e-07, - "litellm_provider": "vertex_ai-ai21_models", - "mode": "chat", - "supports_tool_choice": true - }, - "vertex_ai/jamba-1.5-large@001": { - "max_tokens": 256000, - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 8e-06, - "litellm_provider": "vertex_ai-ai21_models", - "mode": "chat", - "supports_tool_choice": true - }, - "vertex_ai/jamba-1.5": { - "max_tokens": 256000, - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "input_cost_per_token": 2e-07, - "output_cost_per_token": 4e-07, - "litellm_provider": "vertex_ai-ai21_models", - "mode": "chat", - "supports_tool_choice": true - }, - "vertex_ai/jamba-1.5-mini": { - "max_tokens": 256000, - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "input_cost_per_token": 2e-07, - "output_cost_per_token": 4e-07, - "litellm_provider": "vertex_ai-ai21_models", - "mode": "chat", - "supports_tool_choice": true - }, - "vertex_ai/jamba-1.5-large": { - "max_tokens": 256000, - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 8e-06, - "litellm_provider": "vertex_ai-ai21_models", - "mode": "chat", - "supports_tool_choice": true - }, - "vertex_ai/mistral-nemo@2407": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 3e-06, - "litellm_provider": "vertex_ai-mistral_models", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true - }, - "vertex_ai/codestral@latest": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "input_cost_per_token": 2e-07, - "output_cost_per_token": 6e-07, - "litellm_provider": "vertex_ai-mistral_models", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true - }, - "vertex_ai/codestral@2405": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "input_cost_per_token": 2e-07, - "output_cost_per_token": 6e-07, - "litellm_provider": "vertex_ai-mistral_models", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true - }, - "vertex_ai/codestral-2501": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "input_cost_per_token": 2e-07, - "output_cost_per_token": 6e-07, - "litellm_provider": "vertex_ai-mistral_models", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true - }, - "vertex_ai/imagegeneration@006": { - "output_cost_per_image": 0.02, - "litellm_provider": "vertex_ai-image-models", - "mode": "image_generation", - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" - }, - "vertex_ai/imagen-4.0-generate-001": { - "output_cost_per_image": 0.04, - "litellm_provider": "vertex_ai-image-models", - "mode": "image_generation", - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" - }, - "vertex_ai/imagen-4.0-ultra-generate-001": { - "output_cost_per_image": 0.06, - "litellm_provider": "vertex_ai-image-models", - "mode": "image_generation", - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" - }, - "vertex_ai/imagen-4.0-fast-generate-001": { - "output_cost_per_image": 0.02, - "litellm_provider": "vertex_ai-image-models", - "mode": "image_generation", - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" - }, - "vertex_ai/imagen-3.0-generate-002": { - "output_cost_per_image": 0.04, - "litellm_provider": "vertex_ai-image-models", - "mode": "image_generation", - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" - }, - "vertex_ai/imagen-3.0-generate-001": { - "output_cost_per_image": 0.04, - "litellm_provider": "vertex_ai-image-models", - "mode": "image_generation", - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" - }, - "vertex_ai/imagen-3.0-fast-generate-001": { - "output_cost_per_image": 0.02, - "litellm_provider": "vertex_ai-image-models", - "mode": "image_generation", - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" - }, - "vertex_ai/veo-3.0-generate-preview": { - "max_tokens": 1024, - "max_input_tokens": 1024, - "output_cost_per_second": 0.75, - "litellm_provider": "vertex_ai-video-models", - "mode": "video_generation", - "supported_modalities": [ - "text" - ], - "supported_output_modalities": [ - "video" - ], - "source": "https://ai.google.dev/gemini-api/docs/video" - }, - "vertex_ai/veo-3.0-fast-generate-preview": { - "max_tokens": 1024, - "max_input_tokens": 1024, - "output_cost_per_second": 0.40, - "litellm_provider": "vertex_ai-video-models", - "mode": "video_generation", - "supported_modalities": [ - "text" - ], - "supported_output_modalities": [ - "video" - ], - "source": "https://ai.google.dev/gemini-api/docs/video" - }, - "vertex_ai/veo-2.0-generate-001": { - "max_tokens": 1024, - "max_input_tokens": 1024, - "output_cost_per_second": 0.35, - "litellm_provider": "vertex_ai-video-models", - "mode": "video_generation", - "supported_modalities": [ - "text" - ], - "supported_output_modalities": [ - "video" - ], - "source": "https://ai.google.dev/gemini-api/docs/video" - }, - "text-embedding-004": { - "max_tokens": 2048, - "max_input_tokens": 2048, - "output_vector_size": 768, - "input_cost_per_character": 2.5e-08, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 0, - "litellm_provider": "vertex_ai-embedding-models", - "mode": "embedding", - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models" - }, - "gemini-embedding-001": { - "max_tokens": 2048, - "max_input_tokens": 2048, - "output_vector_size": 3072, - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 0, - "litellm_provider": "vertex_ai-embedding-models", - "mode": "embedding", - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models" - }, - "text-embedding-005": { - "max_tokens": 2048, - "max_input_tokens": 2048, - "output_vector_size": 768, - "input_cost_per_character": 2.5e-08, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 0, - "litellm_provider": "vertex_ai-embedding-models", - "mode": "embedding", - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models" - }, - "text-multilingual-embedding-002": { - "max_tokens": 2048, - "max_input_tokens": 2048, - "output_vector_size": 768, - "input_cost_per_character": 2.5e-08, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 0, - "litellm_provider": "vertex_ai-embedding-models", - "mode": "embedding", - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models" - }, - "multimodalembedding": { - "max_tokens": 2048, - "max_input_tokens": 2048, - "output_vector_size": 768, - "input_cost_per_character": 2e-07, - "input_cost_per_image": 0.0001, - "input_cost_per_video_per_second": 0.0005, - "input_cost_per_video_per_second_above_8s_interval": 0.001, - "input_cost_per_video_per_second_above_15s_interval": 0.002, - "input_cost_per_token": 8e-07, - "output_cost_per_token": 0, - "litellm_provider": "vertex_ai-embedding-models", - "mode": "embedding", + "output_cost_per_reasoning_token": 2.5e-06, + "output_cost_per_token": 2.5e-06, + "rpm": 100000, + "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", "supported_endpoints": [ - "/v1/embeddings" + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" ], "supported_modalities": [ "text", "image", + "audio", "video" ], - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models" + "supported_output_modalities": [ + "text" + ], + "supports_audio_output": false, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 8000000 }, - "multimodalembedding@001": { - "max_tokens": 2048, - "max_input_tokens": 2048, - "output_vector_size": 768, - "input_cost_per_character": 2e-07, - "input_cost_per_image": 0.0001, - "input_cost_per_video_per_second": 0.0005, - "input_cost_per_video_per_second_above_8s_interval": 0.001, - "input_cost_per_video_per_second_above_15s_interval": 0.002, - "input_cost_per_token": 8e-07, - "output_cost_per_token": 0, - "litellm_provider": "vertex_ai-embedding-models", - "mode": "embedding", + "gemini/gemini-2.5-flash-image-preview": { + "cache_read_input_token_cost": 7.5e-08, + "input_cost_per_audio_token": 1e-06, + "input_cost_per_token": 3e-07, + "litellm_provider": "gemini", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_image": 0.039, + "output_cost_per_reasoning_token": 3e-05, + "output_cost_per_token": 3e-05, + "rpm": 100000, + "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", "supported_endpoints": [ - "/v1/embeddings" + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" ], "supported_modalities": [ "text", "image", + "audio", "video" ], - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models" + "supported_output_modalities": [ + "text", + "image" + ], + "supports_audio_output": false, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 8000000 }, - "text-embedding-large-exp-03-07": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "output_vector_size": 3072, - "input_cost_per_character": 2.5e-08, + "gemini/gemini-2.5-flash-lite": { + "cache_read_input_token_cost": 2.5e-08, + "input_cost_per_audio_token": 5e-07, "input_cost_per_token": 1e-07, - "output_cost_per_token": 0, - "litellm_provider": "vertex_ai-embedding-models", - "mode": "embedding", - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models" - }, - "textembedding-gecko": { - "max_tokens": 3072, - "max_input_tokens": 3072, - "output_vector_size": 768, - "input_cost_per_character": 2.5e-08, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 0, - "litellm_provider": "vertex_ai-embedding-models", - "mode": "embedding", - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" - }, - "textembedding-gecko-multilingual": { - "max_tokens": 3072, - "max_input_tokens": 3072, - "output_vector_size": 768, - "input_cost_per_character": 2.5e-08, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 0, - "litellm_provider": "vertex_ai-embedding-models", - "mode": "embedding", - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" - }, - "textembedding-gecko-multilingual@001": { - "max_tokens": 3072, - "max_input_tokens": 3072, - "output_vector_size": 768, - "input_cost_per_character": 2.5e-08, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 0, - "litellm_provider": "vertex_ai-embedding-models", - "mode": "embedding", - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" - }, - "textembedding-gecko@001": { - "max_tokens": 3072, - "max_input_tokens": 3072, - "output_vector_size": 768, - "input_cost_per_character": 2.5e-08, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 0, - "litellm_provider": "vertex_ai-embedding-models", - "mode": "embedding", - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" - }, - "textembedding-gecko@003": { - "max_tokens": 3072, - "max_input_tokens": 3072, - "output_vector_size": 768, - "input_cost_per_character": 2.5e-08, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 0, - "litellm_provider": "vertex_ai-embedding-models", - "mode": "embedding", - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" - }, - "text-embedding-preview-0409": { - "max_tokens": 3072, - "max_input_tokens": 3072, - "output_vector_size": 768, - "input_cost_per_token": 6.25e-09, - "input_cost_per_token_batch_requests": 5e-09, - "output_cost_per_token": 0, - "litellm_provider": "vertex_ai-embedding-models", - "mode": "embedding", - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" - }, - "text-multilingual-embedding-preview-0409": { - "max_tokens": 3072, - "max_input_tokens": 3072, - "output_vector_size": 768, - "input_cost_per_token": 6.25e-09, - "output_cost_per_token": 0, - "litellm_provider": "vertex_ai-embedding-models", - "mode": "embedding", - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" - }, - "palm/chat-bison": { - "max_tokens": 4096, - "max_input_tokens": 8192, - "max_output_tokens": 4096, - "input_cost_per_token": 1.25e-07, - "output_cost_per_token": 1.25e-07, - "litellm_provider": "palm", - "mode": "chat", - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" - }, - "palm/chat-bison-001": { - "max_tokens": 4096, - "max_input_tokens": 8192, - "max_output_tokens": 4096, - "input_cost_per_token": 1.25e-07, - "output_cost_per_token": 1.25e-07, - "litellm_provider": "palm", - "mode": "chat", - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" - }, - "palm/text-bison": { - "max_tokens": 1024, - "max_input_tokens": 8192, - "max_output_tokens": 1024, - "input_cost_per_token": 1.25e-07, - "output_cost_per_token": 1.25e-07, - "litellm_provider": "palm", - "mode": "completion", - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" - }, - "palm/text-bison-001": { - "max_tokens": 1024, - "max_input_tokens": 8192, - "max_output_tokens": 1024, - "input_cost_per_token": 1.25e-07, - "output_cost_per_token": 1.25e-07, - "litellm_provider": "palm", - "mode": "completion", - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" - }, - "palm/text-bison-safety-off": { - "max_tokens": 1024, - "max_input_tokens": 8192, - "max_output_tokens": 1024, - "input_cost_per_token": 1.25e-07, - "output_cost_per_token": 1.25e-07, - "litellm_provider": "palm", - "mode": "completion", - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" - }, - "palm/text-bison-safety-recitation-off": { - "max_tokens": 1024, - "max_input_tokens": 8192, - "max_output_tokens": 1024, - "input_cost_per_token": 1.25e-07, - "output_cost_per_token": 1.25e-07, - "litellm_provider": "palm", - "mode": "completion", - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" - }, - "gemini/gemini-1.5-flash-002": { - "max_tokens": 8192, - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, + "litellm_provider": "gemini", "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, "max_pdf_size_mb": 30, - "cache_read_input_token_cost": 1.875e-08, - "cache_creation_input_token_cost": 1e-06, - "input_cost_per_token": 7.5e-08, - "input_cost_per_token_above_128k_tokens": 1.5e-07, - "output_cost_per_token": 3e-07, - "output_cost_per_token_above_128k_tokens": 6e-07, - "litellm_provider": "gemini", + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, "mode": "chat", - "supports_system_messages": true, + "output_cost_per_reasoning_token": 4e-07, + "output_cost_per_token": 4e-07, + "rpm": 15, + "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-lite", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_output": false, "supports_function_calling": true, - "supports_vision": true, - "supports_response_schema": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, "supports_prompt_caching": true, - "tpm": 4000000, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 250000 + }, + "gemini/gemini-2.5-flash-lite-preview-06-17": { + "cache_read_input_token_cost": 2.5e-08, + "input_cost_per_audio_token": 5e-07, + "input_cost_per_token": 1e-07, + "litellm_provider": "gemini", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_reasoning_token": 4e-07, + "output_cost_per_token": 4e-07, + "rpm": 15, + "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-lite", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_output": false, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 250000 + }, + "gemini/gemini-2.5-flash-preview-04-17": { + "cache_read_input_token_cost": 3.75e-08, + "input_cost_per_audio_token": 1e-06, + "input_cost_per_token": 1.5e-07, + "litellm_provider": "gemini", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_reasoning_token": 3.5e-06, + "output_cost_per_token": 6e-07, + "rpm": 10, + "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_output": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 250000 + }, + "gemini/gemini-2.5-flash-preview-05-20": { + "cache_read_input_token_cost": 7.5e-08, + "input_cost_per_audio_token": 1e-06, + "input_cost_per_token": 3e-07, + "litellm_provider": "gemini", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_reasoning_token": 2.5e-06, + "output_cost_per_token": 2.5e-06, + "rpm": 10, + "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_output": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 250000 + }, + "gemini/gemini-2.5-flash-preview-tts": { + "cache_read_input_token_cost": 3.75e-08, + "input_cost_per_audio_token": 1e-06, + "input_cost_per_token": 1.5e-07, + "litellm_provider": "gemini", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_reasoning_token": 3.5e-06, + "output_cost_per_token": 6e-07, + "rpm": 10, + "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "audio" + ], + "supports_audio_output": false, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 250000 + }, + "gemini/gemini-2.5-pro": { + "cache_read_input_token_cost": 3.125e-07, + "input_cost_per_token": 1.25e-06, + "input_cost_per_token_above_200k_tokens": 2.5e-06, + "litellm_provider": "gemini", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_token": 1e-05, + "output_cost_per_token_above_200k_tokens": 1.5e-05, "rpm": 2000, - "source": "https://ai.google.dev/pricing", - "deprecation_date": "2025-09-24", - "supports_tool_choice": true - }, - "gemini/gemini-1.5-flash-001": { - "max_tokens": 8192, - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_pdf_size_mb": 30, - "cache_read_input_token_cost": 1.875e-08, - "cache_creation_input_token_cost": 1e-06, - "input_cost_per_token": 7.5e-08, - "input_cost_per_token_above_128k_tokens": 1.5e-07, - "output_cost_per_token": 3e-07, - "output_cost_per_token_above_128k_tokens": 6e-07, - "litellm_provider": "gemini", - "mode": "chat", - "supports_system_messages": true, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true, "supports_function_calling": true, - "supports_vision": true, - "supports_response_schema": true, + "supports_pdf_input": true, "supports_prompt_caching": true, - "tpm": 4000000, - "rpm": 2000, - "source": "https://ai.google.dev/pricing", - "deprecation_date": "2025-05-24", - "supports_tool_choice": true + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 800000 }, - "gemini/gemini-1.5-flash": { - "max_tokens": 8192, - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, + "gemini/gemini-2.5-pro-exp-03-25": { + "cache_read_input_token_cost": 0.0, + "input_cost_per_token": 0.0, + "input_cost_per_token_above_200k_tokens": 0.0, + "litellm_provider": "gemini", "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, - "max_pdf_size_mb": 30, - "input_cost_per_token": 7.5e-08, - "input_cost_per_token_above_128k_tokens": 1.5e-07, - "output_cost_per_token": 3e-07, - "output_cost_per_token_above_128k_tokens": 6e-07, - "litellm_provider": "gemini", - "mode": "chat", - "supports_system_messages": true, - "supports_function_calling": true, - "supports_vision": true, - "supports_response_schema": true, - "tpm": 4000000, - "rpm": 2000, - "source": "https://ai.google.dev/pricing", - "supports_tool_choice": true - }, - "gemini/gemini-1.5-flash-latest": { - "max_tokens": 8192, - "max_input_tokens": 1048576, - "max_output_tokens": 8192, "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, "max_pdf_size_mb": 30, - "input_cost_per_token": 7.5e-08, - "input_cost_per_token_above_128k_tokens": 1.5e-07, - "output_cost_per_token": 3e-07, - "output_cost_per_token_above_128k_tokens": 6e-07, - "litellm_provider": "gemini", + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, "mode": "chat", - "supports_system_messages": true, + "output_cost_per_token": 0.0, + "output_cost_per_token_above_200k_tokens": 0.0, + "rpm": 5, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true, "supports_function_calling": true, - "supports_vision": true, - "supports_response_schema": true, + "supports_pdf_input": true, "supports_prompt_caching": true, - "tpm": 4000000, - "rpm": 2000, - "source": "https://ai.google.dev/pricing", - "supports_tool_choice": true + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 250000 }, - "gemini/gemini-1.5-flash-8b": { - "max_tokens": 8192, - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, + "gemini/gemini-2.5-pro-preview-03-25": { + "cache_read_input_token_cost": 3.125e-07, + "input_cost_per_audio_token": 7e-07, + "input_cost_per_token": 1.25e-06, + "input_cost_per_token_above_200k_tokens": 2.5e-06, + "litellm_provider": "gemini", "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, - "max_pdf_size_mb": 30, - "input_cost_per_token": 0, - "input_cost_per_token_above_128k_tokens": 0, - "output_cost_per_token": 0, - "output_cost_per_token_above_128k_tokens": 0, - "litellm_provider": "gemini", - "mode": "chat", - "supports_system_messages": true, - "supports_function_calling": true, - "supports_vision": true, - "supports_response_schema": true, - "supports_prompt_caching": true, - "tpm": 4000000, - "rpm": 4000, - "source": "https://ai.google.dev/pricing", - "supports_tool_choice": true - }, - "gemini/gemini-1.5-flash-8b-exp-0924": { - "max_tokens": 8192, - "max_input_tokens": 1048576, - "max_output_tokens": 8192, "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_token": 1e-05, + "output_cost_per_token_above_200k_tokens": 1.5e-05, + "rpm": 10000, + "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-pro-preview", + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_output": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 10000000 + }, + "gemini/gemini-2.5-pro-preview-05-06": { + "cache_read_input_token_cost": 3.125e-07, + "input_cost_per_audio_token": 7e-07, + "input_cost_per_token": 1.25e-06, + "input_cost_per_token_above_200k_tokens": 2.5e-06, + "litellm_provider": "gemini", "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, "max_pdf_size_mb": 30, - "input_cost_per_token": 0, - "input_cost_per_token_above_128k_tokens": 0, - "output_cost_per_token": 0, - "output_cost_per_token_above_128k_tokens": 0, - "litellm_provider": "gemini", + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, "mode": "chat", - "supports_system_messages": true, + "output_cost_per_token": 1e-05, + "output_cost_per_token_above_200k_tokens": 1.5e-05, + "rpm": 10000, + "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-pro-preview", + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_output": false, "supports_function_calling": true, - "supports_vision": true, - "supports_response_schema": true, + "supports_pdf_input": true, "supports_prompt_caching": true, - "tpm": 4000000, - "rpm": 4000, - "source": "https://ai.google.dev/pricing", - "supports_tool_choice": true + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 10000000 + }, + "gemini/gemini-2.5-pro-preview-06-05": { + "cache_read_input_token_cost": 3.125e-07, + "input_cost_per_audio_token": 7e-07, + "input_cost_per_token": 1.25e-06, + "input_cost_per_token_above_200k_tokens": 2.5e-06, + "litellm_provider": "gemini", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_token": 1e-05, + "output_cost_per_token_above_200k_tokens": 1.5e-05, + "rpm": 10000, + "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-pro-preview", + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_output": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 10000000 + }, + "gemini/gemini-2.5-pro-preview-tts": { + "cache_read_input_token_cost": 3.125e-07, + "input_cost_per_audio_token": 7e-07, + "input_cost_per_token": 1.25e-06, + "input_cost_per_token_above_200k_tokens": 2.5e-06, + "litellm_provider": "gemini", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_token": 1e-05, + "output_cost_per_token_above_200k_tokens": 1.5e-05, + "rpm": 10000, + "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-pro-preview", + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "audio" + ], + "supports_audio_output": false, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 10000000 }, "gemini/gemini-exp-1114": { - "max_tokens": 8192, - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_pdf_size_mb": 30, "input_cost_per_token": 0, "input_cost_per_token_above_128k_tokens": 0, - "output_cost_per_token": 0, - "output_cost_per_token_above_128k_tokens": 0, "litellm_provider": "gemini", - "mode": "chat", - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_function_calling": true, - "supports_vision": true, - "supports_response_schema": true, - "tpm": 4000000, - "rpm": 1000, - "source": "https://ai.google.dev/pricing", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, "metadata": { "notes": "Rate limits not documented for gemini-exp-1114. Assuming same as gemini-1.5-pro.", "supports_tool_choice": true - } - }, - "gemini/gemini-exp-1206": { - "max_tokens": 8192, - "max_input_tokens": 2097152, - "max_output_tokens": 8192, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_pdf_size_mb": 30, - "input_cost_per_token": 0, - "input_cost_per_token_above_128k_tokens": 0, + }, + "mode": "chat", "output_cost_per_token": 0, "output_cost_per_token_above_128k_tokens": 0, - "litellm_provider": "gemini", - "mode": "chat", - "supports_system_messages": true, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_response_schema": true, - "tpm": 4000000, "rpm": 1000, "source": "https://ai.google.dev/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "tpm": 4000000 + }, + "gemini/gemini-exp-1206": { + "input_cost_per_token": 0, + "input_cost_per_token_above_128k_tokens": 0, + "litellm_provider": "gemini", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 2097152, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, "metadata": { "notes": "Rate limits not documented for gemini-exp-1206. Assuming same as gemini-1.5-pro.", "supports_tool_choice": true - } - }, - "gemini/gemini-1.5-flash-exp-0827": { - "max_tokens": 8192, - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_pdf_size_mb": 30, - "input_cost_per_token": 0, - "input_cost_per_token_above_128k_tokens": 0, + }, + "mode": "chat", "output_cost_per_token": 0, "output_cost_per_token_above_128k_tokens": 0, - "litellm_provider": "gemini", - "mode": "chat", - "supports_system_messages": true, - "supports_function_calling": true, - "supports_vision": true, - "supports_response_schema": true, - "tpm": 4000000, - "rpm": 2000, - "source": "https://ai.google.dev/pricing", - "supports_tool_choice": true - }, - "gemini/gemini-1.5-flash-8b-exp-0827": { - "max_tokens": 8192, - "max_input_tokens": 1000000, - "max_output_tokens": 8192, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_pdf_size_mb": 30, - "input_cost_per_token": 0, - "input_cost_per_token_above_128k_tokens": 0, - "output_cost_per_token": 0, - "output_cost_per_token_above_128k_tokens": 0, - "litellm_provider": "gemini", - "mode": "chat", - "supports_system_messages": true, - "supports_function_calling": true, - "supports_vision": true, - "supports_response_schema": true, - "tpm": 4000000, - "rpm": 4000, - "source": "https://ai.google.dev/pricing", - "supports_tool_choice": true - }, - "gemini/gemini-pro": { - "max_tokens": 8192, - "max_input_tokens": 32760, - "max_output_tokens": 8192, - "input_cost_per_token": 3.5e-07, - "input_cost_per_token_above_128k_tokens": 7e-07, - "output_cost_per_token": 1.05e-06, - "output_cost_per_token_above_128k_tokens": 2.1e-06, - "litellm_provider": "gemini", - "mode": "chat", - "supports_function_calling": true, - "rpd": 30000, - "tpm": 120000, - "rpm": 360, - "source": "https://ai.google.dev/gemini-api/docs/models/gemini", - "supports_tool_choice": true - }, - "gemini/gemini-1.5-pro": { - "max_tokens": 8192, - "max_input_tokens": 2097152, - "max_output_tokens": 8192, - "input_cost_per_token": 3.5e-06, - "input_cost_per_token_above_128k_tokens": 7e-06, - "output_cost_per_token": 1.05e-05, - "output_cost_per_token_above_128k_tokens": 2.1e-05, - "litellm_provider": "gemini", - "mode": "chat", - "supports_system_messages": true, - "supports_function_calling": true, - "supports_vision": true, - "supports_tool_choice": true, - "supports_response_schema": true, - "tpm": 4000000, - "rpm": 1000, - "source": "https://ai.google.dev/pricing" - }, - "gemini/gemini-1.5-pro-002": { - "max_tokens": 8192, - "max_input_tokens": 2097152, - "max_output_tokens": 8192, - "input_cost_per_token": 3.5e-06, - "input_cost_per_token_above_128k_tokens": 7e-06, - "output_cost_per_token": 1.05e-05, - "output_cost_per_token_above_128k_tokens": 2.1e-05, - "litellm_provider": "gemini", - "mode": "chat", - "supports_system_messages": true, - "supports_function_calling": true, - "supports_vision": true, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_prompt_caching": true, - "tpm": 4000000, "rpm": 1000, "source": "https://ai.google.dev/pricing", - "deprecation_date": "2025-09-24" - }, - "gemini/gemini-1.5-pro-001": { - "max_tokens": 8192, - "max_input_tokens": 2097152, - "max_output_tokens": 8192, - "input_cost_per_token": 3.5e-06, - "input_cost_per_token_above_128k_tokens": 7e-06, - "output_cost_per_token": 1.05e-05, - "output_cost_per_token_above_128k_tokens": 2.1e-05, - "litellm_provider": "gemini", - "mode": "chat", - "supports_system_messages": true, "supports_function_calling": true, - "supports_vision": true, - "supports_tool_choice": true, "supports_response_schema": true, - "supports_prompt_caching": true, - "tpm": 4000000, - "rpm": 1000, - "source": "https://ai.google.dev/pricing", - "deprecation_date": "2025-05-24" - }, - "gemini/gemini-1.5-pro-exp-0801": { - "max_tokens": 8192, - "max_input_tokens": 2097152, - "max_output_tokens": 8192, - "input_cost_per_token": 3.5e-06, - "input_cost_per_token_above_128k_tokens": 7e-06, - "output_cost_per_token": 1.05e-05, - "output_cost_per_token_above_128k_tokens": 2.1e-05, - "litellm_provider": "gemini", - "mode": "chat", "supports_system_messages": true, - "supports_function_calling": true, - "supports_vision": true, "supports_tool_choice": true, - "supports_response_schema": true, - "tpm": 4000000, - "rpm": 1000, - "source": "https://ai.google.dev/pricing" - }, - "gemini/gemini-1.5-pro-exp-0827": { - "max_tokens": 8192, - "max_input_tokens": 2097152, - "max_output_tokens": 8192, - "input_cost_per_token": 0, - "input_cost_per_token_above_128k_tokens": 0, - "output_cost_per_token": 0, - "output_cost_per_token_above_128k_tokens": 0, - "litellm_provider": "gemini", - "mode": "chat", - "supports_system_messages": true, - "supports_function_calling": true, "supports_vision": true, - "supports_tool_choice": true, - "supports_response_schema": true, - "tpm": 4000000, - "rpm": 1000, - "source": "https://ai.google.dev/pricing" - }, - "gemini/gemini-1.5-pro-latest": { - "max_tokens": 8192, - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "input_cost_per_token": 3.5e-06, - "input_cost_per_token_above_128k_tokens": 7e-06, - "output_cost_per_token": 1.05e-06, - "output_cost_per_token_above_128k_tokens": 2.1e-05, - "litellm_provider": "gemini", - "mode": "chat", - "supports_system_messages": true, - "supports_function_calling": true, - "supports_vision": true, - "supports_tool_choice": true, - "supports_response_schema": true, - "tpm": 4000000, - "rpm": 1000, - "source": "https://ai.google.dev/pricing" - }, - "gemini/gemini-pro-vision": { - "max_tokens": 2048, - "max_input_tokens": 30720, - "max_output_tokens": 2048, - "input_cost_per_token": 3.5e-07, - "input_cost_per_token_above_128k_tokens": 7e-07, - "output_cost_per_token": 1.05e-06, - "output_cost_per_token_above_128k_tokens": 2.1e-06, - "litellm_provider": "gemini", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "rpd": 30000, - "tpm": 120000, - "rpm": 360, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", - "supports_tool_choice": true + "tpm": 4000000 }, "gemini/gemini-gemma-2-27b-it": { - "max_tokens": 8192, - "max_output_tokens": 8192, "input_cost_per_token": 3.5e-07, - "output_cost_per_token": 1.05e-06, "litellm_provider": "gemini", + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, + "output_cost_per_token": 1.05e-06, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", - "supports_tool_choice": true + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true }, "gemini/gemini-gemma-2-9b-it": { - "max_tokens": 8192, - "max_output_tokens": 8192, "input_cost_per_token": 3.5e-07, - "output_cost_per_token": 1.05e-06, "litellm_provider": "gemini", + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, + "output_cost_per_token": 1.05e-06, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", - "supports_tool_choice": true + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true }, - "gemini/imagen-4.0-generate-001": { - "output_cost_per_image": 0.04, + "gemini/gemini-pro": { + "input_cost_per_token": 3.5e-07, + "input_cost_per_token_above_128k_tokens": 7e-07, + "litellm_provider": "gemini", + "max_input_tokens": 32760, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.05e-06, + "output_cost_per_token_above_128k_tokens": 2.1e-06, + "rpd": 30000, + "rpm": 360, + "source": "https://ai.google.dev/gemini-api/docs/models/gemini", + "supports_function_calling": true, + "supports_tool_choice": true, + "tpm": 120000 + }, + "gemini/gemini-pro-vision": { + "input_cost_per_token": 3.5e-07, + "input_cost_per_token_above_128k_tokens": 7e-07, + "litellm_provider": "gemini", + "max_input_tokens": 30720, + "max_output_tokens": 2048, + "max_tokens": 2048, + "mode": "chat", + "output_cost_per_token": 1.05e-06, + "output_cost_per_token_above_128k_tokens": 2.1e-06, + "rpd": 30000, + "rpm": 360, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true, + "tpm": 120000 + }, + "gemini/gemma-3-27b-it": { + "input_cost_per_audio_per_second": 0, + "input_cost_per_audio_per_second_above_128k_tokens": 0, + "input_cost_per_character": 0, + "input_cost_per_character_above_128k_tokens": 0, + "input_cost_per_image": 0, + "input_cost_per_image_above_128k_tokens": 0, + "input_cost_per_token": 0, + "input_cost_per_token_above_128k_tokens": 0, + "input_cost_per_video_per_second": 0, + "input_cost_per_video_per_second_above_128k_tokens": 0, + "litellm_provider": "gemini", + "max_input_tokens": 131072, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_character": 0, + "output_cost_per_character_above_128k_tokens": 0, + "output_cost_per_token": 0, + "output_cost_per_token_above_128k_tokens": 0, + "source": "https://aistudio.google.com", + "supports_audio_output": false, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "gemini/imagen-3.0-fast-generate-001": { "litellm_provider": "gemini", "mode": "image_generation", - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" - }, - "gemini/imagen-4.0-ultra-generate-001": { - "output_cost_per_image": 0.06, - "litellm_provider": "gemini", - "mode": "image_generation", - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" - }, - "gemini/imagen-4.0-fast-generate-001": { "output_cost_per_image": 0.02, - "litellm_provider": "gemini", - "mode": "image_generation", - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" - }, - "gemini/imagen-3.0-generate-002": { - "output_cost_per_image": 0.04, - "litellm_provider": "gemini", - "mode": "image_generation", "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" }, "gemini/imagen-3.0-generate-001": { - "output_cost_per_image": 0.04, "litellm_provider": "gemini", "mode": "image_generation", + "output_cost_per_image": 0.04, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" }, - "gemini/imagen-3.0-fast-generate-001": { + "gemini/imagen-3.0-generate-002": { + "litellm_provider": "gemini", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" + }, + "gemini/imagen-4.0-fast-generate-001": { + "litellm_provider": "gemini", + "mode": "image_generation", "output_cost_per_image": 0.02, - "litellm_provider": "gemini", - "mode": "image_generation", "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" }, - "command-a-03-2025": { - "max_tokens": 8000, - "max_input_tokens": 256000, - "max_output_tokens": 8000, - "input_cost_per_token": 2.5e-06, - "output_cost_per_token": 1e-05, - "litellm_provider": "cohere_chat", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true - }, - "command-r": { - "max_tokens": 4096, - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 6e-07, - "litellm_provider": "cohere_chat", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true - }, - "command-r-08-2024": { - "max_tokens": 4096, - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 6e-07, - "litellm_provider": "cohere_chat", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true - }, - "command-r7b-12-2024": { - "max_tokens": 4096, - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 3.75e-08, - "litellm_provider": "cohere_chat", - "mode": "chat", - "supports_function_calling": true, - "source": "https://docs.cohere.com/v2/docs/command-r7b", - "supports_tool_choice": true - }, - "command-light": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 3e-07, - "output_cost_per_token": 6e-07, - "litellm_provider": "cohere_chat", - "mode": "chat", - "supports_tool_choice": true - }, - "command-r-plus": { - "max_tokens": 4096, - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 2.5e-06, - "output_cost_per_token": 1e-05, - "litellm_provider": "cohere_chat", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true - }, - "command-r-plus-08-2024": { - "max_tokens": 4096, - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 2.5e-06, - "output_cost_per_token": 1e-05, - "litellm_provider": "cohere_chat", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true - }, - "command-nightly": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 1e-06, - "output_cost_per_token": 2e-06, - "litellm_provider": "cohere", - "mode": "completion" - }, - "command": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 1e-06, - "output_cost_per_token": 2e-06, - "litellm_provider": "cohere", - "mode": "completion" - }, - "rerank-v3.5": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "max_query_tokens": 2048, - "input_cost_per_token": 0.0, - "input_cost_per_query": 0.002, - "output_cost_per_token": 0.0, - "litellm_provider": "cohere", - "mode": "rerank" - }, - "rerank-english-v3.0": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "max_query_tokens": 2048, - "input_cost_per_token": 0.0, - "input_cost_per_query": 0.002, - "output_cost_per_token": 0.0, - "litellm_provider": "cohere", - "mode": "rerank" - }, - "rerank-multilingual-v3.0": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "max_query_tokens": 2048, - "input_cost_per_token": 0.0, - "input_cost_per_query": 0.002, - "output_cost_per_token": 0.0, - "litellm_provider": "cohere", - "mode": "rerank" - }, - "rerank-english-v2.0": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "max_query_tokens": 2048, - "input_cost_per_token": 0.0, - "input_cost_per_query": 0.002, - "output_cost_per_token": 0.0, - "litellm_provider": "cohere", - "mode": "rerank" - }, - "rerank-multilingual-v2.0": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "max_query_tokens": 2048, - "input_cost_per_token": 0.0, - "input_cost_per_query": 0.002, - "output_cost_per_token": 0.0, - "litellm_provider": "cohere", - "mode": "rerank" - }, - "embed-english-light-v3.0": { - "max_tokens": 1024, - "max_input_tokens": 1024, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 0.0, - "litellm_provider": "cohere", - "mode": "embedding" - }, - "embed-multilingual-v3.0": { - "max_tokens": 1024, - "max_input_tokens": 1024, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 0.0, - "litellm_provider": "cohere", - "supports_embedding_image_input": true, - "mode": "embedding" - }, - "embed-english-v2.0": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 0.0, - "litellm_provider": "cohere", - "mode": "embedding" - }, - "embed-english-light-v2.0": { - "max_tokens": 1024, - "max_input_tokens": 1024, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 0.0, - "litellm_provider": "cohere", - "mode": "embedding" - }, - "embed-multilingual-v2.0": { - "max_tokens": 768, - "max_input_tokens": 768, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 0.0, - "litellm_provider": "cohere", - "mode": "embedding" - }, - "embed-english-v3.0": { - "max_tokens": 1024, - "max_input_tokens": 1024, - "input_cost_per_token": 1e-07, - "input_cost_per_image": 0.0001, - "output_cost_per_token": 0.0, - "litellm_provider": "cohere", - "mode": "embedding", - "supports_image_input": true, - "supports_embedding_image_input": true, - "metadata": { - "notes": "'supports_image_input' is a deprecated field. Use 'supports_embedding_image_input' instead." - } - }, - "replicate/meta/llama-2-13b": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 5e-07, - "litellm_provider": "replicate", - "mode": "chat", - "supports_tool_choice": true - }, - "replicate/meta/llama-2-13b-chat": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 5e-07, - "litellm_provider": "replicate", - "mode": "chat", - "supports_tool_choice": true - }, - "replicate/meta/llama-2-70b": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 6.5e-07, - "output_cost_per_token": 2.75e-06, - "litellm_provider": "replicate", - "mode": "chat", - "supports_tool_choice": true - }, - "replicate/meta/llama-2-70b-chat": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 6.5e-07, - "output_cost_per_token": 2.75e-06, - "litellm_provider": "replicate", - "mode": "chat", - "supports_tool_choice": true - }, - "replicate/meta/llama-2-7b": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 5e-08, - "output_cost_per_token": 2.5e-07, - "litellm_provider": "replicate", - "mode": "chat", - "supports_tool_choice": true - }, - "replicate/meta/llama-2-7b-chat": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 5e-08, - "output_cost_per_token": 2.5e-07, - "litellm_provider": "replicate", - "mode": "chat", - "supports_tool_choice": true - }, - "replicate/meta/llama-3-70b": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 6.5e-07, - "output_cost_per_token": 2.75e-06, - "litellm_provider": "replicate", - "mode": "chat", - "supports_tool_choice": true - }, - "replicate/meta/llama-3-70b-instruct": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 6.5e-07, - "output_cost_per_token": 2.75e-06, - "litellm_provider": "replicate", - "mode": "chat", - "supports_tool_choice": true - }, - "replicate/meta/llama-3-8b": { - "max_tokens": 8086, - "max_input_tokens": 8086, - "max_output_tokens": 8086, - "input_cost_per_token": 5e-08, - "output_cost_per_token": 2.5e-07, - "litellm_provider": "replicate", - "mode": "chat", - "supports_tool_choice": true - }, - "replicate/meta/llama-3-8b-instruct": { - "max_tokens": 8086, - "max_input_tokens": 8086, - "max_output_tokens": 8086, - "input_cost_per_token": 5e-08, - "output_cost_per_token": 2.5e-07, - "litellm_provider": "replicate", - "mode": "chat", - "supports_tool_choice": true - }, - "replicate/mistralai/mistral-7b-v0.1": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 5e-08, - "output_cost_per_token": 2.5e-07, - "litellm_provider": "replicate", - "mode": "chat", - "supports_tool_choice": true - }, - "replicate/mistralai/mistral-7b-instruct-v0.2": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 5e-08, - "output_cost_per_token": 2.5e-07, - "litellm_provider": "replicate", - "mode": "chat", - "supports_tool_choice": true - }, - "replicate/mistralai/mixtral-8x7b-instruct-v0.1": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 3e-07, - "output_cost_per_token": 1e-06, - "litellm_provider": "replicate", - "mode": "chat", - "supports_tool_choice": true - }, - "openrouter/deepseek/deepseek-r1-0528": { - "max_tokens": 8192, - "max_input_tokens": 65336, - "max_output_tokens": 8192, - "input_cost_per_token": 5e-07, - "input_cost_per_token_cache_hit": 1.4e-07, - "output_cost_per_token": 2.15e-06, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_function_calling": true, - "supports_assistant_prefill": true, - "supports_reasoning": true, - "supports_tool_choice": true, - "supports_prompt_caching": true - }, - "openrouter/deepseek/deepseek-chat-v3.1": { - "max_tokens": 8192, - "max_input_tokens": 163840, - "max_output_tokens": 163840, - "input_cost_per_token": 2e-07, - "input_cost_per_token_cache_hit": 2e-08, - "output_cost_per_token": 8e-07, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_function_calling": true, - "supports_assistant_prefill": true, - "supports_reasoning": true, - "supports_tool_choice": true, - "supports_prompt_caching": true - }, - "openrouter/x-ai/grok-4": { - "max_tokens": 256000, - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "source": "https://openrouter.ai/x-ai/grok-4", - "supports_web_search": true - }, - "openrouter/bytedance/ui-tars-1.5-7b": { - "max_tokens": 2048, - "max_input_tokens": 131072, - "max_output_tokens": 2048, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 2e-07, - "litellm_provider": "openrouter", - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models/bytedance/ui-tars-1.5-7b", - "supports_tool_choice": true - }, - "openrouter/deepseek/deepseek-r1": { - "max_tokens": 8192, - "max_input_tokens": 65336, - "max_output_tokens": 8192, - "input_cost_per_token": 5.5e-07, - "input_cost_per_token_cache_hit": 1.4e-07, - "output_cost_per_token": 2.19e-06, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_function_calling": true, - "supports_assistant_prefill": true, - "supports_reasoning": true, - "supports_tool_choice": true, - "supports_prompt_caching": true - }, - "openrouter/deepseek/deepseek-chat": { - "max_tokens": 8192, - "max_input_tokens": 65536, - "max_output_tokens": 8192, - "input_cost_per_token": 1.4e-07, - "output_cost_per_token": 2.8e-07, - "litellm_provider": "openrouter", - "supports_prompt_caching": true, - "mode": "chat", - "supports_tool_choice": true - }, - "openrouter/deepseek/deepseek-chat-v3-0324": { - "max_tokens": 8192, - "max_input_tokens": 65536, - "max_output_tokens": 8192, - "input_cost_per_token": 1.4e-07, - "output_cost_per_token": 2.8e-07, - "litellm_provider": "openrouter", - "supports_prompt_caching": true, - "mode": "chat", - "supports_tool_choice": true - }, - "openrouter/deepseek/deepseek-coder": { - "max_tokens": 8192, - "max_input_tokens": 66000, - "max_output_tokens": 4096, - "input_cost_per_token": 1.4e-07, - "output_cost_per_token": 2.8e-07, - "litellm_provider": "openrouter", - "supports_prompt_caching": true, - "mode": "chat", - "supports_tool_choice": true - }, - "openrouter/microsoft/wizardlm-2-8x22b:nitro": { - "max_tokens": 65536, - "input_cost_per_token": 1e-06, - "output_cost_per_token": 1e-06, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_tool_choice": true - }, - "openrouter/google/gemini-2.5-pro": { - "max_tokens": 8192, - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_pdf_size_mb": 30, - "input_cost_per_audio_token": 7e-07, - "input_cost_per_token": 1.25e-06, - "output_cost_per_token": 1e-05, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_system_messages": true, - "supports_function_calling": true, - "supports_vision": true, - "supports_response_schema": true, - "supports_audio_output": true, - "supports_tool_choice": true - }, - "openrouter/google/gemini-pro-1.5": { - "max_tokens": 8192, - "max_input_tokens": 1000000, - "max_output_tokens": 8192, - "input_cost_per_token": 2.5e-06, - "output_cost_per_token": 7.5e-06, - "input_cost_per_image": 0.00265, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "supports_tool_choice": true - }, - "openrouter/google/gemini-2.0-flash-001": { - "max_tokens": 8192, - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_pdf_size_mb": 30, - "input_cost_per_audio_token": 7e-07, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 4e-07, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_system_messages": true, - "supports_function_calling": true, - "supports_vision": true, - "supports_response_schema": true, - "supports_audio_output": true, - "supports_tool_choice": true - }, - "openrouter/google/gemini-2.5-flash": { - "max_tokens": 8192, - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_pdf_size_mb": 30, - "input_cost_per_audio_token": 7e-07, - "input_cost_per_token": 3e-07, - "output_cost_per_token": 2.5e-06, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_system_messages": true, - "supports_function_calling": true, - "supports_vision": true, - "supports_response_schema": true, - "supports_audio_output": true, - "supports_tool_choice": true - }, - "openrouter/mistralai/mixtral-8x22b-instruct": { - "max_tokens": 65536, - "input_cost_per_token": 6.5e-07, - "output_cost_per_token": 6.5e-07, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_tool_choice": true - }, - "openrouter/cohere/command-r-plus": { - "max_tokens": 128000, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_tool_choice": true - }, - "openrouter/databricks/dbrx-instruct": { - "max_tokens": 32768, - "input_cost_per_token": 6e-07, - "output_cost_per_token": 6e-07, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_tool_choice": true - }, - "openrouter/anthropic/claude-3-haiku": { - "max_tokens": 200000, - "input_cost_per_token": 2.5e-07, - "output_cost_per_token": 1.25e-06, - "input_cost_per_image": 0.0004, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "supports_tool_choice": true - }, - "openrouter/anthropic/claude-3-5-haiku": { - "max_tokens": 200000, - "input_cost_per_token": 1e-06, - "output_cost_per_token": 5e-06, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true - }, - "openrouter/anthropic/claude-3-haiku-20240307": { - "max_tokens": 4096, - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "input_cost_per_token": 2.5e-07, - "output_cost_per_token": 1.25e-06, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 264, - "supports_tool_choice": true - }, - "openrouter/anthropic/claude-3-5-haiku-20241022": { - "max_tokens": 8192, - "max_input_tokens": 200000, - "max_output_tokens": 8192, - "input_cost_per_token": 1e-06, - "output_cost_per_token": 5e-06, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_function_calling": true, - "tool_use_system_prompt_tokens": 264, - "supports_tool_choice": true - }, - "openrouter/anthropic/claude-3.5-sonnet": { - "supports_computer_use": true, - "max_tokens": 8192, - "max_input_tokens": 200000, - "max_output_tokens": 8192, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 159, - "supports_assistant_prefill": true, - "supports_tool_choice": true - }, - "openrouter/anthropic/claude-3.5-sonnet:beta": { - "supports_computer_use": true, - "max_tokens": 8192, - "max_input_tokens": 200000, - "max_output_tokens": 8192, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 159, - "supports_tool_choice": true - }, - "openrouter/anthropic/claude-3.7-sonnet": { - "supports_computer_use": true, - "max_tokens": 128000, - "max_input_tokens": 200000, - "max_output_tokens": 128000, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "input_cost_per_image": 0.0048, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "supports_reasoning": true, - "tool_use_system_prompt_tokens": 159, - "supports_assistant_prefill": true, - "supports_tool_choice": true - }, - "openrouter/anthropic/claude-3.7-sonnet:beta": { - "supports_computer_use": true, - "max_tokens": 128000, - "max_input_tokens": 200000, - "max_output_tokens": 128000, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "input_cost_per_image": 0.0048, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "supports_reasoning": true, - "tool_use_system_prompt_tokens": 159, - "supports_tool_choice": true - }, - "openrouter/anthropic/claude-3-sonnet": { - "max_tokens": 200000, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "input_cost_per_image": 0.0048, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "supports_tool_choice": true - }, - "openrouter/anthropic/claude-sonnet-4": { - "supports_computer_use": true, - "max_tokens": 64000, - "max_input_tokens": 200000, - "max_output_tokens": 64000, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "input_cost_per_image": 0.0048, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "supports_reasoning": true, - "tool_use_system_prompt_tokens": 159, - "supports_assistant_prefill": true, - "supports_tool_choice": true - }, - "openrouter/anthropic/claude-opus-4": { - "max_tokens": 32000, - "max_input_tokens": 200000, - "max_output_tokens": 32000, - "input_cost_per_token": 1.5e-05, - "output_cost_per_token": 7.5e-05, - "input_cost_per_image": 0.0048, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 159, - "supports_assistant_prefill": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_computer_use": true - }, - "openrouter/anthropic/claude-opus-4.1": { - "max_tokens": 32000, - "max_input_tokens": 200000, - "max_output_tokens": 32000, - "input_cost_per_token": 1.5e-05, - "output_cost_per_token": 7.5e-05, - "input_cost_per_image": 0.0048, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 159, - "supports_assistant_prefill": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_computer_use": true - }, - "openrouter/mistralai/mistral-large": { - "max_tokens": 32000, - "input_cost_per_token": 8e-06, - "output_cost_per_token": 2.4e-05, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_tool_choice": true - }, - "openrouter/mistralai/mistral-small-3.1-24b-instruct": { - "max_tokens": 32000, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 3e-07, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_tool_choice": true - }, - "openrouter/mistralai/mistral-small-3.2-24b-instruct": { - "max_tokens": 32000, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 3e-07, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_tool_choice": true - }, - "openrouter/cognitivecomputations/dolphin-mixtral-8x7b": { - "max_tokens": 32769, - "input_cost_per_token": 5e-07, - "output_cost_per_token": 5e-07, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_tool_choice": true - }, - "openrouter/google/gemini-pro-vision": { - "max_tokens": 45875, - "input_cost_per_token": 1.25e-07, - "output_cost_per_token": 3.75e-07, - "input_cost_per_image": 0.0025, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "supports_tool_choice": true - }, - "openrouter/fireworks/firellava-13b": { - "max_tokens": 4096, - "input_cost_per_token": 2e-07, - "output_cost_per_token": 2e-07, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_tool_choice": true - }, - "openrouter/meta-llama/llama-3-8b-instruct:free": { - "max_tokens": 8192, - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_tool_choice": true - }, - "openrouter/meta-llama/llama-3-8b-instruct:extended": { - "max_tokens": 16384, - "input_cost_per_token": 2.25e-07, - "output_cost_per_token": 2.25e-06, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_tool_choice": true - }, - "openrouter/meta-llama/llama-3-70b-instruct:nitro": { - "max_tokens": 8192, - "input_cost_per_token": 9e-07, - "output_cost_per_token": 9e-07, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_tool_choice": true - }, - "openrouter/meta-llama/llama-3-70b-instruct": { - "max_tokens": 8192, - "input_cost_per_token": 5.9e-07, - "output_cost_per_token": 7.9e-07, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_tool_choice": true - }, - "openrouter/openai/o1": { - "max_tokens": 100000, - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "input_cost_per_token": 1.5e-05, - "output_cost_per_token": 6e-05, - "cache_read_input_token_cost": 7.5e-06, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "openrouter/openai/o1-mini": { - "max_tokens": 65536, - "max_input_tokens": 128000, - "max_output_tokens": 65536, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.2e-05, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_vision": false, - "supports_tool_choice": true - }, - "openrouter/openai/o1-mini-2024-09-12": { - "max_tokens": 65536, - "max_input_tokens": 128000, - "max_output_tokens": 65536, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.2e-05, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_vision": false, - "supports_tool_choice": true - }, - "openrouter/openai/o1-preview": { - "max_tokens": 32768, - "max_input_tokens": 128000, - "max_output_tokens": 32768, - "input_cost_per_token": 1.5e-05, - "output_cost_per_token": 6e-05, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_vision": false, - "supports_tool_choice": true - }, - "openrouter/openai/o1-preview-2024-09-12": { - "max_tokens": 32768, - "max_input_tokens": 128000, - "max_output_tokens": 32768, - "input_cost_per_token": 1.5e-05, - "output_cost_per_token": 6e-05, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_vision": false, - "supports_tool_choice": true - }, - "openrouter/openai/o3-mini": { - "max_tokens": 65536, - "max_input_tokens": 128000, - "max_output_tokens": 65536, - "input_cost_per_token": 1.1e-06, - "output_cost_per_token": 4.4e-06, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_function_calling": true, - "supports_reasoning": true, - "supports_parallel_function_calling": true, - "supports_vision": false, - "supports_tool_choice": true - }, - "openrouter/openai/o3-mini-high": { - "max_tokens": 65536, - "max_input_tokens": 128000, - "max_output_tokens": 65536, - "input_cost_per_token": 1.1e-06, - "output_cost_per_token": 4.4e-06, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_function_calling": true, - "supports_reasoning": true, - "supports_parallel_function_calling": true, - "supports_vision": false, - "supports_tool_choice": true - }, - "openrouter/openai/gpt-4o": { - "max_tokens": 4096, - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 2.5e-06, - "output_cost_per_token": 1e-05, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_vision": true, - "supports_tool_choice": true - }, - "openrouter/openai/gpt-4o-2024-05-13": { - "max_tokens": 4096, - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 5e-06, - "output_cost_per_token": 1.5e-05, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_vision": true, - "supports_tool_choice": true - }, - "openrouter/openai/gpt-4-vision-preview": { - "max_tokens": 130000, - "input_cost_per_token": 1e-05, - "output_cost_per_token": 3e-05, - "input_cost_per_image": 0.01445, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "supports_tool_choice": true - }, - "openrouter/openai/gpt-3.5-turbo": { - "max_tokens": 4095, - "input_cost_per_token": 1.5e-06, - "output_cost_per_token": 2e-06, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_tool_choice": true - }, - "openrouter/openai/gpt-3.5-turbo-16k": { - "max_tokens": 16383, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 4e-06, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_tool_choice": true - }, - "openrouter/openai/gpt-4": { - "max_tokens": 8192, - "input_cost_per_token": 3e-05, - "output_cost_per_token": 6e-05, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_tool_choice": true - }, - "openrouter/openai/gpt-4.1": { - "max_tokens": 32768, - "max_input_tokens": 1047576, - "max_output_tokens": 32768, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 8e-06, - "cache_read_input_token_cost": 5e-07, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "openrouter/openai/gpt-4.1-2025-04-14": { - "max_tokens": 32768, - "max_input_tokens": 1047576, - "max_output_tokens": 32768, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 8e-06, - "cache_read_input_token_cost": 5e-07, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "openrouter/openai/gpt-4.1-mini": { - "max_tokens": 32768, - "max_input_tokens": 1047576, - "max_output_tokens": 32768, - "input_cost_per_token": 4e-07, - "output_cost_per_token": 1.6e-06, - "cache_read_input_token_cost": 1e-07, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "openrouter/openai/gpt-4.1-mini-2025-04-14": { - "max_tokens": 32768, - "max_input_tokens": 1047576, - "max_output_tokens": 32768, - "input_cost_per_token": 4e-07, - "output_cost_per_token": 1.6e-06, - "cache_read_input_token_cost": 1e-07, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "openrouter/openai/gpt-4.1-nano": { - "max_tokens": 32768, - "max_input_tokens": 1047576, - "max_output_tokens": 32768, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 4e-07, - "cache_read_input_token_cost": 2.5e-08, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "openrouter/openai/gpt-4.1-nano-2025-04-14": { - "max_tokens": 32768, - "max_input_tokens": 1047576, - "max_output_tokens": 32768, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 4e-07, - "cache_read_input_token_cost": 2.5e-08, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "openrouter/openai/gpt-5-mini": { - "max_tokens": 128000, - "max_input_tokens": 400000, - "max_output_tokens": 128000, - "input_cost_per_token": 2.5e-07, - "output_cost_per_token": 2e-06, - "cache_read_input_token_cost": 2.5e-08, - "litellm_provider": "openrouter", - "mode": "chat", - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_tool_choice": true, - "supports_reasoning": true - }, - "openrouter/openai/gpt-5-nano": { - "max_tokens": 128000, - "max_input_tokens": 400000, - "max_output_tokens": 128000, - "input_cost_per_token": 5e-08, - "output_cost_per_token": 4e-07, - "cache_read_input_token_cost": 5e-09, - "litellm_provider": "openrouter", - "mode": "chat", - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_tool_choice": true, - "supports_reasoning": true - }, - "openrouter/openai/gpt-5-chat": { - "max_tokens": 128000, - "max_input_tokens": 400000, - "max_output_tokens": 128000, - "input_cost_per_token": 1.25e-06, - "output_cost_per_token": 1e-05, - "cache_read_input_token_cost": 1.25e-07, - "litellm_provider": "openrouter", - "mode": "chat", - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_tool_choice": true, - "supports_reasoning": true - }, - "openrouter/openai/gpt-oss-20b": { - "max_tokens": 32768, - "max_input_tokens": 131072, - "max_output_tokens": 32768, - "input_cost_per_token": 1.8e-07, - "output_cost_per_token": 8e-07, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_reasoning": true, - "supports_tool_choice": true, - "source": "https://openrouter.ai/openai/gpt-oss-20b" - }, - "openrouter/openai/gpt-oss-120b": { - "max_tokens": 32768, - "max_input_tokens": 131072, - "max_output_tokens": 32768, - "input_cost_per_token": 1.8e-07, - "output_cost_per_token": 8e-07, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_reasoning": true, - "supports_tool_choice": true, - "source": "https://openrouter.ai/openai/gpt-oss-120b" - }, - "openrouter/anthropic/claude-instant-v1": { - "max_tokens": 100000, - "max_output_tokens": 8191, - "input_cost_per_token": 1.63e-06, - "output_cost_per_token": 5.51e-06, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_tool_choice": true - }, - "openrouter/anthropic/claude-2": { - "max_tokens": 100000, - "max_output_tokens": 8191, - "input_cost_per_token": 1.102e-05, - "output_cost_per_token": 3.268e-05, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_tool_choice": true - }, - "openrouter/anthropic/claude-3-opus": { - "max_tokens": 4096, - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "input_cost_per_token": 1.5e-05, - "output_cost_per_token": 7.5e-05, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 395, - "supports_tool_choice": true - }, - "openrouter/google/palm-2-chat-bison": { - "max_tokens": 25804, - "input_cost_per_token": 5e-07, - "output_cost_per_token": 5e-07, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_tool_choice": true - }, - "openrouter/google/palm-2-codechat-bison": { - "max_tokens": 20070, - "input_cost_per_token": 5e-07, - "output_cost_per_token": 5e-07, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_tool_choice": true - }, - "openrouter/meta-llama/llama-2-13b-chat": { - "max_tokens": 4096, - "input_cost_per_token": 2e-07, - "output_cost_per_token": 2e-07, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_tool_choice": true - }, - "openrouter/meta-llama/llama-2-70b-chat": { - "max_tokens": 4096, - "input_cost_per_token": 1.5e-06, - "output_cost_per_token": 1.5e-06, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_tool_choice": true - }, - "openrouter/meta-llama/codellama-34b-instruct": { - "max_tokens": 8192, - "input_cost_per_token": 5e-07, - "output_cost_per_token": 5e-07, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_tool_choice": true - }, - "openrouter/nousresearch/nous-hermes-llama2-13b": { - "max_tokens": 4096, - "input_cost_per_token": 2e-07, - "output_cost_per_token": 2e-07, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_tool_choice": true - }, - "openrouter/mancer/weaver": { - "max_tokens": 8000, - "input_cost_per_token": 5.625e-06, - "output_cost_per_token": 5.625e-06, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_tool_choice": true - }, - "openrouter/gryphe/mythomax-l2-13b": { - "max_tokens": 8192, - "input_cost_per_token": 1.875e-06, - "output_cost_per_token": 1.875e-06, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_tool_choice": true - }, - "openrouter/jondurbin/airoboros-l2-70b-2.1": { - "max_tokens": 4096, - "input_cost_per_token": 1.3875e-05, - "output_cost_per_token": 1.3875e-05, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_tool_choice": true - }, - "openrouter/undi95/remm-slerp-l2-13b": { - "max_tokens": 6144, - "input_cost_per_token": 1.875e-06, - "output_cost_per_token": 1.875e-06, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_tool_choice": true - }, - "openrouter/pygmalionai/mythalion-13b": { - "max_tokens": 4096, - "input_cost_per_token": 1.875e-06, - "output_cost_per_token": 1.875e-06, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_tool_choice": true - }, - "openrouter/mistralai/mistral-7b-instruct": { - "max_tokens": 8192, - "input_cost_per_token": 1.3e-07, - "output_cost_per_token": 1.3e-07, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_tool_choice": true - }, - "openrouter/mistralai/mistral-7b-instruct:free": { - "max_tokens": 8192, - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_tool_choice": true - }, - "openrouter/qwen/qwen-2.5-coder-32b-instruct": { - "max_tokens": 33792, - "max_input_tokens": 33792, - "max_output_tokens": 33792, - "input_cost_per_token": 1.8e-07, - "output_cost_per_token": 1.8e-07, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_tool_choice": true - }, - "openrouter/qwen/qwen-vl-plus": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 2048, - "input_cost_per_token": 2.1e-07, - "output_cost_per_token": 6.3e-07, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_tool_choice": true - }, - "openrouter/qwen/qwen3-coder": { - "max_tokens": 1000000, - "max_input_tokens": 1000000, - "max_output_tokens": 1000000, - "input_cost_per_token": 1e-06, - "output_cost_per_token": 5e-06, - "litellm_provider": "openrouter", - "source": "https://openrouter.ai/qwen/qwen3-coder", - "mode": "chat", - "supports_tool_choice": true - }, - "openrouter/switchpoint/router": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 8.5e-07, - "output_cost_per_token": 3.4e-06, - "litellm_provider": "openrouter", - "source": "https://openrouter.ai/switchpoint/router", - "mode": "chat", - "supports_tool_choice": true - }, - "j2-ultra": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 1.5e-05, - "output_cost_per_token": 1.5e-05, - "litellm_provider": "ai21", - "mode": "completion" - }, - "jamba-1.5-mini@001": { - "max_tokens": 256000, - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "input_cost_per_token": 2e-07, - "output_cost_per_token": 4e-07, - "litellm_provider": "ai21", - "mode": "chat", - "supports_tool_choice": true - }, - "jamba-1.5-large@001": { - "max_tokens": 256000, - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 8e-06, - "litellm_provider": "ai21", - "mode": "chat", - "supports_tool_choice": true - }, - "jamba-1.5": { - "max_tokens": 256000, - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "input_cost_per_token": 2e-07, - "output_cost_per_token": 4e-07, - "litellm_provider": "ai21", - "mode": "chat", - "supports_tool_choice": true - }, - "jamba-1.5-mini": { - "max_tokens": 256000, - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "input_cost_per_token": 2e-07, - "output_cost_per_token": 4e-07, - "litellm_provider": "ai21", - "mode": "chat", - "supports_tool_choice": true - }, - "jamba-1.5-large": { - "max_tokens": 256000, - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 8e-06, - "litellm_provider": "ai21", - "mode": "chat", - "supports_tool_choice": true - }, - "jamba-large-1.6": { - "max_tokens": 256000, - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 8e-06, - "litellm_provider": "ai21", - "mode": "chat", - "supports_tool_choice": true - }, - "jamba-large-1.7": { - "max_tokens": 256000, - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 8e-06, - "litellm_provider": "ai21", - "mode": "chat", - "supports_tool_choice": true - }, - "jamba-mini-1.6": { - "max_tokens": 256000, - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "input_cost_per_token": 2e-07, - "output_cost_per_token": 4e-07, - "litellm_provider": "ai21", - "mode": "chat", - "supports_tool_choice": true - }, - "jamba-mini-1.7": { - "max_tokens": 256000, - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "input_cost_per_token": 2e-07, - "output_cost_per_token": 4e-07, - "litellm_provider": "ai21", - "mode": "chat", - "supports_tool_choice": true - }, - "j2-mid": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 1e-05, - "output_cost_per_token": 1e-05, - "litellm_provider": "ai21", - "mode": "completion" - }, - "j2-light": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 3e-06, - "litellm_provider": "ai21", - "mode": "completion" - }, - "dolphin": { - "max_tokens": 16384, - "max_input_tokens": 16384, - "max_output_tokens": 16384, - "input_cost_per_token": 5e-07, - "output_cost_per_token": 5e-07, - "litellm_provider": "nlp_cloud", - "mode": "completion" - }, - "chatdolphin": { - "max_tokens": 16384, - "max_input_tokens": 16384, - "max_output_tokens": 16384, - "input_cost_per_token": 5e-07, - "output_cost_per_token": 5e-07, - "litellm_provider": "nlp_cloud", - "mode": "chat" - }, - "luminous-base": { - "max_tokens": 2048, - "input_cost_per_token": 3e-05, - "output_cost_per_token": 3.3e-05, - "litellm_provider": "aleph_alpha", - "mode": "completion" - }, - "luminous-base-control": { - "max_tokens": 2048, - "input_cost_per_token": 3.75e-05, - "output_cost_per_token": 4.125e-05, - "litellm_provider": "aleph_alpha", - "mode": "chat" - }, - "luminous-extended": { - "max_tokens": 2048, - "input_cost_per_token": 4.5e-05, - "output_cost_per_token": 4.95e-05, - "litellm_provider": "aleph_alpha", - "mode": "completion" - }, - "luminous-extended-control": { - "max_tokens": 2048, - "input_cost_per_token": 5.625e-05, - "output_cost_per_token": 6.1875e-05, - "litellm_provider": "aleph_alpha", - "mode": "chat" - }, - "luminous-supreme": { - "max_tokens": 2048, - "input_cost_per_token": 0.000175, - "output_cost_per_token": 0.0001925, - "litellm_provider": "aleph_alpha", - "mode": "completion" - }, - "luminous-supreme-control": { - "max_tokens": 2048, - "input_cost_per_token": 0.00021875, - "output_cost_per_token": 0.000240625, - "litellm_provider": "aleph_alpha", - "mode": "chat" - }, - "ai21.j2-mid-v1": { - "max_tokens": 8191, - "max_input_tokens": 8191, - "max_output_tokens": 8191, - "input_cost_per_token": 1.25e-05, - "output_cost_per_token": 1.25e-05, - "litellm_provider": "bedrock", - "mode": "chat" - }, - "ai21.j2-ultra-v1": { - "max_tokens": 8191, - "max_input_tokens": 8191, - "max_output_tokens": 8191, - "input_cost_per_token": 1.88e-05, - "output_cost_per_token": 1.88e-05, - "litellm_provider": "bedrock", - "mode": "chat" - }, - "ai21.jamba-instruct-v1:0": { - "max_tokens": 4096, - "max_input_tokens": 70000, - "max_output_tokens": 4096, - "input_cost_per_token": 5e-07, - "output_cost_per_token": 7e-07, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_system_messages": true - }, - "ai21.jamba-1-5-large-v1:0": { - "max_tokens": 256000, - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 8e-06, - "litellm_provider": "bedrock", - "mode": "chat" - }, - "ai21.jamba-1-5-mini-v1:0": { - "max_tokens": 256000, - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "input_cost_per_token": 2e-07, - "output_cost_per_token": 4e-07, - "litellm_provider": "bedrock", - "mode": "chat" - }, - "amazon.rerank-v1:0": { - "max_tokens": 32000, - "max_input_tokens": 32000, - "max_output_tokens": 32000, - "max_query_tokens": 32000, - "max_document_chunks_per_query": 100, - "max_tokens_per_document_chunk": 512, - "input_cost_per_token": 0.0, - "input_cost_per_query": 0.001, - "output_cost_per_token": 0.0, - "litellm_provider": "bedrock", - "mode": "rerank" - }, - "amazon.titan-text-lite-v1": { - "max_tokens": 4000, - "max_input_tokens": 42000, - "max_output_tokens": 4000, - "input_cost_per_token": 3e-07, - "output_cost_per_token": 4e-07, - "litellm_provider": "bedrock", - "mode": "chat" - }, - "amazon.titan-text-express-v1": { - "max_tokens": 8000, - "max_input_tokens": 42000, - "max_output_tokens": 8000, - "input_cost_per_token": 1.3e-06, - "output_cost_per_token": 1.7e-06, - "litellm_provider": "bedrock", - "mode": "chat" - }, - "amazon.titan-text-premier-v1:0": { - "max_tokens": 32000, - "max_input_tokens": 42000, - "max_output_tokens": 32000, - "input_cost_per_token": 5e-07, - "output_cost_per_token": 1.5e-06, - "litellm_provider": "bedrock", - "mode": "chat" - }, - "amazon.titan-embed-text-v1": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "output_vector_size": 1536, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 0.0, - "litellm_provider": "bedrock", - "mode": "embedding" - }, - "amazon.titan-embed-text-v2:0": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "output_vector_size": 1024, - "input_cost_per_token": 2e-07, - "output_cost_per_token": 0.0, - "litellm_provider": "bedrock", - "mode": "embedding" - }, - "amazon.titan-embed-image-v1": { - "max_tokens": 128, - "max_input_tokens": 128, - "output_vector_size": 1024, - "input_cost_per_token": 8e-07, - "input_cost_per_image": 6e-05, - "output_cost_per_token": 0.0, - "litellm_provider": "bedrock", - "supports_image_input": true, - "supports_embedding_image_input": true, - "mode": "embedding", - "source": "https://us-east-1.console.aws.amazon.com/bedrock/home?region=us-east-1#/providers?model=amazon.titan-image-generator-v1", - "metadata": { - "notes": "'supports_image_input' is a deprecated field. Use 'supports_embedding_image_input' instead." - } - }, - "mistral.mistral-7b-instruct-v0:2": { - "max_tokens": 8191, - "max_input_tokens": 32000, - "max_output_tokens": 8191, - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 2e-07, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_tool_choice": true - }, - "mistral.mixtral-8x7b-instruct-v0:1": { - "max_tokens": 8191, - "max_input_tokens": 32000, - "max_output_tokens": 8191, - "input_cost_per_token": 4.5e-07, - "output_cost_per_token": 7e-07, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_tool_choice": true - }, - "mistral.mistral-large-2402-v1:0": { - "max_tokens": 8191, - "max_input_tokens": 32000, - "max_output_tokens": 8191, - "input_cost_per_token": 8e-06, - "output_cost_per_token": 2.4e-05, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_function_calling": true - }, - "mistral.mistral-large-2407-v1:0": { - "max_tokens": 8191, - "max_input_tokens": 128000, - "max_output_tokens": 8191, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 9e-06, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true - }, - "mistral.mistral-small-2402-v1:0": { - "max_tokens": 8191, - "max_input_tokens": 32000, - "max_output_tokens": 8191, - "input_cost_per_token": 1e-06, - "output_cost_per_token": 3e-06, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_function_calling": true - }, - "eu.mistral.pixtral-large-2502-v1:0": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 6e-06, - "litellm_provider": "bedrock_converse", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": false - }, - "us.mistral.pixtral-large-2502-v1:0": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 6e-06, - "litellm_provider": "bedrock_converse", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": false - }, - "bedrock/us-west-2/mistral.mixtral-8x7b-instruct-v0:1": { - "max_tokens": 8191, - "max_input_tokens": 32000, - "max_output_tokens": 8191, - "input_cost_per_token": 4.5e-07, - "output_cost_per_token": 7e-07, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_tool_choice": true - }, - "bedrock/us-east-1/mistral.mixtral-8x7b-instruct-v0:1": { - "max_tokens": 8191, - "max_input_tokens": 32000, - "max_output_tokens": 8191, - "input_cost_per_token": 4.5e-07, - "output_cost_per_token": 7e-07, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_tool_choice": true - }, - "bedrock/eu-west-3/mistral.mixtral-8x7b-instruct-v0:1": { - "max_tokens": 8191, - "max_input_tokens": 32000, - "max_output_tokens": 8191, - "input_cost_per_token": 5.9e-07, - "output_cost_per_token": 9.1e-07, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_tool_choice": true - }, - "bedrock/us-west-2/mistral.mistral-7b-instruct-v0:2": { - "max_tokens": 8191, - "max_input_tokens": 32000, - "max_output_tokens": 8191, - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 2e-07, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_tool_choice": true - }, - "bedrock/us-east-1/mistral.mistral-7b-instruct-v0:2": { - "max_tokens": 8191, - "max_input_tokens": 32000, - "max_output_tokens": 8191, - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 2e-07, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_tool_choice": true - }, - "bedrock/eu-west-3/mistral.mistral-7b-instruct-v0:2": { - "max_tokens": 8191, - "max_input_tokens": 32000, - "max_output_tokens": 8191, - "input_cost_per_token": 2e-07, - "output_cost_per_token": 2.6e-07, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_tool_choice": true - }, - "bedrock/us-east-1/mistral.mistral-large-2402-v1:0": { - "max_tokens": 8191, - "max_input_tokens": 32000, - "max_output_tokens": 8191, - "input_cost_per_token": 8e-06, - "output_cost_per_token": 2.4e-05, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_function_calling": true - }, - "bedrock/us-west-2/mistral.mistral-large-2402-v1:0": { - "max_tokens": 8191, - "max_input_tokens": 32000, - "max_output_tokens": 8191, - "input_cost_per_token": 8e-06, - "output_cost_per_token": 2.4e-05, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_function_calling": true - }, - "bedrock/eu-west-3/mistral.mistral-large-2402-v1:0": { - "max_tokens": 8191, - "max_input_tokens": 32000, - "max_output_tokens": 8191, - "input_cost_per_token": 1.04e-05, - "output_cost_per_token": 3.12e-05, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_function_calling": true - }, - "amazon.nova-micro-v1:0": { - "max_tokens": 10000, - "max_input_tokens": 128000, - "max_output_tokens": 10000, - "input_cost_per_token": 3.5e-08, - "output_cost_per_token": 1.4e-07, - "litellm_provider": "bedrock_converse", - "mode": "chat", - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_response_schema": true - }, - "us.amazon.nova-micro-v1:0": { - "max_tokens": 10000, - "max_input_tokens": 128000, - "max_output_tokens": 10000, - "input_cost_per_token": 3.5e-08, - "output_cost_per_token": 1.4e-07, - "litellm_provider": "bedrock_converse", - "mode": "chat", - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_response_schema": true - }, - "eu.amazon.nova-micro-v1:0": { - "max_tokens": 10000, - "max_input_tokens": 128000, - "max_output_tokens": 10000, - "input_cost_per_token": 4.6e-08, - "output_cost_per_token": 1.84e-07, - "litellm_provider": "bedrock_converse", - "mode": "chat", - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_response_schema": true - }, - "amazon.nova-lite-v1:0": { - "max_tokens": 10000, - "max_input_tokens": 300000, - "max_output_tokens": 10000, - "input_cost_per_token": 6e-08, - "output_cost_per_token": 2.4e-07, - "litellm_provider": "bedrock_converse", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_response_schema": true - }, - "us.amazon.nova-lite-v1:0": { - "max_tokens": 10000, - "max_input_tokens": 300000, - "max_output_tokens": 10000, - "input_cost_per_token": 6e-08, - "output_cost_per_token": 2.4e-07, - "litellm_provider": "bedrock_converse", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_response_schema": true - }, - "eu.amazon.nova-lite-v1:0": { - "max_tokens": 10000, - "max_input_tokens": 300000, - "max_output_tokens": 10000, - "input_cost_per_token": 7.8e-08, - "output_cost_per_token": 3.12e-07, - "litellm_provider": "bedrock_converse", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_response_schema": true - }, - "amazon.nova-pro-v1:0": { - "max_tokens": 10000, - "max_input_tokens": 300000, - "max_output_tokens": 10000, - "input_cost_per_token": 8e-07, - "output_cost_per_token": 3.2e-06, - "litellm_provider": "bedrock_converse", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_response_schema": true - }, - "us.amazon.nova-pro-v1:0": { - "max_tokens": 10000, - "max_input_tokens": 300000, - "max_output_tokens": 10000, - "input_cost_per_token": 8e-07, - "output_cost_per_token": 3.2e-06, - "litellm_provider": "bedrock_converse", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_response_schema": true - }, - "1024-x-1024/50-steps/bedrock/amazon.nova-canvas-v1:0": { - "max_input_tokens": 2600, + "gemini/imagen-4.0-generate-001": { + "litellm_provider": "gemini", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" + }, + "gemini/imagen-4.0-ultra-generate-001": { + "litellm_provider": "gemini", + "mode": "image_generation", "output_cost_per_image": 0.06, - "litellm_provider": "bedrock", - "mode": "image_generation" - }, - "eu.amazon.nova-pro-v1:0": { - "max_tokens": 10000, - "max_input_tokens": 300000, - "max_output_tokens": 10000, - "input_cost_per_token": 1.05e-06, - "output_cost_per_token": 4.2e-06, - "litellm_provider": "bedrock_converse", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "source": "https://aws.amazon.com/bedrock/pricing/" - }, - "apac.amazon.nova-micro-v1:0": { - "max_tokens": 10000, - "max_input_tokens": 128000, - "max_output_tokens": 10000, - "input_cost_per_token": 3.7e-08, - "output_cost_per_token": 1.48e-07, - "litellm_provider": "bedrock_converse", - "mode": "chat", - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_response_schema": true - }, - "apac.amazon.nova-lite-v1:0": { - "max_tokens": 10000, - "max_input_tokens": 300000, - "max_output_tokens": 10000, - "input_cost_per_token": 6.3e-08, - "output_cost_per_token": 2.52e-07, - "litellm_provider": "bedrock_converse", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_response_schema": true - }, - "apac.amazon.nova-pro-v1:0": { - "max_tokens": 10000, - "max_input_tokens": 300000, - "max_output_tokens": 10000, - "input_cost_per_token": 8.4e-07, - "output_cost_per_token": 3.36e-06, - "litellm_provider": "bedrock_converse", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_response_schema": true - }, - "us.amazon.nova-premier-v1:0": { - "max_tokens": 10000, - "max_input_tokens": 1000000, - "max_output_tokens": 10000, - "input_cost_per_token": 2.5e-06, - "output_cost_per_token": 1.25e-05, - "litellm_provider": "bedrock_converse", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_prompt_caching": false, - "supports_response_schema": true - }, - "anthropic.claude-3-sonnet-20240229-v1:0": { - "max_tokens": 4096, - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_tool_choice": true - }, - "bedrock/invoke/anthropic.claude-3-5-sonnet-20240620-v1:0": { - "max_tokens": 4096, - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_tool_choice": true, - "metadata": { - "notes": "Anthropic via Invoke route does not currently support pdf input." - } - }, - "anthropic.claude-3-5-sonnet-20240620-v1:0": { - "max_tokens": 4096, - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_tool_choice": true - }, - "openai.gpt-oss-20b-1:0": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "input_cost_per_token": 7e-08, - "output_cost_per_token": 3e-07, - "litellm_provider": "bedrock_converse", - "mode": "chat", - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_function_calling": true, - "supports_reasoning": true - }, - "openai.gpt-oss-120b-1:0": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 6e-07, - "litellm_provider": "bedrock_converse", - "mode": "chat", - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_function_calling": true, - "supports_reasoning": true - }, - "anthropic.claude-opus-4-1-20250805-v1:0": { - "max_tokens": 32000, - "max_input_tokens": 200000, - "max_output_tokens": 32000, - "input_cost_per_token": 1.5e-05, - "output_cost_per_token": 7.5e-05, - "search_context_cost_per_query": { - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01, - "search_context_size_high": 0.01 - }, - "cache_creation_input_token_cost": 1.875e-05, - "cache_read_input_token_cost": 1.5e-06, - "litellm_provider": "bedrock_converse", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 159, - "supports_assistant_prefill": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_computer_use": true - }, - "anthropic.claude-opus-4-20250514-v1:0": { - "max_tokens": 32000, - "max_input_tokens": 200000, - "max_output_tokens": 32000, - "input_cost_per_token": 1.5e-05, - "output_cost_per_token": 7.5e-05, - "search_context_cost_per_query": { - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01, - "search_context_size_high": 0.01 - }, - "cache_creation_input_token_cost": 1.875e-05, - "cache_read_input_token_cost": 1.5e-06, - "litellm_provider": "bedrock_converse", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 159, - "supports_assistant_prefill": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_computer_use": true - }, - "anthropic.claude-sonnet-4-20250514-v1:0": { - "max_tokens": 64000, - "max_input_tokens": 200000, - "max_output_tokens": 64000, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "search_context_cost_per_query": { - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01, - "search_context_size_high": 0.01 - }, - "cache_creation_input_token_cost": 3.75e-06, - "cache_read_input_token_cost": 3e-07, - "litellm_provider": "bedrock_converse", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 159, - "supports_assistant_prefill": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_computer_use": true - }, - "anthropic.claude-3-7-sonnet-20250219-v1:0": { - "supports_computer_use": true, - "max_tokens": 8192, - "max_input_tokens": 200000, - "max_output_tokens": 8192, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "cache_creation_input_token_cost": 3.75e-06, - "cache_read_input_token_cost": 3e-07, - "litellm_provider": "bedrock_converse", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "supports_assistant_prefill": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_pdf_input": true, - "supports_reasoning": true, - "supports_tool_choice": true - }, - "anthropic.claude-3-5-sonnet-20241022-v2:0": { - "supports_computer_use": true, - "max_tokens": 8192, - "max_input_tokens": 200000, - "max_output_tokens": 8192, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "cache_creation_input_token_cost": 3.75e-06, - "cache_read_input_token_cost": 3e-07, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_assistant_prefill": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "anthropic.claude-3-haiku-20240307-v1:0": { - "max_tokens": 4096, - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "input_cost_per_token": 2.5e-07, - "output_cost_per_token": 1.25e-06, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_tool_choice": true - }, - "anthropic.claude-3-5-haiku-20241022-v1:0": { - "max_tokens": 8192, - "max_input_tokens": 200000, - "max_output_tokens": 8192, - "input_cost_per_token": 8e-07, - "output_cost_per_token": 4e-06, - "cache_creation_input_token_cost": 1e-06, - "cache_read_input_token_cost": 8e-08, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_assistant_prefill": true, - "supports_pdf_input": true, - "supports_function_calling": true, - "supports_response_schema": true, - "supports_prompt_caching": true, - "supports_tool_choice": true - }, - "anthropic.claude-3-opus-20240229-v1:0": { - "max_tokens": 4096, - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "input_cost_per_token": 1.5e-05, - "output_cost_per_token": 7.5e-05, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_tool_choice": true - }, - "us.anthropic.claude-3-sonnet-20240229-v1:0": { - "max_tokens": 4096, - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_tool_choice": true - }, - "us.anthropic.claude-3-5-sonnet-20240620-v1:0": { - "max_tokens": 4096, - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_tool_choice": true - }, - "us.anthropic.claude-3-5-sonnet-20241022-v2:0": { - "supports_computer_use": true, - "max_tokens": 8192, - "max_input_tokens": 200000, - "max_output_tokens": 8192, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "cache_creation_input_token_cost": 3.75e-06, - "cache_read_input_token_cost": 3e-07, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_assistant_prefill": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "us.anthropic.claude-3-7-sonnet-20250219-v1:0": { - "supports_computer_use": true, - "max_tokens": 8192, - "max_input_tokens": 200000, - "max_output_tokens": 8192, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "cache_creation_input_token_cost": 3.75e-06, - "cache_read_input_token_cost": 3e-07, - "litellm_provider": "bedrock_converse", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "supports_assistant_prefill": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_pdf_input": true, - "supports_tool_choice": true, - "supports_reasoning": true - }, - "us.anthropic.claude-opus-4-1-20250805-v1:0": { - "max_tokens": 32000, - "max_input_tokens": 200000, - "max_output_tokens": 32000, - "input_cost_per_token": 1.5e-05, - "output_cost_per_token": 7.5e-05, - "search_context_cost_per_query": { - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01, - "search_context_size_high": 0.01 - }, - "cache_creation_input_token_cost": 1.875e-05, - "cache_read_input_token_cost": 1.5e-06, - "litellm_provider": "bedrock_converse", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 159, - "supports_assistant_prefill": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_computer_use": true - }, - "us.anthropic.claude-opus-4-20250514-v1:0": { - "max_tokens": 32000, - "max_input_tokens": 200000, - "max_output_tokens": 32000, - "input_cost_per_token": 1.5e-05, - "output_cost_per_token": 7.5e-05, - "search_context_cost_per_query": { - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01, - "search_context_size_high": 0.01 - }, - "cache_creation_input_token_cost": 1.875e-05, - "cache_read_input_token_cost": 1.5e-06, - "litellm_provider": "bedrock_converse", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 159, - "supports_assistant_prefill": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_computer_use": true - }, - "us.anthropic.claude-sonnet-4-20250514-v1:0": { - "max_tokens": 64000, - "max_input_tokens": 200000, - "max_output_tokens": 64000, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "search_context_cost_per_query": { - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01, - "search_context_size_high": 0.01 - }, - "cache_creation_input_token_cost": 3.75e-06, - "cache_read_input_token_cost": 3e-07, - "litellm_provider": "bedrock_converse", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 159, - "supports_assistant_prefill": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_computer_use": true - }, - "us.anthropic.claude-3-haiku-20240307-v1:0": { - "max_tokens": 4096, - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "input_cost_per_token": 2.5e-07, - "output_cost_per_token": 1.25e-06, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_tool_choice": true - }, - "us.anthropic.claude-3-5-haiku-20241022-v1:0": { - "max_tokens": 8192, - "max_input_tokens": 200000, - "max_output_tokens": 8192, - "input_cost_per_token": 8e-07, - "output_cost_per_token": 4e-06, - "cache_creation_input_token_cost": 1e-06, - "cache_read_input_token_cost": 8e-08, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_assistant_prefill": true, - "supports_pdf_input": true, - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "bedrock/us.anthropic.claude-3-5-haiku-20241022-v1:0": { - "max_tokens": 8192, - "max_input_tokens": 200000, - "max_output_tokens": 8192, - "input_cost_per_token": 8e-07, - "output_cost_per_token": 4e-06, - "cache_creation_input_token_cost": 1e-06, - "cache_read_input_token_cost": 8e-08, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_assistant_prefill": true, - "supports_pdf_input": true, - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "us.anthropic.claude-3-opus-20240229-v1:0": { - "max_tokens": 4096, - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "input_cost_per_token": 1.5e-05, - "output_cost_per_token": 7.5e-05, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_tool_choice": true - }, - "eu.anthropic.claude-3-sonnet-20240229-v1:0": { - "max_tokens": 4096, - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_tool_choice": true - }, - "eu.anthropic.claude-3-5-sonnet-20240620-v1:0": { - "max_tokens": 4096, - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_tool_choice": true - }, - "eu.anthropic.claude-3-5-sonnet-20241022-v2:0": { - "supports_computer_use": true, - "max_tokens": 8192, - "max_input_tokens": 200000, - "max_output_tokens": 8192, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_assistant_prefill": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "eu.anthropic.claude-3-7-sonnet-20250219-v1:0": { - "supports_computer_use": true, - "max_tokens": 8192, - "max_input_tokens": 200000, - "max_output_tokens": 8192, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "supports_assistant_prefill": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_pdf_input": true, - "supports_tool_choice": true, - "supports_reasoning": true - }, - "eu.anthropic.claude-3-haiku-20240307-v1:0": { - "max_tokens": 4096, - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "input_cost_per_token": 2.5e-07, - "output_cost_per_token": 1.25e-06, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_tool_choice": true - }, - "eu.anthropic.claude-opus-4-1-20250805-v1:0": { - "max_tokens": 32000, - "max_input_tokens": 200000, - "max_output_tokens": 32000, - "input_cost_per_token": 1.5e-05, - "output_cost_per_token": 7.5e-05, - "search_context_cost_per_query": { - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01, - "search_context_size_high": 0.01 - }, - "cache_creation_input_token_cost": 1.875e-05, - "cache_read_input_token_cost": 1.5e-06, - "litellm_provider": "bedrock_converse", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 159, - "supports_assistant_prefill": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_computer_use": true - }, - "eu.anthropic.claude-opus-4-20250514-v1:0": { - "max_tokens": 32000, - "max_input_tokens": 200000, - "max_output_tokens": 32000, - "input_cost_per_token": 1.5e-05, - "output_cost_per_token": 7.5e-05, - "search_context_cost_per_query": { - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01, - "search_context_size_high": 0.01 - }, - "cache_creation_input_token_cost": 1.875e-05, - "cache_read_input_token_cost": 1.5e-06, - "litellm_provider": "bedrock_converse", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 159, - "supports_assistant_prefill": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_computer_use": true - }, - "eu.anthropic.claude-sonnet-4-20250514-v1:0": { - "max_tokens": 64000, - "max_input_tokens": 200000, - "max_output_tokens": 64000, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "search_context_cost_per_query": { - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01, - "search_context_size_high": 0.01 - }, - "cache_creation_input_token_cost": 3.75e-06, - "cache_read_input_token_cost": 3e-07, - "litellm_provider": "bedrock_converse", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 159, - "supports_assistant_prefill": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_computer_use": true - }, - "apac.anthropic.claude-3-haiku-20240307-v1:0": { - "max_tokens": 4096, - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "input_cost_per_token": 2.5e-07, - "output_cost_per_token": 1.25e-06, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_tool_choice": true - }, - "apac.anthropic.claude-3-sonnet-20240229-v1:0": { - "max_tokens": 4096, - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_tool_choice": true - }, - "apac.anthropic.claude-3-5-sonnet-20240620-v1:0": { - "max_tokens": 4096, - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_tool_choice": true - }, - "apac.anthropic.claude-3-5-sonnet-20241022-v2:0": { - "max_tokens": 8192, - "max_input_tokens": 200000, - "max_output_tokens": 8192, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "cache_creation_input_token_cost": 3.75e-06, - "cache_read_input_token_cost": 3e-07, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "supports_assistant_prefill": true, - "supports_computer_use": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "apac.anthropic.claude-sonnet-4-20250514-v1:0": { - "max_tokens": 64000, - "max_input_tokens": 200000, - "max_output_tokens": 64000, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "search_context_cost_per_query": { - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01, - "search_context_size_high": 0.01 - }, - "cache_creation_input_token_cost": 3.75e-06, - "cache_read_input_token_cost": 3e-07, - "litellm_provider": "bedrock_converse", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 159, - "supports_assistant_prefill": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_computer_use": true - }, - "eu.anthropic.claude-3-5-haiku-20241022-v1:0": { - "max_tokens": 8192, - "max_input_tokens": 200000, - "max_output_tokens": 8192, - "input_cost_per_token": 2.5e-07, - "output_cost_per_token": 1.25e-06, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_function_calling": true, - "supports_assistant_prefill": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "eu.anthropic.claude-3-opus-20240229-v1:0": { - "max_tokens": 4096, - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "input_cost_per_token": 1.5e-05, - "output_cost_per_token": 7.5e-05, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_tool_choice": true - }, - "anthropic.claude-v1": { - "max_tokens": 8191, - "max_input_tokens": 100000, - "max_output_tokens": 8191, - "input_cost_per_token": 8e-06, - "output_cost_per_token": 2.4e-05, - "litellm_provider": "bedrock", - "mode": "chat" - }, - "bedrock/us-east-1/anthropic.claude-v1": { - "max_tokens": 8191, - "max_input_tokens": 100000, - "max_output_tokens": 8191, - "input_cost_per_token": 8e-06, - "output_cost_per_token": 2.4e-05, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_tool_choice": true - }, - "bedrock/us-west-2/anthropic.claude-v1": { - "max_tokens": 8191, - "max_input_tokens": 100000, - "max_output_tokens": 8191, - "input_cost_per_token": 8e-06, - "output_cost_per_token": 2.4e-05, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_tool_choice": true - }, - "bedrock/ap-northeast-1/anthropic.claude-v1": { - "max_tokens": 8191, - "max_input_tokens": 100000, - "max_output_tokens": 8191, - "input_cost_per_token": 8e-06, - "output_cost_per_token": 2.4e-05, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_tool_choice": true - }, - "bedrock/ap-northeast-1/1-month-commitment/anthropic.claude-v1": { - "max_tokens": 8191, - "max_input_tokens": 100000, - "max_output_tokens": 8191, - "input_cost_per_second": 0.0455, - "output_cost_per_second": 0.0455, - "litellm_provider": "bedrock", - "mode": "chat" - }, - "bedrock/ap-northeast-1/6-month-commitment/anthropic.claude-v1": { - "max_tokens": 8191, - "max_input_tokens": 100000, - "max_output_tokens": 8191, - "input_cost_per_second": 0.02527, - "output_cost_per_second": 0.02527, - "litellm_provider": "bedrock", - "mode": "chat" - }, - "bedrock/eu-central-1/anthropic.claude-v1": { - "max_tokens": 8191, - "max_input_tokens": 100000, - "max_output_tokens": 8191, - "input_cost_per_token": 8e-06, - "output_cost_per_token": 2.4e-05, - "litellm_provider": "bedrock", - "mode": "chat" - }, - "bedrock/eu-central-1/1-month-commitment/anthropic.claude-v1": { - "max_tokens": 8191, - "max_input_tokens": 100000, - "max_output_tokens": 8191, - "input_cost_per_second": 0.0415, - "output_cost_per_second": 0.0415, - "litellm_provider": "bedrock", - "mode": "chat" - }, - "bedrock/eu-central-1/6-month-commitment/anthropic.claude-v1": { - "max_tokens": 8191, - "max_input_tokens": 100000, - "max_output_tokens": 8191, - "input_cost_per_second": 0.02305, - "output_cost_per_second": 0.02305, - "litellm_provider": "bedrock", - "mode": "chat" - }, - "bedrock/us-east-1/1-month-commitment/anthropic.claude-v1": { - "max_tokens": 8191, - "max_input_tokens": 100000, - "max_output_tokens": 8191, - "input_cost_per_second": 0.0175, - "output_cost_per_second": 0.0175, - "litellm_provider": "bedrock", - "mode": "chat" - }, - "bedrock/us-east-1/6-month-commitment/anthropic.claude-v1": { - "max_tokens": 8191, - "max_input_tokens": 100000, - "max_output_tokens": 8191, - "input_cost_per_second": 0.00972, - "output_cost_per_second": 0.00972, - "litellm_provider": "bedrock", - "mode": "chat" - }, - "bedrock/us-west-2/1-month-commitment/anthropic.claude-v1": { - "max_tokens": 8191, - "max_input_tokens": 100000, - "max_output_tokens": 8191, - "input_cost_per_second": 0.0175, - "output_cost_per_second": 0.0175, - "litellm_provider": "bedrock", - "mode": "chat" - }, - "bedrock/us-west-2/6-month-commitment/anthropic.claude-v1": { - "max_tokens": 8191, - "max_input_tokens": 100000, - "max_output_tokens": 8191, - "input_cost_per_second": 0.00972, - "output_cost_per_second": 0.00972, - "litellm_provider": "bedrock", - "mode": "chat" - }, - "anthropic.claude-v2:1": { - "max_tokens": 8191, - "max_input_tokens": 100000, - "max_output_tokens": 8191, - "input_cost_per_token": 8e-06, - "output_cost_per_token": 2.4e-05, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_tool_choice": true - }, - "bedrock/us-east-1/anthropic.claude-v2:1": { - "max_tokens": 8191, - "max_input_tokens": 100000, - "max_output_tokens": 8191, - "input_cost_per_token": 8e-06, - "output_cost_per_token": 2.4e-05, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_tool_choice": true - }, - "bedrock/us-west-2/anthropic.claude-v2:1": { - "max_tokens": 8191, - "max_input_tokens": 100000, - "max_output_tokens": 8191, - "input_cost_per_token": 8e-06, - "output_cost_per_token": 2.4e-05, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_tool_choice": true - }, - "bedrock/ap-northeast-1/anthropic.claude-v2:1": { - "max_tokens": 8191, - "max_input_tokens": 100000, - "max_output_tokens": 8191, - "input_cost_per_token": 8e-06, - "output_cost_per_token": 2.4e-05, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_tool_choice": true - }, - "bedrock/ap-northeast-1/1-month-commitment/anthropic.claude-v2:1": { - "max_tokens": 8191, - "max_input_tokens": 100000, - "max_output_tokens": 8191, - "input_cost_per_second": 0.0455, - "output_cost_per_second": 0.0455, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_tool_choice": true - }, - "bedrock/ap-northeast-1/6-month-commitment/anthropic.claude-v2:1": { - "max_tokens": 8191, - "max_input_tokens": 100000, - "max_output_tokens": 8191, - "input_cost_per_second": 0.02527, - "output_cost_per_second": 0.02527, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_tool_choice": true - }, - "bedrock/eu-central-1/anthropic.claude-v2:1": { - "max_tokens": 8191, - "max_input_tokens": 100000, - "max_output_tokens": 8191, - "input_cost_per_token": 8e-06, - "output_cost_per_token": 2.4e-05, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_tool_choice": true - }, - "bedrock/eu-central-1/1-month-commitment/anthropic.claude-v2:1": { - "max_tokens": 8191, - "max_input_tokens": 100000, - "max_output_tokens": 8191, - "input_cost_per_second": 0.0415, - "output_cost_per_second": 0.0415, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_tool_choice": true - }, - "bedrock/eu-central-1/6-month-commitment/anthropic.claude-v2:1": { - "max_tokens": 8191, - "max_input_tokens": 100000, - "max_output_tokens": 8191, - "input_cost_per_second": 0.02305, - "output_cost_per_second": 0.02305, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_tool_choice": true - }, - "bedrock/us-east-1/1-month-commitment/anthropic.claude-v2:1": { - "max_tokens": 8191, - "max_input_tokens": 100000, - "max_output_tokens": 8191, - "input_cost_per_second": 0.0175, - "output_cost_per_second": 0.0175, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_tool_choice": true - }, - "bedrock/us-east-1/6-month-commitment/anthropic.claude-v2:1": { - "max_tokens": 8191, - "max_input_tokens": 100000, - "max_output_tokens": 8191, - "input_cost_per_second": 0.00972, - "output_cost_per_second": 0.00972, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_tool_choice": true - }, - "bedrock/us-west-2/1-month-commitment/anthropic.claude-v2:1": { - "max_tokens": 8191, - "max_input_tokens": 100000, - "max_output_tokens": 8191, - "input_cost_per_second": 0.0175, - "output_cost_per_second": 0.0175, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_tool_choice": true - }, - "bedrock/us-west-2/6-month-commitment/anthropic.claude-v2:1": { - "max_tokens": 8191, - "max_input_tokens": 100000, - "max_output_tokens": 8191, - "input_cost_per_second": 0.00972, - "output_cost_per_second": 0.00972, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_tool_choice": true - }, - "anthropic.claude-instant-v1": { - "max_tokens": 8191, - "max_input_tokens": 100000, - "max_output_tokens": 8191, - "input_cost_per_token": 8e-07, - "output_cost_per_token": 2.4e-06, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_tool_choice": true - }, - "bedrock/us-east-1/anthropic.claude-instant-v1": { - "max_tokens": 8191, - "max_input_tokens": 100000, - "max_output_tokens": 8191, - "input_cost_per_token": 8e-07, - "output_cost_per_token": 2.4e-06, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_tool_choice": true - }, - "bedrock/us-east-1/1-month-commitment/anthropic.claude-instant-v1": { - "max_tokens": 8191, - "max_input_tokens": 100000, - "max_output_tokens": 8191, - "input_cost_per_second": 0.011, - "output_cost_per_second": 0.011, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_tool_choice": true - }, - "bedrock/us-east-1/6-month-commitment/anthropic.claude-instant-v1": { - "max_tokens": 8191, - "max_input_tokens": 100000, - "max_output_tokens": 8191, - "input_cost_per_second": 0.00611, - "output_cost_per_second": 0.00611, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_tool_choice": true - }, - "bedrock/us-west-2/1-month-commitment/anthropic.claude-instant-v1": { - "max_tokens": 8191, - "max_input_tokens": 100000, - "max_output_tokens": 8191, - "input_cost_per_second": 0.011, - "output_cost_per_second": 0.011, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_tool_choice": true - }, - "bedrock/us-west-2/6-month-commitment/anthropic.claude-instant-v1": { - "max_tokens": 8191, - "max_input_tokens": 100000, - "max_output_tokens": 8191, - "input_cost_per_second": 0.00611, - "output_cost_per_second": 0.00611, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_tool_choice": true - }, - "bedrock/us-west-2/anthropic.claude-instant-v1": { - "max_tokens": 8191, - "max_input_tokens": 100000, - "max_output_tokens": 8191, - "input_cost_per_token": 8e-07, - "output_cost_per_token": 2.4e-06, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_tool_choice": true - }, - "bedrock/ap-northeast-1/anthropic.claude-instant-v1": { - "max_tokens": 8191, - "max_input_tokens": 100000, - "max_output_tokens": 8191, - "input_cost_per_token": 2.23e-06, - "output_cost_per_token": 7.55e-06, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_tool_choice": true - }, - "bedrock/ap-northeast-1/1-month-commitment/anthropic.claude-instant-v1": { - "max_tokens": 8191, - "max_input_tokens": 100000, - "max_output_tokens": 8191, - "input_cost_per_second": 0.01475, - "output_cost_per_second": 0.01475, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_tool_choice": true - }, - "bedrock/ap-northeast-1/6-month-commitment/anthropic.claude-instant-v1": { - "max_tokens": 8191, - "max_input_tokens": 100000, - "max_output_tokens": 8191, - "input_cost_per_second": 0.008194, - "output_cost_per_second": 0.008194, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_tool_choice": true - }, - "bedrock/eu-central-1/anthropic.claude-instant-v1": { - "max_tokens": 8191, - "max_input_tokens": 100000, - "max_output_tokens": 8191, - "input_cost_per_token": 2.48e-06, - "output_cost_per_token": 8.38e-06, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_tool_choice": true - }, - "bedrock/eu-central-1/1-month-commitment/anthropic.claude-instant-v1": { - "max_tokens": 8191, - "max_input_tokens": 100000, - "max_output_tokens": 8191, - "input_cost_per_second": 0.01635, - "output_cost_per_second": 0.01635, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_tool_choice": true - }, - "bedrock/eu-central-1/6-month-commitment/anthropic.claude-instant-v1": { - "max_tokens": 8191, - "max_input_tokens": 100000, - "max_output_tokens": 8191, - "input_cost_per_second": 0.009083, - "output_cost_per_second": 0.009083, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_tool_choice": true - }, - "cohere.rerank-v3-5:0": { - "max_tokens": 32000, - "max_input_tokens": 32000, - "max_output_tokens": 32000, - "max_query_tokens": 32000, - "max_document_chunks_per_query": 100, - "max_tokens_per_document_chunk": 512, - "input_cost_per_token": 0.0, - "input_cost_per_query": 0.002, - "output_cost_per_token": 0.0, - "litellm_provider": "bedrock", - "mode": "rerank" - }, - "cohere.command-text-v14": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 1.5e-06, - "output_cost_per_token": 2e-06, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_tool_choice": true - }, - "bedrock/*/1-month-commitment/cohere.command-text-v14": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_second": 0.011, - "output_cost_per_second": 0.011, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_tool_choice": true - }, - "bedrock/*/6-month-commitment/cohere.command-text-v14": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_second": 0.0066027, - "output_cost_per_second": 0.0066027, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_tool_choice": true - }, - "cohere.command-light-text-v14": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 3e-07, - "output_cost_per_token": 6e-07, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_tool_choice": true - }, - "bedrock/*/1-month-commitment/cohere.command-light-text-v14": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_second": 0.001902, - "output_cost_per_second": 0.001902, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_tool_choice": true - }, - "bedrock/*/6-month-commitment/cohere.command-light-text-v14": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_second": 0.0011416, - "output_cost_per_second": 0.0011416, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_tool_choice": true - }, - "cohere.command-r-plus-v1:0": { - "max_tokens": 4096, - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_tool_choice": true - }, - "cohere.command-r-v1:0": { - "max_tokens": 4096, - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 5e-07, - "output_cost_per_token": 1.5e-06, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_tool_choice": true - }, - "cohere.embed-english-v3": { - "max_tokens": 512, - "max_input_tokens": 512, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 0.0, - "litellm_provider": "bedrock", - "mode": "embedding", - "supports_embedding_image_input": true - }, - "cohere.embed-multilingual-v3": { - "max_tokens": 512, - "max_input_tokens": 512, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 0.0, - "litellm_provider": "bedrock", - "mode": "embedding", - "supports_embedding_image_input": true - }, - "us.deepseek.r1-v1:0": { - "max_tokens": 4096, - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 1.35e-06, - "output_cost_per_token": 5.4e-06, - "litellm_provider": "bedrock_converse", - "mode": "chat", - "supports_reasoning": true, - "supports_function_calling": false, - "supports_tool_choice": false - }, - "meta.llama3-3-70b-instruct-v1:0": { - "max_tokens": 4096, - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 7.2e-07, - "output_cost_per_token": 7.2e-07, - "litellm_provider": "bedrock_converse", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": false - }, - "meta.llama2-13b-chat-v1": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 7.5e-07, - "output_cost_per_token": 1e-06, - "litellm_provider": "bedrock", - "mode": "chat" - }, - "meta.llama2-70b-chat-v1": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 1.95e-06, - "output_cost_per_token": 2.56e-06, - "litellm_provider": "bedrock", - "mode": "chat" - }, - "meta.llama3-8b-instruct-v1:0": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 3e-07, - "output_cost_per_token": 6e-07, - "litellm_provider": "bedrock", - "mode": "chat" - }, - "bedrock/us-east-1/meta.llama3-8b-instruct-v1:0": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 3e-07, - "output_cost_per_token": 6e-07, - "litellm_provider": "bedrock", - "mode": "chat" - }, - "bedrock/us-west-1/meta.llama3-8b-instruct-v1:0": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 3e-07, - "output_cost_per_token": 6e-07, - "litellm_provider": "bedrock", - "mode": "chat" - }, - "bedrock/ap-south-1/meta.llama3-8b-instruct-v1:0": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 3.6e-07, - "output_cost_per_token": 7.2e-07, - "litellm_provider": "bedrock", - "mode": "chat" - }, - "bedrock/ca-central-1/meta.llama3-8b-instruct-v1:0": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 3.5e-07, - "output_cost_per_token": 6.9e-07, - "litellm_provider": "bedrock", - "mode": "chat" - }, - "bedrock/eu-west-1/meta.llama3-8b-instruct-v1:0": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 3.2e-07, - "output_cost_per_token": 6.5e-07, - "litellm_provider": "bedrock", - "mode": "chat" - }, - "bedrock/eu-west-2/meta.llama3-8b-instruct-v1:0": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 3.9e-07, - "output_cost_per_token": 7.8e-07, - "litellm_provider": "bedrock", - "mode": "chat" - }, - "bedrock/sa-east-1/meta.llama3-8b-instruct-v1:0": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 5e-07, - "output_cost_per_token": 1.01e-06, - "litellm_provider": "bedrock", - "mode": "chat" - }, - "meta.llama3-70b-instruct-v1:0": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 2.65e-06, - "output_cost_per_token": 3.5e-06, - "litellm_provider": "bedrock", - "mode": "chat" - }, - "bedrock/us-east-1/meta.llama3-70b-instruct-v1:0": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 2.65e-06, - "output_cost_per_token": 3.5e-06, - "litellm_provider": "bedrock", - "mode": "chat" - }, - "bedrock/us-west-1/meta.llama3-70b-instruct-v1:0": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 2.65e-06, - "output_cost_per_token": 3.5e-06, - "litellm_provider": "bedrock", - "mode": "chat" - }, - "bedrock/ap-south-1/meta.llama3-70b-instruct-v1:0": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 3.18e-06, - "output_cost_per_token": 4.2e-06, - "litellm_provider": "bedrock", - "mode": "chat" - }, - "bedrock/ca-central-1/meta.llama3-70b-instruct-v1:0": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 3.05e-06, - "output_cost_per_token": 4.03e-06, - "litellm_provider": "bedrock", - "mode": "chat" - }, - "bedrock/eu-west-1/meta.llama3-70b-instruct-v1:0": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 2.86e-06, - "output_cost_per_token": 3.78e-06, - "litellm_provider": "bedrock", - "mode": "chat" - }, - "bedrock/eu-west-2/meta.llama3-70b-instruct-v1:0": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 3.45e-06, - "output_cost_per_token": 4.55e-06, - "litellm_provider": "bedrock", - "mode": "chat" - }, - "bedrock/sa-east-1/meta.llama3-70b-instruct-v1:0": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 4.45e-06, - "output_cost_per_token": 5.88e-06, - "litellm_provider": "bedrock", - "mode": "chat" - }, - "meta.llama3-1-8b-instruct-v1:0": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 2048, - "input_cost_per_token": 2.2e-07, - "output_cost_per_token": 2.2e-07, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": false - }, - "us.meta.llama3-1-8b-instruct-v1:0": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 2048, - "input_cost_per_token": 2.2e-07, - "output_cost_per_token": 2.2e-07, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": false - }, - "meta.llama3-1-70b-instruct-v1:0": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 2048, - "input_cost_per_token": 9.9e-07, - "output_cost_per_token": 9.9e-07, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": false - }, - "us.meta.llama3-1-70b-instruct-v1:0": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 2048, - "input_cost_per_token": 9.9e-07, - "output_cost_per_token": 9.9e-07, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": false - }, - "meta.llama3-1-405b-instruct-v1:0": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 5.32e-06, - "output_cost_per_token": 1.6e-05, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": false - }, - "us.meta.llama3-1-405b-instruct-v1:0": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 5.32e-06, - "output_cost_per_token": 1.6e-05, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": false - }, - "meta.llama3-2-1b-instruct-v1:0": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 1e-07, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": false - }, - "us.meta.llama3-2-1b-instruct-v1:0": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 1e-07, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": false - }, - "eu.meta.llama3-2-1b-instruct-v1:0": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 1.3e-07, - "output_cost_per_token": 1.3e-07, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": false - }, - "meta.llama3-2-3b-instruct-v1:0": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 1.5e-07, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": false - }, - "us.meta.llama3-2-3b-instruct-v1:0": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 1.5e-07, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": false - }, - "eu.meta.llama3-2-3b-instruct-v1:0": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 1.9e-07, - "output_cost_per_token": 1.9e-07, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": false - }, - "meta.llama3-2-11b-instruct-v1:0": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 3.5e-07, - "output_cost_per_token": 3.5e-07, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": false, - "supports_vision": true - }, - "us.meta.llama3-2-11b-instruct-v1:0": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 3.5e-07, - "output_cost_per_token": 3.5e-07, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": false, - "supports_vision": true - }, - "meta.llama3-2-90b-instruct-v1:0": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 2e-06, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": false, - "supports_vision": true - }, - "us.meta.llama3-2-90b-instruct-v1:0": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 2e-06, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": false, - "supports_vision": true - }, - "us.meta.llama3-3-70b-instruct-v1:0": { - "max_tokens": 4096, - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 7.2e-07, - "output_cost_per_token": 7.2e-07, - "litellm_provider": "bedrock_converse", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": false - }, - "meta.llama4-maverick-17b-instruct-v1:0": { - "max_tokens": 4096, - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 2.4e-07, - "input_cost_per_token_batches": 1.2e-07, - "output_cost_per_token": 9.7e-07, - "output_cost_per_token_batches": 4.85e-07, - "litellm_provider": "bedrock_converse", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": false, - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text", - "code" - ] - }, - "us.meta.llama4-maverick-17b-instruct-v1:0": { - "max_tokens": 4096, - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 2.4e-07, - "input_cost_per_token_batches": 1.2e-07, - "output_cost_per_token": 9.7e-07, - "output_cost_per_token_batches": 4.85e-07, - "litellm_provider": "bedrock_converse", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": false, - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text", - "code" - ] - }, - "meta.llama4-scout-17b-instruct-v1:0": { - "max_tokens": 4096, - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 1.7e-07, - "input_cost_per_token_batches": 8.5e-08, - "output_cost_per_token": 6.6e-07, - "output_cost_per_token_batches": 3.3e-07, - "litellm_provider": "bedrock_converse", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": false, - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text", - "code" - ] - }, - "us.meta.llama4-scout-17b-instruct-v1:0": { - "max_tokens": 4096, - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 1.7e-07, - "input_cost_per_token_batches": 8.5e-08, - "output_cost_per_token": 6.6e-07, - "output_cost_per_token_batches": 3.3e-07, - "litellm_provider": "bedrock_converse", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": false, - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text", - "code" - ] - }, - "512-x-512/50-steps/stability.stable-diffusion-xl-v0": { - "max_tokens": 77, - "max_input_tokens": 77, - "output_cost_per_image": 0.018, - "litellm_provider": "bedrock", - "mode": "image_generation" - }, - "512-x-512/max-steps/stability.stable-diffusion-xl-v0": { - "max_tokens": 77, - "max_input_tokens": 77, - "output_cost_per_image": 0.036, - "litellm_provider": "bedrock", - "mode": "image_generation" - }, - "max-x-max/50-steps/stability.stable-diffusion-xl-v0": { - "max_tokens": 77, - "max_input_tokens": 77, - "output_cost_per_image": 0.036, - "litellm_provider": "bedrock", - "mode": "image_generation" - }, - "max-x-max/max-steps/stability.stable-diffusion-xl-v0": { - "max_tokens": 77, - "max_input_tokens": 77, - "output_cost_per_image": 0.072, - "litellm_provider": "bedrock", - "mode": "image_generation" - }, - "1024-x-1024/50-steps/stability.stable-diffusion-xl-v1": { - "max_tokens": 77, - "max_input_tokens": 77, - "output_cost_per_image": 0.04, - "litellm_provider": "bedrock", - "mode": "image_generation" - }, - "1024-x-1024/max-steps/stability.stable-diffusion-xl-v1": { - "max_tokens": 77, - "max_input_tokens": 77, - "output_cost_per_image": 0.08, - "litellm_provider": "bedrock", - "mode": "image_generation" - }, - "stability.sd3-large-v1:0": { - "max_tokens": 77, - "max_input_tokens": 77, - "output_cost_per_image": 0.08, - "litellm_provider": "bedrock", - "mode": "image_generation" - }, - "stability.sd3-5-large-v1:0": { - "max_tokens": 77, - "max_input_tokens": 77, - "output_cost_per_image": 0.08, - "litellm_provider": "bedrock", - "mode": "image_generation" - }, - "stability.stable-image-core-v1:0": { - "max_tokens": 77, - "max_input_tokens": 77, - "output_cost_per_image": 0.04, - "litellm_provider": "bedrock", - "mode": "image_generation" - }, - "stability.stable-image-core-v1:1": { - "max_tokens": 77, - "max_input_tokens": 77, - "output_cost_per_image": 0.04, - "litellm_provider": "bedrock", - "mode": "image_generation" - }, - "stability.stable-image-ultra-v1:0": { - "max_tokens": 77, - "max_input_tokens": 77, - "output_cost_per_image": 0.14, - "litellm_provider": "bedrock", - "mode": "image_generation" - }, - "stability.stable-image-ultra-v1:1": { - "max_tokens": 77, - "max_input_tokens": 77, - "output_cost_per_image": 0.14, - "litellm_provider": "bedrock", - "mode": "image_generation" - }, - "sagemaker/meta-textgeneration-llama-2-7b": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "sagemaker", - "mode": "completion" - }, - "sagemaker/meta-textgeneration-llama-2-7b-f": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "sagemaker", - "mode": "chat" - }, - "sagemaker/meta-textgeneration-llama-2-13b": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "sagemaker", - "mode": "completion" - }, - "sagemaker/meta-textgeneration-llama-2-13b-f": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "sagemaker", - "mode": "chat" - }, - "sagemaker/meta-textgeneration-llama-2-70b": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "sagemaker", - "mode": "completion" - }, - "sagemaker/meta-textgeneration-llama-2-70b-b-f": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "sagemaker", - "mode": "chat" - }, - "together-ai-up-to-4b": { - "input_cost_per_token": 1e-07, - "output_cost_per_token": 1e-07, - "litellm_provider": "together_ai", - "mode": "chat" - }, - "together-ai-4.1b-8b": { - "input_cost_per_token": 2e-07, - "output_cost_per_token": 2e-07, - "litellm_provider": "together_ai", - "mode": "chat" - }, - "together-ai-8.1b-21b": { - "max_tokens": 1000, - "input_cost_per_token": 3e-07, - "output_cost_per_token": 3e-07, - "litellm_provider": "together_ai", - "mode": "chat" - }, - "together-ai-21.1b-41b": { - "input_cost_per_token": 8e-07, - "output_cost_per_token": 8e-07, - "litellm_provider": "together_ai", - "mode": "chat" - }, - "together-ai-41.1b-80b": { - "input_cost_per_token": 9e-07, - "output_cost_per_token": 9e-07, - "litellm_provider": "together_ai", - "mode": "chat" - }, - "together-ai-81.1b-110b": { - "input_cost_per_token": 1.8e-06, - "output_cost_per_token": 1.8e-06, - "litellm_provider": "together_ai", - "mode": "chat" - }, - "together-ai-embedding-up-to-150m": { - "input_cost_per_token": 8e-09, - "output_cost_per_token": 0.0, - "litellm_provider": "together_ai", - "mode": "embedding" - }, - "together-ai-embedding-151m-to-350m": { - "input_cost_per_token": 1.6e-08, - "output_cost_per_token": 0.0, - "litellm_provider": "together_ai", - "mode": "embedding" - }, - "together_ai/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo": { - "input_cost_per_token": 1.8e-07, - "output_cost_per_token": 1.8e-07, - "litellm_provider": "together_ai", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "mode": "chat", - "supports_tool_choice": true - }, - "together_ai/meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo": { - "input_cost_per_token": 8.8e-07, - "output_cost_per_token": 8.8e-07, - "litellm_provider": "together_ai", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "mode": "chat", - "supports_tool_choice": true - }, - "together_ai/meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo": { - "input_cost_per_token": 3.5e-06, - "output_cost_per_token": 3.5e-06, - "litellm_provider": "together_ai", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "mode": "chat", - "supports_tool_choice": true - }, - "together_ai/meta-llama/Llama-3.3-70B-Instruct-Turbo": { - "input_cost_per_token": 8.8e-07, - "output_cost_per_token": 8.8e-07, - "litellm_provider": "together_ai", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "mode": "chat", - "supports_tool_choice": true - }, - "together_ai/meta-llama/Llama-3.3-70B-Instruct-Turbo-Free": { + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" + }, + "gemini/learnlm-1.5-pro-experimental": { + "input_cost_per_audio_per_second": 0, + "input_cost_per_audio_per_second_above_128k_tokens": 0, + "input_cost_per_character": 0, + "input_cost_per_character_above_128k_tokens": 0, + "input_cost_per_image": 0, + "input_cost_per_image_above_128k_tokens": 0, "input_cost_per_token": 0, + "input_cost_per_token_above_128k_tokens": 0, + "input_cost_per_video_per_second": 0, + "input_cost_per_video_per_second_above_128k_tokens": 0, + "litellm_provider": "gemini", + "max_input_tokens": 32767, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_character": 0, + "output_cost_per_character_above_128k_tokens": 0, "output_cost_per_token": 0, - "litellm_provider": "together_ai", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "mode": "chat", - "supports_tool_choice": true - }, - "together_ai/mistralai/Mixtral-8x7B-Instruct-v0.1": { - "input_cost_per_token": 6e-07, - "output_cost_per_token": 6e-07, - "litellm_provider": "together_ai", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "mode": "chat", - "supports_tool_choice": true - }, - "together_ai/mistralai/Mistral-7B-Instruct-v0.1": { - "litellm_provider": "together_ai", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "mode": "chat", - "supports_tool_choice": true - }, - "together_ai/togethercomputer/CodeLlama-34b-Instruct": { - "litellm_provider": "together_ai", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "mode": "chat", - "supports_tool_choice": true - }, - "together_ai/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8": { - "input_cost_per_token": 2.7e-07, - "output_cost_per_token": 8.5e-07, - "litellm_provider": "together_ai", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "mode": "chat", - "supports_tool_choice": true - }, - "together_ai/meta-llama/Llama-4-Scout-17B-16E-Instruct": { - "input_cost_per_token": 1.8e-07, - "output_cost_per_token": 5.9e-07, - "litellm_provider": "together_ai", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "mode": "chat", - "supports_tool_choice": true - }, - "together_ai/meta-llama/Llama-3.2-3B-Instruct-Turbo": { - "litellm_provider": "together_ai", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "mode": "chat", - "supports_tool_choice": true - }, - "together_ai/Qwen/Qwen2.5-7B-Instruct-Turbo": { - "litellm_provider": "together_ai", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "mode": "chat", - "supports_tool_choice": true - }, - "together_ai/Qwen/Qwen2.5-72B-Instruct-Turbo": { - "litellm_provider": "together_ai", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "mode": "chat", - "supports_tool_choice": true - }, - "together_ai/Qwen/Qwen3-235B-A22B-Instruct-2507-tput": { - "input_cost_per_token": 2e-07, - "output_cost_per_token": 6e-06, - "max_input_tokens": 262000, - "litellm_provider": "together_ai", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "mode": "chat", - "supports_tool_choice": true, - "source": "https://www.together.ai/models/qwen3-235b-a22b-instruct-2507-fp8" - }, - "together_ai/Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8": { - "input_cost_per_token": 2e-06, - "output_cost_per_token": 2e-06, - "max_input_tokens": 256000, - "litellm_provider": "together_ai", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "mode": "chat", - "supports_tool_choice": true, - "source": "https://www.together.ai/models/qwen3-coder-480b-a35b-instruct" - }, - "together_ai/Qwen/Qwen3-235B-A22B-Thinking-2507": { - "input_cost_per_token": 6.5e-07, - "output_cost_per_token": 3e-06, - "max_input_tokens": 256000, - "litellm_provider": "together_ai", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "mode": "chat", - "supports_tool_choice": true, - "source": "https://www.together.ai/models/qwen3-235b-a22b-thinking-2507" - }, - "together_ai/Qwen/Qwen3-235B-A22B-fp8-tput": { - "input_cost_per_token": 2e-07, - "output_cost_per_token": 6e-07, - "max_input_tokens": 40000, - "litellm_provider": "together_ai", - "supports_function_calling": false, - "supports_parallel_function_calling": false, - "mode": "chat", - "supports_tool_choice": false, - "source": "https://www.together.ai/models/qwen3-235b-a22b-fp8-tput" - }, - "together_ai/deepseek-ai/DeepSeek-V3": { - "input_cost_per_token": 1.25e-06, - "output_cost_per_token": 1.25e-06, - "max_tokens": 8192, - "max_input_tokens": 65536, - "max_output_tokens": 8192, - "litellm_provider": "together_ai", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "mode": "chat", - "supports_tool_choice": true - }, - "together_ai/deepseek-ai/DeepSeek-R1": { - "input_cost_per_token": 3e-06, - "output_cost_per_token": 7e-06, - "max_tokens": 20480, - "max_input_tokens": 128000, - "max_output_tokens": 20480, - "litellm_provider": "together_ai", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "mode": "chat", - "supports_tool_choice": true - }, - "together_ai/deepseek-ai/DeepSeek-R1-0528-tput": { - "input_cost_per_token": 5.5e-07, - "output_cost_per_token": 2.19e-06, - "max_input_tokens": 128000, - "litellm_provider": "together_ai", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "mode": "chat", - "supports_tool_choice": true, - "source": "https://www.together.ai/models/deepseek-r1-0528-throughput" - }, - "together_ai/mistralai/Mistral-Small-24B-Instruct-2501": { - "litellm_provider": "together_ai", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "mode": "chat", - "supports_tool_choice": true - }, - "together_ai/moonshotai/Kimi-K2-Instruct": { - "input_cost_per_token": 1e-06, - "output_cost_per_token": 3e-06, - "litellm_provider": "together_ai", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_parallel_function_calling": true, - "mode": "chat", - "source": "https://www.together.ai/models/kimi-k2-instruct" - }, - "together_ai/openai/gpt-oss-120b": { - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 6e-07, - "max_input_tokens": 128000, - "litellm_provider": "together_ai", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_parallel_function_calling": true, - "mode": "chat", - "source": "https://www.together.ai/models/gpt-oss-120b" - }, - "together_ai/openai/gpt-oss-20b": { - "input_cost_per_token": 5e-08, - "output_cost_per_token": 2e-07, - "max_input_tokens": 128000, - "litellm_provider": "together_ai", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_parallel_function_calling": true, - "mode": "chat", - "source": "https://www.together.ai/models/gpt-oss-20b" - }, - "together_ai/zai-org/GLM-4.5-Air-FP8": { - "input_cost_per_token": 2e-07, - "output_cost_per_token": 1.1e-06, - "max_input_tokens": 128000, - "litellm_provider": "together_ai", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_parallel_function_calling": true, - "mode": "chat", - "source": "https://www.together.ai/models/glm-4-5-air" - }, - "together_ai/deepseek-ai/DeepSeek-V3.1": { - "input_cost_per_token": 0.6e-06, - "output_cost_per_token": 1.7e-06, - "max_tokens": 128000, - "litellm_provider": "together_ai", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_reasoning": true, - "mode": "chat", - "supports_tool_choice": true, - "source": "https://www.together.ai/models/deepseek-v3-1" - }, - "ollama/codegemma": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "ollama", - "mode": "completion" - }, - "ollama/codegeex4": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 8192, - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "ollama", - "mode": "chat", - "supports_function_calling": false - }, - "ollama/deepseek-coder-v2-instruct": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 8192, - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "ollama", - "mode": "chat", - "supports_function_calling": true - }, - "ollama/deepseek-coder-v2-base": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "ollama", - "mode": "completion", - "supports_function_calling": true - }, - "ollama/deepseek-coder-v2-lite-instruct": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 8192, - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "ollama", - "mode": "chat", - "supports_function_calling": true - }, - "ollama/deepseek-coder-v2-lite-base": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "ollama", - "mode": "completion", - "supports_function_calling": true - }, - "ollama/internlm2_5-20b-chat": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 8192, - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "ollama", - "mode": "chat", - "supports_function_calling": true - }, - "ollama/llama2": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "ollama", - "mode": "chat" - }, - "ollama/llama2:7b": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "ollama", - "mode": "chat" - }, - "ollama/llama2:13b": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "ollama", - "mode": "chat" - }, - "ollama/llama2:70b": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "ollama", - "mode": "chat" - }, - "ollama/llama2-uncensored": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "ollama", - "mode": "completion" - }, - "ollama/llama3": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "ollama", - "mode": "chat" - }, - "ollama/llama3:8b": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "ollama", - "mode": "chat" - }, - "ollama/llama3:70b": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "ollama", - "mode": "chat" - }, - "ollama/llama3.1": { - "max_tokens": 32768, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "ollama", - "mode": "chat", - "supports_function_calling": true - }, - "ollama/mistral-large-instruct-2407": { - "max_tokens": 65536, - "max_input_tokens": 65536, - "max_output_tokens": 8192, - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "ollama", - "mode": "chat", - "supports_function_calling": true - }, - "ollama/mistral": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "ollama", - "mode": "completion", - "supports_function_calling": true - }, - "ollama/mistral-7B-Instruct-v0.1": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "ollama", - "mode": "chat", - "supports_function_calling": true - }, - "ollama/mistral-7B-Instruct-v0.2": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "ollama", - "mode": "chat", - "supports_function_calling": true - }, - "ollama/mixtral-8x7B-Instruct-v0.1": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "ollama", - "mode": "chat", - "supports_function_calling": true - }, - "ollama/mixtral-8x22B-Instruct-v0.1": { - "max_tokens": 65536, - "max_input_tokens": 65536, - "max_output_tokens": 65536, - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "ollama", - "mode": "chat", - "supports_function_calling": true - }, - "ollama/codellama": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "ollama", - "mode": "completion" - }, - "ollama/orca-mini": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "ollama", - "mode": "completion" - }, - "ollama/vicuna": { - "max_tokens": 2048, - "max_input_tokens": 2048, - "max_output_tokens": 2048, - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "ollama", - "mode": "completion" - }, - "deepinfra/Gryphe/MythoMax-L2-13b": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 7.2e-08, - "output_cost_per_token": 7.2e-08, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": true - }, - "deepinfra/NousResearch/Hermes-3-Llama-3.1-405B": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 7e-07, - "output_cost_per_token": 8e-07, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": true - }, - "deepinfra/NousResearch/Hermes-3-Llama-3.1-70B": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 2.8e-07, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": false - }, - "deepinfra/Qwen/QwQ-32B": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 4e-07, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": true - }, - "deepinfra/Qwen/Qwen2.5-72B-Instruct": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "input_cost_per_token": 1.2e-07, - "output_cost_per_token": 3.9e-07, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": true - }, - "deepinfra/Qwen/Qwen2.5-7B-Instruct": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "input_cost_per_token": 4e-08, - "output_cost_per_token": 1e-07, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": false - }, - "deepinfra/Qwen/Qwen2.5-VL-32B-Instruct": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "input_cost_per_token": 2e-07, - "output_cost_per_token": 6e-07, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": true - }, - "deepinfra/Qwen/Qwen3-14B": { - "max_tokens": 40960, - "max_input_tokens": 40960, - "max_output_tokens": 40960, - "input_cost_per_token": 6e-08, - "output_cost_per_token": 2.4e-07, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": true - }, - "deepinfra/Qwen/Qwen3-235B-A22B": { - "max_tokens": 40960, - "max_input_tokens": 40960, - "max_output_tokens": 40960, - "input_cost_per_token": 1.3e-07, - "output_cost_per_token": 6e-07, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": true - }, - "deepinfra/Qwen/Qwen3-235B-A22B-Instruct-2507": { - "max_tokens": 262144, - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "input_cost_per_token": 1.3e-07, - "output_cost_per_token": 6e-07, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": true - }, - "deepinfra/Qwen/Qwen3-235B-A22B-Thinking-2507": { - "max_tokens": 262144, - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "input_cost_per_token": 1.3e-07, - "output_cost_per_token": 6e-07, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": true - }, - "deepinfra/Qwen/Qwen3-30B-A3B": { - "max_tokens": 40960, - "max_input_tokens": 40960, - "max_output_tokens": 40960, - "input_cost_per_token": 8e-08, - "output_cost_per_token": 2.9e-07, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": true - }, - "deepinfra/Qwen/Qwen3-32B": { - "max_tokens": 40960, - "max_input_tokens": 40960, - "max_output_tokens": 40960, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 3e-07, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": true - }, - "deepinfra/Qwen/Qwen3-Coder-480B-A35B-Instruct": { - "max_tokens": 262144, - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "input_cost_per_token": 4e-07, - "output_cost_per_token": 1.6e-06, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": true - }, - "deepinfra/Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo": { - "max_tokens": 262144, - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "input_cost_per_token": 3e-07, - "output_cost_per_token": 1.2e-06, - "cache_read_input_token_cost": 2.4e-07, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": true - }, - "deepinfra/Sao10K/L3-8B-Lunaris-v1-Turbo": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 2e-08, - "output_cost_per_token": 5e-08, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": false - }, - "deepinfra/Sao10K/L3.1-70B-Euryale-v2.2": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 6.5e-07, - "output_cost_per_token": 7.5e-07, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": false - }, - "deepinfra/Sao10K/L3.3-70B-Euryale-v2.3": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 6.5e-07, - "output_cost_per_token": 7.5e-07, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": false - }, - "deepinfra/allenai/olmOCR-7B-0725-FP8": { - "max_tokens": 16384, - "max_input_tokens": 16384, - "max_output_tokens": 16384, - "input_cost_per_token": 2.7e-07, - "output_cost_per_token": 1.5e-06, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": false - }, - "deepinfra/anthropic/claude-3-7-sonnet-latest": { - "max_tokens": 200000, - "max_input_tokens": 200000, - "max_output_tokens": 200000, - "input_cost_per_token": 3.3e-06, - "output_cost_per_token": 1.65e-05, - "cache_read_input_token_cost": 3.3e-07, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": true - }, - "deepinfra/anthropic/claude-4-opus": { - "max_tokens": 200000, - "max_input_tokens": 200000, - "max_output_tokens": 200000, - "input_cost_per_token": 1.65e-05, - "output_cost_per_token": 8.25e-05, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": true - }, - "deepinfra/anthropic/claude-4-sonnet": { - "max_tokens": 200000, - "max_input_tokens": 200000, - "max_output_tokens": 200000, - "input_cost_per_token": 3.3e-06, - "output_cost_per_token": 1.65e-05, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": true - }, - "deepinfra/deepseek-ai/DeepSeek-R1": { - "max_tokens": 163840, - "max_input_tokens": 163840, - "max_output_tokens": 163840, - "input_cost_per_token": 7e-07, - "output_cost_per_token": 2.4e-06, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": true - }, - "deepinfra/deepseek-ai/DeepSeek-R1-0528": { - "max_tokens": 163840, - "max_input_tokens": 163840, - "max_output_tokens": 163840, - "input_cost_per_token": 5e-07, - "output_cost_per_token": 2.15e-06, - "cache_read_input_token_cost": 4e-07, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": true - }, - "deepinfra/deepseek-ai/DeepSeek-R1-0528-Turbo": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "input_cost_per_token": 1e-06, - "output_cost_per_token": 3e-06, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": true - }, - "deepinfra/deepseek-ai/DeepSeek-R1-Distill-Llama-70B": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 4e-07, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": false - }, - "deepinfra/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 7.5e-08, - "output_cost_per_token": 1.5e-07, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": true - }, - "deepinfra/deepseek-ai/DeepSeek-R1-Turbo": { - "max_tokens": 40960, - "max_input_tokens": 40960, - "max_output_tokens": 40960, - "input_cost_per_token": 1e-06, - "output_cost_per_token": 3e-06, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": true - }, - "deepinfra/deepseek-ai/DeepSeek-V3": { - "max_tokens": 163840, - "max_input_tokens": 163840, - "max_output_tokens": 163840, - "input_cost_per_token": 3.8e-07, - "output_cost_per_token": 8.9e-07, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": true - }, - "deepinfra/deepseek-ai/DeepSeek-V3-0324": { - "max_tokens": 163840, - "max_input_tokens": 163840, - "max_output_tokens": 163840, - "input_cost_per_token": 2.8e-07, - "output_cost_per_token": 8.8e-07, - "cache_read_input_token_cost": 2.24e-07, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": true - }, - "deepinfra/deepseek-ai/DeepSeek-V3.1": { - "max_tokens": 163840, - "max_input_tokens": 163840, - "max_output_tokens": 163840, - "input_cost_per_token": 2.7e-07, - "output_cost_per_token": 1e-06, - "cache_read_input_token_cost": 2.16e-07, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": true, - "supports_reasoning": true - }, - "deepinfra/google/gemini-2.0-flash-001": { - "max_tokens": 1000000, - "max_input_tokens": 1000000, - "max_output_tokens": 1000000, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 4e-07, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": true - }, - "deepinfra/google/gemini-2.5-flash": { - "max_tokens": 1000000, - "max_input_tokens": 1000000, - "max_output_tokens": 1000000, - "input_cost_per_token": 2.1e-07, - "output_cost_per_token": 1.75e-06, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": true - }, - "deepinfra/google/gemini-2.5-pro": { - "max_tokens": 1000000, - "max_input_tokens": 1000000, - "max_output_tokens": 1000000, - "input_cost_per_token": 8.75e-07, - "output_cost_per_token": 7e-06, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": true - }, - "deepinfra/google/gemma-3-12b-it": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 5e-08, - "output_cost_per_token": 1e-07, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": true - }, - "deepinfra/google/gemma-3-27b-it": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 9e-08, - "output_cost_per_token": 1.7e-07, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": true - }, - "deepinfra/google/gemma-3-4b-it": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 4e-08, - "output_cost_per_token": 8e-08, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": true - }, - "deepinfra/meta-llama/Llama-3.2-11B-Vision-Instruct": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 4.9e-08, - "output_cost_per_token": 4.9e-08, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": false - }, - "deepinfra/meta-llama/Llama-3.2-3B-Instruct": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 1.2e-08, - "output_cost_per_token": 2.4e-08, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": true - }, - "deepinfra/meta-llama/Llama-3.3-70B-Instruct": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 2.3e-07, - "output_cost_per_token": 4e-07, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": true - }, - "deepinfra/meta-llama/Llama-3.3-70B-Instruct-Turbo": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 3.8e-08, - "output_cost_per_token": 1.2e-07, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": true - }, - "deepinfra/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8": { - "max_tokens": 1048576, - "max_input_tokens": 1048576, - "max_output_tokens": 1048576, - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 6e-07, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": true - }, - "deepinfra/meta-llama/Llama-4-Scout-17B-16E-Instruct": { - "max_tokens": 327680, - "max_input_tokens": 327680, - "max_output_tokens": 327680, - "input_cost_per_token": 8e-08, - "output_cost_per_token": 3e-07, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": true - }, - "deepinfra/meta-llama/Llama-Guard-3-8B": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 5.5e-08, - "output_cost_per_token": 5.5e-08, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": false - }, - "deepinfra/meta-llama/Llama-Guard-4-12B": { - "max_tokens": 163840, - "max_input_tokens": 163840, - "max_output_tokens": 163840, - "input_cost_per_token": 1.8e-07, - "output_cost_per_token": 1.8e-07, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": false - }, - "deepinfra/meta-llama/Meta-Llama-3-8B-Instruct": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 3e-08, - "output_cost_per_token": 6e-08, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": true - }, - "deepinfra/meta-llama/Meta-Llama-3.1-70B-Instruct": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 2.3e-07, - "output_cost_per_token": 4e-07, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": true - }, - "deepinfra/meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 2.8e-07, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": true - }, - "deepinfra/meta-llama/Meta-Llama-3.1-8B-Instruct": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 3e-08, - "output_cost_per_token": 5e-08, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": true - }, - "deepinfra/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 1.5e-08, - "output_cost_per_token": 2e-08, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": true - }, - "deepinfra/microsoft/WizardLM-2-8x22B": { - "max_tokens": 65536, - "max_input_tokens": 65536, - "max_output_tokens": 65536, - "input_cost_per_token": 4.8e-07, - "output_cost_per_token": 4.8e-07, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": false - }, - "deepinfra/microsoft/phi-4": { - "max_tokens": 16384, - "max_input_tokens": 16384, - "max_output_tokens": 16384, - "input_cost_per_token": 7e-08, - "output_cost_per_token": 1.4e-07, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": true - }, - "deepinfra/mistralai/Mistral-Nemo-Instruct-2407": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 2e-08, - "output_cost_per_token": 4e-08, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": true - }, - "deepinfra/mistralai/Mistral-Small-24B-Instruct-2501": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "input_cost_per_token": 5e-08, - "output_cost_per_token": 8e-08, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": true - }, - "deepinfra/mistralai/Mistral-Small-3.2-24B-Instruct-2506": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "input_cost_per_token": 5e-08, - "output_cost_per_token": 1e-07, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": true - }, - "deepinfra/mistralai/Mixtral-8x7B-Instruct-v0.1": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "input_cost_per_token": 8e-08, - "output_cost_per_token": 2.4e-07, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": true - }, - "deepinfra/moonshotai/Kimi-K2-Instruct": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 5e-07, - "output_cost_per_token": 2e-06, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": true - }, - "deepinfra/nvidia/Llama-3.1-Nemotron-70B-Instruct": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 1.2e-07, - "output_cost_per_token": 3e-07, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": true - }, - "deepinfra/openai/gpt-oss-120b": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 9e-08, - "output_cost_per_token": 4.5e-07, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": true - }, - "deepinfra/openai/gpt-oss-20b": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 4e-08, - "output_cost_per_token": 1.6e-07, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": true - }, - "deepinfra/zai-org/GLM-4.5": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 5.5e-07, - "output_cost_per_token": 2e-06, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": true - }, - "deepinfra/zai-org/GLM-4.5-Air": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 2e-07, - "output_cost_per_token": 1.1e-06, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": true - }, - "perplexity/codellama-34b-instruct": { - "max_tokens": 16384, - "max_input_tokens": 16384, - "max_output_tokens": 16384, - "input_cost_per_token": 3.5e-07, - "output_cost_per_token": 1.4e-06, - "litellm_provider": "perplexity", - "mode": "chat" - }, - "perplexity/codellama-70b-instruct": { - "max_tokens": 16384, - "max_input_tokens": 16384, - "max_output_tokens": 16384, - "input_cost_per_token": 7e-07, - "output_cost_per_token": 2.8e-06, - "litellm_provider": "perplexity", - "mode": "chat" - }, - "perplexity/llama-3.1-70b-instruct": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 1e-06, - "output_cost_per_token": 1e-06, - "litellm_provider": "perplexity", - "mode": "chat" - }, - "perplexity/llama-3.1-8b-instruct": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 2e-07, - "output_cost_per_token": 2e-07, - "litellm_provider": "perplexity", - "mode": "chat" - }, - "perplexity/llama-3.1-sonar-huge-128k-online": { - "max_tokens": 127072, - "max_input_tokens": 127072, - "max_output_tokens": 127072, - "input_cost_per_token": 5e-06, - "output_cost_per_token": 5e-06, - "litellm_provider": "perplexity", - "mode": "chat", - "deprecation_date": "2025-02-22" - }, - "perplexity/llama-3.1-sonar-large-128k-online": { - "max_tokens": 127072, - "max_input_tokens": 127072, - "max_output_tokens": 127072, - "input_cost_per_token": 1e-06, - "output_cost_per_token": 1e-06, - "litellm_provider": "perplexity", - "mode": "chat", - "deprecation_date": "2025-02-22" - }, - "perplexity/llama-3.1-sonar-large-128k-chat": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 1e-06, - "output_cost_per_token": 1e-06, - "litellm_provider": "perplexity", - "mode": "chat", - "deprecation_date": "2025-02-22" - }, - "perplexity/llama-3.1-sonar-small-128k-chat": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 2e-07, - "output_cost_per_token": 2e-07, - "litellm_provider": "perplexity", - "mode": "chat", - "deprecation_date": "2025-02-22" - }, - "perplexity/llama-3.1-sonar-small-128k-online": { - "max_tokens": 127072, - "max_input_tokens": 127072, - "max_output_tokens": 127072, - "input_cost_per_token": 2e-07, - "output_cost_per_token": 2e-07, - "litellm_provider": "perplexity", - "mode": "chat", - "deprecation_date": "2025-02-22" - }, - "perplexity/pplx-7b-chat": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 7e-08, - "output_cost_per_token": 2.8e-07, - "litellm_provider": "perplexity", - "mode": "chat" - }, - "perplexity/pplx-70b-chat": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 7e-07, - "output_cost_per_token": 2.8e-06, - "litellm_provider": "perplexity", - "mode": "chat" - }, - "perplexity/pplx-7b-online": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 0.0, - "output_cost_per_token": 2.8e-07, - "input_cost_per_request": 0.005, - "litellm_provider": "perplexity", - "mode": "chat" - }, - "perplexity/pplx-70b-online": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 0.0, - "output_cost_per_token": 2.8e-06, - "input_cost_per_request": 0.005, - "litellm_provider": "perplexity", - "mode": "chat" - }, - "perplexity/llama-2-70b-chat": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 7e-07, - "output_cost_per_token": 2.8e-06, - "litellm_provider": "perplexity", - "mode": "chat" - }, - "perplexity/mistral-7b-instruct": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 7e-08, - "output_cost_per_token": 2.8e-07, - "litellm_provider": "perplexity", - "mode": "chat" - }, - "perplexity/mixtral-8x7b-instruct": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 7e-08, - "output_cost_per_token": 2.8e-07, - "litellm_provider": "perplexity", - "mode": "chat" - }, - "perplexity/sonar-small-chat": { - "max_tokens": 16384, - "max_input_tokens": 16384, - "max_output_tokens": 16384, - "input_cost_per_token": 7e-08, - "output_cost_per_token": 2.8e-07, - "litellm_provider": "perplexity", - "mode": "chat" - }, - "perplexity/sonar-small-online": { - "max_tokens": 12000, - "max_input_tokens": 12000, - "max_output_tokens": 12000, - "input_cost_per_token": 0, - "output_cost_per_token": 2.8e-07, - "input_cost_per_request": 0.005, - "litellm_provider": "perplexity", - "mode": "chat" - }, - "perplexity/sonar-medium-chat": { - "max_tokens": 16384, - "max_input_tokens": 16384, - "max_output_tokens": 16384, - "input_cost_per_token": 6e-07, - "output_cost_per_token": 1.8e-06, - "litellm_provider": "perplexity", - "mode": "chat" - }, - "perplexity/sonar-medium-online": { - "max_tokens": 12000, - "max_input_tokens": 12000, - "max_output_tokens": 12000, - "input_cost_per_token": 0, - "output_cost_per_token": 1.8e-06, - "input_cost_per_request": 0.005, - "litellm_provider": "perplexity", - "mode": "chat" - }, - "perplexity/sonar": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "input_cost_per_token": 1e-06, - "output_cost_per_token": 1e-06, - "litellm_provider": "perplexity", - "mode": "chat", - "search_context_cost_per_query": { - "search_context_size_low": 0.005, - "search_context_size_medium": 0.008, - "search_context_size_high": 0.012 - }, - "supports_web_search": true - }, - "perplexity/sonar-pro": { - "max_tokens": 8000, - "max_input_tokens": 200000, - "max_output_tokens": 8000, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "litellm_provider": "perplexity", - "mode": "chat", - "search_context_cost_per_query": { - "search_context_size_low": 0.006, - "search_context_size_medium": 0.01, - "search_context_size_high": 0.014 - }, - "supports_web_search": true - }, - "perplexity/sonar-reasoning": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "input_cost_per_token": 1e-06, - "output_cost_per_token": 5e-06, - "litellm_provider": "perplexity", - "mode": "chat", - "search_context_cost_per_query": { - "search_context_size_low": 0.005, - "search_context_size_medium": 0.008, - "search_context_size_high": 0.014 - }, - "supports_web_search": true, - "supports_reasoning": true - }, - "perplexity/sonar-reasoning-pro": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 8e-06, - "litellm_provider": "perplexity", - "mode": "chat", - "search_context_cost_per_query": { - "search_context_size_low": 0.006, - "search_context_size_medium": 0.01, - "search_context_size_high": 0.014 - }, - "supports_web_search": true, - "supports_reasoning": true - }, - "perplexity/sonar-deep-research": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 8e-06, - "output_cost_per_reasoning_token": 3e-06, - "citation_cost_per_token": 2e-06, - "search_context_cost_per_query": { - "search_context_size_low": 0.005, - "search_context_size_medium": 0.005, - "search_context_size_high": 0.005 - }, - "litellm_provider": "perplexity", - "mode": "chat", - "supports_reasoning": true, - "supports_web_search": true - }, - "fireworks_ai/accounts/fireworks/models/llama-v3p2-1b-instruct": { - "max_tokens": 16384, - "max_input_tokens": 16384, - "max_output_tokens": 16384, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 1e-07, - "litellm_provider": "fireworks_ai", - "mode": "chat", - "supports_function_calling": false, - "supports_response_schema": true, - "source": "https://fireworks.ai/pricing", - "supports_tool_choice": false - }, - "fireworks_ai/accounts/fireworks/models/llama-v3p2-3b-instruct": { - "max_tokens": 16384, - "max_input_tokens": 16384, - "max_output_tokens": 16384, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 1e-07, - "litellm_provider": "fireworks_ai", - "mode": "chat", - "supports_function_calling": false, - "supports_response_schema": true, - "source": "https://fireworks.ai/pricing", - "supports_tool_choice": false - }, - "fireworks_ai/accounts/fireworks/models/llama-v3p1-8b-instruct": { - "max_tokens": 16384, - "max_input_tokens": 16384, - "max_output_tokens": 16384, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 1e-07, - "litellm_provider": "fireworks_ai", - "mode": "chat", - "supports_function_calling": false, - "supports_response_schema": true, - "source": "https://fireworks.ai/pricing", - "supports_tool_choice": false - }, - "fireworks_ai/accounts/fireworks/models/llama-v3p2-11b-vision-instruct": { - "max_tokens": 16384, - "max_input_tokens": 16384, - "max_output_tokens": 16384, - "input_cost_per_token": 2e-07, - "output_cost_per_token": 2e-07, - "litellm_provider": "fireworks_ai", - "mode": "chat", - "supports_function_calling": false, - "supports_vision": true, - "supports_response_schema": true, - "source": "https://fireworks.ai/pricing", - "supports_tool_choice": false - }, - "fireworks_ai/accounts/fireworks/models/llama-v3p2-90b-vision-instruct": { - "max_tokens": 16384, - "max_input_tokens": 16384, - "max_output_tokens": 16384, - "input_cost_per_token": 9e-07, - "output_cost_per_token": 9e-07, - "litellm_provider": "fireworks_ai", - "mode": "chat", - "supports_tool_choice": false, - "supports_vision": true, - "supports_response_schema": true, - "source": "https://fireworks.ai/pricing" - }, - "fireworks_ai/accounts/fireworks/models/firefunction-v2": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 9e-07, - "output_cost_per_token": 9e-07, - "litellm_provider": "fireworks_ai", - "mode": "chat", + "output_cost_per_token_above_128k_tokens": 0, + "source": "https://aistudio.google.com", + "supports_audio_output": false, "supports_function_calling": true, "supports_response_schema": true, - "source": "https://fireworks.ai/pricing", - "supports_tool_choice": true - }, - "fireworks_ai/accounts/fireworks/models/mixtral-8x22b-instruct-hf": { - "max_tokens": 65536, - "max_input_tokens": 65536, - "max_output_tokens": 65536, - "input_cost_per_token": 1.2e-06, - "output_cost_per_token": 1.2e-06, - "litellm_provider": "fireworks_ai", - "mode": "chat", - "supports_function_calling": true, - "supports_response_schema": true, - "source": "https://fireworks.ai/pricing", - "supports_tool_choice": true - }, - "fireworks_ai/accounts/fireworks/models/qwen2-72b-instruct": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "input_cost_per_token": 9e-07, - "output_cost_per_token": 9e-07, - "litellm_provider": "fireworks_ai", - "mode": "chat", - "supports_function_calling": false, - "supports_response_schema": true, - "source": "https://fireworks.ai/pricing", - "supports_tool_choice": false - }, - "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-32b-instruct": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 9e-07, - "output_cost_per_token": 9e-07, - "litellm_provider": "fireworks_ai", - "mode": "chat", - "supports_function_calling": false, - "supports_response_schema": true, - "source": "https://fireworks.ai/pricing", - "supports_tool_choice": false - }, - "fireworks_ai/accounts/fireworks/models/yi-large": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 3e-06, - "litellm_provider": "fireworks_ai", - "mode": "chat", - "supports_function_calling": false, - "supports_response_schema": true, - "source": "https://fireworks.ai/pricing", - "supports_tool_choice": false - }, - "fireworks_ai/accounts/fireworks/models/deepseek-coder-v2-instruct": { - "max_tokens": 65536, - "max_input_tokens": 65536, - "max_output_tokens": 65536, - "input_cost_per_token": 1.2e-06, - "output_cost_per_token": 1.2e-06, - "litellm_provider": "fireworks_ai", - "mode": "chat", - "supports_function_calling": false, - "supports_response_schema": true, - "source": "https://fireworks.ai/pricing", - "supports_tool_choice": false - }, - "fireworks_ai/accounts/fireworks/models/deepseek-v3": { - "max_tokens": 8192, - "max_input_tokens": 128000, - "max_output_tokens": 8192, - "input_cost_per_token": 9e-07, - "output_cost_per_token": 9e-07, - "litellm_provider": "fireworks_ai", - "mode": "chat", - "supports_response_schema": true, - "source": "https://fireworks.ai/pricing", - "supports_tool_choice": false - }, - "fireworks_ai/accounts/fireworks/models/deepseek-v3-0324": { - "max_tokens": 163840, - "max_input_tokens": 163840, - "max_output_tokens": 163840, - "input_cost_per_token": 9e-07, - "output_cost_per_token": 9e-07, - "litellm_provider": "fireworks_ai", - "mode": "chat", - "supports_response_schema": true, - "source": "https://fireworks.ai/models/fireworks/deepseek-v3-0324", - "supports_tool_choice": false - }, - "fireworks_ai/accounts/fireworks/models/deepseek-r1": { - "max_tokens": 20480, - "max_input_tokens": 128000, - "max_output_tokens": 20480, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 8e-06, - "litellm_provider": "fireworks_ai", - "mode": "chat", - "supports_response_schema": true, - "source": "https://fireworks.ai/pricing", - "supports_tool_choice": false - }, - "fireworks_ai/accounts/fireworks/models/deepseek-r1-basic": { - "max_tokens": 20480, - "max_input_tokens": 128000, - "max_output_tokens": 20480, - "input_cost_per_token": 5.5e-07, - "output_cost_per_token": 2.19e-06, - "litellm_provider": "fireworks_ai", - "mode": "chat", - "supports_response_schema": true, - "source": "https://fireworks.ai/pricing", - "supports_tool_choice": false - }, - "fireworks_ai/accounts/fireworks/models/deepseek-r1-0528": { - "max_tokens": 160000, - "max_input_tokens": 160000, - "max_output_tokens": 160000, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 8e-06, - "litellm_provider": "fireworks_ai", - "mode": "chat", - "source": "https://fireworks.ai/pricing", - "supports_tool_choice": false, - "supports_response_schema": true - }, - "fireworks_ai/accounts/fireworks/models/deepseek-v3p1": { - "max_tokens": 8192, - "max_input_tokens": 128000, - "max_output_tokens": 8192, - "input_cost_per_token": 5.6e-07, - "output_cost_per_token": 1.68e-06, - "litellm_provider": "fireworks_ai", - "mode": "chat", - "supports_response_schema": true, - "source": "https://fireworks.ai/pricing", - "supports_tool_choice": true - }, - "fireworks_ai/accounts/fireworks/models/kimi-k2-instruct": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 16384, - "input_cost_per_token": 6e-07, - "output_cost_per_token": 2.5e-06, - "litellm_provider": "fireworks_ai", - "mode": "chat", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "source": "https://fireworks.ai/models/fireworks/kimi-k2-instruct" - }, - "fireworks_ai/accounts/fireworks/models/llama-v3p1-405b-instruct": { - "max_tokens": 16384, - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 3e-06, - "litellm_provider": "fireworks_ai", - "mode": "chat", - "supports_response_schema": true, - "source": "https://fireworks.ai/pricing", - "supports_tool_choice": true, - "supports_function_calling": true - }, - "fireworks_ai/accounts/fireworks/models/llama4-maverick-instruct-basic": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 2.2e-07, - "output_cost_per_token": 8.8e-07, - "litellm_provider": "fireworks_ai", - "mode": "chat", - "supports_response_schema": true, - "source": "https://fireworks.ai/pricing", - "supports_tool_choice": false - }, - "fireworks_ai/accounts/fireworks/models/llama4-scout-instruct-basic": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 6e-07, - "litellm_provider": "fireworks_ai", - "mode": "chat", - "supports_response_schema": true, - "source": "https://fireworks.ai/pricing", - "supports_tool_choice": false - }, - "fireworks_ai/accounts/fireworks/models/glm-4p5": { - "max_tokens": 96000, - "max_input_tokens": 128000, - "max_output_tokens": 96000, - "input_cost_per_token": 5.5e-07, - "output_cost_per_token": 2.19e-06, - "litellm_provider": "fireworks_ai", - "mode": "chat", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "source": "https://fireworks.ai/models/fireworks/glm-4p5" - }, - "fireworks_ai/accounts/fireworks/models/glm-4p5-air": { - "max_tokens": 96000, - "max_input_tokens": 128000, - "max_output_tokens": 96000, - "input_cost_per_token": 2.2e-07, - "output_cost_per_token": 8.8e-07, - "litellm_provider": "fireworks_ai", - "mode": "chat", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "source": "https://artificialanalysis.ai/models/glm-4-5-air" - }, - "fireworks_ai/accounts/fireworks/models/gpt-oss-120b": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 6e-07, - "litellm_provider": "fireworks_ai", - "mode": "chat", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "source": "https://fireworks.ai/pricing" - }, - "fireworks_ai/accounts/fireworks/models/gpt-oss-20b": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 5e-08, - "output_cost_per_token": 2e-07, - "litellm_provider": "fireworks_ai", - "mode": "chat", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "source": "https://fireworks.ai/pricing" - }, - "fireworks_ai/nomic-ai/nomic-embed-text-v1.5": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "input_cost_per_token": 8e-09, - "output_cost_per_token": 0.0, - "litellm_provider": "fireworks_ai-embedding-models", - "mode": "embedding", - "source": "https://fireworks.ai/pricing" - }, - "fireworks_ai/nomic-ai/nomic-embed-text-v1": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "input_cost_per_token": 8e-09, - "output_cost_per_token": 0.0, - "litellm_provider": "fireworks_ai-embedding-models", - "mode": "embedding", - "source": "https://fireworks.ai/pricing" - }, - "fireworks_ai/WhereIsAI/UAE-Large-V1": { - "max_tokens": 512, - "max_input_tokens": 512, - "input_cost_per_token": 1.6e-08, - "output_cost_per_token": 0.0, - "litellm_provider": "fireworks_ai-embedding-models", - "mode": "embedding", - "source": "https://fireworks.ai/pricing" - }, - "fireworks_ai/thenlper/gte-large": { - "max_tokens": 512, - "max_input_tokens": 512, - "input_cost_per_token": 1.6e-08, - "output_cost_per_token": 0.0, - "litellm_provider": "fireworks_ai-embedding-models", - "mode": "embedding", - "source": "https://fireworks.ai/pricing" - }, - "fireworks_ai/thenlper/gte-base": { - "max_tokens": 512, - "max_input_tokens": 512, - "input_cost_per_token": 8e-09, - "output_cost_per_token": 0.0, - "litellm_provider": "fireworks_ai-embedding-models", - "mode": "embedding", - "source": "https://fireworks.ai/pricing" - }, - "fireworks-ai-up-to-4b": { - "input_cost_per_token": 2e-07, - "output_cost_per_token": 2e-07, - "litellm_provider": "fireworks_ai" - }, - "fireworks-ai-4.1b-to-16b": { - "input_cost_per_token": 2e-07, - "output_cost_per_token": 2e-07, - "litellm_provider": "fireworks_ai" - }, - "fireworks-ai-above-16b": { - "input_cost_per_token": 9e-07, - "output_cost_per_token": 9e-07, - "litellm_provider": "fireworks_ai" - }, - "fireworks-ai-moe-up-to-56b": { - "input_cost_per_token": 5e-07, - "output_cost_per_token": 5e-07, - "litellm_provider": "fireworks_ai" - }, - "fireworks-ai-56b-to-176b": { - "input_cost_per_token": 1.2e-06, - "output_cost_per_token": 1.2e-06, - "litellm_provider": "fireworks_ai" - }, - "fireworks-ai-default": { - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "fireworks_ai" - }, - "fireworks-ai-embedding-up-to-150m": { - "input_cost_per_token": 8e-09, - "output_cost_per_token": 0.0, - "litellm_provider": "fireworks_ai-embedding-models" - }, - "fireworks-ai-embedding-150m-to-350m": { - "input_cost_per_token": 1.6e-08, - "output_cost_per_token": 0.0, - "litellm_provider": "fireworks_ai-embedding-models" - }, - "anyscale/mistralai/Mistral-7B-Instruct-v0.1": { - "max_tokens": 16384, - "max_input_tokens": 16384, - "max_output_tokens": 16384, - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 1.5e-07, - "litellm_provider": "anyscale", - "mode": "chat", - "supports_function_calling": true, - "source": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/mistralai-Mistral-7B-Instruct-v0.1" - }, - "anyscale/mistralai/Mixtral-8x7B-Instruct-v0.1": { - "max_tokens": 16384, - "max_input_tokens": 16384, - "max_output_tokens": 16384, - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 1.5e-07, - "litellm_provider": "anyscale", - "mode": "chat", - "supports_function_calling": true, - "source": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/mistralai-Mixtral-8x7B-Instruct-v0.1" - }, - "anyscale/mistralai/Mixtral-8x22B-Instruct-v0.1": { - "max_tokens": 65536, - "max_input_tokens": 65536, - "max_output_tokens": 65536, - "input_cost_per_token": 9e-07, - "output_cost_per_token": 9e-07, - "litellm_provider": "anyscale", - "mode": "chat", - "supports_function_calling": true, - "source": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/mistralai-Mixtral-8x22B-Instruct-v0.1" - }, - "anyscale/HuggingFaceH4/zephyr-7b-beta": { - "max_tokens": 16384, - "max_input_tokens": 16384, - "max_output_tokens": 16384, - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 1.5e-07, - "litellm_provider": "anyscale", - "mode": "chat" - }, - "anyscale/google/gemma-7b-it": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 1.5e-07, - "litellm_provider": "anyscale", - "mode": "chat", - "source": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/google-gemma-7b-it" - }, - "anyscale/meta-llama/Llama-2-7b-chat-hf": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 1.5e-07, - "litellm_provider": "anyscale", - "mode": "chat" - }, - "anyscale/meta-llama/Llama-2-13b-chat-hf": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 2.5e-07, - "output_cost_per_token": 2.5e-07, - "litellm_provider": "anyscale", - "mode": "chat" - }, - "anyscale/meta-llama/Llama-2-70b-chat-hf": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 1e-06, - "output_cost_per_token": 1e-06, - "litellm_provider": "anyscale", - "mode": "chat" - }, - "anyscale/codellama/CodeLlama-34b-Instruct-hf": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 1e-06, - "output_cost_per_token": 1e-06, - "litellm_provider": "anyscale", - "mode": "chat" - }, - "anyscale/codellama/CodeLlama-70b-Instruct-hf": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 1e-06, - "output_cost_per_token": 1e-06, - "litellm_provider": "anyscale", - "mode": "chat", - "source": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/codellama-CodeLlama-70b-Instruct-hf" - }, - "anyscale/meta-llama/Meta-Llama-3-8B-Instruct": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 1.5e-07, - "litellm_provider": "anyscale", - "mode": "chat", - "source": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/meta-llama-Meta-Llama-3-8B-Instruct" - }, - "anyscale/meta-llama/Meta-Llama-3-70B-Instruct": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 1e-06, - "output_cost_per_token": 1e-06, - "litellm_provider": "anyscale", - "mode": "chat", - "source": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/meta-llama-Meta-Llama-3-70B-Instruct" - }, - "cloudflare/@cf/meta/llama-2-7b-chat-fp16": { - "max_tokens": 3072, - "max_input_tokens": 3072, - "max_output_tokens": 3072, - "input_cost_per_token": 1.923e-06, - "output_cost_per_token": 1.923e-06, - "litellm_provider": "cloudflare", - "mode": "chat" - }, - "cloudflare/@cf/meta/llama-2-7b-chat-int8": { - "max_tokens": 2048, - "max_input_tokens": 2048, - "max_output_tokens": 2048, - "input_cost_per_token": 1.923e-06, - "output_cost_per_token": 1.923e-06, - "litellm_provider": "cloudflare", - "mode": "chat" - }, - "cloudflare/@cf/mistral/mistral-7b-instruct-v0.1": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 1.923e-06, - "output_cost_per_token": 1.923e-06, - "litellm_provider": "cloudflare", - "mode": "chat" - }, - "cloudflare/@hf/thebloke/codellama-7b-instruct-awq": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 1.923e-06, - "output_cost_per_token": 1.923e-06, - "litellm_provider": "cloudflare", - "mode": "chat" - }, - "v0/v0-1.0-md": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "litellm_provider": "v0", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_vision": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "v0/v0-1.5-md": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "litellm_provider": "v0", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_vision": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "v0/v0-1.5-lg": { - "max_tokens": 512000, - "max_input_tokens": 512000, - "max_output_tokens": 512000, - "input_cost_per_token": 1.5e-05, - "output_cost_per_token": 7.5e-05, - "litellm_provider": "v0", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_vision": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "lambda_ai/deepseek-llama3.3-70b": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 2e-07, - "output_cost_per_token": 6e-07, - "litellm_provider": "lambda_ai", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_reasoning": true + "supports_vision": true }, - "lambda_ai/deepseek-r1-0528": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 2e-07, - "output_cost_per_token": 6e-07, - "litellm_provider": "lambda_ai", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_reasoning": true - }, - "lambda_ai/deepseek-r1-671b": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 8e-07, - "output_cost_per_token": 8e-07, - "litellm_provider": "lambda_ai", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_reasoning": true - }, - "lambda_ai/deepseek-v3-0324": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 2e-07, - "output_cost_per_token": 6e-07, - "litellm_provider": "lambda_ai", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "lambda_ai/hermes3-405b": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 8e-07, - "output_cost_per_token": 8e-07, - "litellm_provider": "lambda_ai", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "lambda_ai/hermes3-70b": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 1.2e-07, - "output_cost_per_token": 3e-07, - "litellm_provider": "lambda_ai", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "lambda_ai/hermes3-8b": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 2.5e-08, - "output_cost_per_token": 4e-08, - "litellm_provider": "lambda_ai", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "lambda_ai/lfm-40b": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 2e-07, - "litellm_provider": "lambda_ai", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "lambda_ai/lfm-7b": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 2.5e-08, - "output_cost_per_token": 4e-08, - "litellm_provider": "lambda_ai", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "lambda_ai/llama-4-maverick-17b-128e-instruct-fp8": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 8192, - "input_cost_per_token": 5e-08, - "output_cost_per_token": 1e-07, - "litellm_provider": "lambda_ai", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "lambda_ai/llama-4-scout-17b-16e-instruct": { - "max_tokens": 16384, - "max_input_tokens": 16384, - "max_output_tokens": 8192, - "input_cost_per_token": 5e-08, - "output_cost_per_token": 1e-07, - "litellm_provider": "lambda_ai", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "lambda_ai/llama3.1-405b-instruct-fp8": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 8e-07, - "output_cost_per_token": 8e-07, - "litellm_provider": "lambda_ai", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "lambda_ai/llama3.1-70b-instruct-fp8": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 1.2e-07, - "output_cost_per_token": 3e-07, - "litellm_provider": "lambda_ai", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "lambda_ai/llama3.1-8b-instruct": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 2.5e-08, - "output_cost_per_token": 4e-08, - "litellm_provider": "lambda_ai", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "lambda_ai/llama3.1-nemotron-70b-instruct-fp8": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 1.2e-07, - "output_cost_per_token": 3e-07, - "litellm_provider": "lambda_ai", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "lambda_ai/llama3.2-11b-vision-instruct": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 1.5e-08, - "output_cost_per_token": 2.5e-08, - "litellm_provider": "lambda_ai", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_vision": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "lambda_ai/llama3.2-3b-instruct": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 1.5e-08, - "output_cost_per_token": 2.5e-08, - "litellm_provider": "lambda_ai", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "lambda_ai/llama3.3-70b-instruct-fp8": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 1.2e-07, - "output_cost_per_token": 3e-07, - "litellm_provider": "lambda_ai", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "lambda_ai/qwen25-coder-32b-instruct": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 5e-08, - "output_cost_per_token": 1e-07, - "litellm_provider": "lambda_ai", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "lambda_ai/qwen3-32b-fp8": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 5e-08, - "output_cost_per_token": 1e-07, - "litellm_provider": "lambda_ai", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_reasoning": true - }, - "hyperbolic/moonshotai/Kimi-K2-Instruct": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 2e-06, - "litellm_provider": "hyperbolic", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "hyperbolic/deepseek-ai/DeepSeek-R1-0528": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 2.5e-07, - "output_cost_per_token": 2.5e-07, - "litellm_provider": "hyperbolic", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "hyperbolic/Qwen/Qwen3-235B-A22B": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 2e-06, - "litellm_provider": "hyperbolic", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "hyperbolic/deepseek-ai/DeepSeek-V3-0324": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "input_cost_per_token": 4e-07, - "output_cost_per_token": 4e-07, - "litellm_provider": "hyperbolic", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "hyperbolic/Qwen/QwQ-32B": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 2e-07, - "output_cost_per_token": 2e-07, - "litellm_provider": "hyperbolic", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "hyperbolic/deepseek-ai/DeepSeek-R1": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "input_cost_per_token": 4e-07, - "output_cost_per_token": 4e-07, - "litellm_provider": "hyperbolic", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "hyperbolic/deepseek-ai/DeepSeek-V3": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "input_cost_per_token": 2e-07, - "output_cost_per_token": 2e-07, - "litellm_provider": "hyperbolic", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "hyperbolic/meta-llama/Llama-3.3-70B-Instruct": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 1.2e-07, - "output_cost_per_token": 3e-07, - "litellm_provider": "hyperbolic", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "hyperbolic/Qwen/Qwen2.5-Coder-32B-Instruct": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "input_cost_per_token": 1.2e-07, - "output_cost_per_token": 3e-07, - "litellm_provider": "hyperbolic", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "hyperbolic/meta-llama/Llama-3.2-3B-Instruct": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "input_cost_per_token": 1.2e-07, - "output_cost_per_token": 3e-07, - "litellm_provider": "hyperbolic", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "hyperbolic/Qwen/Qwen2.5-72B-Instruct": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 1.2e-07, - "output_cost_per_token": 3e-07, - "litellm_provider": "hyperbolic", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "hyperbolic/meta-llama/Meta-Llama-3-70B-Instruct": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 1.2e-07, - "output_cost_per_token": 3e-07, - "litellm_provider": "hyperbolic", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "hyperbolic/NousResearch/Hermes-3-Llama-3.1-70B": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "input_cost_per_token": 1.2e-07, - "output_cost_per_token": 3e-07, - "litellm_provider": "hyperbolic", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "hyperbolic/meta-llama/Meta-Llama-3.1-405B-Instruct": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "input_cost_per_token": 1.2e-07, - "output_cost_per_token": 3e-07, - "litellm_provider": "hyperbolic", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "hyperbolic/meta-llama/Meta-Llama-3.1-8B-Instruct": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "input_cost_per_token": 1.2e-07, - "output_cost_per_token": 3e-07, - "litellm_provider": "hyperbolic", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "hyperbolic/meta-llama/Meta-Llama-3.1-70B-Instruct": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "input_cost_per_token": 1.2e-07, - "output_cost_per_token": 3e-07, - "litellm_provider": "hyperbolic", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "voyage/voyage-lite-01": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 0.0, - "litellm_provider": "voyage", - "mode": "embedding" - }, - "voyage/voyage-large-2": { - "max_tokens": 16000, - "max_input_tokens": 16000, - "input_cost_per_token": 1.2e-07, - "output_cost_per_token": 0.0, - "litellm_provider": "voyage", - "mode": "embedding" - }, - "voyage/voyage-finance-2": { - "max_tokens": 32000, - "max_input_tokens": 32000, - "input_cost_per_token": 1.2e-07, - "output_cost_per_token": 0.0, - "litellm_provider": "voyage", - "mode": "embedding" - }, - "voyage/voyage-lite-02-instruct": { - "max_tokens": 4000, - "max_input_tokens": 4000, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 0.0, - "litellm_provider": "voyage", - "mode": "embedding" - }, - "voyage/voyage-law-2": { - "max_tokens": 16000, - "max_input_tokens": 16000, - "input_cost_per_token": 1.2e-07, - "output_cost_per_token": 0.0, - "litellm_provider": "voyage", - "mode": "embedding" - }, - "voyage/voyage-code-2": { - "max_tokens": 16000, - "max_input_tokens": 16000, - "input_cost_per_token": 1.2e-07, - "output_cost_per_token": 0.0, - "litellm_provider": "voyage", - "mode": "embedding" - }, - "voyage/voyage-2": { - "max_tokens": 4000, - "max_input_tokens": 4000, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 0.0, - "litellm_provider": "voyage", - "mode": "embedding" - }, - "voyage/voyage-3-large": { - "max_tokens": 32000, - "max_input_tokens": 32000, - "input_cost_per_token": 1.8e-07, - "output_cost_per_token": 0.0, - "litellm_provider": "voyage", - "mode": "embedding" - }, - "voyage/voyage-3": { - "max_tokens": 32000, - "max_input_tokens": 32000, - "input_cost_per_token": 6e-08, - "output_cost_per_token": 0.0, - "litellm_provider": "voyage", - "mode": "embedding" - }, - "voyage/voyage-3-lite": { - "max_tokens": 32000, - "max_input_tokens": 32000, - "input_cost_per_token": 2e-08, - "output_cost_per_token": 0.0, - "litellm_provider": "voyage", - "mode": "embedding" - }, - "voyage/voyage-code-3": { - "max_tokens": 32000, - "max_input_tokens": 32000, - "input_cost_per_token": 1.8e-07, - "output_cost_per_token": 0.0, - "litellm_provider": "voyage", - "mode": "embedding" - }, - "voyage/voyage-multimodal-3": { - "max_tokens": 32000, - "max_input_tokens": 32000, - "input_cost_per_token": 1.2e-07, - "output_cost_per_token": 0.0, - "litellm_provider": "voyage", - "mode": "embedding" - }, - "voyage/voyage-context-3": { - "max_tokens": 120000, - "max_input_tokens": 120000, - "input_cost_per_token": 1.8e-07, - "output_cost_per_token": 0.0, - "litellm_provider": "voyage", - "mode": "embedding" - }, - "voyage/rerank-2": { - "max_tokens": 16000, - "max_input_tokens": 16000, - "max_output_tokens": 16000, - "max_query_tokens": 16000, - "input_cost_per_token": 5e-08, - "input_cost_per_query": 5e-08, - "output_cost_per_token": 0.0, - "litellm_provider": "voyage", - "mode": "rerank" - }, - "voyage/rerank-2-lite": { - "max_tokens": 8000, - "max_input_tokens": 8000, - "max_output_tokens": 8000, - "max_query_tokens": 8000, - "input_cost_per_token": 2e-08, - "input_cost_per_query": 2e-08, - "output_cost_per_token": 0.0, - "litellm_provider": "voyage", - "mode": "rerank" - }, - "databricks/databricks-claude-3-7-sonnet": { - "max_tokens": 200000, - "max_input_tokens": 200000, - "max_output_tokens": 128000, - "input_cost_per_token": 2.5e-06, - "input_dbu_cost_per_token": 3.571e-05, - "output_cost_per_token": 1.7857e-05, - "output_db_cost_per_token": 0.000214286, - "litellm_provider": "databricks", - "mode": "chat", - "source": "https://www.databricks.com/product/pricing/foundation-model-serving", - "metadata": { - "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Claude 3.7 conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." - }, - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true - }, - "databricks/databricks-meta-llama-3-1-405b-instruct": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "input_cost_per_token": 5e-06, - "input_dbu_cost_per_token": 7.1429e-05, - "output_cost_per_token": 1.500002e-05, - "output_db_cost_per_token": 0.000214286, - "litellm_provider": "databricks", - "mode": "chat", - "source": "https://www.databricks.com/product/pricing/foundation-model-serving", - "metadata": { - "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." - }, - "supports_tool_choice": true - }, - "databricks/databricks-meta-llama-3-3-70b-instruct": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "input_cost_per_token": 1.00002e-06, - "input_dbu_cost_per_token": 1.4286e-05, - "output_cost_per_token": 2.99999e-06, - "output_dbu_cost_per_token": 4.2857e-05, - "litellm_provider": "databricks", - "mode": "chat", - "source": "https://www.databricks.com/product/pricing/foundation-model-serving", - "metadata": { - "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." - }, - "supports_tool_choice": true - }, - "databricks/databricks-llama-4-maverick": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "input_cost_per_token": 5e-06, - "input_dbu_cost_per_token": 7.143e-05, - "output_cost_per_token": 1.5e-05, - "output_dbu_cost_per_token": 0.00021429, - "litellm_provider": "databricks", - "mode": "chat", - "source": "https://www.databricks.com/product/pricing/foundation-model-serving", - "metadata": { - "notes": "Databricks documentation now provides both DBU costs (_dbu_cost_per_token) and dollar costs(_cost_per_token)." - }, - "supports_tool_choice": true - }, - "databricks/databricks-meta-llama-3-70b-instruct": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "input_cost_per_token": 1.00002e-06, - "input_dbu_cost_per_token": 1.4286e-05, - "output_cost_per_token": 2.99999e-06, - "output_dbu_cost_per_token": 4.2857e-05, - "litellm_provider": "databricks", - "mode": "chat", - "source": "https://www.databricks.com/product/pricing/foundation-model-serving", - "metadata": { - "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." - }, - "supports_tool_choice": true - }, - "databricks/databricks-llama-2-70b-chat": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 5.0001e-07, - "input_dbu_cost_per_token": 7.143e-06, - "output_cost_per_token": 1.5e-06, - "output_dbu_cost_per_token": 2.1429e-05, - "litellm_provider": "databricks", - "mode": "chat", - "source": "https://www.databricks.com/product/pricing/foundation-model-serving", - "metadata": { - "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." - }, - "supports_tool_choice": true - }, - "databricks/databricks-mixtral-8x7b-instruct": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 5.0001e-07, - "input_dbu_cost_per_token": 7.143e-06, - "output_cost_per_token": 9.9902e-07, - "output_dbu_cost_per_token": 1.4286e-05, - "litellm_provider": "databricks", - "mode": "chat", - "source": "https://www.databricks.com/product/pricing/foundation-model-serving", - "metadata": { - "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." - }, - "supports_tool_choice": true - }, - "databricks/databricks-mpt-30b-instruct": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 9.9902e-07, - "input_dbu_cost_per_token": 1.4286e-05, - "output_cost_per_token": 9.9902e-07, - "output_dbu_cost_per_token": 1.4286e-05, - "litellm_provider": "databricks", - "mode": "chat", - "source": "https://www.databricks.com/product/pricing/foundation-model-serving", - "metadata": { - "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." - }, - "supports_tool_choice": true - }, - "databricks/databricks-mpt-7b-instruct": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 5.0001e-07, - "input_dbu_cost_per_token": 7.143e-06, - "output_cost_per_token": 0.0, - "output_dbu_cost_per_token": 0.0, - "litellm_provider": "databricks", - "mode": "chat", - "source": "https://www.databricks.com/product/pricing/foundation-model-serving", - "metadata": { - "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." - }, - "supports_tool_choice": true - }, - "databricks/databricks-bge-large-en": { - "max_tokens": 512, - "max_input_tokens": 512, - "output_vector_size": 1024, - "input_cost_per_token": 1.0003e-07, - "input_dbu_cost_per_token": 1.429e-06, - "output_cost_per_token": 0.0, - "output_dbu_cost_per_token": 0.0, - "litellm_provider": "databricks", - "mode": "embedding", - "source": "https://www.databricks.com/product/pricing/foundation-model-serving", - "metadata": { - "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." - } - }, - "databricks/databricks-gte-large-en": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "output_vector_size": 1024, - "input_cost_per_token": 1.2999e-07, - "input_dbu_cost_per_token": 1.857e-06, - "output_cost_per_token": 0.0, - "output_dbu_cost_per_token": 0.0, - "litellm_provider": "databricks", - "mode": "embedding", - "source": "https://www.databricks.com/product/pricing/foundation-model-serving", - "metadata": { - "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." - } - }, - "sambanova/Meta-Llama-3.1-8B-Instruct": { - "max_tokens": 16384, - "max_input_tokens": 16384, - "max_output_tokens": 16384, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 2e-07, - "litellm_provider": "sambanova", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": true, - "source": "https://cloud.sambanova.ai/plans/pricing" - }, - "sambanova/Meta-Llama-3.1-405B-Instruct": { - "max_tokens": 16384, - "max_input_tokens": 16384, - "max_output_tokens": 16384, - "input_cost_per_token": 5e-06, - "output_cost_per_token": 1e-05, - "litellm_provider": "sambanova", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": true, - "source": "https://cloud.sambanova.ai/plans/pricing" - }, - "sambanova/Meta-Llama-3.2-1B-Instruct": { - "max_tokens": 16384, - "max_input_tokens": 16384, - "max_output_tokens": 16384, - "input_cost_per_token": 4e-08, - "output_cost_per_token": 8e-08, - "litellm_provider": "sambanova", - "mode": "chat", - "source": "https://cloud.sambanova.ai/plans/pricing" - }, - "sambanova/Meta-Llama-3.2-3B-Instruct": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 8e-08, - "output_cost_per_token": 1.6e-07, - "litellm_provider": "sambanova", - "mode": "chat", - "source": "https://cloud.sambanova.ai/plans/pricing" - }, - "sambanova/Llama-4-Maverick-17B-128E-Instruct": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 6.3e-07, - "output_cost_per_token": 1.8e-06, - "litellm_provider": "sambanova", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_vision": true, - "source": "https://cloud.sambanova.ai/plans/pricing", - "metadata": { - "notes": "For vision models, images are converted to 6432 input tokens and are billed at that amount" - } - }, - "sambanova/Llama-4-Scout-17B-16E-Instruct": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 4e-07, - "output_cost_per_token": 7e-07, - "litellm_provider": "sambanova", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": true, - "source": "https://cloud.sambanova.ai/plans/pricing", - "metadata": { - "notes": "For vision models, images are converted to 6432 input tokens and are billed at that amount" - } - }, - "sambanova/Meta-Llama-3.3-70B-Instruct": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 6e-07, - "output_cost_per_token": 1.2e-06, - "litellm_provider": "sambanova", - "mode": "chat", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "source": "https://cloud.sambanova.ai/plans/pricing" - }, - "sambanova/Meta-Llama-Guard-3-8B": { - "max_tokens": 16384, - "max_input_tokens": 16384, - "max_output_tokens": 16384, - "input_cost_per_token": 3e-07, - "output_cost_per_token": 3e-07, - "litellm_provider": "sambanova", - "mode": "chat", - "source": "https://cloud.sambanova.ai/plans/pricing" - }, - "sambanova/Qwen3-32B": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 4e-07, - "output_cost_per_token": 8e-07, - "litellm_provider": "sambanova", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "mode": "chat", - "source": "https://cloud.sambanova.ai/plans/pricing" - }, - "sambanova/QwQ-32B": { - "max_tokens": 16384, - "max_input_tokens": 16384, - "max_output_tokens": 16384, - "input_cost_per_token": 5e-07, - "output_cost_per_token": 1e-06, - "litellm_provider": "sambanova", - "mode": "chat", - "source": "https://cloud.sambanova.ai/plans/pricing" - }, - "sambanova/Qwen2-Audio-7B-Instruct": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 5e-07, - "output_cost_per_token": 0.0001, - "litellm_provider": "sambanova", - "mode": "chat", - "supports_audio_input": true, - "source": "https://cloud.sambanova.ai/plans/pricing" - }, - "sambanova/DeepSeek-R1-Distill-Llama-70B": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 7e-07, - "output_cost_per_token": 1.4e-06, - "litellm_provider": "sambanova", - "mode": "chat", - "source": "https://cloud.sambanova.ai/plans/pricing" - }, - "sambanova/DeepSeek-R1": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "input_cost_per_token": 5e-06, - "output_cost_per_token": 7e-06, - "litellm_provider": "sambanova", - "mode": "chat", - "source": "https://cloud.sambanova.ai/plans/pricing" - }, - "sambanova/DeepSeek-V3-0324": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 4.5e-06, - "litellm_provider": "sambanova", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "source": "https://cloud.sambanova.ai/plans/pricing" - }, - "assemblyai/nano": { - "mode": "audio_transcription", - "input_cost_per_second": 0.00010278, - "output_cost_per_second": 0.0, - "litellm_provider": "assemblyai" - }, - "assemblyai/best": { - "mode": "audio_transcription", - "input_cost_per_second": 3.333e-05, - "output_cost_per_second": 0.0, - "litellm_provider": "assemblyai" - }, - "jina-reranker-v2-base-multilingual": { - "max_tokens": 1024, + "gemini/veo-2.0-generate-001": { + "litellm_provider": "gemini", "max_input_tokens": 1024, - "max_output_tokens": 1024, - "max_document_chunks_per_query": 2048, - "input_cost_per_token": 1.8e-08, - "output_cost_per_token": 1.8e-08, - "litellm_provider": "jina_ai", - "mode": "rerank" - }, - "snowflake/deepseek-r1": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 8192, - "litellm_provider": "snowflake", - "supports_reasoning": true, - "mode": "chat" - }, - "snowflake/snowflake-arctic": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 8192, - "litellm_provider": "snowflake", - "mode": "chat" - }, - "snowflake/claude-3-5-sonnet": { - "supports_computer_use": true, - "max_tokens": 18000, - "max_input_tokens": 18000, - "max_output_tokens": 8192, - "litellm_provider": "snowflake", - "mode": "chat" - }, - "snowflake/mistral-large": { - "max_tokens": 32000, - "max_input_tokens": 32000, - "max_output_tokens": 8192, - "litellm_provider": "snowflake", - "mode": "chat" - }, - "snowflake/mistral-large2": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 8192, - "litellm_provider": "snowflake", - "mode": "chat" - }, - "snowflake/reka-flash": { - "max_tokens": 100000, - "max_input_tokens": 100000, - "max_output_tokens": 8192, - "litellm_provider": "snowflake", - "mode": "chat" - }, - "snowflake/reka-core": { - "max_tokens": 32000, - "max_input_tokens": 32000, - "max_output_tokens": 8192, - "litellm_provider": "snowflake", - "mode": "chat" - }, - "snowflake/jamba-instruct": { - "max_tokens": 256000, - "max_input_tokens": 256000, - "max_output_tokens": 8192, - "litellm_provider": "snowflake", - "mode": "chat" - }, - "snowflake/jamba-1.5-mini": { - "max_tokens": 256000, - "max_input_tokens": 256000, - "max_output_tokens": 8192, - "litellm_provider": "snowflake", - "mode": "chat" - }, - "snowflake/jamba-1.5-large": { - "max_tokens": 256000, - "max_input_tokens": 256000, - "max_output_tokens": 8192, - "litellm_provider": "snowflake", - "mode": "chat" - }, - "snowflake/mixtral-8x7b": { - "max_tokens": 32000, - "max_input_tokens": 32000, - "max_output_tokens": 8192, - "litellm_provider": "snowflake", - "mode": "chat" - }, - "snowflake/llama2-70b-chat": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 8192, - "litellm_provider": "snowflake", - "mode": "chat" - }, - "snowflake/llama3-8b": { - "max_tokens": 8000, - "max_input_tokens": 8000, - "max_output_tokens": 8192, - "litellm_provider": "snowflake", - "mode": "chat" - }, - "snowflake/llama3-70b": { - "max_tokens": 8000, - "max_input_tokens": 8000, - "max_output_tokens": 8192, - "litellm_provider": "snowflake", - "mode": "chat" - }, - "snowflake/llama3.1-8b": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 8192, - "litellm_provider": "snowflake", - "mode": "chat" - }, - "snowflake/llama3.1-70b": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 8192, - "litellm_provider": "snowflake", - "mode": "chat" - }, - "snowflake/llama3.3-70b": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 8192, - "litellm_provider": "snowflake", - "mode": "chat" - }, - "snowflake/snowflake-llama-3.3-70b": { - "max_tokens": 8000, - "max_input_tokens": 8000, - "max_output_tokens": 8192, - "litellm_provider": "snowflake", - "mode": "chat" - }, - "snowflake/llama3.1-405b": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 8192, - "litellm_provider": "snowflake", - "mode": "chat" - }, - "snowflake/snowflake-llama-3.1-405b": { - "max_tokens": 8000, - "max_input_tokens": 8000, - "max_output_tokens": 8192, - "litellm_provider": "snowflake", - "mode": "chat" - }, - "snowflake/llama3.2-1b": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 8192, - "litellm_provider": "snowflake", - "mode": "chat" - }, - "snowflake/llama3.2-3b": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 8192, - "litellm_provider": "snowflake", - "mode": "chat" - }, - "snowflake/mistral-7b": { - "max_tokens": 32000, - "max_input_tokens": 32000, - "max_output_tokens": 8192, - "litellm_provider": "snowflake", - "mode": "chat" - }, - "snowflake/gemma-7b": { - "max_tokens": 8000, - "max_input_tokens": 8000, - "max_output_tokens": 8192, - "litellm_provider": "snowflake", - "mode": "chat" - }, - "gradient_ai/anthropic-claude-3.7-sonnet": { - "input_cost_per_token": 3e-06, - "output_cost_per_token": 15e-06, - "litellm_provider": "gradient_ai", - "mode": "chat", "max_tokens": 1024, - "supported_endpoints": ["/v1/chat/completions"], - "supported_modalities": ["text"], + "mode": "video_generation", + "output_cost_per_second": 0.35, + "source": "https://ai.google.dev/gemini-api/docs/video", + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "gemini/veo-3.0-fast-generate-preview": { + "litellm_provider": "gemini", + "max_input_tokens": 1024, + "max_tokens": 1024, + "mode": "video_generation", + "output_cost_per_second": 0.4, + "source": "https://ai.google.dev/gemini-api/docs/video", + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "gemini/veo-3.0-generate-preview": { + "litellm_provider": "gemini", + "max_input_tokens": 1024, + "max_tokens": 1024, + "mode": "video_generation", + "output_cost_per_second": 0.75, + "source": "https://ai.google.dev/gemini-api/docs/video", + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "gpt-3.5-turbo": { + "input_cost_per_token": 1.5e-06, + "litellm_provider": "openai", + "max_input_tokens": 16385, + "max_output_tokens": 4096, + "max_tokens": 4097, + "mode": "chat", + "output_cost_per_token": 2e-06, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "gpt-3.5-turbo-0125": { + "input_cost_per_token": 5e-07, + "litellm_provider": "openai", + "max_input_tokens": 16385, + "max_output_tokens": 4096, + "max_tokens": 16385, + "mode": "chat", + "output_cost_per_token": 1.5e-06, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "gpt-3.5-turbo-0301": { + "input_cost_per_token": 1.5e-06, + "litellm_provider": "openai", + "max_input_tokens": 4097, + "max_output_tokens": 4096, + "max_tokens": 4097, + "mode": "chat", + "output_cost_per_token": 2e-06, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "gpt-3.5-turbo-0613": { + "input_cost_per_token": 1.5e-06, + "litellm_provider": "openai", + "max_input_tokens": 4097, + "max_output_tokens": 4096, + "max_tokens": 4097, + "mode": "chat", + "output_cost_per_token": 2e-06, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "gpt-3.5-turbo-1106": { + "input_cost_per_token": 1e-06, + "litellm_provider": "openai", + "max_input_tokens": 16385, + "max_output_tokens": 4096, + "max_tokens": 16385, + "mode": "chat", + "output_cost_per_token": 2e-06, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "gpt-3.5-turbo-16k": { + "input_cost_per_token": 3e-06, + "litellm_provider": "openai", + "max_input_tokens": 16385, + "max_output_tokens": 4096, + "max_tokens": 16385, + "mode": "chat", + "output_cost_per_token": 4e-06, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "gpt-3.5-turbo-16k-0613": { + "input_cost_per_token": 3e-06, + "litellm_provider": "openai", + "max_input_tokens": 16385, + "max_output_tokens": 4096, + "max_tokens": 16385, + "mode": "chat", + "output_cost_per_token": 4e-06, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "gpt-3.5-turbo-instruct": { + "input_cost_per_token": 1.5e-06, + "litellm_provider": "text-completion-openai", + "max_input_tokens": 8192, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "completion", + "output_cost_per_token": 2e-06 + }, + "gpt-3.5-turbo-instruct-0914": { + "input_cost_per_token": 1.5e-06, + "litellm_provider": "text-completion-openai", + "max_input_tokens": 8192, + "max_output_tokens": 4097, + "max_tokens": 4097, + "mode": "completion", + "output_cost_per_token": 2e-06 + }, + "gpt-4": { + "input_cost_per_token": 3e-05, + "litellm_provider": "openai", + "max_input_tokens": 8192, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 6e-05, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "gpt-4-0125-preview": { + "input_cost_per_token": 1e-05, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 3e-05, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "gpt-4-0314": { + "input_cost_per_token": 3e-05, + "litellm_provider": "openai", + "max_input_tokens": 8192, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 6e-05, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "gpt-4-0613": { + "deprecation_date": "2025-06-06", + "input_cost_per_token": 3e-05, + "litellm_provider": "openai", + "max_input_tokens": 8192, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 6e-05, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "gpt-4-1106-preview": { + "input_cost_per_token": 1e-05, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 3e-05, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "gpt-4-1106-vision-preview": { + "deprecation_date": "2024-12-06", + "input_cost_per_token": 1e-05, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 3e-05, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "gpt-4-32k": { + "input_cost_per_token": 6e-05, + "litellm_provider": "openai", + "max_input_tokens": 32768, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.00012, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "gpt-4-32k-0314": { + "input_cost_per_token": 6e-05, + "litellm_provider": "openai", + "max_input_tokens": 32768, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.00012, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "gpt-4-32k-0613": { + "input_cost_per_token": 6e-05, + "litellm_provider": "openai", + "max_input_tokens": 32768, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.00012, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "gpt-4-turbo": { + "input_cost_per_token": 1e-05, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 3e-05, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "gpt-4-turbo-2024-04-09": { + "input_cost_per_token": 1e-05, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 3e-05, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "gpt-4-turbo-preview": { + "input_cost_per_token": 1e-05, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 3e-05, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "gpt-4-vision-preview": { + "deprecation_date": "2024-12-06", + "input_cost_per_token": 1e-05, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 3e-05, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "gpt-4.1": { + "cache_read_input_token_cost": 5e-07, + "input_cost_per_token": 2e-06, + "input_cost_per_token_batches": 1e-06, + "litellm_provider": "openai", + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 8e-06, + "output_cost_per_token_batches": 4e-06, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "gpt-4.1-2025-04-14": { + "cache_read_input_token_cost": 5e-07, + "input_cost_per_token": 2e-06, + "input_cost_per_token_batches": 1e-06, + "litellm_provider": "openai", + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 8e-06, + "output_cost_per_token_batches": 4e-06, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "gpt-4.1-mini": { + "cache_read_input_token_cost": 1e-07, + "input_cost_per_token": 4e-07, + "input_cost_per_token_batches": 2e-07, + "litellm_provider": "openai", + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 1.6e-06, + "output_cost_per_token_batches": 8e-07, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "gpt-4.1-mini-2025-04-14": { + "cache_read_input_token_cost": 1e-07, + "input_cost_per_token": 4e-07, + "input_cost_per_token_batches": 2e-07, + "litellm_provider": "openai", + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 1.6e-06, + "output_cost_per_token_batches": 8e-07, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "gpt-4.1-nano": { + "cache_read_input_token_cost": 2.5e-08, + "input_cost_per_token": 1e-07, + "input_cost_per_token_batches": 5e-08, + "litellm_provider": "openai", + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 4e-07, + "output_cost_per_token_batches": 2e-07, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "gpt-4.1-nano-2025-04-14": { + "cache_read_input_token_cost": 2.5e-08, + "input_cost_per_token": 1e-07, + "input_cost_per_token_batches": 5e-08, + "litellm_provider": "openai", + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 4e-07, + "output_cost_per_token_batches": 2e-07, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "gpt-4.5-preview": { + "cache_read_input_token_cost": 3.75e-05, + "input_cost_per_token": 7.5e-05, + "input_cost_per_token_batches": 3.75e-05, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 0.00015, + "output_cost_per_token_batches": 7.5e-05, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "gpt-4.5-preview-2025-02-27": { + "cache_read_input_token_cost": 3.75e-05, + "deprecation_date": "2025-07-14", + "input_cost_per_token": 7.5e-05, + "input_cost_per_token_batches": 3.75e-05, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 0.00015, + "output_cost_per_token_batches": 7.5e-05, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "gpt-4o": { + "cache_read_input_token_cost": 1.25e-06, + "input_cost_per_token": 2.5e-06, + "input_cost_per_token_batches": 1.25e-06, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1e-05, + "output_cost_per_token_batches": 5e-06, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "gpt-4o-2024-05-13": { + "input_cost_per_token": 5e-06, + "input_cost_per_token_batches": 2.5e-06, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "output_cost_per_token_batches": 7.5e-06, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "gpt-4o-2024-08-06": { + "cache_read_input_token_cost": 1.25e-06, + "input_cost_per_token": 2.5e-06, + "input_cost_per_token_batches": 1.25e-06, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1e-05, + "output_cost_per_token_batches": 5e-06, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "gpt-4o-2024-11-20": { + "cache_read_input_token_cost": 1.25e-06, + "input_cost_per_token": 2.5e-06, + "input_cost_per_token_batches": 1.25e-06, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1e-05, + "output_cost_per_token_batches": 5e-06, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "gpt-4o-audio-preview": { + "input_cost_per_audio_token": 0.0001, + "input_cost_per_token": 2.5e-06, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_audio_token": 0.0002, + "output_cost_per_token": 1e-05, + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "gpt-4o-audio-preview-2024-10-01": { + "input_cost_per_audio_token": 0.0001, + "input_cost_per_token": 2.5e-06, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_audio_token": 0.0002, + "output_cost_per_token": 1e-05, + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "gpt-4o-audio-preview-2024-12-17": { + "input_cost_per_audio_token": 4e-05, + "input_cost_per_token": 2.5e-06, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_audio_token": 8e-05, + "output_cost_per_token": 1e-05, + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "gpt-4o-audio-preview-2025-06-03": { + "input_cost_per_audio_token": 4e-05, + "input_cost_per_token": 2.5e-06, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_audio_token": 8e-05, + "output_cost_per_token": 1e-05, + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "gpt-4o-mini": { + "cache_read_input_token_cost": 7.5e-08, + "input_cost_per_token": 1.5e-07, + "input_cost_per_token_batches": 7.5e-08, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 6e-07, + "output_cost_per_token_batches": 3e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "gpt-4o-mini-2024-07-18": { + "cache_read_input_token_cost": 7.5e-08, + "input_cost_per_token": 1.5e-07, + "input_cost_per_token_batches": 7.5e-08, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 6e-07, + "output_cost_per_token_batches": 3e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.03, + "search_context_size_low": 0.025, + "search_context_size_medium": 0.0275 + }, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "gpt-4o-mini-audio-preview": { + "input_cost_per_audio_token": 1e-05, + "input_cost_per_token": 1.5e-07, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_audio_token": 2e-05, + "output_cost_per_token": 6e-07, + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "gpt-4o-mini-audio-preview-2024-12-17": { + "input_cost_per_audio_token": 1e-05, + "input_cost_per_token": 1.5e-07, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_audio_token": 2e-05, + "output_cost_per_token": 6e-07, + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "gpt-4o-mini-realtime-preview": { + "cache_creation_input_audio_token_cost": 3e-07, + "cache_read_input_token_cost": 3e-07, + "input_cost_per_audio_token": 1e-05, + "input_cost_per_token": 6e-07, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_audio_token": 2e-05, + "output_cost_per_token": 2.4e-06, + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "gpt-4o-mini-realtime-preview-2024-12-17": { + "cache_creation_input_audio_token_cost": 3e-07, + "cache_read_input_token_cost": 3e-07, + "input_cost_per_audio_token": 1e-05, + "input_cost_per_token": 6e-07, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_audio_token": 2e-05, + "output_cost_per_token": 2.4e-06, + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "gpt-4o-mini-search-preview": { + "cache_read_input_token_cost": 7.5e-08, + "input_cost_per_token": 1.5e-07, + "input_cost_per_token_batches": 7.5e-08, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 6e-07, + "output_cost_per_token_batches": 3e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.03, + "search_context_size_low": 0.025, + "search_context_size_medium": 0.0275 + }, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "gpt-4o-mini-search-preview-2025-03-11": { + "cache_read_input_token_cost": 7.5e-08, + "input_cost_per_token": 1.5e-07, + "input_cost_per_token_batches": 7.5e-08, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 6e-07, + "output_cost_per_token_batches": 3e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "gpt-4o-mini-transcribe": { + "input_cost_per_audio_token": 3e-06, + "input_cost_per_token": 1.25e-06, + "litellm_provider": "openai", + "max_input_tokens": 16000, + "max_output_tokens": 2000, + "mode": "audio_transcription", + "output_cost_per_token": 5e-06, + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "gpt-4o-mini-tts": { + "input_cost_per_token": 2.5e-06, + "litellm_provider": "openai", + "mode": "audio_speech", + "output_cost_per_audio_token": 1.2e-05, + "output_cost_per_second": 0.00025, + "output_cost_per_token": 1e-05, + "supported_endpoints": [ + "/v1/audio/speech" + ], + "supported_modalities": [ + "text", + "audio" + ], + "supported_output_modalities": [ + "audio" + ] + }, + "gpt-4o-realtime-preview": { + "cache_read_input_token_cost": 2.5e-06, + "input_cost_per_audio_token": 4e-05, + "input_cost_per_token": 5e-06, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_audio_token": 8e-05, + "output_cost_per_token": 2e-05, + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "gpt-4o-realtime-preview-2024-10-01": { + "cache_creation_input_audio_token_cost": 2e-05, + "cache_read_input_token_cost": 2.5e-06, + "input_cost_per_audio_token": 0.0001, + "input_cost_per_token": 5e-06, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_audio_token": 0.0002, + "output_cost_per_token": 2e-05, + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "gpt-4o-realtime-preview-2024-12-17": { + "cache_read_input_token_cost": 2.5e-06, + "input_cost_per_audio_token": 4e-05, + "input_cost_per_token": 5e-06, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_audio_token": 8e-05, + "output_cost_per_token": 2e-05, + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "gpt-4o-realtime-preview-2025-06-03": { + "cache_read_input_token_cost": 2.5e-06, + "input_cost_per_audio_token": 4e-05, + "input_cost_per_token": 5e-06, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_audio_token": 8e-05, + "output_cost_per_token": 2e-05, + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "gpt-4o-search-preview": { + "cache_read_input_token_cost": 1.25e-06, + "input_cost_per_token": 2.5e-06, + "input_cost_per_token_batches": 1.25e-06, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1e-05, + "output_cost_per_token_batches": 5e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.05, + "search_context_size_low": 0.03, + "search_context_size_medium": 0.035 + }, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "gpt-4o-search-preview-2025-03-11": { + "cache_read_input_token_cost": 1.25e-06, + "input_cost_per_token": 2.5e-06, + "input_cost_per_token_batches": 1.25e-06, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1e-05, + "output_cost_per_token_batches": 5e-06, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "gpt-4o-transcribe": { + "input_cost_per_audio_token": 6e-06, + "input_cost_per_token": 2.5e-06, + "litellm_provider": "openai", + "max_input_tokens": 16000, + "max_output_tokens": 2000, + "mode": "audio_transcription", + "output_cost_per_token": 1e-05, + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "gpt-5": { + "cache_read_input_token_cost": 1.25e-07, + "input_cost_per_token": 1.25e-06, + "litellm_provider": "openai", + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "gpt-5-2025-08-07": { + "cache_read_input_token_cost": 1.25e-07, + "input_cost_per_token": 1.25e-06, + "litellm_provider": "openai", + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "gpt-5-chat": { + "cache_read_input_token_cost": 1.25e-07, + "input_cost_per_token": 1.25e-06, + "litellm_provider": "openai", + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": false, + "supports_native_streaming": true, + "supports_parallel_function_calling": false, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": false, + "supports_vision": true + }, + "gpt-5-chat-latest": { + "cache_read_input_token_cost": 1.25e-07, + "input_cost_per_token": 1.25e-06, + "litellm_provider": "openai", + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": false, + "supports_native_streaming": true, + "supports_parallel_function_calling": false, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": false, + "supports_vision": true + }, + "gpt-5-mini": { + "cache_read_input_token_cost": 2.5e-08, + "input_cost_per_token": 2.5e-07, + "litellm_provider": "openai", + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2e-06, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "gpt-5-mini-2025-08-07": { + "cache_read_input_token_cost": 2.5e-08, + "input_cost_per_token": 2.5e-07, + "litellm_provider": "openai", + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2e-06, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "gpt-5-nano": { + "cache_read_input_token_cost": 5e-09, + "input_cost_per_token": 5e-08, + "litellm_provider": "openai", + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4e-07, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "gpt-5-nano-2025-08-07": { + "cache_read_input_token_cost": 5e-09, + "input_cost_per_token": 5e-08, + "litellm_provider": "openai", + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4e-07, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "gpt-image-1": { + "input_cost_per_pixel": 4.0054321e-08, + "litellm_provider": "openai", + "mode": "image_generation", + "output_cost_per_pixel": 0.0, + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "gpt-realtime": { + "cache_creation_input_audio_token_cost": 4e-07, + "cache_read_input_token_cost": 4e-07, + "input_cost_per_audio_token": 3.2e-05, + "input_cost_per_image": 5e-06, + "input_cost_per_token": 4e-06, + "litellm_provider": "openai", + "max_input_tokens": 32000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_audio_token": 6.4e-05, + "output_cost_per_token": 1.6e-05, + "supported_endpoints": [ + "/v1/realtime" + ], + "supported_modalities": [ + "text", + "image", + "audio" + ], + "supported_output_modalities": [ + "text", + "audio" + ], + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "gpt-realtime-2025-08-28": { + "cache_creation_input_audio_token_cost": 4e-07, + "cache_read_input_token_cost": 4e-07, + "input_cost_per_audio_token": 3.2e-05, + "input_cost_per_image": 5e-06, + "input_cost_per_token": 4e-06, + "litellm_provider": "openai", + "max_input_tokens": 32000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_audio_token": 6.4e-05, + "output_cost_per_token": 1.6e-05, + "supported_endpoints": [ + "/v1/realtime" + ], + "supported_modalities": [ + "text", + "image", + "audio" + ], + "supported_output_modalities": [ + "text", + "audio" + ], + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "gradient_ai/alibaba-qwen3-32b": { + "litellm_provider": "gradient_ai", + "max_tokens": 2048, + "mode": "chat", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supported_modalities": [ + "text" + ], "supports_tool_choice": false }, - "gradient_ai/anthropic-claude-3.5-sonnet": { - "input_cost_per_token": 3e-06, - "output_cost_per_token": 15e-06, + "gradient_ai/anthropic-claude-3-opus": { + "input_cost_per_token": 1.5e-05, "litellm_provider": "gradient_ai", - "mode": "chat", "max_tokens": 1024, - "supported_endpoints": ["/v1/chat/completions"], - "supported_modalities": ["text"], + "mode": "chat", + "output_cost_per_token": 7.5e-05, + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supported_modalities": [ + "text" + ], "supports_tool_choice": false }, "gradient_ai/anthropic-claude-3.5-haiku": { "input_cost_per_token": 8e-07, - "output_cost_per_token": 4e-06, "litellm_provider": "gradient_ai", - "mode": "chat", "max_tokens": 1024, - "supported_endpoints": ["/v1/chat/completions"], - "supported_modalities": ["text"], + "mode": "chat", + "output_cost_per_token": 4e-06, + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supported_modalities": [ + "text" + ], "supports_tool_choice": false }, - "gradient_ai/anthropic-claude-3-opus": { - "input_cost_per_token": 15e-06, - "output_cost_per_token": 75e-06, + "gradient_ai/anthropic-claude-3.5-sonnet": { + "input_cost_per_token": 3e-06, "litellm_provider": "gradient_ai", - "mode": "chat", "max_tokens": 1024, - "supported_endpoints": ["/v1/chat/completions"], - "supported_modalities": ["text"], + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supported_modalities": [ + "text" + ], + "supports_tool_choice": false + }, + "gradient_ai/anthropic-claude-3.7-sonnet": { + "input_cost_per_token": 3e-06, + "litellm_provider": "gradient_ai", + "max_tokens": 1024, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supported_modalities": [ + "text" + ], "supports_tool_choice": false }, "gradient_ai/deepseek-r1-distill-llama-70b": { - "input_cost_per_token": 99e-08, - "output_cost_per_token": 99e-08, + "input_cost_per_token": 9.9e-07, "litellm_provider": "gradient_ai", - "mode": "chat", "max_tokens": 8000, - "supported_endpoints": ["/v1/chat/completions"], - "supported_modalities": ["text"], - "supports_tool_choice": false - }, - "gradient_ai/llama3.3-70b-instruct": { - "input_cost_per_token": 65e-08, - "output_cost_per_token": 65e-08, - "litellm_provider": "gradient_ai", "mode": "chat", - "max_tokens": 2048, - "supported_endpoints": ["/v1/chat/completions"], - "supported_modalities": ["text"], + "output_cost_per_token": 9.9e-07, + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supported_modalities": [ + "text" + ], "supports_tool_choice": false }, "gradient_ai/llama3-8b-instruct": { "input_cost_per_token": 2e-07, - "output_cost_per_token": 2e-07, "litellm_provider": "gradient_ai", - "mode": "chat", "max_tokens": 512, - "supported_endpoints": ["/v1/chat/completions"], - "supported_modalities": ["text"], + "mode": "chat", + "output_cost_per_token": 2e-07, + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supported_modalities": [ + "text" + ], + "supports_tool_choice": false + }, + "gradient_ai/llama3.3-70b-instruct": { + "input_cost_per_token": 6.5e-07, + "litellm_provider": "gradient_ai", + "max_tokens": 2048, + "mode": "chat", + "output_cost_per_token": 6.5e-07, + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supported_modalities": [ + "text" + ], "supports_tool_choice": false }, "gradient_ai/mistral-nemo-instruct-2407": { "input_cost_per_token": 3e-07, - "output_cost_per_token": 3e-07, "litellm_provider": "gradient_ai", - "mode": "chat", "max_tokens": 512, - "supported_endpoints": ["/v1/chat/completions"], - "supported_modalities": ["text"], - "supports_tool_choice": false - }, - "gradient_ai/openai-o3": { - "input_cost_per_token": 2e-06, - "output_cost_per_token": 8e-06, - "litellm_provider": "gradient_ai", "mode": "chat", - "max_tokens": 100000, - "supported_endpoints": ["/v1/chat/completions"], - "supported_modalities": ["text"], - "supports_tool_choice": false - }, - "gradient_ai/openai-o3-mini": { - "input_cost_per_token": 11e-07, - "output_cost_per_token": 44e-07, - "litellm_provider": "gradient_ai", - "mode": "chat", - "max_tokens": 100000, - "supported_endpoints": ["/v1/chat/completions"], - "supported_modalities": ["text"], + "output_cost_per_token": 3e-07, + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supported_modalities": [ + "text" + ], "supports_tool_choice": false }, "gradient_ai/openai-gpt-4o": { "litellm_provider": "gradient_ai", - "mode": "chat", "max_tokens": 16384, - "supported_endpoints": ["/v1/chat/completions"], - "supported_modalities": ["text"], + "mode": "chat", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supported_modalities": [ + "text" + ], "supports_tool_choice": false }, "gradient_ai/openai-gpt-4o-mini": { "litellm_provider": "gradient_ai", - "mode": "chat", "max_tokens": 16384, - "supported_endpoints": ["/v1/chat/completions"], - "supported_modalities": ["text"], + "mode": "chat", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supported_modalities": [ + "text" + ], "supports_tool_choice": false }, - "gradient_ai/alibaba-qwen3-32b": { + "gradient_ai/openai-o3": { + "input_cost_per_token": 2e-06, "litellm_provider": "gradient_ai", + "max_tokens": 100000, "mode": "chat", - "max_tokens": 2048, - "supported_endpoints": ["/v1/chat/completions"], - "supported_modalities": ["text"], + "output_cost_per_token": 8e-06, + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supported_modalities": [ + "text" + ], "supports_tool_choice": false }, - "nscale/meta-llama/Llama-4-Scout-17B-16E-Instruct": { - "input_cost_per_token": 9e-08, - "output_cost_per_token": 2.9e-07, - "litellm_provider": "nscale", + "gradient_ai/openai-o3-mini": { + "input_cost_per_token": 1.1e-06, + "litellm_provider": "gradient_ai", + "max_tokens": 100000, "mode": "chat", - "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" + "output_cost_per_token": 4.4e-06, + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supported_modalities": [ + "text" + ], + "supports_tool_choice": false }, - "nscale/Qwen/Qwen2.5-Coder-3B-Instruct": { - "input_cost_per_token": 1e-08, - "output_cost_per_token": 3e-08, - "litellm_provider": "nscale", + "groq/deepseek-r1-distill-llama-70b": { + "input_cost_per_token": 7.5e-07, + "litellm_provider": "groq", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" + "output_cost_per_token": 9.9e-07, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true }, - "nscale/Qwen/Qwen2.5-Coder-7B-Instruct": { - "input_cost_per_token": 1e-08, - "output_cost_per_token": 3e-08, - "litellm_provider": "nscale", - "mode": "chat", - "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" + "groq/distil-whisper-large-v3-en": { + "input_cost_per_second": 5.56e-06, + "litellm_provider": "groq", + "mode": "audio_transcription", + "output_cost_per_second": 0.0 }, - "nscale/Qwen/Qwen2.5-Coder-32B-Instruct": { - "input_cost_per_token": 6e-08, - "output_cost_per_token": 2e-07, - "litellm_provider": "nscale", - "mode": "chat", - "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" - }, - "nscale/Qwen/QwQ-32B": { - "input_cost_per_token": 1.8e-07, - "output_cost_per_token": 2e-07, - "litellm_provider": "nscale", - "mode": "chat", - "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" - }, - "nscale/deepseek-ai/DeepSeek-R1-Distill-Llama-70B": { - "input_cost_per_token": 3.75e-07, - "output_cost_per_token": 3.75e-07, - "litellm_provider": "nscale", - "mode": "chat", - "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models", - "metadata": { - "notes": "Pricing listed as $0.75/1M tokens total. Assumed 50/50 split for input/output." - } - }, - "nscale/deepseek-ai/DeepSeek-R1-Distill-Llama-8B": { - "input_cost_per_token": 2.5e-08, - "output_cost_per_token": 2.5e-08, - "litellm_provider": "nscale", - "mode": "chat", - "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models", - "metadata": { - "notes": "Pricing listed as $0.05/1M tokens total. Assumed 50/50 split for input/output." - } - }, - "nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B": { - "input_cost_per_token": 9e-08, - "output_cost_per_token": 9e-08, - "litellm_provider": "nscale", - "mode": "chat", - "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models", - "metadata": { - "notes": "Pricing listed as $0.18/1M tokens total. Assumed 50/50 split for input/output." - } - }, - "nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B": { - "input_cost_per_token": 2e-07, - "output_cost_per_token": 2e-07, - "litellm_provider": "nscale", - "mode": "chat", - "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models", - "metadata": { - "notes": "Pricing listed as $0.40/1M tokens total. Assumed 50/50 split for input/output." - } - }, - "nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B": { + "groq/gemma-7b-it": { + "deprecation_date": "2024-12-18", "input_cost_per_token": 7e-08, + "litellm_provider": "groq", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", "output_cost_per_token": 7e-08, - "litellm_provider": "nscale", - "mode": "chat", - "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models", - "metadata": { - "notes": "Pricing listed as $0.14/1M tokens total. Assumed 50/50 split for input/output." - } - }, - "nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B": { - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 1.5e-07, - "litellm_provider": "nscale", - "mode": "chat", - "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models", - "metadata": { - "notes": "Pricing listed as $0.30/1M tokens total. Assumed 50/50 split for input/output." - } - }, - "nscale/mistralai/mixtral-8x22b-instruct-v0.1": { - "input_cost_per_token": 6e-07, - "output_cost_per_token": 6e-07, - "litellm_provider": "nscale", - "mode": "chat", - "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models", - "metadata": { - "notes": "Pricing listed as $1.20/1M tokens total. Assumed 50/50 split for input/output." - } - }, - "nscale/meta-llama/Llama-3.1-8B-Instruct": { - "input_cost_per_token": 3e-08, - "output_cost_per_token": 3e-08, - "litellm_provider": "nscale", - "mode": "chat", - "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models", - "metadata": { - "notes": "Pricing listed as $0.06/1M tokens total. Assumed 50/50 split for input/output." - } - }, - "nscale/meta-llama/Llama-3.3-70B-Instruct": { - "input_cost_per_token": 2e-07, - "output_cost_per_token": 2e-07, - "litellm_provider": "nscale", - "mode": "chat", - "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models", - "metadata": { - "notes": "Pricing listed as $0.40/1M tokens total. Assumed 50/50 split for input/output." - } - }, - "nscale/black-forest-labs/FLUX.1-schnell": { - "mode": "image_generation", - "input_cost_per_pixel": 1.3e-09, - "output_cost_per_pixel": 0.0, - "litellm_provider": "nscale", - "supported_endpoints": [ - "/v1/images/generations" - ], - "source": "https://docs.nscale.com/docs/inference/serverless-models/current#image-models" - }, - "nscale/stabilityai/stable-diffusion-xl-base-1.0": { - "mode": "image_generation", - "input_cost_per_pixel": 3e-09, - "output_cost_per_pixel": 0.0, - "litellm_provider": "nscale", - "supported_endpoints": [ - "/v1/images/generations" - ], - "source": "https://docs.nscale.com/docs/inference/serverless-models/current#image-models" - }, - "featherless_ai/featherless-ai/Qwerky-72B": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 4096, - "litellm_provider": "featherless_ai", - "mode": "chat" - }, - "featherless_ai/featherless-ai/Qwerky-QwQ-32B": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 4096, - "litellm_provider": "featherless_ai", - "mode": "chat" - }, - "deepgram/nova-3": { - "mode": "audio_transcription", - "input_cost_per_second": 7.167e-05, - "output_cost_per_second": 0.0, - "litellm_provider": "deepgram", - "supported_endpoints": [ - "/v1/audio/transcriptions" - ], - "source": "https://deepgram.com/pricing", - "metadata": { - "original_pricing_per_minute": 0.0043, - "calculation": "$0.0043/60 seconds = $0.00007167 per second" - } - }, - "deepgram/nova-3-general": { - "mode": "audio_transcription", - "input_cost_per_second": 7.167e-05, - "output_cost_per_second": 0.0, - "litellm_provider": "deepgram", - "supported_endpoints": [ - "/v1/audio/transcriptions" - ], - "source": "https://deepgram.com/pricing", - "metadata": { - "original_pricing_per_minute": 0.0043, - "calculation": "$0.0043/60 seconds = $0.00007167 per second" - } - }, - "deepgram/nova-3-medical": { - "mode": "audio_transcription", - "input_cost_per_second": 8.667e-05, - "output_cost_per_second": 0.0, - "litellm_provider": "deepgram", - "supported_endpoints": [ - "/v1/audio/transcriptions" - ], - "source": "https://deepgram.com/pricing", - "metadata": { - "original_pricing_per_minute": 0.0052, - "calculation": "$0.0052/60 seconds = $0.00008667 per second (multilingual)" - } - }, - "deepgram/nova-2": { - "mode": "audio_transcription", - "input_cost_per_second": 7.167e-05, - "output_cost_per_second": 0.0, - "litellm_provider": "deepgram", - "supported_endpoints": [ - "/v1/audio/transcriptions" - ], - "source": "https://deepgram.com/pricing", - "metadata": { - "original_pricing_per_minute": 0.0043, - "calculation": "$0.0043/60 seconds = $0.00007167 per second" - } - }, - "deepgram/nova-2-general": { - "mode": "audio_transcription", - "input_cost_per_second": 7.167e-05, - "output_cost_per_second": 0.0, - "litellm_provider": "deepgram", - "supported_endpoints": [ - "/v1/audio/transcriptions" - ], - "source": "https://deepgram.com/pricing", - "metadata": { - "original_pricing_per_minute": 0.0043, - "calculation": "$0.0043/60 seconds = $0.00007167 per second" - } - }, - "deepgram/nova-2-meeting": { - "mode": "audio_transcription", - "input_cost_per_second": 7.167e-05, - "output_cost_per_second": 0.0, - "litellm_provider": "deepgram", - "supported_endpoints": [ - "/v1/audio/transcriptions" - ], - "source": "https://deepgram.com/pricing", - "metadata": { - "original_pricing_per_minute": 0.0043, - "calculation": "$0.0043/60 seconds = $0.00007167 per second" - } - }, - "deepgram/nova-2-phonecall": { - "mode": "audio_transcription", - "input_cost_per_second": 7.167e-05, - "output_cost_per_second": 0.0, - "litellm_provider": "deepgram", - "supported_endpoints": [ - "/v1/audio/transcriptions" - ], - "source": "https://deepgram.com/pricing", - "metadata": { - "original_pricing_per_minute": 0.0043, - "calculation": "$0.0043/60 seconds = $0.00007167 per second" - } - }, - "deepgram/nova-2-voicemail": { - "mode": "audio_transcription", - "input_cost_per_second": 7.167e-05, - "output_cost_per_second": 0.0, - "litellm_provider": "deepgram", - "supported_endpoints": [ - "/v1/audio/transcriptions" - ], - "source": "https://deepgram.com/pricing", - "metadata": { - "original_pricing_per_minute": 0.0043, - "calculation": "$0.0043/60 seconds = $0.00007167 per second" - } - }, - "deepgram/nova-2-finance": { - "mode": "audio_transcription", - "input_cost_per_second": 7.167e-05, - "output_cost_per_second": 0.0, - "litellm_provider": "deepgram", - "supported_endpoints": [ - "/v1/audio/transcriptions" - ], - "source": "https://deepgram.com/pricing", - "metadata": { - "original_pricing_per_minute": 0.0043, - "calculation": "$0.0043/60 seconds = $0.00007167 per second" - } - }, - "deepgram/nova-2-conversationalai": { - "mode": "audio_transcription", - "input_cost_per_second": 7.167e-05, - "output_cost_per_second": 0.0, - "litellm_provider": "deepgram", - "supported_endpoints": [ - "/v1/audio/transcriptions" - ], - "source": "https://deepgram.com/pricing", - "metadata": { - "original_pricing_per_minute": 0.0043, - "calculation": "$0.0043/60 seconds = $0.00007167 per second" - } - }, - "deepgram/nova-2-video": { - "mode": "audio_transcription", - "input_cost_per_second": 7.167e-05, - "output_cost_per_second": 0.0, - "litellm_provider": "deepgram", - "supported_endpoints": [ - "/v1/audio/transcriptions" - ], - "source": "https://deepgram.com/pricing", - "metadata": { - "original_pricing_per_minute": 0.0043, - "calculation": "$0.0043/60 seconds = $0.00007167 per second" - } - }, - "deepgram/nova-2-drivethru": { - "mode": "audio_transcription", - "input_cost_per_second": 7.167e-05, - "output_cost_per_second": 0.0, - "litellm_provider": "deepgram", - "supported_endpoints": [ - "/v1/audio/transcriptions" - ], - "source": "https://deepgram.com/pricing", - "metadata": { - "original_pricing_per_minute": 0.0043, - "calculation": "$0.0043/60 seconds = $0.00007167 per second" - } - }, - "deepgram/nova-2-automotive": { - "mode": "audio_transcription", - "input_cost_per_second": 7.167e-05, - "output_cost_per_second": 0.0, - "litellm_provider": "deepgram", - "supported_endpoints": [ - "/v1/audio/transcriptions" - ], - "source": "https://deepgram.com/pricing", - "metadata": { - "original_pricing_per_minute": 0.0043, - "calculation": "$0.0043/60 seconds = $0.00007167 per second" - } - }, - "deepgram/nova-2-atc": { - "mode": "audio_transcription", - "input_cost_per_second": 7.167e-05, - "output_cost_per_second": 0.0, - "litellm_provider": "deepgram", - "supported_endpoints": [ - "/v1/audio/transcriptions" - ], - "source": "https://deepgram.com/pricing", - "metadata": { - "original_pricing_per_minute": 0.0043, - "calculation": "$0.0043/60 seconds = $0.00007167 per second" - } - }, - "deepgram/nova": { - "mode": "audio_transcription", - "input_cost_per_second": 7.167e-05, - "output_cost_per_second": 0.0, - "litellm_provider": "deepgram", - "supported_endpoints": [ - "/v1/audio/transcriptions" - ], - "source": "https://deepgram.com/pricing", - "metadata": { - "original_pricing_per_minute": 0.0043, - "calculation": "$0.0043/60 seconds = $0.00007167 per second" - } - }, - "deepgram/nova-general": { - "mode": "audio_transcription", - "input_cost_per_second": 7.167e-05, - "output_cost_per_second": 0.0, - "litellm_provider": "deepgram", - "supported_endpoints": [ - "/v1/audio/transcriptions" - ], - "source": "https://deepgram.com/pricing", - "metadata": { - "original_pricing_per_minute": 0.0043, - "calculation": "$0.0043/60 seconds = $0.00007167 per second" - } - }, - "deepgram/nova-phonecall": { - "mode": "audio_transcription", - "input_cost_per_second": 7.167e-05, - "output_cost_per_second": 0.0, - "litellm_provider": "deepgram", - "supported_endpoints": [ - "/v1/audio/transcriptions" - ], - "source": "https://deepgram.com/pricing", - "metadata": { - "original_pricing_per_minute": 0.0043, - "calculation": "$0.0043/60 seconds = $0.00007167 per second" - } - }, - "deepgram/enhanced": { - "mode": "audio_transcription", - "input_cost_per_second": 0.00024167, - "output_cost_per_second": 0.0, - "litellm_provider": "deepgram", - "supported_endpoints": [ - "/v1/audio/transcriptions" - ], - "source": "https://deepgram.com/pricing", - "metadata": { - "original_pricing_per_minute": 0.0145, - "calculation": "$0.0145/60 seconds = $0.00024167 per second" - } - }, - "deepgram/enhanced-general": { - "mode": "audio_transcription", - "input_cost_per_second": 0.00024167, - "output_cost_per_second": 0.0, - "litellm_provider": "deepgram", - "supported_endpoints": [ - "/v1/audio/transcriptions" - ], - "source": "https://deepgram.com/pricing", - "metadata": { - "original_pricing_per_minute": 0.0145, - "calculation": "$0.0145/60 seconds = $0.00024167 per second" - } - }, - "deepgram/enhanced-meeting": { - "mode": "audio_transcription", - "input_cost_per_second": 0.00024167, - "output_cost_per_second": 0.0, - "litellm_provider": "deepgram", - "supported_endpoints": [ - "/v1/audio/transcriptions" - ], - "source": "https://deepgram.com/pricing", - "metadata": { - "original_pricing_per_minute": 0.0145, - "calculation": "$0.0145/60 seconds = $0.00024167 per second" - } - }, - "deepgram/enhanced-phonecall": { - "mode": "audio_transcription", - "input_cost_per_second": 0.00024167, - "output_cost_per_second": 0.0, - "litellm_provider": "deepgram", - "supported_endpoints": [ - "/v1/audio/transcriptions" - ], - "source": "https://deepgram.com/pricing", - "metadata": { - "original_pricing_per_minute": 0.0145, - "calculation": "$0.0145/60 seconds = $0.00024167 per second" - } - }, - "deepgram/enhanced-finance": { - "mode": "audio_transcription", - "input_cost_per_second": 0.00024167, - "output_cost_per_second": 0.0, - "litellm_provider": "deepgram", - "supported_endpoints": [ - "/v1/audio/transcriptions" - ], - "source": "https://deepgram.com/pricing", - "metadata": { - "original_pricing_per_minute": 0.0145, - "calculation": "$0.0145/60 seconds = $0.00024167 per second" - } - }, - "deepgram/base": { - "mode": "audio_transcription", - "input_cost_per_second": 0.00020833, - "output_cost_per_second": 0.0, - "litellm_provider": "deepgram", - "supported_endpoints": [ - "/v1/audio/transcriptions" - ], - "source": "https://deepgram.com/pricing", - "metadata": { - "original_pricing_per_minute": 0.0125, - "calculation": "$0.0125/60 seconds = $0.00020833 per second" - } - }, - "deepgram/base-general": { - "mode": "audio_transcription", - "input_cost_per_second": 0.00020833, - "output_cost_per_second": 0.0, - "litellm_provider": "deepgram", - "supported_endpoints": [ - "/v1/audio/transcriptions" - ], - "source": "https://deepgram.com/pricing", - "metadata": { - "original_pricing_per_minute": 0.0125, - "calculation": "$0.0125/60 seconds = $0.00020833 per second" - } - }, - "deepgram/base-meeting": { - "mode": "audio_transcription", - "input_cost_per_second": 0.00020833, - "output_cost_per_second": 0.0, - "litellm_provider": "deepgram", - "supported_endpoints": [ - "/v1/audio/transcriptions" - ], - "source": "https://deepgram.com/pricing", - "metadata": { - "original_pricing_per_minute": 0.0125, - "calculation": "$0.0125/60 seconds = $0.00020833 per second" - } - }, - "deepgram/base-phonecall": { - "mode": "audio_transcription", - "input_cost_per_second": 0.00020833, - "output_cost_per_second": 0.0, - "litellm_provider": "deepgram", - "supported_endpoints": [ - "/v1/audio/transcriptions" - ], - "source": "https://deepgram.com/pricing", - "metadata": { - "original_pricing_per_minute": 0.0125, - "calculation": "$0.0125/60 seconds = $0.00020833 per second" - } - }, - "deepgram/base-voicemail": { - "mode": "audio_transcription", - "input_cost_per_second": 0.00020833, - "output_cost_per_second": 0.0, - "litellm_provider": "deepgram", - "supported_endpoints": [ - "/v1/audio/transcriptions" - ], - "source": "https://deepgram.com/pricing", - "metadata": { - "original_pricing_per_minute": 0.0125, - "calculation": "$0.0125/60 seconds = $0.00020833 per second" - } - }, - "deepgram/base-finance": { - "mode": "audio_transcription", - "input_cost_per_second": 0.00020833, - "output_cost_per_second": 0.0, - "litellm_provider": "deepgram", - "supported_endpoints": [ - "/v1/audio/transcriptions" - ], - "source": "https://deepgram.com/pricing", - "metadata": { - "original_pricing_per_minute": 0.0125, - "calculation": "$0.0125/60 seconds = $0.00020833 per second" - } - }, - "deepgram/base-conversationalai": { - "mode": "audio_transcription", - "input_cost_per_second": 0.00020833, - "output_cost_per_second": 0.0, - "litellm_provider": "deepgram", - "supported_endpoints": [ - "/v1/audio/transcriptions" - ], - "source": "https://deepgram.com/pricing", - "metadata": { - "original_pricing_per_minute": 0.0125, - "calculation": "$0.0125/60 seconds = $0.00020833 per second" - } - }, - "deepgram/base-video": { - "mode": "audio_transcription", - "input_cost_per_second": 0.00020833, - "output_cost_per_second": 0.0, - "litellm_provider": "deepgram", - "supported_endpoints": [ - "/v1/audio/transcriptions" - ], - "source": "https://deepgram.com/pricing", - "metadata": { - "original_pricing_per_minute": 0.0125, - "calculation": "$0.0125/60 seconds = $0.00020833 per second" - } - }, - "deepgram/whisper": { - "mode": "audio_transcription", - "input_cost_per_second": 0.0001, - "output_cost_per_second": 0.0, - "litellm_provider": "deepgram", - "supported_endpoints": [ - "/v1/audio/transcriptions" - ], - "source": "https://deepgram.com/pricing", - "metadata": { - "notes": "Deepgram's hosted OpenAI Whisper models - pricing may differ from native Deepgram models" - } - }, - "deepgram/whisper-tiny": { - "mode": "audio_transcription", - "input_cost_per_second": 0.0001, - "output_cost_per_second": 0.0, - "litellm_provider": "deepgram", - "supported_endpoints": [ - "/v1/audio/transcriptions" - ], - "source": "https://deepgram.com/pricing", - "metadata": { - "notes": "Deepgram's hosted OpenAI Whisper models - pricing may differ from native Deepgram models" - } - }, - "deepgram/whisper-base": { - "mode": "audio_transcription", - "input_cost_per_second": 0.0001, - "output_cost_per_second": 0.0, - "litellm_provider": "deepgram", - "supported_endpoints": [ - "/v1/audio/transcriptions" - ], - "source": "https://deepgram.com/pricing", - "metadata": { - "notes": "Deepgram's hosted OpenAI Whisper models - pricing may differ from native Deepgram models" - } - }, - "deepgram/whisper-small": { - "mode": "audio_transcription", - "input_cost_per_second": 0.0001, - "output_cost_per_second": 0.0, - "litellm_provider": "deepgram", - "supported_endpoints": [ - "/v1/audio/transcriptions" - ], - "source": "https://deepgram.com/pricing", - "metadata": { - "notes": "Deepgram's hosted OpenAI Whisper models - pricing may differ from native Deepgram models" - } - }, - "deepgram/whisper-medium": { - "mode": "audio_transcription", - "input_cost_per_second": 0.0001, - "output_cost_per_second": 0.0, - "litellm_provider": "deepgram", - "supported_endpoints": [ - "/v1/audio/transcriptions" - ], - "source": "https://deepgram.com/pricing", - "metadata": { - "notes": "Deepgram's hosted OpenAI Whisper models - pricing may differ from native Deepgram models" - } - }, - "deepgram/whisper-large": { - "mode": "audio_transcription", - "input_cost_per_second": 0.0001, - "output_cost_per_second": 0.0, - "litellm_provider": "deepgram", - "supported_endpoints": [ - "/v1/audio/transcriptions" - ], - "source": "https://deepgram.com/pricing", - "metadata": { - "notes": "Deepgram's hosted OpenAI Whisper models - pricing may differ from native Deepgram models" - } - }, - "elevenlabs/scribe_v1": { - "mode": "audio_transcription", - "input_cost_per_second": 6.11e-05, - "output_cost_per_second": 0.0, - "litellm_provider": "elevenlabs", - "supported_endpoints": [ - "/v1/audio/transcriptions" - ], - "source": "https://elevenlabs.io/pricing", - "metadata": { - "original_pricing_per_hour": 0.22, - "calculation": "$0.22/hour = $0.00366/minute = $0.0000611 per second (enterprise pricing)", - "notes": "ElevenLabs Scribe v1 - state-of-the-art speech recognition model with 99 language support" - } - }, - "elevenlabs/scribe_v1_experimental": { - "mode": "audio_transcription", - "input_cost_per_second": 6.11e-05, - "output_cost_per_second": 0.0, - "litellm_provider": "elevenlabs", - "supported_endpoints": [ - "/v1/audio/transcriptions" - ], - "source": "https://elevenlabs.io/pricing", - "metadata": { - "original_pricing_per_hour": 0.22, - "calculation": "$0.22/hour = $0.00366/minute = $0.0000611 per second (enterprise pricing)", - "notes": "ElevenLabs Scribe v1 experimental - enhanced version of the main Scribe model" - } - }, - "bedrock/us-gov-east-1/amazon.titan-embed-text-v1": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "output_vector_size": 1536, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 0.0, - "litellm_provider": "bedrock", - "mode": "embedding" - }, - "bedrock/us-gov-east-1/amazon.titan-embed-text-v2:0": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "output_vector_size": 1024, - "input_cost_per_token": 2e-07, - "output_cost_per_token": 0.0, - "litellm_provider": "bedrock", - "mode": "embedding" - }, - "bedrock/us-gov-east-1/amazon.titan-text-express-v1": { - "max_tokens": 8000, - "max_input_tokens": 42000, - "max_output_tokens": 8000, - "input_cost_per_token": 1.3e-06, - "output_cost_per_token": 1.7e-06, - "litellm_provider": "bedrock", - "mode": "chat" - }, - "bedrock/us-gov-east-1/amazon.titan-text-lite-v1": { - "max_tokens": 4000, - "max_input_tokens": 42000, - "max_output_tokens": 4000, - "input_cost_per_token": 3e-07, - "output_cost_per_token": 4e-07, - "litellm_provider": "bedrock", - "mode": "chat" - }, - "bedrock/us-gov-east-1/amazon.titan-text-premier-v1:0": { - "max_tokens": 32000, - "max_input_tokens": 42000, - "max_output_tokens": 32000, - "input_cost_per_token": 5e-07, - "output_cost_per_token": 1.5e-06, - "litellm_provider": "bedrock", - "mode": "chat" - }, - "bedrock/us-gov-east-1/anthropic.claude-3-5-sonnet-20240620-v1:0": { - "max_tokens": 8192, - "max_input_tokens": 200000, - "max_output_tokens": 8192, - "input_cost_per_token": 3.6e-06, - "output_cost_per_token": 1.8e-05, - "litellm_provider": "bedrock", - "mode": "chat", "supports_function_calling": true, "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, "supports_tool_choice": true }, - "bedrock/us-gov-east-1/anthropic.claude-3-haiku-20240307-v1:0": { - "max_tokens": 4096, - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "input_cost_per_token": 3e-07, - "output_cost_per_token": 1.5e-06, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_tool_choice": true - }, - "bedrock/us-gov-east-1/meta.llama3-70b-instruct-v1:0": { - "max_tokens": 2048, - "max_input_tokens": 8000, - "max_output_tokens": 2048, - "input_cost_per_token": 2.65e-06, - "output_cost_per_token": 3.5e-06, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_pdf_input": true - }, - "bedrock/us-gov-east-1/meta.llama3-8b-instruct-v1:0": { - "max_tokens": 2048, - "max_input_tokens": 8000, - "max_output_tokens": 2048, - "input_cost_per_token": 3e-07, - "output_cost_per_token": 2.65e-06, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_pdf_input": true - }, - "bedrock/us-gov-west-1/amazon.titan-embed-text-v1": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "output_vector_size": 1536, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 0.0, - "litellm_provider": "bedrock", - "mode": "embedding" - }, - "bedrock/us-gov-west-1/amazon.titan-embed-text-v2:0": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "output_vector_size": 1024, + "groq/gemma2-9b-it": { "input_cost_per_token": 2e-07, - "output_cost_per_token": 0.0, - "litellm_provider": "bedrock", - "mode": "embedding" - }, - "bedrock/us-gov-west-1/amazon.titan-text-express-v1": { - "max_tokens": 8000, - "max_input_tokens": 42000, - "max_output_tokens": 8000, - "input_cost_per_token": 1.3e-06, - "output_cost_per_token": 1.7e-06, - "litellm_provider": "bedrock", - "mode": "chat" - }, - "bedrock/us-gov-west-1/amazon.titan-text-lite-v1": { - "max_tokens": 4000, - "max_input_tokens": 42000, - "max_output_tokens": 4000, - "input_cost_per_token": 3e-07, - "output_cost_per_token": 4e-07, - "litellm_provider": "bedrock", - "mode": "chat" - }, - "bedrock/us-gov-west-1/amazon.titan-text-premier-v1:0": { - "max_tokens": 32000, - "max_input_tokens": 42000, - "max_output_tokens": 32000, - "input_cost_per_token": 5e-07, - "output_cost_per_token": 1.5e-06, - "litellm_provider": "bedrock", - "mode": "chat" - }, - "bedrock/us-gov-west-1/anthropic.claude-3-5-sonnet-20240620-v1:0": { + "litellm_provider": "groq", + "max_input_tokens": 8192, + "max_output_tokens": 8192, "max_tokens": 8192, - "max_input_tokens": 200000, - "max_output_tokens": 8192, - "input_cost_per_token": 3.6e-06, - "output_cost_per_token": 1.8e-05, - "litellm_provider": "bedrock", "mode": "chat", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_tool_choice": true - }, - "bedrock/us-gov-west-1/anthropic.claude-3-haiku-20240307-v1:0": { - "max_tokens": 4096, - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "input_cost_per_token": 3e-07, - "output_cost_per_token": 1.5e-06, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_tool_choice": true - }, - "bedrock/us-gov-west-1/meta.llama3-70b-instruct-v1:0": { - "max_tokens": 2048, - "max_input_tokens": 8000, - "max_output_tokens": 2048, - "input_cost_per_token": 2.65e-06, - "output_cost_per_token": 3.5e-06, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_pdf_input": true - }, - "bedrock/us-gov-west-1/meta.llama3-8b-instruct-v1:0": { - "max_tokens": 2048, - "max_input_tokens": 8000, - "max_output_tokens": 2048, - "input_cost_per_token": 3e-07, - "output_cost_per_token": 2.65e-06, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_pdf_input": true - }, - "bedrock/us-gov-east-1/amazon.nova-pro-v1:0": { - "max_tokens": 10000, - "max_input_tokens": 300000, - "max_output_tokens": 10000, - "input_cost_per_token": 9.6e-07, - "output_cost_per_token": 3.84e-06, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_response_schema": true - }, - "bedrock/us-gov-west-1/amazon.nova-pro-v1:0": { - "max_tokens": 10000, - "max_input_tokens": 300000, - "max_output_tokens": 10000, - "input_cost_per_token": 9.6e-07, - "output_cost_per_token": 3.84e-06, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_response_schema": true - }, - "dashscope/qwen-max": { - "max_tokens": 32768, - "max_input_tokens": 30720, - "max_output_tokens": 8192, - "input_cost_per_token": 1.6e-06, - "output_cost_per_token": 6.4e-06, - "litellm_provider": "dashscope", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "mode": "chat", - "source": "https://www.alibabacloud.com/help/en/model-studio/models" - }, - "dashscope/qwen-plus-latest": { - "max_tokens": 1000000, - "max_input_tokens": 997952, - "max_output_tokens": 32768, - "litellm_provider": "dashscope", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "mode": "chat", - "tiered_pricing": [ - {"range": [0, 256e3], "input_cost_per_token": 4e-07, "output_cost_per_token": 1.2e-06, "output_cost_per_reasoning_token": 4e-06}, - {"range": [256e3, 1e6], "input_cost_per_token": 1.2e-06, "output_cost_per_token": 3.6e-06, "output_cost_per_reasoning_token": 1.2e-05} - ], - "source": "https://www.alibabacloud.com/help/en/model-studio/models" - }, - "dashscope/qwen-turbo-latest": { - "max_tokens": 1000000, - "max_input_tokens": 1000000, - "max_output_tokens": 16384, - "input_cost_per_token": 5e-08, "output_cost_per_token": 2e-07, - "output_cost_per_reasoning_token": 5e-07, - "litellm_provider": "dashscope", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "mode": "chat", - "source": "https://www.alibabacloud.com/help/en/model-studio/models" - }, - "dashscope/qwen3-30b-a3b": { - "max_tokens": 131072, - "max_input_tokens": 129024, - "max_output_tokens": 16384, - "litellm_provider": "dashscope", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "mode": "chat", - "source": "https://www.alibabacloud.com/help/en/model-studio/models" - }, - "dashscope/qwen3-max-preview": { - "max_tokens": 262144, - "max_input_tokens": 258048, - "max_output_tokens": 65536, - "litellm_provider": "dashscope", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "mode": "chat", - "tiered_pricing": [ - {"range": [0, 32e3], "input_cost_per_token": 1.2e-06, "output_cost_per_token": 6e-06}, - {"range": [32e3, 128e3], "input_cost_per_token": 2.4e-06, "output_cost_per_token": 1.2e-05}, - {"range": [128e3, 252e3], "input_cost_per_token": 3.0e-06, "output_cost_per_token": 1.5e-05} - ], - "source": "https://www.alibabacloud.com/help/en/model-studio/models" - }, - "dashscope/qwen-plus": { - "max_tokens": 131072, - "max_input_tokens": 129024, - "max_output_tokens": 16384, - "input_cost_per_token": 4e-07, - "output_cost_per_token": 1.2e-06, - "litellm_provider": "dashscope", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "mode": "chat", - "source": "https://www.alibabacloud.com/help/en/model-studio/models" - }, - "dashscope/qwen-flash": { - "max_tokens": 1000000, - "max_input_tokens": 997952, - "max_output_tokens": 32768, - "litellm_provider": "dashscope", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "mode": "chat", - "tiered_pricing": [ - {"range": [0, 256e3], "input_cost_per_token": 5e-08, "output_cost_per_token": 4e-07}, - {"range": [256e3, 1e6], "input_cost_per_token": 2.5e-07, "output_cost_per_token": 2e-06} - ], - "source": "https://www.alibabacloud.com/help/en/model-studio/models" - }, - "dashscope/qwen-coder": { - "max_tokens": 1000000, - "max_input_tokens": 1000000, - "max_output_tokens": 16384, - "input_cost_per_token": 3e-07, - "output_cost_per_token": 1.5e-06, - "litellm_provider": "dashscope", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "mode": "chat", - "source": "https://www.alibabacloud.com/help/en/model-studio/models" - }, - "dashscope/qwen3-coder-plus": { - "max_tokens": 1000000, - "max_input_tokens": 997952, - "max_output_tokens": 65536, - "litellm_provider": "dashscope", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "mode": "chat", - "tiered_pricing": [ - {"range": [0, 32e3], "input_cost_per_token": 1e-06, "output_cost_per_token": 5e-06, "cache_read_input_token_cost": 1e-07}, - {"range": [32e3, 128e3], "input_cost_per_token": 1.8e-06, "output_cost_per_token": 9e-06, "cache_read_input_token_cost": 1.8e-07}, - {"range": [128e3, 256e3], "input_cost_per_token": 3e-06, "output_cost_per_token": 1.5e-05, "cache_read_input_token_cost": 3e-07}, - {"range": [256e3, 1e6], "input_cost_per_token": 6e-06, "output_cost_per_token": 6e-05, "cache_read_input_token_cost": 6e-07} - ], - "source": "https://www.alibabacloud.com/help/en/model-studio/models" - }, - "dashscope/qwen3-coder-plus-2025-07-22": { - "max_tokens": 1000000, - "max_input_tokens": 997952, - "max_output_tokens": 65536, - "litellm_provider": "dashscope", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "mode": "chat", - "tiered_pricing": [ - {"range": [0, 32e3], "input_cost_per_token": 1e-06, "output_cost_per_token": 5e-06}, - {"range": [32e3, 128e3], "input_cost_per_token": 1.8e-06, "output_cost_per_token": 9e-06}, - {"range": [128e3, 256e3], "input_cost_per_token": 3e-06, "output_cost_per_token": 1.5e-05}, - {"range": [256e3, 1e6], "input_cost_per_token": 6e-06, "output_cost_per_token": 6e-05} - ], - "source": "https://www.alibabacloud.com/help/en/model-studio/models" - }, - "dashscope/qwen3-coder-flash": { - "max_tokens": 1000000, - "max_input_tokens": 997952, - "max_output_tokens": 65536, - "litellm_provider": "dashscope", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "mode": "chat", - "tiered_pricing": [ - {"range": [0, 32e3], "input_cost_per_token": 3e-07, "output_cost_per_token": 1.5e-06, "cache_read_input_token_cost": 8e-08}, - {"range": [32e3, 128e3], "input_cost_per_token": 5e-07, "output_cost_per_token": 2.5e-06, "cache_read_input_token_cost": 1.2e-07}, - {"range": [128e3, 256e3], "input_cost_per_token": 8e-07, "output_cost_per_token": 4e-06, "cache_read_input_token_cost": 2e-07}, - {"range": [256e3, 1e6], "input_cost_per_token": 1.6e-06, "output_cost_per_token": 9.6e-06, "cache_read_input_token_cost": 4e-07} - ], - "source": "https://www.alibabacloud.com/help/en/model-studio/models" - }, - "dashscope/qwen3-coder-flash-2025-07-28": { - "max_tokens": 1000000, - "max_input_tokens": 997952, - "max_output_tokens": 65536, - "litellm_provider": "dashscope", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "mode": "chat", - "tiered_pricing": [ - {"range": [0, 32e3], "input_cost_per_token": 3e-07, "output_cost_per_token": 1.5e-06}, - {"range": [32e3, 128e3], "input_cost_per_token": 5e-07, "output_cost_per_token": 2.5e-06}, - {"range": [128e3, 256e3], "input_cost_per_token": 8e-07, "output_cost_per_token": 4e-06}, - {"range": [256e3, 1e6], "input_cost_per_token": 1.6e-06, "output_cost_per_token": 9.6e-06} - ], - "source": "https://www.alibabacloud.com/help/en/model-studio/models" - }, - "dashscope/qwen-plus-2025-09-11": { - "max_tokens": 1000000, - "max_input_tokens": 997952, - "max_output_tokens": 32768, - "litellm_provider": "dashscope", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "mode": "chat", - "tiered_pricing": [ - {"range": [0, 256e3], "input_cost_per_token": 4e-07, "output_cost_per_token": 1.2e-06, "output_cost_per_reasoning_token": 4e-06}, - {"range": [256e3, 1e6], "input_cost_per_token": 1.2e-06, "output_cost_per_token": 3.6e-06, "output_cost_per_reasoning_token": 1.2e-05} - ], - "source": "https://www.alibabacloud.com/help/en/model-studio/models" - }, - "dashscope/qwen-plus-2025-07-28": { - "max_tokens": 1000000, - "max_input_tokens": 997952, - "max_output_tokens": 32768, - "litellm_provider": "dashscope", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "mode": "chat", - "tiered_pricing": [ - {"range": [0, 256e3], "input_cost_per_token": 4e-07, "output_cost_per_token": 1.2e-06, "output_cost_per_reasoning_token": 4e-06}, - {"range": [256e3, 1e6], "input_cost_per_token": 1.2e-06, "output_cost_per_token": 3.6e-06, "output_cost_per_reasoning_token": 1.2e-05} - ], - "source": "https://www.alibabacloud.com/help/en/model-studio/models" - }, - "dashscope/qwen-plus-2025-07-14": { - "max_tokens": 131072, - "max_input_tokens": 129024, - "max_output_tokens": 16384, - "input_cost_per_token": 4e-07, - "output_cost_per_token": 1.2e-06, - "output_cost_per_reasoning_token": 4e-06, - "litellm_provider": "dashscope", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "mode": "chat", - "source": "https://www.alibabacloud.com/help/en/model-studio/models" - }, - "dashscope/qwen-plus-2025-04-28": { - "max_tokens": 131072, - "max_input_tokens": 129024, - "max_output_tokens": 16384, - "input_cost_per_token": 4e-07, - "output_cost_per_token": 1.2e-06, - "output_cost_per_reasoning_token": 4e-06, - "litellm_provider": "dashscope", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "mode": "chat", - "source": "https://www.alibabacloud.com/help/en/model-studio/models" - }, - "dashscope/qwen-plus-2025-01-25": { - "max_tokens": 131072, - "max_input_tokens": 129024, - "max_output_tokens": 8192, - "input_cost_per_token": 4e-07, - "output_cost_per_token": 1.2e-06, - "litellm_provider": "dashscope", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "mode": "chat", - "source": "https://www.alibabacloud.com/help/en/model-studio/models" - }, - "dashscope/qwen-flash-2025-07-28": { - "max_tokens": 1000000, - "max_input_tokens": 997952, - "max_output_tokens": 32768, - "litellm_provider": "dashscope", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "mode": "chat", - "tiered_pricing": [ - {"range": [0, 256e3], "input_cost_per_token": 5e-08, "output_cost_per_token": 4e-07}, - {"range": [256e3, 1e6], "input_cost_per_token": 2.5e-07, "output_cost_per_token": 2e-06} - ], - "source": "https://www.alibabacloud.com/help/en/model-studio/models" - }, - "dashscope/qwen-turbo": { - "max_tokens": 131072, - "max_input_tokens": 129024, - "max_output_tokens": 16384, - "input_cost_per_token": 5e-08, - "output_cost_per_token": 2e-07, - "output_cost_per_reasoning_token": 5e-07, - "litellm_provider": "dashscope", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "mode": "chat", - "source": "https://www.alibabacloud.com/help/en/model-studio/models" - }, - "dashscope/qwen-turbo-2025-04-28": { - "max_tokens": 1000000, - "max_input_tokens": 1000000, - "max_output_tokens": 16384, - "input_cost_per_token": 5e-08, - "output_cost_per_token": 2e-07, - "output_cost_per_reasoning_token": 5e-07, - "litellm_provider": "dashscope", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "mode": "chat", - "source": "https://www.alibabacloud.com/help/en/model-studio/models" - }, - "dashscope/qwen-turbo-2024-11-01": { - "max_tokens": 1000000, - "max_input_tokens": 1000000, - "max_output_tokens": 8192, - "input_cost_per_token": 5e-08, - "output_cost_per_token": 2e-07, - "litellm_provider": "dashscope", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "mode": "chat", - "source": "https://www.alibabacloud.com/help/en/model-studio/models" - }, - "dashscope/qwq-plus": { - "max_tokens": 131072, - "max_input_tokens": 98304, - "max_output_tokens": 8192, - "input_cost_per_token": 8e-07, - "output_cost_per_token": 2.4e-06, - "litellm_provider": "dashscope", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "mode": "chat", - "source": "https://www.alibabacloud.com/help/en/model-studio/models" - }, - "moonshot/moonshot-v1-8k": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 2e-07, - "output_cost_per_token": 2e-06, - "litellm_provider": "moonshot", - "supports_function_calling": true, - "supports_tool_choice": true, - "mode": "chat", - "source": "https://platform.moonshot.ai/docs/pricing" - }, - "moonshot/moonshot-v1-32k": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "input_cost_per_token": 1e-06, - "output_cost_per_token": 3e-06, - "litellm_provider": "moonshot", - "supports_function_calling": true, - "supports_tool_choice": true, - "mode": "chat", - "source": "https://platform.moonshot.ai/docs/pricing" - }, - "moonshot/moonshot-v1-128k": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 5e-06, - "litellm_provider": "moonshot", - "supports_function_calling": true, - "supports_tool_choice": true, - "mode": "chat", - "source": "https://platform.moonshot.ai/docs/pricing" - }, - "moonshot/moonshot-v1-auto": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 5e-06, - "litellm_provider": "moonshot", - "supports_function_calling": true, - "supports_tool_choice": true, - "mode": "chat", - "source": "https://platform.moonshot.ai/docs/pricing" - }, - "moonshot/kimi-k2-0711-preview": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 6e-07, - "output_cost_per_token": 2.5e-06, - "cache_read_input_token_cost": 1.5e-07, - "litellm_provider": "moonshot", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_web_search": true, - "mode": "chat", - "source": "https://platform.moonshot.ai/docs/pricing/chat#generation-model-kimi-k2" - }, - "moonshot/moonshot-v1-32k-0430": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "input_cost_per_token": 1e-06, - "output_cost_per_token": 3e-06, - "litellm_provider": "moonshot", - "supports_function_calling": true, - "supports_tool_choice": true, - "mode": "chat", - "source": "https://platform.moonshot.ai/docs/pricing" - }, - "moonshot/moonshot-v1-128k-0430": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 5e-06, - "litellm_provider": "moonshot", - "supports_function_calling": true, - "supports_tool_choice": true, - "mode": "chat", - "source": "https://platform.moonshot.ai/docs/pricing" - }, - "moonshot/moonshot-v1-8k-0430": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 2e-07, - "output_cost_per_token": 2e-06, - "litellm_provider": "moonshot", - "supports_function_calling": true, - "supports_tool_choice": true, - "mode": "chat", - "source": "https://platform.moonshot.ai/docs/pricing" - }, - "moonshot/kimi-latest": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 5e-06, - "cache_read_input_token_cost": 1.5e-07, - "litellm_provider": "moonshot", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_vision": true, - "mode": "chat", - "source": "https://platform.moonshot.ai/docs/pricing" - }, - "moonshot/kimi-latest-8k": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 2e-07, - "output_cost_per_token": 2e-06, - "cache_read_input_token_cost": 1.5e-07, - "litellm_provider": "moonshot", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_vision": true, - "mode": "chat", - "source": "https://platform.moonshot.ai/docs/pricing" - }, - "moonshot/kimi-latest-32k": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "input_cost_per_token": 1e-06, - "output_cost_per_token": 3e-06, - "cache_read_input_token_cost": 1.5e-07, - "litellm_provider": "moonshot", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_vision": true, - "mode": "chat", - "source": "https://platform.moonshot.ai/docs/pricing" - }, - "moonshot/kimi-latest-128k": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 5e-06, - "cache_read_input_token_cost": 1.5e-07, - "litellm_provider": "moonshot", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_vision": true, - "mode": "chat", - "source": "https://platform.moonshot.ai/docs/pricing" - }, - "moonshot/kimi-thinking-preview": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 3e-05, - "output_cost_per_token": 3e-05, - "litellm_provider": "moonshot", - "supports_vision": true, - "mode": "chat", - "source": "https://platform.moonshot.ai/docs/pricing" - }, - "moonshot/moonshot-v1-8k-vision-preview": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 2e-07, - "output_cost_per_token": 2e-06, - "litellm_provider": "moonshot", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_vision": true, - "mode": "chat", - "source": "https://platform.moonshot.ai/docs/pricing" - }, - "moonshot/moonshot-v1-32k-vision-preview": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "input_cost_per_token": 1e-06, - "output_cost_per_token": 3e-06, - "litellm_provider": "moonshot", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_vision": true, - "mode": "chat", - "source": "https://platform.moonshot.ai/docs/pricing" - }, - "moonshot/moonshot-v1-128k-vision-preview": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 5e-06, - "litellm_provider": "moonshot", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_vision": true, - "mode": "chat", - "source": "https://platform.moonshot.ai/docs/pricing" - }, - "recraft/recraftv3": { - "mode": "image_generation", - "output_cost_per_image": 0.04, - "litellm_provider": "recraft", - "supported_endpoints": [ - "/v1/images/generations" - ], - "source": "https://www.recraft.ai/docs#pricing" - }, - "recraft/recraftv2": { - "mode": "image_generation", - "output_cost_per_image": 0.022, - "litellm_provider": "recraft", - "supported_endpoints": [ - "/v1/images/generations" - ], - "source": "https://www.recraft.ai/docs#pricing" - }, - "morph/morph-v3-fast": { - "max_tokens": 16000, - "max_input_tokens": 16000, - "max_output_tokens": 16000, - "input_cost_per_token": 8e-07, - "output_cost_per_token": 1.2e-06, - "litellm_provider": "morph", - "mode": "chat", "supports_function_calling": false, - "supports_parallel_function_calling": false, - "supports_vision": false, - "supports_system_messages": true, + "supports_response_schema": true, "supports_tool_choice": false }, - "morph/morph-v3-large": { - "max_tokens": 16000, - "max_input_tokens": 16000, - "max_output_tokens": 16000, + "groq/llama-3.1-405b-reasoning": { + "input_cost_per_token": 5.9e-07, + "litellm_provider": "groq", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 7.9e-07, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "groq/llama-3.1-70b-versatile": { + "deprecation_date": "2025-01-24", + "input_cost_per_token": 5.9e-07, + "litellm_provider": "groq", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 7.9e-07, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "groq/llama-3.1-8b-instant": { + "input_cost_per_token": 5e-08, + "litellm_provider": "groq", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 8e-08, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "groq/llama-3.2-11b-text-preview": { + "deprecation_date": "2024-10-28", + "input_cost_per_token": 1.8e-07, + "litellm_provider": "groq", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.8e-07, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "groq/llama-3.2-11b-vision-preview": { + "deprecation_date": "2025-04-14", + "input_cost_per_token": 1.8e-07, + "litellm_provider": "groq", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.8e-07, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "groq/llama-3.2-1b-preview": { + "deprecation_date": "2025-04-14", + "input_cost_per_token": 4e-08, + "litellm_provider": "groq", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 4e-08, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "groq/llama-3.2-3b-preview": { + "deprecation_date": "2025-04-14", + "input_cost_per_token": 6e-08, + "litellm_provider": "groq", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 6e-08, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "groq/llama-3.2-90b-text-preview": { + "deprecation_date": "2024-11-25", "input_cost_per_token": 9e-07, - "output_cost_per_token": 1.9e-06, - "litellm_provider": "morph", - "mode": "chat", - "supports_function_calling": false, - "supports_parallel_function_calling": false, - "supports_vision": false, - "supports_system_messages": true, - "supports_tool_choice": false - }, - "heroku/claude-4-sonnet": { + "litellm_provider": "groq", + "max_input_tokens": 8192, + "max_output_tokens": 8192, "max_tokens": 8192, - "litellm_provider": "heroku", "mode": "chat", + "output_cost_per_token": 9e-07, "supports_function_calling": true, - "supports_system_messages": true, + "supports_response_schema": true, "supports_tool_choice": true }, - "heroku/claude-3-7-sonnet": { + "groq/llama-3.2-90b-vision-preview": { + "deprecation_date": "2025-04-14", + "input_cost_per_token": 9e-07, + "litellm_provider": "groq", + "max_input_tokens": 8192, + "max_output_tokens": 8192, "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 9e-07, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "groq/llama-3.3-70b-specdec": { + "deprecation_date": "2025-04-14", + "input_cost_per_token": 5.9e-07, + "litellm_provider": "groq", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 9.9e-07, + "supports_tool_choice": true + }, + "groq/llama-3.3-70b-versatile": { + "input_cost_per_token": 5.9e-07, + "litellm_provider": "groq", + "max_input_tokens": 128000, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 7.9e-07, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "groq/llama-guard-3-8b": { + "input_cost_per_token": 2e-07, + "litellm_provider": "groq", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 2e-07 + }, + "groq/llama2-70b-4096": { + "input_cost_per_token": 7e-07, + "litellm_provider": "groq", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 8e-07, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "groq/llama3-groq-70b-8192-tool-use-preview": { + "deprecation_date": "2025-01-06", + "input_cost_per_token": 8.9e-07, + "litellm_provider": "groq", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 8.9e-07, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "groq/llama3-groq-8b-8192-tool-use-preview": { + "deprecation_date": "2025-01-06", + "input_cost_per_token": 1.9e-07, + "litellm_provider": "groq", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.9e-07, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "groq/meta-llama/llama-4-maverick-17b-128e-instruct": { + "input_cost_per_token": 2e-07, + "litellm_provider": "groq", + "max_input_tokens": 131072, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 6e-07, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "groq/meta-llama/llama-4-scout-17b-16e-instruct": { + "input_cost_per_token": 1.1e-07, + "litellm_provider": "groq", + "max_input_tokens": 131072, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 3.4e-07, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "groq/mistral-saba-24b": { + "input_cost_per_token": 7.9e-07, + "litellm_provider": "groq", + "max_input_tokens": 32000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 7.9e-07 + }, + "groq/mixtral-8x7b-32768": { + "deprecation_date": "2025-03-20", + "input_cost_per_token": 2.4e-07, + "litellm_provider": "groq", + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 2.4e-07, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "groq/moonshotai/kimi-k2-instruct": { + "input_cost_per_token": 1e-06, + "litellm_provider": "groq", + "max_input_tokens": 131072, + "max_output_tokens": 16384, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 3e-06, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "groq/openai/gpt-oss-120b": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "groq", + "max_input_tokens": 131072, + "max_output_tokens": 32766, + "max_tokens": 32766, + "mode": "chat", + "output_cost_per_token": 7.5e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_web_search": true + }, + "groq/openai/gpt-oss-20b": { + "input_cost_per_token": 1e-07, + "litellm_provider": "groq", + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 5e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_web_search": true + }, + "groq/playai-tts": { + "input_cost_per_character": 5e-05, + "litellm_provider": "groq", + "max_input_tokens": 10000, + "max_output_tokens": 10000, + "max_tokens": 10000, + "mode": "audio_speech" + }, + "groq/qwen/qwen3-32b": { + "input_cost_per_token": 2.9e-07, + "litellm_provider": "groq", + "max_input_tokens": 131000, + "max_output_tokens": 131000, + "max_tokens": 131000, + "mode": "chat", + "output_cost_per_token": 5.9e-07, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "groq/whisper-large-v3": { + "input_cost_per_second": 3.083e-05, + "litellm_provider": "groq", + "mode": "audio_transcription", + "output_cost_per_second": 0.0 + }, + "groq/whisper-large-v3-turbo": { + "input_cost_per_second": 1.111e-05, + "litellm_provider": "groq", + "mode": "audio_transcription", + "output_cost_per_second": 0.0 + }, + "hd/1024-x-1024/dall-e-3": { + "input_cost_per_pixel": 7.629e-08, + "litellm_provider": "openai", + "mode": "image_generation", + "output_cost_per_pixel": 0.0 + }, + "hd/1024-x-1792/dall-e-3": { + "input_cost_per_pixel": 6.539e-08, + "litellm_provider": "openai", + "mode": "image_generation", + "output_cost_per_pixel": 0.0 + }, + "hd/1792-x-1024/dall-e-3": { + "input_cost_per_pixel": 6.539e-08, + "litellm_provider": "openai", + "mode": "image_generation", + "output_cost_per_pixel": 0.0 + }, + "heroku/claude-3-5-haiku": { "litellm_provider": "heroku", + "max_tokens": 4096, "mode": "chat", "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true }, "heroku/claude-3-5-sonnet-latest": { - "max_tokens": 8192, "litellm_provider": "heroku", + "max_tokens": 8192, "mode": "chat", "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true }, - "heroku/claude-3-5-haiku": { - "max_tokens": 4096, + "heroku/claude-3-7-sonnet": { "litellm_provider": "heroku", + "max_tokens": 8192, "mode": "chat", "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true }, - "vercel_ai_gateway/alibaba/qwen3-coder": { - "max_tokens": 262144, - "input_cost_per_token": 4e-07, - "output_cost_per_token": 1.6e-06, - "max_output_tokens": 66536, - "max_input_tokens": 262144, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/mistral/codestral-embed": { - "max_tokens": 0, - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 0.0, - "max_output_tokens": 0, - "max_input_tokens": 0, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/google/gemini-2.5-pro": { - "max_tokens": 1048576, - "input_cost_per_token": 2.5e-06, - "output_cost_per_token": 1e-05, - "max_output_tokens": 65536, - "max_input_tokens": 1048576, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/deepseek/deepseek-v3": { - "max_tokens": 128000, - "input_cost_per_token": 9e-07, - "output_cost_per_token": 9e-07, - "max_output_tokens": 8192, - "max_input_tokens": 128000, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/amazon/nova-lite": { - "max_tokens": 300000, - "input_cost_per_token": 6e-08, - "output_cost_per_token": 2.4e-07, - "max_output_tokens": 8192, - "max_input_tokens": 300000, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/meta/llama-4-scout": { - "max_tokens": 131072, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 3e-07, - "max_output_tokens": 8192, - "max_input_tokens": 131072, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/meta/llama-3.2-1b": { - "max_tokens": 128000, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 1e-07, - "max_output_tokens": 8192, - "max_input_tokens": 128000, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/mistral/mistral-small": { - "max_tokens": 32000, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 3e-07, - "max_output_tokens": 4000, - "max_input_tokens": 32000, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/google/gemini-2.5-flash": { - "max_tokens": 1000000, - "input_cost_per_token": 3e-07, - "output_cost_per_token": 2.5e-06, - "max_output_tokens": 65536, - "max_input_tokens": 1000000, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/inception/mercury-coder-small": { - "max_tokens": 32000, - "input_cost_per_token": 2.5e-07, - "output_cost_per_token": 1e-06, - "max_output_tokens": 16384, - "max_input_tokens": 32000, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/openai/text-embedding-3-small": { - "max_tokens": 0, - "input_cost_per_token": 2e-08, - "output_cost_per_token": 0.0, - "max_output_tokens": 0, - "max_input_tokens": 0, - "litellm_provider": "vercel_ai_gateway", - "mode": "embedding" - }, - "vercel_ai_gateway/xai/grok-2-vision": { - "max_tokens": 32768, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 1e-05, - "max_output_tokens": 32768, - "max_input_tokens": 32768, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/xai/grok-2": { - "max_tokens": 131072, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 1e-05, - "max_output_tokens": 4000, - "max_input_tokens": 131072, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/deepseek/deepseek-r1-distill-llama-70b": { - "max_tokens": 131072, - "input_cost_per_token": 7.5e-07, - "output_cost_per_token": 9.9e-07, - "max_output_tokens": 131072, - "max_input_tokens": 131072, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/meta/llama-3.1-70b": { - "max_tokens": 128000, - "input_cost_per_token": 7.2e-07, - "output_cost_per_token": 7.2e-07, - "max_output_tokens": 8192, - "max_input_tokens": 128000, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/xai/grok-3": { - "max_tokens": 131072, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "max_output_tokens": 131072, - "max_input_tokens": 131072, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/alibaba/qwen-3-235b": { - "max_tokens": 40960, - "input_cost_per_token": 2e-07, - "output_cost_per_token": 6e-07, - "max_output_tokens": 16384, - "max_input_tokens": 40960, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/xai/grok-3-fast": { - "max_tokens": 131072, - "input_cost_per_token": 5e-06, - "output_cost_per_token": 2.5e-05, - "max_output_tokens": 131072, - "max_input_tokens": 131072, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/vercel/v0-1.5-md": { - "max_tokens": 128000, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "max_output_tokens": 32768, - "max_input_tokens": 128000, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/openai/o4-mini": { - "max_tokens": 200000, - "input_cost_per_token": 1.1e-06, - "output_cost_per_token": 4.4e-06, - "max_output_tokens": 100000, - "max_input_tokens": 200000, - "cache_read_input_token_cost": 2.75e-07, - "cache_creation_input_token_cost": 0.0, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/mistral/magistral-medium": { - "max_tokens": 128000, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 5e-06, - "max_output_tokens": 64000, - "max_input_tokens": 128000, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/amazon/titan-embed-text-v2": { - "max_tokens": 0, - "input_cost_per_token": 2e-08, - "output_cost_per_token": 0.0, - "max_output_tokens": 0, - "max_input_tokens": 0, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/alibaba/qwen-3-30b": { - "max_tokens": 40960, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 3e-07, - "max_output_tokens": 16384, - "max_input_tokens": 40960, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/zai/glm-4.5-air": { - "max_tokens": 128000, - "input_cost_per_token": 2e-07, - "output_cost_per_token": 1.1e-06, - "max_output_tokens": 96000, - "max_input_tokens": 128000, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/openai/gpt-4-turbo": { - "max_tokens": 128000, - "input_cost_per_token": 1e-05, - "output_cost_per_token": 3e-05, - "max_output_tokens": 4096, - "max_input_tokens": 128000, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/mistral/mistral-large": { - "max_tokens": 32000, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 6e-06, - "max_output_tokens": 4000, - "max_input_tokens": 32000, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/perplexity/sonar-pro": { - "max_tokens": 200000, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "max_output_tokens": 8000, - "max_input_tokens": 200000, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/meta/llama-3.2-90b": { - "max_tokens": 128000, - "input_cost_per_token": 7.2e-07, - "output_cost_per_token": 7.2e-07, - "max_output_tokens": 8192, - "max_input_tokens": 128000, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/meta/llama-3-8b": { + "heroku/claude-4-sonnet": { + "litellm_provider": "heroku", "max_tokens": 8192, - "input_cost_per_token": 5e-08, - "output_cost_per_token": 8e-08, - "max_output_tokens": 8192, - "max_input_tokens": 8192, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" + "mode": "chat", + "supports_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true }, - "vercel_ai_gateway/google/text-embedding-005": { - "max_tokens": 0, - "input_cost_per_token": 2.5e-08, - "output_cost_per_token": 0.0, - "max_output_tokens": 0, - "max_input_tokens": 0, - "litellm_provider": "vercel_ai_gateway", - "mode": "embedding" + "high/1024-x-1024/gpt-image-1": { + "input_cost_per_pixel": 1.59263611e-07, + "litellm_provider": "openai", + "mode": "image_generation", + "output_cost_per_pixel": 0.0, + "supported_endpoints": [ + "/v1/images/generations" + ] }, - "vercel_ai_gateway/mistral/pixtral-large": { - "max_tokens": 128000, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 6e-06, - "max_output_tokens": 4000, - "max_input_tokens": 128000, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" + "high/1024-x-1536/gpt-image-1": { + "input_cost_per_pixel": 1.58945719e-07, + "litellm_provider": "openai", + "mode": "image_generation", + "output_cost_per_pixel": 0.0, + "supported_endpoints": [ + "/v1/images/generations" + ] }, - "vercel_ai_gateway/anthropic/claude-3.5-sonnet": { - "max_tokens": 200000, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "max_output_tokens": 8192, - "max_input_tokens": 200000, - "cache_read_input_token_cost": 3e-07, - "cache_creation_input_token_cost": 3.75e-06, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" + "high/1536-x-1024/gpt-image-1": { + "input_cost_per_pixel": 1.58945719e-07, + "litellm_provider": "openai", + "mode": "image_generation", + "output_cost_per_pixel": 0.0, + "supported_endpoints": [ + "/v1/images/generations" + ] }, - "vercel_ai_gateway/amazon/nova-micro": { - "max_tokens": 128000, - "input_cost_per_token": 3.5e-08, - "output_cost_per_token": 1.4e-07, - "max_output_tokens": 8192, - "max_input_tokens": 128000, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/cohere/command-r": { - "max_tokens": 128000, - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 6e-07, - "max_output_tokens": 4096, - "max_input_tokens": 128000, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/morph/morph-v3-large": { - "max_tokens": 32768, - "input_cost_per_token": 9e-07, - "output_cost_per_token": 1.9e-06, - "max_output_tokens": 16384, - "max_input_tokens": 32768, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/mistral/mixtral-8x22b-instruct": { - "max_tokens": 65536, - "input_cost_per_token": 1.2e-06, - "output_cost_per_token": 1.2e-06, - "max_output_tokens": 2048, - "max_input_tokens": 65536, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/xai/grok-4": { - "max_tokens": 256000, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "max_output_tokens": 256000, - "max_input_tokens": 256000, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/meta/llama-3.1-8b": { - "max_tokens": 131000, - "input_cost_per_token": 5e-08, - "output_cost_per_token": 8e-08, - "max_output_tokens": 131072, - "max_input_tokens": 131000, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/anthropic/claude-3-opus": { - "max_tokens": 200000, - "input_cost_per_token": 1.5e-05, - "output_cost_per_token": 7.5e-05, - "max_output_tokens": 4096, - "max_input_tokens": 200000, - "cache_read_input_token_cost": 1.5e-06, - "cache_creation_input_token_cost": 1.875e-05, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/zai/glm-4.5": { - "max_tokens": 131072, - "input_cost_per_token": 6e-07, - "output_cost_per_token": 2.2e-06, - "max_output_tokens": 131072, - "max_input_tokens": 131072, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/openai/gpt-4o": { - "max_tokens": 128000, - "input_cost_per_token": 2.5e-06, - "output_cost_per_token": 1e-05, - "max_output_tokens": 16384, - "max_input_tokens": 128000, - "cache_read_input_token_cost": 1.25e-06, - "cache_creation_input_token_cost": 0.0, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/openai/o3-mini": { - "max_tokens": 200000, - "input_cost_per_token": 1.1e-06, - "output_cost_per_token": 4.4e-06, - "max_output_tokens": 100000, - "max_input_tokens": 200000, - "cache_read_input_token_cost": 5.5e-07, - "cache_creation_input_token_cost": 0.0, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/mistral/ministral-8b": { - "max_tokens": 128000, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 1e-07, - "max_output_tokens": 4000, - "max_input_tokens": 128000, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/openai/o3": { - "max_tokens": 200000, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 8e-06, - "max_output_tokens": 100000, - "max_input_tokens": 200000, - "cache_read_input_token_cost": 5e-07, - "cache_creation_input_token_cost": 0.0, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/vercel/v0-1.0-md": { - "max_tokens": 128000, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "max_output_tokens": 32000, - "max_input_tokens": 128000, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/google/text-multilingual-embedding-002": { - "max_tokens": 0, - "input_cost_per_token": 2.5e-08, - "output_cost_per_token": 0.0, - "max_output_tokens": 0, - "max_input_tokens": 0, - "litellm_provider": "vercel_ai_gateway", - "mode": "embedding" - }, - "vercel_ai_gateway/amazon/nova-pro": { - "max_tokens": 300000, - "input_cost_per_token": 8e-07, - "output_cost_per_token": 3.2e-06, - "max_output_tokens": 8192, - "max_input_tokens": 300000, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/morph/morph-v3-fast": { - "max_tokens": 32768, - "input_cost_per_token": 8e-07, - "output_cost_per_token": 1.2e-06, - "max_output_tokens": 16384, - "max_input_tokens": 32768, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/openai/gpt-3.5-turbo": { - "max_tokens": 16385, - "input_cost_per_token": 5e-07, - "output_cost_per_token": 1.5e-06, - "max_output_tokens": 4096, - "max_input_tokens": 16385, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/mistral/codestral": { - "max_tokens": 256000, - "input_cost_per_token": 3e-07, - "output_cost_per_token": 9e-07, - "max_output_tokens": 4000, - "max_input_tokens": 256000, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/meta/llama-3.2-11b": { - "max_tokens": 128000, - "input_cost_per_token": 1.6e-07, - "output_cost_per_token": 1.6e-07, - "max_output_tokens": 8192, - "max_input_tokens": 128000, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/meta/llama-3-70b": { - "max_tokens": 8192, - "input_cost_per_token": 5.9e-07, - "output_cost_per_token": 7.9e-07, - "max_output_tokens": 8192, - "max_input_tokens": 8192, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/xai/grok-3-mini-fast": { - "max_tokens": 131072, - "input_cost_per_token": 6e-07, - "output_cost_per_token": 4e-06, - "max_output_tokens": 131072, - "max_input_tokens": 131072, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/openai/text-embedding-3-large": { - "max_tokens": 0, - "input_cost_per_token": 1.3e-07, - "output_cost_per_token": 0.0, - "max_output_tokens": 0, - "max_input_tokens": 0, - "litellm_provider": "vercel_ai_gateway", - "mode": "embedding" - }, - "vercel_ai_gateway/google/gemini-2.0-flash-lite": { - "max_tokens": 1048576, - "input_cost_per_token": 7.5e-08, - "output_cost_per_token": 3e-07, - "max_output_tokens": 8192, - "max_input_tokens": 1048576, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/mistral/ministral-3b": { - "max_tokens": 128000, - "input_cost_per_token": 4e-08, - "output_cost_per_token": 4e-08, - "max_output_tokens": 4000, - "max_input_tokens": 128000, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/perplexity/sonar-reasoning-pro": { - "max_tokens": 127000, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 8e-06, - "max_output_tokens": 8000, - "max_input_tokens": 127000, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/google/gemini-embedding-001": { - "max_tokens": 0, - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 0.0, - "max_output_tokens": 0, - "max_input_tokens": 0, - "litellm_provider": "vercel_ai_gateway", - "mode": "embedding" - }, - "vercel_ai_gateway/anthropic/claude-3-haiku": { - "max_tokens": 200000, - "input_cost_per_token": 2.5e-07, - "output_cost_per_token": 1.25e-06, - "max_output_tokens": 4096, - "max_input_tokens": 200000, - "cache_read_input_token_cost": 3e-08, - "cache_creation_input_token_cost": 3e-07, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/openai/o1": { - "max_tokens": 200000, - "input_cost_per_token": 1.5e-05, - "output_cost_per_token": 6e-05, - "max_output_tokens": 100000, - "max_input_tokens": 200000, - "cache_read_input_token_cost": 7.5e-06, - "cache_creation_input_token_cost": 0.0, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/deepseek/deepseek-r1": { - "max_tokens": 128000, - "input_cost_per_token": 5.5e-07, - "output_cost_per_token": 2.19e-06, - "max_output_tokens": 8192, - "max_input_tokens": 128000, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/mistral/mistral-embed": { - "max_tokens": 0, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 0.0, - "max_output_tokens": 0, - "max_input_tokens": 0, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/openai/gpt-4.1-mini": { - "max_tokens": 1047576, - "input_cost_per_token": 4e-07, - "output_cost_per_token": 1.6e-06, - "max_output_tokens": 32768, - "max_input_tokens": 1047576, - "cache_read_input_token_cost": 1e-07, - "cache_creation_input_token_cost": 0.0, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/openai/gpt-4o-mini": { - "max_tokens": 128000, - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 6e-07, - "max_output_tokens": 16384, - "max_input_tokens": 128000, - "cache_read_input_token_cost": 7.5e-08, - "cache_creation_input_token_cost": 0.0, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/alibaba/qwen-3-14b": { - "max_tokens": 40960, - "input_cost_per_token": 8e-08, - "output_cost_per_token": 2.4e-07, - "max_output_tokens": 16384, - "max_input_tokens": 40960, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/anthropic/claude-4-opus": { - "max_tokens": 200000, - "input_cost_per_token": 1.5e-05, - "output_cost_per_token": 7.5e-05, - "max_output_tokens": 32000, - "max_input_tokens": 200000, - "cache_read_input_token_cost": 1.5e-06, - "cache_creation_input_token_cost": 1.875e-05, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/mistral/mistral-saba-24b": { - "max_tokens": 32768, - "input_cost_per_token": 7.9e-07, - "output_cost_per_token": 7.9e-07, - "max_output_tokens": 32768, - "max_input_tokens": 32768, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/perplexity/sonar-reasoning": { - "max_tokens": 127000, - "input_cost_per_token": 1e-06, - "output_cost_per_token": 5e-06, - "max_output_tokens": 8000, - "max_input_tokens": 127000, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/anthropic/claude-3.5-haiku": { - "max_tokens": 200000, - "input_cost_per_token": 8e-07, - "output_cost_per_token": 4e-06, - "max_output_tokens": 8192, - "max_input_tokens": 200000, - "cache_read_input_token_cost": 8e-08, - "cache_creation_input_token_cost": 1e-06, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/cohere/command-a": { - "max_tokens": 256000, - "input_cost_per_token": 2.5e-06, - "output_cost_per_token": 1e-05, - "max_output_tokens": 8000, - "max_input_tokens": 256000, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/google/gemma-2-9b": { - "max_tokens": 8192, - "input_cost_per_token": 2e-07, - "output_cost_per_token": 2e-07, - "max_output_tokens": 8192, - "max_input_tokens": 8192, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/meta/llama-3.2-3b": { - "max_tokens": 128000, - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 1.5e-07, - "max_output_tokens": 8192, - "max_input_tokens": 128000, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/openai/gpt-4.1-nano": { - "max_tokens": 1047576, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 4e-07, - "max_output_tokens": 32768, - "max_input_tokens": 1047576, - "cache_read_input_token_cost": 2.5e-08, - "cache_creation_input_token_cost": 0.0, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/anthropic/claude-4-sonnet": { - "max_tokens": 200000, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "max_output_tokens": 64000, - "max_input_tokens": 200000, - "cache_read_input_token_cost": 3e-07, - "cache_creation_input_token_cost": 3.75e-06, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/perplexity/sonar": { - "max_tokens": 127000, - "input_cost_per_token": 1e-06, - "output_cost_per_token": 1e-06, - "max_output_tokens": 8000, - "max_input_tokens": 127000, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/meta/llama-4-maverick": { - "max_tokens": 131072, - "input_cost_per_token": 2e-07, - "output_cost_per_token": 6e-07, - "max_output_tokens": 8192, - "max_input_tokens": 131072, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/openai/text-embedding-ada-002": { - "max_tokens": 0, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 0.0, - "max_output_tokens": 0, - "max_input_tokens": 0, - "litellm_provider": "vercel_ai_gateway", - "mode": "embedding" - }, - "vercel_ai_gateway/xai/grok-3-mini": { - "max_tokens": 131072, - "input_cost_per_token": 3e-07, - "output_cost_per_token": 5e-07, - "max_output_tokens": 131072, - "max_input_tokens": 131072, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/cohere/embed-v4.0": { - "max_tokens": 0, + "hyperbolic/NousResearch/Hermes-3-Llama-3.1-70B": { "input_cost_per_token": 1.2e-07, - "output_cost_per_token": 0.0, - "max_output_tokens": 0, - "max_input_tokens": 0, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/meta/llama-3.3-70b": { - "max_tokens": 128000, - "input_cost_per_token": 7.2e-07, - "output_cost_per_token": 7.2e-07, - "max_output_tokens": 8192, - "max_input_tokens": 128000, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/cohere/command-r-plus": { - "max_tokens": 128000, - "input_cost_per_token": 2.5e-06, - "output_cost_per_token": 1e-05, - "max_output_tokens": 4096, - "max_input_tokens": 128000, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/openai/gpt-3.5-turbo-instruct": { - "max_tokens": 8192, - "input_cost_per_token": 1.5e-06, - "output_cost_per_token": 2e-06, - "max_output_tokens": 4096, - "max_input_tokens": 8192, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/mistral/devstral-small": { - "max_tokens": 128000, - "input_cost_per_token": 7e-08, - "output_cost_per_token": 2.8e-07, - "max_output_tokens": 128000, - "max_input_tokens": 128000, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/anthropic/claude-3.7-sonnet": { - "max_tokens": 200000, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "max_output_tokens": 64000, - "max_input_tokens": 200000, - "cache_read_input_token_cost": 3e-07, - "cache_creation_input_token_cost": 3.75e-06, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/google/gemini-2.0-flash": { - "max_tokens": 1048576, - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 6e-07, - "max_output_tokens": 8192, - "max_input_tokens": 1048576, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/mistral/pixtral-12b": { - "max_tokens": 128000, - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 1.5e-07, - "max_output_tokens": 4000, - "max_input_tokens": 128000, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/mistral/magistral-small": { - "max_tokens": 128000, - "input_cost_per_token": 5e-07, - "output_cost_per_token": 1.5e-06, - "max_output_tokens": 64000, - "max_input_tokens": 128000, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/moonshotai/kimi-k2": { - "max_tokens": 131072, - "input_cost_per_token": 5.5e-07, - "output_cost_per_token": 2.2e-06, - "max_output_tokens": 16384, - "max_input_tokens": 131072, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/alibaba/qwen-3-32b": { - "max_tokens": 40960, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 3e-07, - "max_output_tokens": 16384, - "max_input_tokens": 40960, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/openai/gpt-4.1": { - "max_tokens": 1047576, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 8e-06, + "litellm_provider": "hyperbolic", + "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_input_tokens": 1047576, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 3e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "hyperbolic/Qwen/QwQ-32B": { + "input_cost_per_token": 2e-07, + "litellm_provider": "hyperbolic", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "hyperbolic/Qwen/Qwen2.5-72B-Instruct": { + "input_cost_per_token": 1.2e-07, + "litellm_provider": "hyperbolic", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 3e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "hyperbolic/Qwen/Qwen2.5-Coder-32B-Instruct": { + "input_cost_per_token": 1.2e-07, + "litellm_provider": "hyperbolic", + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 3e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "hyperbolic/Qwen/Qwen3-235B-A22B": { + "input_cost_per_token": 2e-06, + "litellm_provider": "hyperbolic", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2e-06, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "hyperbolic/deepseek-ai/DeepSeek-R1": { + "input_cost_per_token": 4e-07, + "litellm_provider": "hyperbolic", + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 4e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "hyperbolic/deepseek-ai/DeepSeek-R1-0528": { + "input_cost_per_token": 2.5e-07, + "litellm_provider": "hyperbolic", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2.5e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "hyperbolic/deepseek-ai/DeepSeek-V3": { + "input_cost_per_token": 2e-07, + "litellm_provider": "hyperbolic", + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 2e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "hyperbolic/deepseek-ai/DeepSeek-V3-0324": { + "input_cost_per_token": 4e-07, + "litellm_provider": "hyperbolic", + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 4e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "hyperbolic/meta-llama/Llama-3.2-3B-Instruct": { + "input_cost_per_token": 1.2e-07, + "litellm_provider": "hyperbolic", + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 3e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "hyperbolic/meta-llama/Llama-3.3-70B-Instruct": { + "input_cost_per_token": 1.2e-07, + "litellm_provider": "hyperbolic", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 3e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "hyperbolic/meta-llama/Meta-Llama-3-70B-Instruct": { + "input_cost_per_token": 1.2e-07, + "litellm_provider": "hyperbolic", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 3e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "hyperbolic/meta-llama/Meta-Llama-3.1-405B-Instruct": { + "input_cost_per_token": 1.2e-07, + "litellm_provider": "hyperbolic", + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 3e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "hyperbolic/meta-llama/Meta-Llama-3.1-70B-Instruct": { + "input_cost_per_token": 1.2e-07, + "litellm_provider": "hyperbolic", + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 3e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "hyperbolic/meta-llama/Meta-Llama-3.1-8B-Instruct": { + "input_cost_per_token": 1.2e-07, + "litellm_provider": "hyperbolic", + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 3e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "hyperbolic/moonshotai/Kimi-K2-Instruct": { + "input_cost_per_token": 2e-06, + "litellm_provider": "hyperbolic", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2e-06, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "j2-light": { + "input_cost_per_token": 3e-06, + "litellm_provider": "ai21", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "completion", + "output_cost_per_token": 3e-06 + }, + "j2-mid": { + "input_cost_per_token": 1e-05, + "litellm_provider": "ai21", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "completion", + "output_cost_per_token": 1e-05 + }, + "j2-ultra": { + "input_cost_per_token": 1.5e-05, + "litellm_provider": "ai21", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "completion", + "output_cost_per_token": 1.5e-05 + }, + "jamba-1.5": { + "input_cost_per_token": 2e-07, + "litellm_provider": "ai21", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 4e-07, + "supports_tool_choice": true + }, + "jamba-1.5-large": { + "input_cost_per_token": 2e-06, + "litellm_provider": "ai21", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 8e-06, + "supports_tool_choice": true + }, + "jamba-1.5-large@001": { + "input_cost_per_token": 2e-06, + "litellm_provider": "ai21", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 8e-06, + "supports_tool_choice": true + }, + "jamba-1.5-mini": { + "input_cost_per_token": 2e-07, + "litellm_provider": "ai21", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 4e-07, + "supports_tool_choice": true + }, + "jamba-1.5-mini@001": { + "input_cost_per_token": 2e-07, + "litellm_provider": "ai21", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 4e-07, + "supports_tool_choice": true + }, + "jamba-large-1.6": { + "input_cost_per_token": 2e-06, + "litellm_provider": "ai21", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 8e-06, + "supports_tool_choice": true + }, + "jamba-large-1.7": { + "input_cost_per_token": 2e-06, + "litellm_provider": "ai21", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 8e-06, + "supports_tool_choice": true + }, + "jamba-mini-1.6": { + "input_cost_per_token": 2e-07, + "litellm_provider": "ai21", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 4e-07, + "supports_tool_choice": true + }, + "jamba-mini-1.7": { + "input_cost_per_token": 2e-07, + "litellm_provider": "ai21", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 4e-07, + "supports_tool_choice": true + }, + "jina-reranker-v2-base-multilingual": { + "input_cost_per_token": 1.8e-08, + "litellm_provider": "jina_ai", + "max_document_chunks_per_query": 2048, + "max_input_tokens": 1024, + "max_output_tokens": 1024, + "max_tokens": 1024, + "mode": "rerank", + "output_cost_per_token": 1.8e-08 + }, + "lambda_ai/deepseek-llama3.3-70b": { + "input_cost_per_token": 2e-07, + "litellm_provider": "lambda_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 6e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "lambda_ai/deepseek-r1-0528": { + "input_cost_per_token": 2e-07, + "litellm_provider": "lambda_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 6e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "lambda_ai/deepseek-r1-671b": { + "input_cost_per_token": 8e-07, + "litellm_provider": "lambda_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 8e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "lambda_ai/deepseek-v3-0324": { + "input_cost_per_token": 2e-07, + "litellm_provider": "lambda_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 6e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "lambda_ai/hermes3-405b": { + "input_cost_per_token": 8e-07, + "litellm_provider": "lambda_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 8e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "lambda_ai/hermes3-70b": { + "input_cost_per_token": 1.2e-07, + "litellm_provider": "lambda_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 3e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "lambda_ai/hermes3-8b": { + "input_cost_per_token": 2.5e-08, + "litellm_provider": "lambda_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4e-08, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "lambda_ai/lfm-40b": { + "input_cost_per_token": 1e-07, + "litellm_provider": "lambda_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "lambda_ai/lfm-7b": { + "input_cost_per_token": 2.5e-08, + "litellm_provider": "lambda_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4e-08, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "lambda_ai/llama-4-maverick-17b-128e-instruct-fp8": { + "input_cost_per_token": 5e-08, + "litellm_provider": "lambda_ai", + "max_input_tokens": 131072, + "max_output_tokens": 8192, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "lambda_ai/llama-4-scout-17b-16e-instruct": { + "input_cost_per_token": 5e-08, + "litellm_provider": "lambda_ai", + "max_input_tokens": 16384, + "max_output_tokens": 8192, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "lambda_ai/llama3.1-405b-instruct-fp8": { + "input_cost_per_token": 8e-07, + "litellm_provider": "lambda_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 8e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "lambda_ai/llama3.1-70b-instruct-fp8": { + "input_cost_per_token": 1.2e-07, + "litellm_provider": "lambda_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 3e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "lambda_ai/llama3.1-8b-instruct": { + "input_cost_per_token": 2.5e-08, + "litellm_provider": "lambda_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4e-08, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "lambda_ai/llama3.1-nemotron-70b-instruct-fp8": { + "input_cost_per_token": 1.2e-07, + "litellm_provider": "lambda_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 3e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "lambda_ai/llama3.2-11b-vision-instruct": { + "input_cost_per_token": 1.5e-08, + "litellm_provider": "lambda_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2.5e-08, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "lambda_ai/llama3.2-3b-instruct": { + "input_cost_per_token": 1.5e-08, + "litellm_provider": "lambda_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2.5e-08, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "lambda_ai/llama3.3-70b-instruct-fp8": { + "input_cost_per_token": 1.2e-07, + "litellm_provider": "lambda_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 3e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "lambda_ai/qwen25-coder-32b-instruct": { + "input_cost_per_token": 5e-08, + "litellm_provider": "lambda_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "lambda_ai/qwen3-32b-fp8": { + "input_cost_per_token": 5e-08, + "litellm_provider": "lambda_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "low/1024-x-1024/gpt-image-1": { + "input_cost_per_pixel": 1.0490417e-08, + "litellm_provider": "openai", + "mode": "image_generation", + "output_cost_per_pixel": 0.0, + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "low/1024-x-1536/gpt-image-1": { + "input_cost_per_pixel": 1.0172526e-08, + "litellm_provider": "openai", + "mode": "image_generation", + "output_cost_per_pixel": 0.0, + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "low/1536-x-1024/gpt-image-1": { + "input_cost_per_pixel": 1.0172526e-08, + "litellm_provider": "openai", + "mode": "image_generation", + "output_cost_per_pixel": 0.0, + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "luminous-base": { + "input_cost_per_token": 3e-05, + "litellm_provider": "aleph_alpha", + "max_tokens": 2048, + "mode": "completion", + "output_cost_per_token": 3.3e-05 + }, + "luminous-base-control": { + "input_cost_per_token": 3.75e-05, + "litellm_provider": "aleph_alpha", + "max_tokens": 2048, + "mode": "chat", + "output_cost_per_token": 4.125e-05 + }, + "luminous-extended": { + "input_cost_per_token": 4.5e-05, + "litellm_provider": "aleph_alpha", + "max_tokens": 2048, + "mode": "completion", + "output_cost_per_token": 4.95e-05 + }, + "luminous-extended-control": { + "input_cost_per_token": 5.625e-05, + "litellm_provider": "aleph_alpha", + "max_tokens": 2048, + "mode": "chat", + "output_cost_per_token": 6.1875e-05 + }, + "luminous-supreme": { + "input_cost_per_token": 0.000175, + "litellm_provider": "aleph_alpha", + "max_tokens": 2048, + "mode": "completion", + "output_cost_per_token": 0.0001925 + }, + "luminous-supreme-control": { + "input_cost_per_token": 0.00021875, + "litellm_provider": "aleph_alpha", + "max_tokens": 2048, + "mode": "chat", + "output_cost_per_token": 0.000240625 + }, + "max-x-max/50-steps/stability.stable-diffusion-xl-v0": { + "litellm_provider": "bedrock", + "max_input_tokens": 77, + "max_tokens": 77, + "mode": "image_generation", + "output_cost_per_image": 0.036 + }, + "max-x-max/max-steps/stability.stable-diffusion-xl-v0": { + "litellm_provider": "bedrock", + "max_input_tokens": 77, + "max_tokens": 77, + "mode": "image_generation", + "output_cost_per_image": 0.072 + }, + "medium/1024-x-1024/gpt-image-1": { + "input_cost_per_pixel": 4.0054321e-08, + "litellm_provider": "openai", + "mode": "image_generation", + "output_cost_per_pixel": 0.0, + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "medium/1024-x-1536/gpt-image-1": { + "input_cost_per_pixel": 4.0054321e-08, + "litellm_provider": "openai", + "mode": "image_generation", + "output_cost_per_pixel": 0.0, + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "medium/1536-x-1024/gpt-image-1": { + "input_cost_per_pixel": 4.0054321e-08, + "litellm_provider": "openai", + "mode": "image_generation", + "output_cost_per_pixel": 0.0, + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "medlm-large": { + "input_cost_per_character": 5e-06, + "litellm_provider": "vertex_ai-language-models", + "max_input_tokens": 8192, + "max_output_tokens": 1024, + "max_tokens": 1024, + "mode": "chat", + "output_cost_per_character": 1.5e-05, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "supports_tool_choice": true + }, + "medlm-medium": { + "input_cost_per_character": 5e-07, + "litellm_provider": "vertex_ai-language-models", + "max_input_tokens": 32768, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_character": 1e-06, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "supports_tool_choice": true + }, + "meta.llama2-13b-chat-v1": { + "input_cost_per_token": 7.5e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1e-06 + }, + "meta.llama2-70b-chat-v1": { + "input_cost_per_token": 1.95e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 2.56e-06 + }, + "meta.llama3-1-405b-instruct-v1:0": { + "input_cost_per_token": 5.32e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.6e-05, + "supports_function_calling": true, + "supports_tool_choice": false + }, + "meta.llama3-1-70b-instruct-v1:0": { + "input_cost_per_token": 9.9e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 128000, + "max_output_tokens": 2048, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 9.9e-07, + "supports_function_calling": true, + "supports_tool_choice": false + }, + "meta.llama3-1-8b-instruct-v1:0": { + "input_cost_per_token": 2.2e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 128000, + "max_output_tokens": 2048, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2.2e-07, + "supports_function_calling": true, + "supports_tool_choice": false + }, + "meta.llama3-2-11b-instruct-v1:0": { + "input_cost_per_token": 3.5e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 3.5e-07, + "supports_function_calling": true, + "supports_tool_choice": false, + "supports_vision": true + }, + "meta.llama3-2-1b-instruct-v1:0": { + "input_cost_per_token": 1e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-07, + "supports_function_calling": true, + "supports_tool_choice": false + }, + "meta.llama3-2-3b-instruct-v1:0": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.5e-07, + "supports_function_calling": true, + "supports_tool_choice": false + }, + "meta.llama3-2-90b-instruct-v1:0": { + "input_cost_per_token": 2e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2e-06, + "supports_function_calling": true, + "supports_tool_choice": false, + "supports_vision": true + }, + "meta.llama3-3-70b-instruct-v1:0": { + "input_cost_per_token": 7.2e-07, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 7.2e-07, + "supports_function_calling": true, + "supports_tool_choice": false + }, + "meta.llama3-70b-instruct-v1:0": { + "input_cost_per_token": 2.65e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 3.5e-06 + }, + "meta.llama3-8b-instruct-v1:0": { + "input_cost_per_token": 3e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 6e-07 + }, + "meta.llama4-maverick-17b-instruct-v1:0": { + "input_cost_per_token": 2.4e-07, + "input_cost_per_token_batches": 1.2e-07, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 9.7e-07, + "output_cost_per_token_batches": 4.85e-07, + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text", + "code" + ], + "supports_function_calling": true, + "supports_tool_choice": false + }, + "meta.llama4-scout-17b-instruct-v1:0": { + "input_cost_per_token": 1.7e-07, + "input_cost_per_token_batches": 8.5e-08, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 6.6e-07, + "output_cost_per_token_batches": 3.3e-07, + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text", + "code" + ], + "supports_function_calling": true, + "supports_tool_choice": false + }, + "meta_llama/Llama-3.3-70B-Instruct": { + "litellm_provider": "meta_llama", + "max_input_tokens": 128000, + "max_output_tokens": 4028, + "max_tokens": 128000, + "mode": "chat", + "source": "https://llama.developer.meta.com/docs/models", + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_tool_choice": true + }, + "meta_llama/Llama-3.3-8B-Instruct": { + "litellm_provider": "meta_llama", + "max_input_tokens": 128000, + "max_output_tokens": 4028, + "max_tokens": 128000, + "mode": "chat", + "source": "https://llama.developer.meta.com/docs/models", + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_tool_choice": true + }, + "meta_llama/Llama-4-Maverick-17B-128E-Instruct-FP8": { + "litellm_provider": "meta_llama", + "max_input_tokens": 1000000, + "max_output_tokens": 4028, + "max_tokens": 128000, + "mode": "chat", + "source": "https://llama.developer.meta.com/docs/models", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_tool_choice": true + }, + "meta_llama/Llama-4-Scout-17B-16E-Instruct-FP8": { + "litellm_provider": "meta_llama", + "max_input_tokens": 10000000, + "max_output_tokens": 4028, + "max_tokens": 128000, + "mode": "chat", + "source": "https://llama.developer.meta.com/docs/models", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_tool_choice": true + }, + "mistral.mistral-7b-instruct-v0:2": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 2e-07, + "supports_tool_choice": true + }, + "mistral.mistral-large-2402-v1:0": { + "input_cost_per_token": 8e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 2.4e-05, + "supports_function_calling": true + }, + "mistral.mistral-large-2407-v1:0": { + "input_cost_per_token": 3e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 128000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 9e-06, + "supports_function_calling": true, + "supports_tool_choice": true + }, + "mistral.mistral-small-2402-v1:0": { + "input_cost_per_token": 1e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 3e-06, + "supports_function_calling": true + }, + "mistral.mixtral-8x7b-instruct-v0:1": { + "input_cost_per_token": 4.5e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 7e-07, + "supports_tool_choice": true + }, + "mistral/codestral-2405": { + "input_cost_per_token": 1e-06, + "litellm_provider": "mistral", + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 3e-06, + "supports_assistant_prefill": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "mistral/codestral-latest": { + "input_cost_per_token": 1e-06, + "litellm_provider": "mistral", + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 3e-06, + "supports_assistant_prefill": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "mistral/codestral-mamba-latest": { + "input_cost_per_token": 2.5e-07, + "litellm_provider": "mistral", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 2.5e-07, + "source": "https://mistral.ai/technology/", + "supports_assistant_prefill": true, + "supports_tool_choice": true + }, + "mistral/devstral-medium-2507": { + "input_cost_per_token": 4e-07, + "litellm_provider": "mistral", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2e-06, + "source": "https://mistral.ai/news/devstral", + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "mistral/devstral-small-2505": { + "input_cost_per_token": 1e-07, + "litellm_provider": "mistral", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 3e-07, + "source": "https://mistral.ai/news/devstral", + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "mistral/devstral-small-2507": { + "input_cost_per_token": 1e-07, + "litellm_provider": "mistral", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 3e-07, + "source": "https://mistral.ai/news/devstral", + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "mistral/magistral-medium-2506": { + "input_cost_per_token": 2e-06, + "litellm_provider": "mistral", + "max_input_tokens": 40000, + "max_output_tokens": 40000, + "max_tokens": 40000, + "mode": "chat", + "output_cost_per_token": 5e-06, + "source": "https://mistral.ai/news/magistral", + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "mistral/magistral-medium-latest": { + "input_cost_per_token": 2e-06, + "litellm_provider": "mistral", + "max_input_tokens": 40000, + "max_output_tokens": 40000, + "max_tokens": 40000, + "mode": "chat", + "output_cost_per_token": 5e-06, + "source": "https://mistral.ai/news/magistral", + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "mistral/magistral-small-2506": { + "input_cost_per_token": 5e-07, + "litellm_provider": "mistral", + "max_input_tokens": 40000, + "max_output_tokens": 40000, + "max_tokens": 40000, + "mode": "chat", + "output_cost_per_token": 1.5e-06, + "source": "https://mistral.ai/pricing#api-pricing", + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "mistral/magistral-small-latest": { + "input_cost_per_token": 5e-07, + "litellm_provider": "mistral", + "max_input_tokens": 40000, + "max_output_tokens": 40000, + "max_tokens": 40000, + "mode": "chat", + "output_cost_per_token": 1.5e-06, + "source": "https://mistral.ai/pricing#api-pricing", + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "mistral/mistral-embed": { + "input_cost_per_token": 1e-07, + "litellm_provider": "mistral", + "max_input_tokens": 8192, + "max_tokens": 8192, + "mode": "embedding" + }, + "mistral/mistral-large-2402": { + "input_cost_per_token": 4e-06, + "litellm_provider": "mistral", + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 1.2e-05, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "mistral/mistral-large-2407": { + "input_cost_per_token": 3e-06, + "litellm_provider": "mistral", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 9e-06, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "mistral/mistral-large-2411": { + "input_cost_per_token": 2e-06, + "litellm_provider": "mistral", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 6e-06, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "mistral/mistral-large-latest": { + "input_cost_per_token": 2e-06, + "litellm_provider": "mistral", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 6e-06, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "mistral/mistral-medium": { + "input_cost_per_token": 2.7e-06, + "litellm_provider": "mistral", + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 8.1e-06, + "supports_assistant_prefill": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "mistral/mistral-medium-2312": { + "input_cost_per_token": 2.7e-06, + "litellm_provider": "mistral", + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 8.1e-06, + "supports_assistant_prefill": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "mistral/mistral-medium-2505": { + "input_cost_per_token": 4e-07, + "litellm_provider": "mistral", + "max_input_tokens": 131072, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 2e-06, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "mistral/mistral-medium-latest": { + "input_cost_per_token": 4e-07, + "litellm_provider": "mistral", + "max_input_tokens": 131072, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 2e-06, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "mistral/mistral-small": { + "input_cost_per_token": 1e-07, + "litellm_provider": "mistral", + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 3e-07, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "mistral/mistral-small-latest": { + "input_cost_per_token": 1e-07, + "litellm_provider": "mistral", + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 3e-07, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "mistral/mistral-tiny": { + "input_cost_per_token": 2.5e-07, + "litellm_provider": "mistral", + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 2.5e-07, + "supports_assistant_prefill": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "mistral/open-codestral-mamba": { + "input_cost_per_token": 2.5e-07, + "litellm_provider": "mistral", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 2.5e-07, + "source": "https://mistral.ai/technology/", + "supports_assistant_prefill": true, + "supports_tool_choice": true + }, + "mistral/open-mistral-7b": { + "input_cost_per_token": 2.5e-07, + "litellm_provider": "mistral", + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 2.5e-07, + "supports_assistant_prefill": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "mistral/open-mistral-nemo": { + "input_cost_per_token": 3e-07, + "litellm_provider": "mistral", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 3e-07, + "source": "https://mistral.ai/technology/", + "supports_assistant_prefill": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "mistral/open-mistral-nemo-2407": { + "input_cost_per_token": 3e-07, + "litellm_provider": "mistral", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 3e-07, + "source": "https://mistral.ai/technology/", + "supports_assistant_prefill": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "mistral/open-mixtral-8x22b": { + "input_cost_per_token": 2e-06, + "litellm_provider": "mistral", + "max_input_tokens": 65336, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 6e-06, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "mistral/open-mixtral-8x7b": { + "input_cost_per_token": 7e-07, + "litellm_provider": "mistral", + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 7e-07, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "mistral/pixtral-12b-2409": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "mistral", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.5e-07, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "mistral/pixtral-large-2411": { + "input_cost_per_token": 2e-06, + "litellm_provider": "mistral", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 6e-06, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "mistral/pixtral-large-latest": { + "input_cost_per_token": 2e-06, + "litellm_provider": "mistral", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 6e-06, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "moonshot/kimi-k2-0711-preview": { + "cache_read_input_token_cost": 1.5e-07, + "input_cost_per_token": 6e-07, + "litellm_provider": "moonshot", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2.5e-06, + "source": "https://platform.moonshot.ai/docs/pricing/chat#generation-model-kimi-k2", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_web_search": true + }, + "moonshot/kimi-latest": { + "cache_read_input_token_cost": 1.5e-07, + "input_cost_per_token": 2e-06, + "litellm_provider": "moonshot", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 5e-06, + "source": "https://platform.moonshot.ai/docs/pricing", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "moonshot/kimi-latest-128k": { + "cache_read_input_token_cost": 1.5e-07, + "input_cost_per_token": 2e-06, + "litellm_provider": "moonshot", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 5e-06, + "source": "https://platform.moonshot.ai/docs/pricing", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "moonshot/kimi-latest-32k": { + "cache_read_input_token_cost": 1.5e-07, + "input_cost_per_token": 1e-06, + "litellm_provider": "moonshot", + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 3e-06, + "source": "https://platform.moonshot.ai/docs/pricing", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "moonshot/kimi-latest-8k": { + "cache_read_input_token_cost": 1.5e-07, + "input_cost_per_token": 2e-07, + "litellm_provider": "moonshot", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 2e-06, + "source": "https://platform.moonshot.ai/docs/pricing", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "moonshot/kimi-thinking-preview": { + "input_cost_per_token": 3e-05, + "litellm_provider": "moonshot", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 3e-05, + "source": "https://platform.moonshot.ai/docs/pricing", + "supports_vision": true + }, + "moonshot/moonshot-v1-128k": { + "input_cost_per_token": 2e-06, + "litellm_provider": "moonshot", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 5e-06, + "source": "https://platform.moonshot.ai/docs/pricing", + "supports_function_calling": true, + "supports_tool_choice": true + }, + "moonshot/moonshot-v1-128k-0430": { + "input_cost_per_token": 2e-06, + "litellm_provider": "moonshot", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 5e-06, + "source": "https://platform.moonshot.ai/docs/pricing", + "supports_function_calling": true, + "supports_tool_choice": true + }, + "moonshot/moonshot-v1-128k-vision-preview": { + "input_cost_per_token": 2e-06, + "litellm_provider": "moonshot", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 5e-06, + "source": "https://platform.moonshot.ai/docs/pricing", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "moonshot/moonshot-v1-32k": { + "input_cost_per_token": 1e-06, + "litellm_provider": "moonshot", + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 3e-06, + "source": "https://platform.moonshot.ai/docs/pricing", + "supports_function_calling": true, + "supports_tool_choice": true + }, + "moonshot/moonshot-v1-32k-0430": { + "input_cost_per_token": 1e-06, + "litellm_provider": "moonshot", + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 3e-06, + "source": "https://platform.moonshot.ai/docs/pricing", + "supports_function_calling": true, + "supports_tool_choice": true + }, + "moonshot/moonshot-v1-32k-vision-preview": { + "input_cost_per_token": 1e-06, + "litellm_provider": "moonshot", + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 3e-06, + "source": "https://platform.moonshot.ai/docs/pricing", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "moonshot/moonshot-v1-8k": { + "input_cost_per_token": 2e-07, + "litellm_provider": "moonshot", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 2e-06, + "source": "https://platform.moonshot.ai/docs/pricing", + "supports_function_calling": true, + "supports_tool_choice": true + }, + "moonshot/moonshot-v1-8k-0430": { + "input_cost_per_token": 2e-07, + "litellm_provider": "moonshot", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 2e-06, + "source": "https://platform.moonshot.ai/docs/pricing", + "supports_function_calling": true, + "supports_tool_choice": true + }, + "moonshot/moonshot-v1-8k-vision-preview": { + "input_cost_per_token": 2e-07, + "litellm_provider": "moonshot", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 2e-06, + "source": "https://platform.moonshot.ai/docs/pricing", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "moonshot/moonshot-v1-auto": { + "input_cost_per_token": 2e-06, + "litellm_provider": "moonshot", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 5e-06, + "source": "https://platform.moonshot.ai/docs/pricing", + "supports_function_calling": true, + "supports_tool_choice": true + }, + "morph/morph-v3-fast": { + "input_cost_per_token": 8e-07, + "litellm_provider": "morph", + "max_input_tokens": 16000, + "max_output_tokens": 16000, + "max_tokens": 16000, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "supports_function_calling": false, + "supports_parallel_function_calling": false, + "supports_system_messages": true, + "supports_tool_choice": false, + "supports_vision": false + }, + "morph/morph-v3-large": { + "input_cost_per_token": 9e-07, + "litellm_provider": "morph", + "max_input_tokens": 16000, + "max_output_tokens": 16000, + "max_tokens": 16000, + "mode": "chat", + "output_cost_per_token": 1.9e-06, + "supports_function_calling": false, + "supports_parallel_function_calling": false, + "supports_system_messages": true, + "supports_tool_choice": false, + "supports_vision": false + }, + "multimodalembedding": { + "input_cost_per_character": 2e-07, + "input_cost_per_image": 0.0001, + "input_cost_per_token": 8e-07, + "input_cost_per_video_per_second": 0.0005, + "input_cost_per_video_per_second_above_15s_interval": 0.002, + "input_cost_per_video_per_second_above_8s_interval": 0.001, + "litellm_provider": "vertex_ai-embedding-models", + "max_input_tokens": 2048, + "max_tokens": 2048, + "mode": "embedding", + "output_cost_per_token": 0, + "output_vector_size": 768, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models", + "supported_endpoints": [ + "/v1/embeddings" + ], + "supported_modalities": [ + "text", + "image", + "video" + ] + }, + "multimodalembedding@001": { + "input_cost_per_character": 2e-07, + "input_cost_per_image": 0.0001, + "input_cost_per_token": 8e-07, + "input_cost_per_video_per_second": 0.0005, + "input_cost_per_video_per_second_above_15s_interval": 0.002, + "input_cost_per_video_per_second_above_8s_interval": 0.001, + "litellm_provider": "vertex_ai-embedding-models", + "max_input_tokens": 2048, + "max_tokens": 2048, + "mode": "embedding", + "output_cost_per_token": 0, + "output_vector_size": 768, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models", + "supported_endpoints": [ + "/v1/embeddings" + ], + "supported_modalities": [ + "text", + "image", + "video" + ] + }, + "nscale/Qwen/QwQ-32B": { + "input_cost_per_token": 1.8e-07, + "litellm_provider": "nscale", + "mode": "chat", + "output_cost_per_token": 2e-07, + "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" + }, + "nscale/Qwen/Qwen2.5-Coder-32B-Instruct": { + "input_cost_per_token": 6e-08, + "litellm_provider": "nscale", + "mode": "chat", + "output_cost_per_token": 2e-07, + "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" + }, + "nscale/Qwen/Qwen2.5-Coder-3B-Instruct": { + "input_cost_per_token": 1e-08, + "litellm_provider": "nscale", + "mode": "chat", + "output_cost_per_token": 3e-08, + "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" + }, + "nscale/Qwen/Qwen2.5-Coder-7B-Instruct": { + "input_cost_per_token": 1e-08, + "litellm_provider": "nscale", + "mode": "chat", + "output_cost_per_token": 3e-08, + "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" + }, + "nscale/black-forest-labs/FLUX.1-schnell": { + "input_cost_per_pixel": 1.3e-09, + "litellm_provider": "nscale", + "mode": "image_generation", + "output_cost_per_pixel": 0.0, + "source": "https://docs.nscale.com/docs/inference/serverless-models/current#image-models", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "nscale/deepseek-ai/DeepSeek-R1-Distill-Llama-70B": { + "input_cost_per_token": 3.75e-07, + "litellm_provider": "nscale", + "metadata": { + "notes": "Pricing listed as $0.75/1M tokens total. Assumed 50/50 split for input/output." + }, + "mode": "chat", + "output_cost_per_token": 3.75e-07, + "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" + }, + "nscale/deepseek-ai/DeepSeek-R1-Distill-Llama-8B": { + "input_cost_per_token": 2.5e-08, + "litellm_provider": "nscale", + "metadata": { + "notes": "Pricing listed as $0.05/1M tokens total. Assumed 50/50 split for input/output." + }, + "mode": "chat", + "output_cost_per_token": 2.5e-08, + "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" + }, + "nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B": { + "input_cost_per_token": 9e-08, + "litellm_provider": "nscale", + "metadata": { + "notes": "Pricing listed as $0.18/1M tokens total. Assumed 50/50 split for input/output." + }, + "mode": "chat", + "output_cost_per_token": 9e-08, + "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" + }, + "nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B": { + "input_cost_per_token": 7e-08, + "litellm_provider": "nscale", + "metadata": { + "notes": "Pricing listed as $0.14/1M tokens total. Assumed 50/50 split for input/output." + }, + "mode": "chat", + "output_cost_per_token": 7e-08, + "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" + }, + "nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "nscale", + "metadata": { + "notes": "Pricing listed as $0.30/1M tokens total. Assumed 50/50 split for input/output." + }, + "mode": "chat", + "output_cost_per_token": 1.5e-07, + "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" + }, + "nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B": { + "input_cost_per_token": 2e-07, + "litellm_provider": "nscale", + "metadata": { + "notes": "Pricing listed as $0.40/1M tokens total. Assumed 50/50 split for input/output." + }, + "mode": "chat", + "output_cost_per_token": 2e-07, + "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" + }, + "nscale/meta-llama/Llama-3.1-8B-Instruct": { + "input_cost_per_token": 3e-08, + "litellm_provider": "nscale", + "metadata": { + "notes": "Pricing listed as $0.06/1M tokens total. Assumed 50/50 split for input/output." + }, + "mode": "chat", + "output_cost_per_token": 3e-08, + "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" + }, + "nscale/meta-llama/Llama-3.3-70B-Instruct": { + "input_cost_per_token": 2e-07, + "litellm_provider": "nscale", + "metadata": { + "notes": "Pricing listed as $0.40/1M tokens total. Assumed 50/50 split for input/output." + }, + "mode": "chat", + "output_cost_per_token": 2e-07, + "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" + }, + "nscale/meta-llama/Llama-4-Scout-17B-16E-Instruct": { + "input_cost_per_token": 9e-08, + "litellm_provider": "nscale", + "mode": "chat", + "output_cost_per_token": 2.9e-07, + "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" + }, + "nscale/mistralai/mixtral-8x22b-instruct-v0.1": { + "input_cost_per_token": 6e-07, + "litellm_provider": "nscale", + "metadata": { + "notes": "Pricing listed as $1.20/1M tokens total. Assumed 50/50 split for input/output." + }, + "mode": "chat", + "output_cost_per_token": 6e-07, + "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" + }, + "nscale/stabilityai/stable-diffusion-xl-base-1.0": { + "input_cost_per_pixel": 3e-09, + "litellm_provider": "nscale", + "mode": "image_generation", + "output_cost_per_pixel": 0.0, + "source": "https://docs.nscale.com/docs/inference/serverless-models/current#image-models", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "o1": { + "cache_read_input_token_cost": 7.5e-06, + "input_cost_per_token": 1.5e-05, + "litellm_provider": "openai", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 6e-05, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "o1-2024-12-17": { + "cache_read_input_token_cost": 7.5e-06, + "input_cost_per_token": 1.5e-05, + "litellm_provider": "openai", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 6e-05, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "o1-mini": { + "cache_read_input_token_cost": 5.5e-07, + "input_cost_per_token": 1.1e-06, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_vision": true + }, + "o1-mini-2024-09-12": { + "cache_read_input_token_cost": 1.5e-06, + "input_cost_per_token": 3e-06, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 1.2e-05, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_vision": true + }, + "o1-preview": { + "cache_read_input_token_cost": 7.5e-06, + "input_cost_per_token": 1.5e-05, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 6e-05, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_vision": true + }, + "o1-preview-2024-09-12": { + "cache_read_input_token_cost": 7.5e-06, + "input_cost_per_token": 1.5e-05, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 6e-05, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_vision": true + }, + "o1-pro": { + "input_cost_per_token": 0.00015, + "input_cost_per_token_batches": 7.5e-05, + "litellm_provider": "openai", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "responses", + "output_cost_per_token": 0.0006, + "output_cost_per_token_batches": 0.0003, + "supported_endpoints": [ + "/v1/responses", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": false, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "o1-pro-2025-03-19": { + "input_cost_per_token": 0.00015, + "input_cost_per_token_batches": 7.5e-05, + "litellm_provider": "openai", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "responses", + "output_cost_per_token": 0.0006, + "output_cost_per_token_batches": 0.0003, + "supported_endpoints": [ + "/v1/responses", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": false, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "o3": { "cache_read_input_token_cost": 5e-07, - "cache_creation_input_token_cost": 0.0, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "oci/meta.llama-4-maverick-17b-128e-instruct-fp8": { - "max_tokens": 512000, - "max_input_tokens": 512000, - "max_output_tokens": 4000, - "input_cost_per_token": 7.2e-07, - "output_cost_per_token": 7.2e-07, - "litellm_provider": "oci", + "input_cost_per_token": 2e-06, + "litellm_provider": "openai", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, "mode": "chat", + "output_cost_per_token": 8e-06, + "supported_endpoints": [ + "/v1/responses", + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], "supports_function_calling": true, - "supports_response_schema": false, - "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing" + "supports_parallel_function_calling": false, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true }, - "oci/meta.llama-4-scout-17b-16e-instruct": { - "max_tokens": 192000, - "max_input_tokens": 192000, - "max_output_tokens": 4000, - "input_cost_per_token": 7.2e-07, - "output_cost_per_token": 7.2e-07, - "litellm_provider": "oci", + "o3-2025-04-16": { + "cache_read_input_token_cost": 5e-07, + "input_cost_per_token": 2e-06, + "litellm_provider": "openai", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, "mode": "chat", + "output_cost_per_token": 8e-06, + "supported_endpoints": [ + "/v1/responses", + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], "supports_function_calling": true, - "supports_response_schema": false, - "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing" + "supports_parallel_function_calling": false, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true }, - "oci/meta.llama-3.3-70b-instruct": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 4000, - "input_cost_per_token": 7.2e-07, - "output_cost_per_token": 7.2e-07, - "litellm_provider": "oci", - "mode": "chat", + "o3-deep-research": { + "cache_read_input_token_cost": 2.5e-06, + "input_cost_per_token": 1e-05, + "input_cost_per_token_batches": 5e-06, + "litellm_provider": "openai", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "responses", + "output_cost_per_token": 4e-05, + "output_cost_per_token_batches": 2e-05, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], "supports_function_calling": true, - "supports_response_schema": false, - "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing" + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true }, - "oci/meta.llama-3.2-90b-vision-instruct": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 4000, - "input_cost_per_token": 2.0e-06, - "output_cost_per_token": 2.0e-06, - "litellm_provider": "oci", - "mode": "chat", + "o3-deep-research-2025-06-26": { + "cache_read_input_token_cost": 2.5e-06, + "input_cost_per_token": 1e-05, + "input_cost_per_token_batches": 5e-06, + "litellm_provider": "openai", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "responses", + "output_cost_per_token": 4e-05, + "output_cost_per_token_batches": 2e-05, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], "supports_function_calling": true, - "supports_response_schema": false, - "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing" + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "o3-mini": { + "cache_read_input_token_cost": 5.5e-07, + "input_cost_per_token": 1.1e-06, + "litellm_provider": "openai", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "supports_function_calling": true, + "supports_parallel_function_calling": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "o3-mini-2025-01-31": { + "cache_read_input_token_cost": 5.5e-07, + "input_cost_per_token": 1.1e-06, + "litellm_provider": "openai", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "supports_function_calling": true, + "supports_parallel_function_calling": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "o3-pro": { + "input_cost_per_token": 2e-05, + "input_cost_per_token_batches": 1e-05, + "litellm_provider": "openai", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "responses", + "output_cost_per_token": 8e-05, + "output_cost_per_token_batches": 4e-05, + "supported_endpoints": [ + "/v1/responses", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": false, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "o3-pro-2025-06-10": { + "input_cost_per_token": 2e-05, + "input_cost_per_token_batches": 1e-05, + "litellm_provider": "openai", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "responses", + "output_cost_per_token": 8e-05, + "output_cost_per_token_batches": 4e-05, + "supported_endpoints": [ + "/v1/responses", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": false, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "o4-mini": { + "cache_read_input_token_cost": 2.75e-07, + "input_cost_per_token": 1.1e-06, + "litellm_provider": "openai", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "supports_function_calling": true, + "supports_parallel_function_calling": false, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "o4-mini-2025-04-16": { + "cache_read_input_token_cost": 2.75e-07, + "input_cost_per_token": 1.1e-06, + "litellm_provider": "openai", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "supports_function_calling": true, + "supports_parallel_function_calling": false, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "o4-mini-deep-research": { + "cache_read_input_token_cost": 5e-07, + "input_cost_per_token": 2e-06, + "input_cost_per_token_batches": 1e-06, + "litellm_provider": "openai", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "responses", + "output_cost_per_token": 8e-06, + "output_cost_per_token_batches": 4e-06, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "o4-mini-deep-research-2025-06-26": { + "cache_read_input_token_cost": 5e-07, + "input_cost_per_token": 2e-06, + "input_cost_per_token_batches": 1e-06, + "litellm_provider": "openai", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "responses", + "output_cost_per_token": 8e-06, + "output_cost_per_token_batches": 4e-06, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true }, "oci/meta.llama-3.1-405b-instruct": { - "max_tokens": 128000, + "input_cost_per_token": 1.068e-05, + "litellm_provider": "oci", "max_input_tokens": 128000, "max_output_tokens": 4000, - "input_cost_per_token": 1.068e-05, - "output_cost_per_token": 1.068e-05, - "litellm_provider": "oci", - "mode": "chat", - "supports_function_calling": true, - "supports_response_schema": false, - "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing" - }, - - "oci/xai.grok-4": { "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "input_cost_per_token": 3.0e-06, - "output_cost_per_token": 1.5e-07, - "litellm_provider": "oci", "mode": "chat", + "output_cost_per_token": 1.068e-05, + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, - "supports_response_schema": false, - "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing" + "supports_response_schema": false + }, + "oci/meta.llama-3.2-90b-vision-instruct": { + "input_cost_per_token": 2e-06, + "litellm_provider": "oci", + "max_input_tokens": 128000, + "max_output_tokens": 4000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2e-06, + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", + "supports_function_calling": true, + "supports_response_schema": false + }, + "oci/meta.llama-3.3-70b-instruct": { + "input_cost_per_token": 7.2e-07, + "litellm_provider": "oci", + "max_input_tokens": 128000, + "max_output_tokens": 4000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 7.2e-07, + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", + "supports_function_calling": true, + "supports_response_schema": false + }, + "oci/meta.llama-4-maverick-17b-128e-instruct-fp8": { + "input_cost_per_token": 7.2e-07, + "litellm_provider": "oci", + "max_input_tokens": 512000, + "max_output_tokens": 4000, + "max_tokens": 512000, + "mode": "chat", + "output_cost_per_token": 7.2e-07, + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", + "supports_function_calling": true, + "supports_response_schema": false + }, + "oci/meta.llama-4-scout-17b-16e-instruct": { + "input_cost_per_token": 7.2e-07, + "litellm_provider": "oci", + "max_input_tokens": 192000, + "max_output_tokens": 4000, + "max_tokens": 192000, + "mode": "chat", + "output_cost_per_token": 7.2e-07, + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", + "supports_function_calling": true, + "supports_response_schema": false }, "oci/xai.grok-3": { - "max_tokens": 131072, + "input_cost_per_token": 3e-06, + "litellm_provider": "oci", "max_input_tokens": 131072, "max_output_tokens": 131072, - "input_cost_per_token": 3.0e-06, + "max_tokens": 131072, + "mode": "chat", "output_cost_per_token": 1.5e-07, - "litellm_provider": "oci", - "mode": "chat", + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, - "supports_response_schema": false, - "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing" - }, - "oci/xai.grok-3-mini": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 3.0e-07, - "output_cost_per_token": 5.0e-07, - "litellm_provider": "oci", - "mode": "chat", - "supports_function_calling": true, - "supports_response_schema": false, - "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing" + "supports_response_schema": false }, "oci/xai.grok-3-fast": { - "max_tokens": 131072, + "input_cost_per_token": 5e-06, + "litellm_provider": "oci", "max_input_tokens": 131072, "max_output_tokens": 131072, - "input_cost_per_token": 5.0e-06, - "output_cost_per_token": 2.5e-05, - "litellm_provider": "oci", + "max_tokens": 131072, "mode": "chat", + "output_cost_per_token": 2.5e-05, + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, - "supports_response_schema": false, - "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing" + "supports_response_schema": false + }, + "oci/xai.grok-3-mini": { + "input_cost_per_token": 3e-07, + "litellm_provider": "oci", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 5e-07, + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", + "supports_function_calling": true, + "supports_response_schema": false }, "oci/xai.grok-3-mini-fast": { - "max_tokens": 131072, + "input_cost_per_token": 6e-07, + "litellm_provider": "oci", "max_input_tokens": 131072, "max_output_tokens": 131072, - "input_cost_per_token": 6.0e-07, - "output_cost_per_token": 4.0e-06, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4e-06, + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", + "supports_function_calling": true, + "supports_response_schema": false + }, + "oci/xai.grok-4": { + "input_cost_per_token": 3e-06, "litellm_provider": "oci", - "mode": "chat", - "supports_function_calling": true, - "supports_response_schema": false, - "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing" - }, - "aiml/flux/kontext-pro/text-to-image":{ - "output_cost_per_image": 0.042, - "litellm_provider": "aiml", - "mode": "image_generation", - "supported_endpoints": [ - "/v1/images/generations" - ], - "source": "https://docs.aimlapi.com/", - "metadata": { - "notes": "Flux Pro v1.1 - Enhanced version with improved capabilities and 6x faster inference speed" - } - - }, - "aiml/flux/kontext-max/text-to-image": { - "output_cost_per_image": 0.084, - "litellm_provider": "aiml", - "mode": "image_generation", - "supported_endpoints": [ - "/v1/images/generations" - ], - "source": "https://docs.aimlapi.com/", - "metadata": { - "notes": "Flux Pro v1.1 - Enhanced version with improved capabilities and 6x faster inference speed" - } - }, - "aiml/flux-pro/v1.1-ultra": { - "output_cost_per_image": 0.063, - "litellm_provider": "aiml", - "mode": "image_generation", - "supported_endpoints": [ - "/v1/images/generations" - ] - }, - "aiml/flux-pro/v1.1": { - "output_cost_per_image": 0.042, - "litellm_provider": "aiml", - "mode": "image_generation", - "supported_endpoints": [ - "/v1/images/generations" - ] - }, - "aiml/flux-realism": { - "output_cost_per_image": 0.037, - "litellm_provider": "aiml", - "mode": "image_generation", - "supported_endpoints": [ - "/v1/images/generations" - ], - "source": "https://docs.aimlapi.com/", - "metadata": { - "notes": "Flux Pro - Professional-grade image generation model" - } - }, - "aiml/flux/schnell": { - "output_cost_per_image": 0.003, - "litellm_provider": "aiml", - "mode": "image_generation", - "supported_endpoints": [ - "/v1/images/generations" - ], - "source": "https://docs.aimlapi.com/", - "metadata": { - "notes": "Flux Schnell - Fast generation model optimized for speed" - } - }, - "aiml/flux/dev": { - "output_cost_per_image": 0.026, - "litellm_provider": "aiml", - "mode": "image_generation", - "supported_endpoints": [ - "/v1/images/generations" - ], - "source": "https://docs.aimlapi.com/", - "metadata": { - "notes": "Flux Dev - Development version optimized for experimentation" - } - }, - "aiml/flux-pro": { - "output_cost_per_image": 0.053, - "litellm_provider": "aiml", - "mode": "image_generation", - "supported_endpoints": [ - "/v1/images/generations" - ], - "source": "https://docs.aimlapi.com/", - "metadata": { - "notes": "Flux Dev - Development version optimized for experimentation" - } - }, - "aiml/dall-e-3": { - "output_cost_per_image": 0.042, - "litellm_provider": "aiml", - "mode": "image_generation", - "supported_endpoints": [ - "/v1/images/generations" - ], - "source": "https://docs.aimlapi.com/", - "metadata": { - "notes": "DALL-E 3 via AI/ML API - High-quality text-to-image generation" - } - }, - "aiml/dall-e-2": { - "output_cost_per_image": 0.021, - "litellm_provider": "aiml", - "mode": "image_generation", - "supported_endpoints": [ - "/v1/images/generations" - ], - "source": "https://docs.aimlapi.com/", - "metadata": { - "notes": "DALL-E 2 via AI/ML API - Reliable text-to-image generation" - } - }, - "doubao-embedding-large": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "output_vector_size": 2048, - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "volcengine", - "mode": "embedding", - "metadata": { - "notes": "Volcengine Doubao embedding model - large version with 2048 dimensions" - } - }, - "doubao-embedding-large-text-250515": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "output_vector_size": 2048, - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "volcengine", - "mode": "embedding", - "metadata": { - "notes": "Volcengine Doubao embedding model - text-250515 version with 2048 dimensions" - } - }, - "doubao-embedding-large-text-240915": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "output_vector_size": 4096, - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "volcengine", - "mode": "embedding", - "metadata": { - "notes": "Volcengine Doubao embedding model - text-240915 version with 4096 dimensions" - } - }, - "doubao-embedding": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "output_vector_size": 2560, - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "volcengine", - "mode": "embedding", - "metadata": { - "notes": "Volcengine Doubao embedding model - standard version with 2560 dimensions" - } - }, - "doubao-embedding-text-240715": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "output_vector_size": 2560, - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "volcengine", - "mode": "embedding", - "metadata": { - "notes": "Volcengine Doubao embedding model - text-240715 version with 2560 dimensions" - } - }, - "ovhcloud/Qwen2.5-VL-72B-Instruct": { - "max_tokens": 32000, - "max_input_tokens": 32000, - "max_output_tokens": 32000, - "input_cost_per_token": 9.1e-07, - "output_cost_per_token": 9.1e-07, - "litellm_provider": "ovhcloud", - "mode": "chat", - "supports_function_calling": false, - "supports_response_schema": true, - "supports_tool_choice": false, - "supports_vision": true, - "source": "https://endpoints.ai.cloud.ovh.net/models/qwen2-5-vl-72b-instruct" - }, - "ovhcloud/llava-v1.6-mistral-7b-hf": { - "max_tokens": 32000, - "max_input_tokens": 32000, - "max_output_tokens": 32000, - "input_cost_per_token": 2.9e-07, - "output_cost_per_token": 2.9e-07, - "litellm_provider": "ovhcloud", - "mode": "chat", - "supports_function_calling": false, - "supports_response_schema": true, - "supports_tool_choice": false, - "supports_vision": true, - "source": "https://endpoints.ai.cloud.ovh.net/models/llava-next-mistral-7b" - }, - "ovhcloud/gpt-oss-120b": { - "max_tokens": 131000, - "max_input_tokens": 131000, - "max_output_tokens": 131000, - "input_cost_per_token": 8e-08, - "output_cost_per_token": 4e-07, - "litellm_provider": "ovhcloud", - "mode": "chat", - "supports_function_calling": false, - "supports_response_schema": true, - "supports_tool_choice": false, - "supports_reasoning": true, - "source": "https://endpoints.ai.cloud.ovh.net/models/gpt-oss-120b" - }, - "ovhcloud/Meta-Llama-3_3-70B-Instruct": { - "max_tokens": 131000, - "max_input_tokens": 131000, - "max_output_tokens": 131000, - "input_cost_per_token": 6.7e-07, - "output_cost_per_token": 6.7e-07, - "litellm_provider": "ovhcloud", - "mode": "chat", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "source": "https://endpoints.ai.cloud.ovh.net/models/meta-llama-3-3-70b-instruct" - }, - "ovhcloud/Qwen2.5-Coder-32B-Instruct": { - "max_tokens": 32000, - "max_input_tokens": 32000, - "max_output_tokens": 32000, - "input_cost_per_token": 8.7e-07, - "output_cost_per_token": 8.7e-07, - "litellm_provider": "ovhcloud", - "mode": "chat", - "supports_function_calling": false, - "supports_response_schema": true, - "supports_tool_choice": false, - "source": "https://endpoints.ai.cloud.ovh.net/models/qwen2-5-coder-32b-instruct" - }, - "ovhcloud/Mixtral-8x7B-Instruct-v0.1": { - "max_tokens": 32000, - "max_input_tokens": 32000, - "max_output_tokens": 32000, - "input_cost_per_token": 6.3e-07, - "output_cost_per_token": 6.3e-07, - "litellm_provider": "ovhcloud", - "mode": "chat", - "supports_function_calling": false, - "supports_response_schema": true, - "supports_tool_choice": false, - "source": "https://endpoints.ai.cloud.ovh.net/models/mixtral-8x7b-instruct-v0-1" - }, - "ovhcloud/Meta-Llama-3_1-70B-Instruct": { - "max_tokens": 131000, - "max_input_tokens": 131000, - "max_output_tokens": 131000, - "input_cost_per_token": 6.7e-07, - "output_cost_per_token": 6.7e-07, - "litellm_provider": "ovhcloud", - "mode": "chat", - "supports_function_calling": false, - "supports_response_schema": false, - "supports_tool_choice": false, - "source": "https://endpoints.ai.cloud.ovh.net/models/meta-llama-3-1-70b-instruct" - }, - "ovhcloud/Mistral-Small-3.2-24B-Instruct-2506": { - "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, - "input_cost_per_token": 9e-08, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.5e-07, + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", + "supports_function_calling": true, + "supports_response_schema": false + }, + "ollama/codegeex4": { + "input_cost_per_token": 0.0, + "litellm_provider": "ollama", + "max_input_tokens": 32768, + "max_output_tokens": 8192, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 0.0, + "supports_function_calling": false + }, + "ollama/codegemma": { + "input_cost_per_token": 0.0, + "litellm_provider": "ollama", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "completion", + "output_cost_per_token": 0.0 + }, + "ollama/codellama": { + "input_cost_per_token": 0.0, + "litellm_provider": "ollama", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "completion", + "output_cost_per_token": 0.0 + }, + "ollama/deepseek-coder-v2-base": { + "input_cost_per_token": 0.0, + "litellm_provider": "ollama", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "completion", + "output_cost_per_token": 0.0, + "supports_function_calling": true + }, + "ollama/deepseek-coder-v2-instruct": { + "input_cost_per_token": 0.0, + "litellm_provider": "ollama", + "max_input_tokens": 32768, + "max_output_tokens": 8192, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 0.0, + "supports_function_calling": true + }, + "ollama/deepseek-coder-v2-lite-base": { + "input_cost_per_token": 0.0, + "litellm_provider": "ollama", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "completion", + "output_cost_per_token": 0.0, + "supports_function_calling": true + }, + "ollama/deepseek-coder-v2-lite-instruct": { + "input_cost_per_token": 0.0, + "litellm_provider": "ollama", + "max_input_tokens": 32768, + "max_output_tokens": 8192, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 0.0, + "supports_function_calling": true + }, + "ollama/internlm2_5-20b-chat": { + "input_cost_per_token": 0.0, + "litellm_provider": "ollama", + "max_input_tokens": 32768, + "max_output_tokens": 8192, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 0.0, + "supports_function_calling": true + }, + "ollama/llama2": { + "input_cost_per_token": 0.0, + "litellm_provider": "ollama", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.0 + }, + "ollama/llama2-uncensored": { + "input_cost_per_token": 0.0, + "litellm_provider": "ollama", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "completion", + "output_cost_per_token": 0.0 + }, + "ollama/llama2:13b": { + "input_cost_per_token": 0.0, + "litellm_provider": "ollama", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.0 + }, + "ollama/llama2:70b": { + "input_cost_per_token": 0.0, + "litellm_provider": "ollama", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.0 + }, + "ollama/llama2:7b": { + "input_cost_per_token": 0.0, + "litellm_provider": "ollama", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.0 + }, + "ollama/llama3": { + "input_cost_per_token": 0.0, + "litellm_provider": "ollama", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.0 + }, + "ollama/llama3.1": { + "input_cost_per_token": 0.0, + "litellm_provider": "ollama", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 0.0, + "supports_function_calling": true + }, + "ollama/llama3:70b": { + "input_cost_per_token": 0.0, + "litellm_provider": "ollama", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.0 + }, + "ollama/llama3:8b": { + "input_cost_per_token": 0.0, + "litellm_provider": "ollama", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.0 + }, + "ollama/mistral": { + "input_cost_per_token": 0.0, + "litellm_provider": "ollama", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "completion", + "output_cost_per_token": 0.0, + "supports_function_calling": true + }, + "ollama/mistral-7B-Instruct-v0.1": { + "input_cost_per_token": 0.0, + "litellm_provider": "ollama", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.0, + "supports_function_calling": true + }, + "ollama/mistral-7B-Instruct-v0.2": { + "input_cost_per_token": 0.0, + "litellm_provider": "ollama", + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 0.0, + "supports_function_calling": true + }, + "ollama/mistral-large-instruct-2407": { + "input_cost_per_token": 0.0, + "litellm_provider": "ollama", + "max_input_tokens": 65536, + "max_output_tokens": 8192, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 0.0, + "supports_function_calling": true + }, + "ollama/mixtral-8x22B-Instruct-v0.1": { + "input_cost_per_token": 0.0, + "litellm_provider": "ollama", + "max_input_tokens": 65536, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 0.0, + "supports_function_calling": true + }, + "ollama/mixtral-8x7B-Instruct-v0.1": { + "input_cost_per_token": 0.0, + "litellm_provider": "ollama", + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 0.0, + "supports_function_calling": true + }, + "ollama/orca-mini": { + "input_cost_per_token": 0.0, + "litellm_provider": "ollama", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "completion", + "output_cost_per_token": 0.0 + }, + "ollama/vicuna": { + "input_cost_per_token": 0.0, + "litellm_provider": "ollama", + "max_input_tokens": 2048, + "max_output_tokens": 2048, + "max_tokens": 2048, + "mode": "completion", + "output_cost_per_token": 0.0 + }, + "omni-moderation-2024-09-26": { + "input_cost_per_token": 0.0, + "litellm_provider": "openai", + "max_input_tokens": 32768, + "max_output_tokens": 0, + "max_tokens": 32768, + "mode": "moderation", + "output_cost_per_token": 0.0 + }, + "omni-moderation-latest": { + "input_cost_per_token": 0.0, + "litellm_provider": "openai", + "max_input_tokens": 32768, + "max_output_tokens": 0, + "max_tokens": 32768, + "mode": "moderation", + "output_cost_per_token": 0.0 + }, + "omni-moderation-latest-intents": { + "input_cost_per_token": 0.0, + "litellm_provider": "openai", + "max_input_tokens": 32768, + "max_output_tokens": 0, + "max_tokens": 32768, + "mode": "moderation", + "output_cost_per_token": 0.0 + }, + "openai.gpt-oss-120b-1:0": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 6e-07, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "openai.gpt-oss-20b-1:0": { + "input_cost_per_token": 7e-08, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 3e-07, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "openrouter/anthropic/claude-2": { + "input_cost_per_token": 1.102e-05, + "litellm_provider": "openrouter", + "max_output_tokens": 8191, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 3.268e-05, + "supports_tool_choice": true + }, + "openrouter/anthropic/claude-3-5-haiku": { + "input_cost_per_token": 1e-06, + "litellm_provider": "openrouter", + "max_tokens": 200000, + "mode": "chat", + "output_cost_per_token": 5e-06, + "supports_function_calling": true, + "supports_tool_choice": true + }, + "openrouter/anthropic/claude-3-5-haiku-20241022": { + "input_cost_per_token": 1e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 5e-06, + "supports_function_calling": true, + "supports_tool_choice": true, + "tool_use_system_prompt_tokens": 264 + }, + "openrouter/anthropic/claude-3-haiku": { + "input_cost_per_image": 0.0004, + "input_cost_per_token": 2.5e-07, + "litellm_provider": "openrouter", + "max_tokens": 200000, + "mode": "chat", + "output_cost_per_token": 1.25e-06, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "openrouter/anthropic/claude-3-haiku-20240307": { + "input_cost_per_token": 2.5e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.25e-06, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 264 + }, + "openrouter/anthropic/claude-3-opus": { + "input_cost_per_token": 1.5e-05, + "litellm_provider": "openrouter", + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 7.5e-05, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 395 + }, + "openrouter/anthropic/claude-3-sonnet": { + "input_cost_per_image": 0.0048, + "input_cost_per_token": 3e-06, + "litellm_provider": "openrouter", + "max_tokens": 200000, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "openrouter/anthropic/claude-3.5-sonnet": { + "input_cost_per_token": 3e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159 + }, + "openrouter/anthropic/claude-3.5-sonnet:beta": { + "input_cost_per_token": 3e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159 + }, + "openrouter/anthropic/claude-3.7-sonnet": { + "input_cost_per_image": 0.0048, + "input_cost_per_token": 3e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 200000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159 + }, + "openrouter/anthropic/claude-3.7-sonnet:beta": { + "input_cost_per_image": 0.0048, + "input_cost_per_token": 3e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 200000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159 + }, + "openrouter/anthropic/claude-instant-v1": { + "input_cost_per_token": 1.63e-06, + "litellm_provider": "openrouter", + "max_output_tokens": 8191, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 5.51e-06, + "supports_tool_choice": true + }, + "openrouter/anthropic/claude-opus-4": { + "input_cost_per_image": 0.0048, + "input_cost_per_token": 1.5e-05, + "litellm_provider": "openrouter", + "max_input_tokens": 200000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 7.5e-05, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159 + }, + "openrouter/anthropic/claude-opus-4.1": { + "input_cost_per_image": 0.0048, + "input_cost_per_token": 1.5e-05, + "litellm_provider": "openrouter", + "max_input_tokens": 200000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 7.5e-05, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159 + }, + "openrouter/anthropic/claude-sonnet-4": { + "input_cost_per_image": 0.0048, + "input_cost_per_token": 3e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159 + }, + "openrouter/bytedance/ui-tars-1.5-7b": { + "input_cost_per_token": 1e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 2048, + "max_tokens": 2048, + "mode": "chat", + "output_cost_per_token": 2e-07, + "source": "https://openrouter.ai/api/v1/models/bytedance/ui-tars-1.5-7b", + "supports_tool_choice": true + }, + "openrouter/cognitivecomputations/dolphin-mixtral-8x7b": { + "input_cost_per_token": 5e-07, + "litellm_provider": "openrouter", + "max_tokens": 32769, + "mode": "chat", + "output_cost_per_token": 5e-07, + "supports_tool_choice": true + }, + "openrouter/cohere/command-r-plus": { + "input_cost_per_token": 3e-06, + "litellm_provider": "openrouter", + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "supports_tool_choice": true + }, + "openrouter/databricks/dbrx-instruct": { + "input_cost_per_token": 6e-07, + "litellm_provider": "openrouter", + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 6e-07, + "supports_tool_choice": true + }, + "openrouter/deepseek/deepseek-chat": { + "input_cost_per_token": 1.4e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 65536, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", "output_cost_per_token": 2.8e-07, + "supports_prompt_caching": true, + "supports_tool_choice": true + }, + "openrouter/deepseek/deepseek-chat-v3-0324": { + "input_cost_per_token": 1.4e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 65536, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 2.8e-07, + "supports_prompt_caching": true, + "supports_tool_choice": true + }, + "openrouter/deepseek/deepseek-chat-v3.1": { + "input_cost_per_token": 2e-07, + "input_cost_per_token_cache_hit": 2e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 163840, + "max_output_tokens": 163840, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 8e-07, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "openrouter/deepseek/deepseek-coder": { + "input_cost_per_token": 1.4e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 66000, + "max_output_tokens": 4096, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 2.8e-07, + "supports_prompt_caching": true, + "supports_tool_choice": true + }, + "openrouter/deepseek/deepseek-r1": { + "input_cost_per_token": 5.5e-07, + "input_cost_per_token_cache_hit": 1.4e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 65336, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 2.19e-06, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "openrouter/deepseek/deepseek-r1-0528": { + "input_cost_per_token": 5e-07, + "input_cost_per_token_cache_hit": 1.4e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 65336, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 2.15e-06, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "openrouter/fireworks/firellava-13b": { + "input_cost_per_token": 2e-07, + "litellm_provider": "openrouter", + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 2e-07, + "supports_tool_choice": true + }, + "openrouter/google/gemini-2.0-flash-001": { + "input_cost_per_audio_token": 7e-07, + "input_cost_per_token": 1e-07, + "litellm_provider": "openrouter", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_token": 4e-07, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "openrouter/google/gemini-2.5-flash": { + "input_cost_per_audio_token": 7e-07, + "input_cost_per_token": 3e-07, + "litellm_provider": "openrouter", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_token": 2.5e-06, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "openrouter/google/gemini-2.5-pro": { + "input_cost_per_audio_token": 7e-07, + "input_cost_per_token": 1.25e-06, + "litellm_provider": "openrouter", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_token": 1e-05, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "openrouter/google/gemini-pro-1.5": { + "input_cost_per_image": 0.00265, + "input_cost_per_token": 2.5e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 7.5e-06, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "openrouter/google/gemini-pro-vision": { + "input_cost_per_image": 0.0025, + "input_cost_per_token": 1.25e-07, + "litellm_provider": "openrouter", + "max_tokens": 45875, + "mode": "chat", + "output_cost_per_token": 3.75e-07, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "openrouter/google/palm-2-chat-bison": { + "input_cost_per_token": 5e-07, + "litellm_provider": "openrouter", + "max_tokens": 25804, + "mode": "chat", + "output_cost_per_token": 5e-07, + "supports_tool_choice": true + }, + "openrouter/google/palm-2-codechat-bison": { + "input_cost_per_token": 5e-07, + "litellm_provider": "openrouter", + "max_tokens": 20070, + "mode": "chat", + "output_cost_per_token": 5e-07, + "supports_tool_choice": true + }, + "openrouter/gryphe/mythomax-l2-13b": { + "input_cost_per_token": 1.875e-06, + "litellm_provider": "openrouter", + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.875e-06, + "supports_tool_choice": true + }, + "openrouter/jondurbin/airoboros-l2-70b-2.1": { + "input_cost_per_token": 1.3875e-05, + "litellm_provider": "openrouter", + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.3875e-05, + "supports_tool_choice": true + }, + "openrouter/mancer/weaver": { + "input_cost_per_token": 5.625e-06, + "litellm_provider": "openrouter", + "max_tokens": 8000, + "mode": "chat", + "output_cost_per_token": 5.625e-06, + "supports_tool_choice": true + }, + "openrouter/meta-llama/codellama-34b-instruct": { + "input_cost_per_token": 5e-07, + "litellm_provider": "openrouter", + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 5e-07, + "supports_tool_choice": true + }, + "openrouter/meta-llama/llama-2-13b-chat": { + "input_cost_per_token": 2e-07, + "litellm_provider": "openrouter", + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 2e-07, + "supports_tool_choice": true + }, + "openrouter/meta-llama/llama-2-70b-chat": { + "input_cost_per_token": 1.5e-06, + "litellm_provider": "openrouter", + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.5e-06, + "supports_tool_choice": true + }, + "openrouter/meta-llama/llama-3-70b-instruct": { + "input_cost_per_token": 5.9e-07, + "litellm_provider": "openrouter", + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 7.9e-07, + "supports_tool_choice": true + }, + "openrouter/meta-llama/llama-3-70b-instruct:nitro": { + "input_cost_per_token": 9e-07, + "litellm_provider": "openrouter", + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 9e-07, + "supports_tool_choice": true + }, + "openrouter/meta-llama/llama-3-8b-instruct:extended": { + "input_cost_per_token": 2.25e-07, + "litellm_provider": "openrouter", + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 2.25e-06, + "supports_tool_choice": true + }, + "openrouter/meta-llama/llama-3-8b-instruct:free": { + "input_cost_per_token": 0.0, + "litellm_provider": "openrouter", + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.0, + "supports_tool_choice": true + }, + "openrouter/microsoft/wizardlm-2-8x22b:nitro": { + "input_cost_per_token": 1e-06, + "litellm_provider": "openrouter", + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 1e-06, + "supports_tool_choice": true + }, + "openrouter/mistralai/mistral-7b-instruct": { + "input_cost_per_token": 1.3e-07, + "litellm_provider": "openrouter", + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.3e-07, + "supports_tool_choice": true + }, + "openrouter/mistralai/mistral-7b-instruct:free": { + "input_cost_per_token": 0.0, + "litellm_provider": "openrouter", + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.0, + "supports_tool_choice": true + }, + "openrouter/mistralai/mistral-large": { + "input_cost_per_token": 8e-06, + "litellm_provider": "openrouter", + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 2.4e-05, + "supports_tool_choice": true + }, + "openrouter/mistralai/mistral-small-3.1-24b-instruct": { + "input_cost_per_token": 1e-07, + "litellm_provider": "openrouter", + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 3e-07, + "supports_tool_choice": true + }, + "openrouter/mistralai/mistral-small-3.2-24b-instruct": { + "input_cost_per_token": 1e-07, + "litellm_provider": "openrouter", + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 3e-07, + "supports_tool_choice": true + }, + "openrouter/mistralai/mixtral-8x22b-instruct": { + "input_cost_per_token": 6.5e-07, + "litellm_provider": "openrouter", + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 6.5e-07, + "supports_tool_choice": true + }, + "openrouter/nousresearch/nous-hermes-llama2-13b": { + "input_cost_per_token": 2e-07, + "litellm_provider": "openrouter", + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 2e-07, + "supports_tool_choice": true + }, + "openrouter/openai/gpt-3.5-turbo": { + "input_cost_per_token": 1.5e-06, + "litellm_provider": "openrouter", + "max_tokens": 4095, + "mode": "chat", + "output_cost_per_token": 2e-06, + "supports_tool_choice": true + }, + "openrouter/openai/gpt-3.5-turbo-16k": { + "input_cost_per_token": 3e-06, + "litellm_provider": "openrouter", + "max_tokens": 16383, + "mode": "chat", + "output_cost_per_token": 4e-06, + "supports_tool_choice": true + }, + "openrouter/openai/gpt-4": { + "input_cost_per_token": 3e-05, + "litellm_provider": "openrouter", + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 6e-05, + "supports_tool_choice": true + }, + "openrouter/openai/gpt-4-vision-preview": { + "input_cost_per_image": 0.01445, + "input_cost_per_token": 1e-05, + "litellm_provider": "openrouter", + "max_tokens": 130000, + "mode": "chat", + "output_cost_per_token": 3e-05, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "openrouter/openai/gpt-4.1": { + "cache_read_input_token_cost": 5e-07, + "input_cost_per_token": 2e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 8e-06, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "openrouter/openai/gpt-4.1-2025-04-14": { + "cache_read_input_token_cost": 5e-07, + "input_cost_per_token": 2e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 8e-06, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "openrouter/openai/gpt-4.1-mini": { + "cache_read_input_token_cost": 1e-07, + "input_cost_per_token": 4e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 1.6e-06, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "openrouter/openai/gpt-4.1-mini-2025-04-14": { + "cache_read_input_token_cost": 1e-07, + "input_cost_per_token": 4e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 1.6e-06, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "openrouter/openai/gpt-4.1-nano": { + "cache_read_input_token_cost": 2.5e-08, + "input_cost_per_token": 1e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 4e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "openrouter/openai/gpt-4.1-nano-2025-04-14": { + "cache_read_input_token_cost": 2.5e-08, + "input_cost_per_token": 1e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 4e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "openrouter/openai/gpt-4o": { + "input_cost_per_token": 2.5e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1e-05, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "openrouter/openai/gpt-4o-2024-05-13": { + "input_cost_per_token": 5e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "openrouter/openai/gpt-5-chat": { + "cache_read_input_token_cost": 1.25e-07, + "input_cost_per_token": 1.25e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_reasoning": true, + "supports_tool_choice": true + }, + "openrouter/openai/gpt-5-mini": { + "cache_read_input_token_cost": 2.5e-08, + "input_cost_per_token": 2.5e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2e-06, + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_reasoning": true, + "supports_tool_choice": true + }, + "openrouter/openai/gpt-5-nano": { + "cache_read_input_token_cost": 5e-09, + "input_cost_per_token": 5e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4e-07, + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_reasoning": true, + "supports_tool_choice": true + }, + "openrouter/openai/gpt-oss-120b": { + "input_cost_per_token": 1.8e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 8e-07, + "source": "https://openrouter.ai/openai/gpt-oss-120b", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "openrouter/openai/gpt-oss-20b": { + "input_cost_per_token": 1.8e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 8e-07, + "source": "https://openrouter.ai/openai/gpt-oss-20b", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "openrouter/openai/o1": { + "cache_read_input_token_cost": 7.5e-06, + "input_cost_per_token": 1.5e-05, + "litellm_provider": "openrouter", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 6e-05, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "openrouter/openai/o1-mini": { + "input_cost_per_token": 3e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 128000, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 1.2e-05, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "openrouter/openai/o1-mini-2024-09-12": { + "input_cost_per_token": 3e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 128000, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 1.2e-05, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "openrouter/openai/o1-preview": { + "input_cost_per_token": 1.5e-05, + "litellm_provider": "openrouter", + "max_input_tokens": 128000, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 6e-05, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "openrouter/openai/o1-preview-2024-09-12": { + "input_cost_per_token": 1.5e-05, + "litellm_provider": "openrouter", + "max_input_tokens": 128000, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 6e-05, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "openrouter/openai/o3-mini": { + "input_cost_per_token": 1.1e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 128000, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "openrouter/openai/o3-mini-high": { + "input_cost_per_token": 1.1e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 128000, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "openrouter/pygmalionai/mythalion-13b": { + "input_cost_per_token": 1.875e-06, + "litellm_provider": "openrouter", + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.875e-06, + "supports_tool_choice": true + }, + "openrouter/qwen/qwen-2.5-coder-32b-instruct": { + "input_cost_per_token": 1.8e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 33792, + "max_output_tokens": 33792, + "max_tokens": 33792, + "mode": "chat", + "output_cost_per_token": 1.8e-07, + "supports_tool_choice": true + }, + "openrouter/qwen/qwen-vl-plus": { + "input_cost_per_token": 2.1e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 8192, + "max_output_tokens": 2048, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 6.3e-07, + "supports_tool_choice": true + }, + "openrouter/qwen/qwen3-coder": { + "input_cost_per_token": 1e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "max_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 5e-06, + "source": "https://openrouter.ai/qwen/qwen3-coder", + "supports_tool_choice": true + }, + "openrouter/switchpoint/router": { + "input_cost_per_token": 8.5e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 3.4e-06, + "source": "https://openrouter.ai/switchpoint/router", + "supports_tool_choice": true + }, + "openrouter/undi95/remm-slerp-l2-13b": { + "input_cost_per_token": 1.875e-06, + "litellm_provider": "openrouter", + "max_tokens": 6144, + "mode": "chat", + "output_cost_per_token": 1.875e-06, + "supports_tool_choice": true + }, + "openrouter/x-ai/grok-4": { + "input_cost_per_token": 3e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "source": "https://openrouter.ai/x-ai/grok-4", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_web_search": true + }, + "ovhcloud/DeepSeek-R1-Distill-Llama-70B": { + "input_cost_per_token": 6.7e-07, "litellm_provider": "ovhcloud", + "max_input_tokens": 131000, + "max_output_tokens": 131000, + "max_tokens": 131000, + "mode": "chat", + "output_cost_per_token": 6.7e-07, + "source": "https://endpoints.ai.cloud.ovh.net/models/deepseek-r1-distill-llama-70b", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "ovhcloud/Llama-3.1-8B-Instruct": { + "input_cost_per_token": 1e-07, + "litellm_provider": "ovhcloud", + "max_input_tokens": 131000, + "max_output_tokens": 131000, + "max_tokens": 131000, + "mode": "chat", + "output_cost_per_token": 1e-07, + "source": "https://endpoints.ai.cloud.ovh.net/models/llama-3-1-8b-instruct", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "ovhcloud/Meta-Llama-3_1-70B-Instruct": { + "input_cost_per_token": 6.7e-07, + "litellm_provider": "ovhcloud", + "max_input_tokens": 131000, + "max_output_tokens": 131000, + "max_tokens": 131000, + "mode": "chat", + "output_cost_per_token": 6.7e-07, + "source": "https://endpoints.ai.cloud.ovh.net/models/meta-llama-3-1-70b-instruct", + "supports_function_calling": false, + "supports_response_schema": false, + "supports_tool_choice": false + }, + "ovhcloud/Meta-Llama-3_3-70B-Instruct": { + "input_cost_per_token": 6.7e-07, + "litellm_provider": "ovhcloud", + "max_input_tokens": 131000, + "max_output_tokens": 131000, + "max_tokens": 131000, + "mode": "chat", + "output_cost_per_token": 6.7e-07, + "source": "https://endpoints.ai.cloud.ovh.net/models/meta-llama-3-3-70b-instruct", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "ovhcloud/Mistral-7B-Instruct-v0.3": { + "input_cost_per_token": 1e-07, + "litellm_provider": "ovhcloud", + "max_input_tokens": 127000, + "max_output_tokens": 127000, + "max_tokens": 127000, + "mode": "chat", + "output_cost_per_token": 1e-07, + "source": "https://endpoints.ai.cloud.ovh.net/models/mistral-7b-instruct-v0-3", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "ovhcloud/Mistral-Nemo-Instruct-2407": { + "input_cost_per_token": 1.3e-07, + "litellm_provider": "ovhcloud", + "max_input_tokens": 118000, + "max_output_tokens": 118000, + "max_tokens": 118000, + "mode": "chat", + "output_cost_per_token": 1.3e-07, + "source": "https://endpoints.ai.cloud.ovh.net/models/mistral-nemo-instruct-2407", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "ovhcloud/Mistral-Small-3.2-24B-Instruct-2506": { + "input_cost_per_token": 9e-08, + "litellm_provider": "ovhcloud", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2.8e-07, + "source": "https://endpoints.ai.cloud.ovh.net/models/mistral-small-3-2-24b-instruct-2506", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "ovhcloud/Mixtral-8x7B-Instruct-v0.1": { + "input_cost_per_token": 6.3e-07, + "litellm_provider": "ovhcloud", + "max_input_tokens": 32000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 6.3e-07, + "source": "https://endpoints.ai.cloud.ovh.net/models/mixtral-8x7b-instruct-v0-1", + "supports_function_calling": false, + "supports_response_schema": true, + "supports_tool_choice": false + }, + "ovhcloud/Qwen2.5-Coder-32B-Instruct": { + "input_cost_per_token": 8.7e-07, + "litellm_provider": "ovhcloud", + "max_input_tokens": 32000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 8.7e-07, + "source": "https://endpoints.ai.cloud.ovh.net/models/qwen2-5-coder-32b-instruct", + "supports_function_calling": false, + "supports_response_schema": true, + "supports_tool_choice": false + }, + "ovhcloud/Qwen2.5-VL-72B-Instruct": { + "input_cost_per_token": 9.1e-07, + "litellm_provider": "ovhcloud", + "max_input_tokens": 32000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 9.1e-07, + "source": "https://endpoints.ai.cloud.ovh.net/models/qwen2-5-vl-72b-instruct", + "supports_function_calling": false, + "supports_response_schema": true, + "supports_tool_choice": false, + "supports_vision": true + }, + "ovhcloud/Qwen3-32B": { + "input_cost_per_token": 8e-08, + "litellm_provider": "ovhcloud", + "max_input_tokens": 32000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 2.3e-07, + "source": "https://endpoints.ai.cloud.ovh.net/models/qwen3-32b", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "ovhcloud/gpt-oss-120b": { + "input_cost_per_token": 8e-08, + "litellm_provider": "ovhcloud", + "max_input_tokens": 131000, + "max_output_tokens": 131000, + "max_tokens": 131000, + "mode": "chat", + "output_cost_per_token": 4e-07, + "source": "https://endpoints.ai.cloud.ovh.net/models/gpt-oss-120b", + "supports_function_calling": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": false + }, + "ovhcloud/gpt-oss-20b": { + "input_cost_per_token": 4e-08, + "litellm_provider": "ovhcloud", + "max_input_tokens": 131000, + "max_output_tokens": 131000, + "max_tokens": 131000, + "mode": "chat", + "output_cost_per_token": 1.5e-07, + "source": "https://endpoints.ai.cloud.ovh.net/models/gpt-oss-20b", + "supports_function_calling": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": false + }, + "ovhcloud/llava-v1.6-mistral-7b-hf": { + "input_cost_per_token": 2.9e-07, + "litellm_provider": "ovhcloud", + "max_input_tokens": 32000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 2.9e-07, + "source": "https://endpoints.ai.cloud.ovh.net/models/llava-next-mistral-7b", + "supports_function_calling": false, + "supports_response_schema": true, + "supports_tool_choice": false, + "supports_vision": true + }, + "ovhcloud/mamba-codestral-7B-v0.1": { + "input_cost_per_token": 1.9e-07, + "litellm_provider": "ovhcloud", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 1.9e-07, + "source": "https://endpoints.ai.cloud.ovh.net/models/mamba-codestral-7b-v0-1", + "supports_function_calling": false, + "supports_response_schema": true, + "supports_tool_choice": false + }, + "palm/chat-bison": { + "input_cost_per_token": 1.25e-07, + "litellm_provider": "palm", + "max_input_tokens": 8192, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.25e-07, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" + }, + "palm/chat-bison-001": { + "input_cost_per_token": 1.25e-07, + "litellm_provider": "palm", + "max_input_tokens": 8192, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.25e-07, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" + }, + "palm/text-bison": { + "input_cost_per_token": 1.25e-07, + "litellm_provider": "palm", + "max_input_tokens": 8192, + "max_output_tokens": 1024, + "max_tokens": 1024, + "mode": "completion", + "output_cost_per_token": 1.25e-07, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" + }, + "palm/text-bison-001": { + "input_cost_per_token": 1.25e-07, + "litellm_provider": "palm", + "max_input_tokens": 8192, + "max_output_tokens": 1024, + "max_tokens": 1024, + "mode": "completion", + "output_cost_per_token": 1.25e-07, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" + }, + "palm/text-bison-safety-off": { + "input_cost_per_token": 1.25e-07, + "litellm_provider": "palm", + "max_input_tokens": 8192, + "max_output_tokens": 1024, + "max_tokens": 1024, + "mode": "completion", + "output_cost_per_token": 1.25e-07, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" + }, + "palm/text-bison-safety-recitation-off": { + "input_cost_per_token": 1.25e-07, + "litellm_provider": "palm", + "max_input_tokens": 8192, + "max_output_tokens": 1024, + "max_tokens": 1024, + "mode": "completion", + "output_cost_per_token": 1.25e-07, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" + }, + "perplexity/codellama-34b-instruct": { + "input_cost_per_token": 3.5e-07, + "litellm_provider": "perplexity", + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1.4e-06 + }, + "perplexity/codellama-70b-instruct": { + "input_cost_per_token": 7e-07, + "litellm_provider": "perplexity", + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 2.8e-06 + }, + "perplexity/llama-2-70b-chat": { + "input_cost_per_token": 7e-07, + "litellm_provider": "perplexity", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 2.8e-06 + }, + "perplexity/llama-3.1-70b-instruct": { + "input_cost_per_token": 1e-06, + "litellm_provider": "perplexity", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1e-06 + }, + "perplexity/llama-3.1-8b-instruct": { + "input_cost_per_token": 2e-07, + "litellm_provider": "perplexity", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2e-07 + }, + "perplexity/llama-3.1-sonar-huge-128k-online": { + "deprecation_date": "2025-02-22", + "input_cost_per_token": 5e-06, + "litellm_provider": "perplexity", + "max_input_tokens": 127072, + "max_output_tokens": 127072, + "max_tokens": 127072, + "mode": "chat", + "output_cost_per_token": 5e-06 + }, + "perplexity/llama-3.1-sonar-large-128k-chat": { + "deprecation_date": "2025-02-22", + "input_cost_per_token": 1e-06, + "litellm_provider": "perplexity", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1e-06 + }, + "perplexity/llama-3.1-sonar-large-128k-online": { + "deprecation_date": "2025-02-22", + "input_cost_per_token": 1e-06, + "litellm_provider": "perplexity", + "max_input_tokens": 127072, + "max_output_tokens": 127072, + "max_tokens": 127072, + "mode": "chat", + "output_cost_per_token": 1e-06 + }, + "perplexity/llama-3.1-sonar-small-128k-chat": { + "deprecation_date": "2025-02-22", + "input_cost_per_token": 2e-07, + "litellm_provider": "perplexity", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2e-07 + }, + "perplexity/llama-3.1-sonar-small-128k-online": { + "deprecation_date": "2025-02-22", + "input_cost_per_token": 2e-07, + "litellm_provider": "perplexity", + "max_input_tokens": 127072, + "max_output_tokens": 127072, + "max_tokens": 127072, + "mode": "chat", + "output_cost_per_token": 2e-07 + }, + "perplexity/mistral-7b-instruct": { + "input_cost_per_token": 7e-08, + "litellm_provider": "perplexity", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 2.8e-07 + }, + "perplexity/mixtral-8x7b-instruct": { + "input_cost_per_token": 7e-08, + "litellm_provider": "perplexity", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 2.8e-07 + }, + "perplexity/pplx-70b-chat": { + "input_cost_per_token": 7e-07, + "litellm_provider": "perplexity", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 2.8e-06 + }, + "perplexity/pplx-70b-online": { + "input_cost_per_request": 0.005, + "input_cost_per_token": 0.0, + "litellm_provider": "perplexity", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 2.8e-06 + }, + "perplexity/pplx-7b-chat": { + "input_cost_per_token": 7e-08, + "litellm_provider": "perplexity", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 2.8e-07 + }, + "perplexity/pplx-7b-online": { + "input_cost_per_request": 0.005, + "input_cost_per_token": 0.0, + "litellm_provider": "perplexity", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 2.8e-07 + }, + "perplexity/sonar": { + "input_cost_per_token": 1e-06, + "litellm_provider": "perplexity", + "max_input_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.012, + "search_context_size_low": 0.005, + "search_context_size_medium": 0.008 + }, + "supports_web_search": true + }, + "perplexity/sonar-deep-research": { + "citation_cost_per_token": 2e-06, + "input_cost_per_token": 2e-06, + "litellm_provider": "perplexity", + "max_input_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_reasoning_token": 3e-06, + "output_cost_per_token": 8e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.005, + "search_context_size_low": 0.005, + "search_context_size_medium": 0.005 + }, + "supports_reasoning": true, + "supports_web_search": true + }, + "perplexity/sonar-medium-chat": { + "input_cost_per_token": 6e-07, + "litellm_provider": "perplexity", + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1.8e-06 + }, + "perplexity/sonar-medium-online": { + "input_cost_per_request": 0.005, + "input_cost_per_token": 0, + "litellm_provider": "perplexity", + "max_input_tokens": 12000, + "max_output_tokens": 12000, + "max_tokens": 12000, + "mode": "chat", + "output_cost_per_token": 1.8e-06 + }, + "perplexity/sonar-pro": { + "input_cost_per_token": 3e-06, + "litellm_provider": "perplexity", + "max_input_tokens": 200000, + "max_output_tokens": 8000, + "max_tokens": 8000, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.006, + "search_context_size_medium": 0.01 + }, + "supports_web_search": true + }, + "perplexity/sonar-reasoning": { + "input_cost_per_token": 1e-06, + "litellm_provider": "perplexity", + "max_input_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.005, + "search_context_size_medium": 0.008 + }, + "supports_reasoning": true, + "supports_web_search": true + }, + "perplexity/sonar-reasoning-pro": { + "input_cost_per_token": 2e-06, + "litellm_provider": "perplexity", + "max_input_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 8e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.006, + "search_context_size_medium": 0.01 + }, + "supports_reasoning": true, + "supports_web_search": true + }, + "perplexity/sonar-small-chat": { + "input_cost_per_token": 7e-08, + "litellm_provider": "perplexity", + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 2.8e-07 + }, + "perplexity/sonar-small-online": { + "input_cost_per_request": 0.005, + "input_cost_per_token": 0, + "litellm_provider": "perplexity", + "max_input_tokens": 12000, + "max_output_tokens": 12000, + "max_tokens": 12000, + "mode": "chat", + "output_cost_per_token": 2.8e-07 + }, + "recraft/recraftv2": { + "litellm_provider": "recraft", + "mode": "image_generation", + "output_cost_per_image": 0.022, + "source": "https://www.recraft.ai/docs#pricing", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "recraft/recraftv3": { + "litellm_provider": "recraft", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://www.recraft.ai/docs#pricing", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "replicate/meta/llama-2-13b": { + "input_cost_per_token": 1e-07, + "litellm_provider": "replicate", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 5e-07, + "supports_tool_choice": true + }, + "replicate/meta/llama-2-13b-chat": { + "input_cost_per_token": 1e-07, + "litellm_provider": "replicate", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 5e-07, + "supports_tool_choice": true + }, + "replicate/meta/llama-2-70b": { + "input_cost_per_token": 6.5e-07, + "litellm_provider": "replicate", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 2.75e-06, + "supports_tool_choice": true + }, + "replicate/meta/llama-2-70b-chat": { + "input_cost_per_token": 6.5e-07, + "litellm_provider": "replicate", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 2.75e-06, + "supports_tool_choice": true + }, + "replicate/meta/llama-2-7b": { + "input_cost_per_token": 5e-08, + "litellm_provider": "replicate", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 2.5e-07, + "supports_tool_choice": true + }, + "replicate/meta/llama-2-7b-chat": { + "input_cost_per_token": 5e-08, + "litellm_provider": "replicate", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 2.5e-07, + "supports_tool_choice": true + }, + "replicate/meta/llama-3-70b": { + "input_cost_per_token": 6.5e-07, + "litellm_provider": "replicate", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 2.75e-06, + "supports_tool_choice": true + }, + "replicate/meta/llama-3-70b-instruct": { + "input_cost_per_token": 6.5e-07, + "litellm_provider": "replicate", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 2.75e-06, + "supports_tool_choice": true + }, + "replicate/meta/llama-3-8b": { + "input_cost_per_token": 5e-08, + "litellm_provider": "replicate", + "max_input_tokens": 8086, + "max_output_tokens": 8086, + "max_tokens": 8086, + "mode": "chat", + "output_cost_per_token": 2.5e-07, + "supports_tool_choice": true + }, + "replicate/meta/llama-3-8b-instruct": { + "input_cost_per_token": 5e-08, + "litellm_provider": "replicate", + "max_input_tokens": 8086, + "max_output_tokens": 8086, + "max_tokens": 8086, + "mode": "chat", + "output_cost_per_token": 2.5e-07, + "supports_tool_choice": true + }, + "replicate/mistralai/mistral-7b-instruct-v0.2": { + "input_cost_per_token": 5e-08, + "litellm_provider": "replicate", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 2.5e-07, + "supports_tool_choice": true + }, + "replicate/mistralai/mistral-7b-v0.1": { + "input_cost_per_token": 5e-08, + "litellm_provider": "replicate", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 2.5e-07, + "supports_tool_choice": true + }, + "replicate/mistralai/mixtral-8x7b-instruct-v0.1": { + "input_cost_per_token": 3e-07, + "litellm_provider": "replicate", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1e-06, + "supports_tool_choice": true + }, + "rerank-english-v2.0": { + "input_cost_per_query": 0.002, + "input_cost_per_token": 0.0, + "litellm_provider": "cohere", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_query_tokens": 2048, + "max_tokens": 4096, + "mode": "rerank", + "output_cost_per_token": 0.0 + }, + "rerank-english-v3.0": { + "input_cost_per_query": 0.002, + "input_cost_per_token": 0.0, + "litellm_provider": "cohere", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_query_tokens": 2048, + "max_tokens": 4096, + "mode": "rerank", + "output_cost_per_token": 0.0 + }, + "rerank-multilingual-v2.0": { + "input_cost_per_query": 0.002, + "input_cost_per_token": 0.0, + "litellm_provider": "cohere", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_query_tokens": 2048, + "max_tokens": 4096, + "mode": "rerank", + "output_cost_per_token": 0.0 + }, + "rerank-multilingual-v3.0": { + "input_cost_per_query": 0.002, + "input_cost_per_token": 0.0, + "litellm_provider": "cohere", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_query_tokens": 2048, + "max_tokens": 4096, + "mode": "rerank", + "output_cost_per_token": 0.0 + }, + "rerank-v3.5": { + "input_cost_per_query": 0.002, + "input_cost_per_token": 0.0, + "litellm_provider": "cohere", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_query_tokens": 2048, + "max_tokens": 4096, + "mode": "rerank", + "output_cost_per_token": 0.0 + }, + "sagemaker/meta-textgeneration-llama-2-13b": { + "input_cost_per_token": 0.0, + "litellm_provider": "sagemaker", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "completion", + "output_cost_per_token": 0.0 + }, + "sagemaker/meta-textgeneration-llama-2-13b-f": { + "input_cost_per_token": 0.0, + "litellm_provider": "sagemaker", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.0 + }, + "sagemaker/meta-textgeneration-llama-2-70b": { + "input_cost_per_token": 0.0, + "litellm_provider": "sagemaker", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "completion", + "output_cost_per_token": 0.0 + }, + "sagemaker/meta-textgeneration-llama-2-70b-b-f": { + "input_cost_per_token": 0.0, + "litellm_provider": "sagemaker", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.0 + }, + "sagemaker/meta-textgeneration-llama-2-7b": { + "input_cost_per_token": 0.0, + "litellm_provider": "sagemaker", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "completion", + "output_cost_per_token": 0.0 + }, + "sagemaker/meta-textgeneration-llama-2-7b-f": { + "input_cost_per_token": 0.0, + "litellm_provider": "sagemaker", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.0 + }, + "sambanova/DeepSeek-R1": { + "input_cost_per_token": 5e-06, + "litellm_provider": "sambanova", + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 7e-06, + "source": "https://cloud.sambanova.ai/plans/pricing" + }, + "sambanova/DeepSeek-R1-Distill-Llama-70B": { + "input_cost_per_token": 7e-07, + "litellm_provider": "sambanova", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.4e-06, + "source": "https://cloud.sambanova.ai/plans/pricing" + }, + "sambanova/DeepSeek-V3-0324": { + "input_cost_per_token": 3e-06, + "litellm_provider": "sambanova", + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 4.5e-06, + "source": "https://cloud.sambanova.ai/plans/pricing", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "sambanova/Llama-4-Maverick-17B-128E-Instruct": { + "input_cost_per_token": 6.3e-07, + "litellm_provider": "sambanova", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "metadata": { + "notes": "For vision models, images are converted to 6432 input tokens and are billed at that amount" + }, + "mode": "chat", + "output_cost_per_token": 1.8e-06, + "source": "https://cloud.sambanova.ai/plans/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "sambanova/Llama-4-Scout-17B-16E-Instruct": { + "input_cost_per_token": 4e-07, + "litellm_provider": "sambanova", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "metadata": { + "notes": "For vision models, images are converted to 6432 input tokens and are billed at that amount" + }, + "mode": "chat", + "output_cost_per_token": 7e-07, + "source": "https://cloud.sambanova.ai/plans/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "sambanova/Meta-Llama-3.1-405B-Instruct": { + "input_cost_per_token": 5e-06, + "litellm_provider": "sambanova", + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1e-05, + "source": "https://cloud.sambanova.ai/plans/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "sambanova/Meta-Llama-3.1-8B-Instruct": { + "input_cost_per_token": 1e-07, + "litellm_provider": "sambanova", + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 2e-07, + "source": "https://cloud.sambanova.ai/plans/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "sambanova/Meta-Llama-3.2-1B-Instruct": { + "input_cost_per_token": 4e-08, + "litellm_provider": "sambanova", + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 8e-08, + "source": "https://cloud.sambanova.ai/plans/pricing" + }, + "sambanova/Meta-Llama-3.2-3B-Instruct": { + "input_cost_per_token": 8e-08, + "litellm_provider": "sambanova", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.6e-07, + "source": "https://cloud.sambanova.ai/plans/pricing" + }, + "sambanova/Meta-Llama-3.3-70B-Instruct": { + "input_cost_per_token": 6e-07, + "litellm_provider": "sambanova", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://cloud.sambanova.ai/plans/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "sambanova/Meta-Llama-Guard-3-8B": { + "input_cost_per_token": 3e-07, + "litellm_provider": "sambanova", + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 3e-07, + "source": "https://cloud.sambanova.ai/plans/pricing" + }, + "sambanova/QwQ-32B": { + "input_cost_per_token": 5e-07, + "litellm_provider": "sambanova", + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1e-06, + "source": "https://cloud.sambanova.ai/plans/pricing" + }, + "sambanova/Qwen2-Audio-7B-Instruct": { + "input_cost_per_token": 5e-07, + "litellm_provider": "sambanova", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.0001, + "source": "https://cloud.sambanova.ai/plans/pricing", + "supports_audio_input": true + }, + "sambanova/Qwen3-32B": { + "input_cost_per_token": 4e-07, + "litellm_provider": "sambanova", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 8e-07, + "source": "https://cloud.sambanova.ai/plans/pricing", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "sample_spec": { + "code_interpreter_cost_per_session": 0.0, + "computer_use_input_cost_per_1k_tokens": 0.0, + "computer_use_output_cost_per_1k_tokens": 0.0, + "deprecation_date": "date when the model becomes deprecated in the format YYYY-MM-DD", + "file_search_cost_per_1k_calls": 0.0, + "file_search_cost_per_gb_per_day": 0.0, + "input_cost_per_audio_token": 0.0, + "input_cost_per_token": 0.0, + "litellm_provider": "one of https://docs.litellm.ai/docs/providers", + "max_input_tokens": "max input tokens, if the provider specifies it. if not default to max_tokens", + "max_output_tokens": "max output tokens, if the provider specifies it. if not default to max_tokens", + "max_tokens": "LEGACY parameter. set to max_output_tokens if provider specifies it. IF not set to max_input_tokens, if provider specifies it.", + "mode": "one of: chat, embedding, completion, image_generation, audio_transcription, audio_speech, image_generation, moderation, rerank", + "output_cost_per_reasoning_token": 0.0, + "output_cost_per_token": 0.0, + "search_context_cost_per_query": { + "search_context_size_high": 0.0, + "search_context_size_low": 0.0, + "search_context_size_medium": 0.0 + }, + "supported_regions": [ + "global", + "us-west-2", + "eu-west-1", + "ap-southeast-1", + "ap-northeast-1" + ], + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_vision": true, + "supports_web_search": true, + "vector_store_cost_per_gb_per_day": 0.0 + }, + "snowflake/claude-3-5-sonnet": { + "litellm_provider": "snowflake", + "max_input_tokens": 18000, + "max_output_tokens": 8192, + "max_tokens": 18000, + "mode": "chat", + "supports_computer_use": true + }, + "snowflake/deepseek-r1": { + "litellm_provider": "snowflake", + "max_input_tokens": 32768, + "max_output_tokens": 8192, + "max_tokens": 32768, + "mode": "chat", + "supports_reasoning": true + }, + "snowflake/gemma-7b": { + "litellm_provider": "snowflake", + "max_input_tokens": 8000, + "max_output_tokens": 8192, + "max_tokens": 8000, + "mode": "chat" + }, + "snowflake/jamba-1.5-large": { + "litellm_provider": "snowflake", + "max_input_tokens": 256000, + "max_output_tokens": 8192, + "max_tokens": 256000, + "mode": "chat" + }, + "snowflake/jamba-1.5-mini": { + "litellm_provider": "snowflake", + "max_input_tokens": 256000, + "max_output_tokens": 8192, + "max_tokens": 256000, + "mode": "chat" + }, + "snowflake/jamba-instruct": { + "litellm_provider": "snowflake", + "max_input_tokens": 256000, + "max_output_tokens": 8192, + "max_tokens": 256000, + "mode": "chat" + }, + "snowflake/llama2-70b-chat": { + "litellm_provider": "snowflake", + "max_input_tokens": 4096, + "max_output_tokens": 8192, + "max_tokens": 4096, + "mode": "chat" + }, + "snowflake/llama3-70b": { + "litellm_provider": "snowflake", + "max_input_tokens": 8000, + "max_output_tokens": 8192, + "max_tokens": 8000, + "mode": "chat" + }, + "snowflake/llama3-8b": { + "litellm_provider": "snowflake", + "max_input_tokens": 8000, + "max_output_tokens": 8192, + "max_tokens": 8000, + "mode": "chat" + }, + "snowflake/llama3.1-405b": { + "litellm_provider": "snowflake", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 128000, + "mode": "chat" + }, + "snowflake/llama3.1-70b": { + "litellm_provider": "snowflake", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 128000, + "mode": "chat" + }, + "snowflake/llama3.1-8b": { + "litellm_provider": "snowflake", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 128000, + "mode": "chat" + }, + "snowflake/llama3.2-1b": { + "litellm_provider": "snowflake", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 128000, + "mode": "chat" + }, + "snowflake/llama3.2-3b": { + "litellm_provider": "snowflake", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 128000, + "mode": "chat" + }, + "snowflake/llama3.3-70b": { + "litellm_provider": "snowflake", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 128000, + "mode": "chat" + }, + "snowflake/mistral-7b": { + "litellm_provider": "snowflake", + "max_input_tokens": 32000, + "max_output_tokens": 8192, + "max_tokens": 32000, + "mode": "chat" + }, + "snowflake/mistral-large": { + "litellm_provider": "snowflake", + "max_input_tokens": 32000, + "max_output_tokens": 8192, + "max_tokens": 32000, + "mode": "chat" + }, + "snowflake/mistral-large2": { + "litellm_provider": "snowflake", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 128000, + "mode": "chat" + }, + "snowflake/mixtral-8x7b": { + "litellm_provider": "snowflake", + "max_input_tokens": 32000, + "max_output_tokens": 8192, + "max_tokens": 32000, + "mode": "chat" + }, + "snowflake/reka-core": { + "litellm_provider": "snowflake", + "max_input_tokens": 32000, + "max_output_tokens": 8192, + "max_tokens": 32000, + "mode": "chat" + }, + "snowflake/reka-flash": { + "litellm_provider": "snowflake", + "max_input_tokens": 100000, + "max_output_tokens": 8192, + "max_tokens": 100000, + "mode": "chat" + }, + "snowflake/snowflake-arctic": { + "litellm_provider": "snowflake", + "max_input_tokens": 4096, + "max_output_tokens": 8192, + "max_tokens": 4096, + "mode": "chat" + }, + "snowflake/snowflake-llama-3.1-405b": { + "litellm_provider": "snowflake", + "max_input_tokens": 8000, + "max_output_tokens": 8192, + "max_tokens": 8000, + "mode": "chat" + }, + "snowflake/snowflake-llama-3.3-70b": { + "litellm_provider": "snowflake", + "max_input_tokens": 8000, + "max_output_tokens": 8192, + "max_tokens": 8000, + "mode": "chat" + }, + "stability.sd3-5-large-v1:0": { + "litellm_provider": "bedrock", + "max_input_tokens": 77, + "max_tokens": 77, + "mode": "image_generation", + "output_cost_per_image": 0.08 + }, + "stability.sd3-large-v1:0": { + "litellm_provider": "bedrock", + "max_input_tokens": 77, + "max_tokens": 77, + "mode": "image_generation", + "output_cost_per_image": 0.08 + }, + "stability.stable-image-core-v1:0": { + "litellm_provider": "bedrock", + "max_input_tokens": 77, + "max_tokens": 77, + "mode": "image_generation", + "output_cost_per_image": 0.04 + }, + "stability.stable-image-core-v1:1": { + "litellm_provider": "bedrock", + "max_input_tokens": 77, + "max_tokens": 77, + "mode": "image_generation", + "output_cost_per_image": 0.04 + }, + "stability.stable-image-ultra-v1:0": { + "litellm_provider": "bedrock", + "max_input_tokens": 77, + "max_tokens": 77, + "mode": "image_generation", + "output_cost_per_image": 0.14 + }, + "stability.stable-image-ultra-v1:1": { + "litellm_provider": "bedrock", + "max_input_tokens": 77, + "max_tokens": 77, + "mode": "image_generation", + "output_cost_per_image": 0.14 + }, + "standard/1024-x-1024/dall-e-3": { + "input_cost_per_pixel": 3.81469e-08, + "litellm_provider": "openai", + "mode": "image_generation", + "output_cost_per_pixel": 0.0 + }, + "standard/1024-x-1792/dall-e-3": { + "input_cost_per_pixel": 4.359e-08, + "litellm_provider": "openai", + "mode": "image_generation", + "output_cost_per_pixel": 0.0 + }, + "standard/1792-x-1024/dall-e-3": { + "input_cost_per_pixel": 4.359e-08, + "litellm_provider": "openai", + "mode": "image_generation", + "output_cost_per_pixel": 0.0 + }, + "text-bison": { + "input_cost_per_character": 2.5e-07, + "litellm_provider": "vertex_ai-text-models", + "max_input_tokens": 8192, + "max_output_tokens": 2048, + "max_tokens": 2048, + "mode": "completion", + "output_cost_per_character": 5e-07, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" + }, + "text-bison32k": { + "input_cost_per_character": 2.5e-07, + "input_cost_per_token": 1.25e-07, + "litellm_provider": "vertex_ai-text-models", + "max_input_tokens": 8192, + "max_output_tokens": 1024, + "max_tokens": 1024, + "mode": "completion", + "output_cost_per_character": 5e-07, + "output_cost_per_token": 1.25e-07, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" + }, + "text-bison32k@002": { + "input_cost_per_character": 2.5e-07, + "input_cost_per_token": 1.25e-07, + "litellm_provider": "vertex_ai-text-models", + "max_input_tokens": 8192, + "max_output_tokens": 1024, + "max_tokens": 1024, + "mode": "completion", + "output_cost_per_character": 5e-07, + "output_cost_per_token": 1.25e-07, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" + }, + "text-bison@001": { + "input_cost_per_character": 2.5e-07, + "litellm_provider": "vertex_ai-text-models", + "max_input_tokens": 8192, + "max_output_tokens": 1024, + "max_tokens": 1024, + "mode": "completion", + "output_cost_per_character": 5e-07, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" + }, + "text-bison@002": { + "input_cost_per_character": 2.5e-07, + "litellm_provider": "vertex_ai-text-models", + "max_input_tokens": 8192, + "max_output_tokens": 1024, + "max_tokens": 1024, + "mode": "completion", + "output_cost_per_character": 5e-07, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" + }, + "text-completion-codestral/codestral-2405": { + "input_cost_per_token": 0.0, + "litellm_provider": "text-completion-codestral", + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "completion", + "output_cost_per_token": 0.0, + "source": "https://docs.mistral.ai/capabilities/code_generation/" + }, + "text-completion-codestral/codestral-latest": { + "input_cost_per_token": 0.0, + "litellm_provider": "text-completion-codestral", + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "completion", + "output_cost_per_token": 0.0, + "source": "https://docs.mistral.ai/capabilities/code_generation/" + }, + "text-embedding-004": { + "input_cost_per_character": 2.5e-08, + "input_cost_per_token": 1e-07, + "litellm_provider": "vertex_ai-embedding-models", + "max_input_tokens": 2048, + "max_tokens": 2048, + "mode": "embedding", + "output_cost_per_token": 0, + "output_vector_size": 768, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models" + }, + "text-embedding-005": { + "input_cost_per_character": 2.5e-08, + "input_cost_per_token": 1e-07, + "litellm_provider": "vertex_ai-embedding-models", + "max_input_tokens": 2048, + "max_tokens": 2048, + "mode": "embedding", + "output_cost_per_token": 0, + "output_vector_size": 768, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models" + }, + "text-embedding-3-large": { + "input_cost_per_token": 1.3e-07, + "input_cost_per_token_batches": 6.5e-08, + "litellm_provider": "openai", + "max_input_tokens": 8191, + "max_tokens": 8191, + "mode": "embedding", + "output_cost_per_token": 0.0, + "output_cost_per_token_batches": 0.0, + "output_vector_size": 3072 + }, + "text-embedding-3-small": { + "input_cost_per_token": 2e-08, + "input_cost_per_token_batches": 1e-08, + "litellm_provider": "openai", + "max_input_tokens": 8191, + "max_tokens": 8191, + "mode": "embedding", + "output_cost_per_token": 0.0, + "output_cost_per_token_batches": 0.0, + "output_vector_size": 1536 + }, + "text-embedding-ada-002": { + "input_cost_per_token": 1e-07, + "litellm_provider": "openai", + "max_input_tokens": 8191, + "max_tokens": 8191, + "mode": "embedding", + "output_cost_per_token": 0.0, + "output_vector_size": 1536 + }, + "text-embedding-ada-002-v2": { + "input_cost_per_token": 1e-07, + "input_cost_per_token_batches": 5e-08, + "litellm_provider": "openai", + "max_input_tokens": 8191, + "max_tokens": 8191, + "mode": "embedding", + "output_cost_per_token": 0.0, + "output_cost_per_token_batches": 0.0 + }, + "text-embedding-large-exp-03-07": { + "input_cost_per_character": 2.5e-08, + "input_cost_per_token": 1e-07, + "litellm_provider": "vertex_ai-embedding-models", + "max_input_tokens": 8192, + "max_tokens": 8192, + "mode": "embedding", + "output_cost_per_token": 0, + "output_vector_size": 3072, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models" + }, + "text-embedding-preview-0409": { + "input_cost_per_token": 6.25e-09, + "input_cost_per_token_batch_requests": 5e-09, + "litellm_provider": "vertex_ai-embedding-models", + "max_input_tokens": 3072, + "max_tokens": 3072, + "mode": "embedding", + "output_cost_per_token": 0, + "output_vector_size": 768, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" + }, + "text-moderation-007": { + "input_cost_per_token": 0.0, + "litellm_provider": "openai", + "max_input_tokens": 32768, + "max_output_tokens": 0, + "max_tokens": 32768, + "mode": "moderation", + "output_cost_per_token": 0.0 + }, + "text-moderation-latest": { + "input_cost_per_token": 0.0, + "litellm_provider": "openai", + "max_input_tokens": 32768, + "max_output_tokens": 0, + "max_tokens": 32768, + "mode": "moderation", + "output_cost_per_token": 0.0 + }, + "text-moderation-stable": { + "input_cost_per_token": 0.0, + "litellm_provider": "openai", + "max_input_tokens": 32768, + "max_output_tokens": 0, + "max_tokens": 32768, + "mode": "moderation", + "output_cost_per_token": 0.0 + }, + "text-multilingual-embedding-002": { + "input_cost_per_character": 2.5e-08, + "input_cost_per_token": 1e-07, + "litellm_provider": "vertex_ai-embedding-models", + "max_input_tokens": 2048, + "max_tokens": 2048, + "mode": "embedding", + "output_cost_per_token": 0, + "output_vector_size": 768, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models" + }, + "text-multilingual-embedding-preview-0409": { + "input_cost_per_token": 6.25e-09, + "litellm_provider": "vertex_ai-embedding-models", + "max_input_tokens": 3072, + "max_tokens": 3072, + "mode": "embedding", + "output_cost_per_token": 0, + "output_vector_size": 768, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" + }, + "text-unicorn": { + "input_cost_per_token": 1e-05, + "litellm_provider": "vertex_ai-text-models", + "max_input_tokens": 8192, + "max_output_tokens": 1024, + "max_tokens": 1024, + "mode": "completion", + "output_cost_per_token": 2.8e-05, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" + }, + "text-unicorn@001": { + "input_cost_per_token": 1e-05, + "litellm_provider": "vertex_ai-text-models", + "max_input_tokens": 8192, + "max_output_tokens": 1024, + "max_tokens": 1024, + "mode": "completion", + "output_cost_per_token": 2.8e-05, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" + }, + "textembedding-gecko": { + "input_cost_per_character": 2.5e-08, + "input_cost_per_token": 1e-07, + "litellm_provider": "vertex_ai-embedding-models", + "max_input_tokens": 3072, + "max_tokens": 3072, + "mode": "embedding", + "output_cost_per_token": 0, + "output_vector_size": 768, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" + }, + "textembedding-gecko-multilingual": { + "input_cost_per_character": 2.5e-08, + "input_cost_per_token": 1e-07, + "litellm_provider": "vertex_ai-embedding-models", + "max_input_tokens": 3072, + "max_tokens": 3072, + "mode": "embedding", + "output_cost_per_token": 0, + "output_vector_size": 768, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" + }, + "textembedding-gecko-multilingual@001": { + "input_cost_per_character": 2.5e-08, + "input_cost_per_token": 1e-07, + "litellm_provider": "vertex_ai-embedding-models", + "max_input_tokens": 3072, + "max_tokens": 3072, + "mode": "embedding", + "output_cost_per_token": 0, + "output_vector_size": 768, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" + }, + "textembedding-gecko@001": { + "input_cost_per_character": 2.5e-08, + "input_cost_per_token": 1e-07, + "litellm_provider": "vertex_ai-embedding-models", + "max_input_tokens": 3072, + "max_tokens": 3072, + "mode": "embedding", + "output_cost_per_token": 0, + "output_vector_size": 768, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" + }, + "textembedding-gecko@003": { + "input_cost_per_character": 2.5e-08, + "input_cost_per_token": 1e-07, + "litellm_provider": "vertex_ai-embedding-models", + "max_input_tokens": 3072, + "max_tokens": 3072, + "mode": "embedding", + "output_cost_per_token": 0, + "output_vector_size": 768, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" + }, + "together-ai-21.1b-41b": { + "input_cost_per_token": 8e-07, + "litellm_provider": "together_ai", + "mode": "chat", + "output_cost_per_token": 8e-07 + }, + "together-ai-4.1b-8b": { + "input_cost_per_token": 2e-07, + "litellm_provider": "together_ai", + "mode": "chat", + "output_cost_per_token": 2e-07 + }, + "together-ai-41.1b-80b": { + "input_cost_per_token": 9e-07, + "litellm_provider": "together_ai", + "mode": "chat", + "output_cost_per_token": 9e-07 + }, + "together-ai-8.1b-21b": { + "input_cost_per_token": 3e-07, + "litellm_provider": "together_ai", + "max_tokens": 1000, + "mode": "chat", + "output_cost_per_token": 3e-07 + }, + "together-ai-81.1b-110b": { + "input_cost_per_token": 1.8e-06, + "litellm_provider": "together_ai", + "mode": "chat", + "output_cost_per_token": 1.8e-06 + }, + "together-ai-embedding-151m-to-350m": { + "input_cost_per_token": 1.6e-08, + "litellm_provider": "together_ai", + "mode": "embedding", + "output_cost_per_token": 0.0 + }, + "together-ai-embedding-up-to-150m": { + "input_cost_per_token": 8e-09, + "litellm_provider": "together_ai", + "mode": "embedding", + "output_cost_per_token": 0.0 + }, + "together-ai-up-to-4b": { + "input_cost_per_token": 1e-07, + "litellm_provider": "together_ai", + "mode": "chat", + "output_cost_per_token": 1e-07 + }, + "together_ai/Qwen/Qwen2.5-72B-Instruct-Turbo": { + "litellm_provider": "together_ai", "mode": "chat", "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true + }, + "together_ai/Qwen/Qwen2.5-7B-Instruct-Turbo": { + "litellm_provider": "together_ai", + "mode": "chat", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true + }, + "together_ai/Qwen/Qwen3-235B-A22B-Instruct-2507-tput": { + "input_cost_per_token": 2e-07, + "litellm_provider": "together_ai", + "max_input_tokens": 262000, + "mode": "chat", + "output_cost_per_token": 6e-06, + "source": "https://www.together.ai/models/qwen3-235b-a22b-instruct-2507-fp8", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true + }, + "together_ai/Qwen/Qwen3-235B-A22B-Thinking-2507": { + "input_cost_per_token": 6.5e-07, + "litellm_provider": "together_ai", + "max_input_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 3e-06, + "source": "https://www.together.ai/models/qwen3-235b-a22b-thinking-2507", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true + }, + "together_ai/Qwen/Qwen3-235B-A22B-fp8-tput": { + "input_cost_per_token": 2e-07, + "litellm_provider": "together_ai", + "max_input_tokens": 40000, + "mode": "chat", + "output_cost_per_token": 6e-07, + "source": "https://www.together.ai/models/qwen3-235b-a22b-fp8-tput", + "supports_function_calling": false, + "supports_parallel_function_calling": false, + "supports_tool_choice": false + }, + "together_ai/Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8": { + "input_cost_per_token": 2e-06, + "litellm_provider": "together_ai", + "max_input_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 2e-06, + "source": "https://www.together.ai/models/qwen3-coder-480b-a35b-instruct", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true + }, + "together_ai/deepseek-ai/DeepSeek-R1": { + "input_cost_per_token": 3e-06, + "litellm_provider": "together_ai", + "max_input_tokens": 128000, + "max_output_tokens": 20480, + "max_tokens": 20480, + "mode": "chat", + "output_cost_per_token": 7e-06, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true + }, + "together_ai/deepseek-ai/DeepSeek-R1-0528-tput": { + "input_cost_per_token": 5.5e-07, + "litellm_provider": "together_ai", + "max_input_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2.19e-06, + "source": "https://www.together.ai/models/deepseek-r1-0528-throughput", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true + }, + "together_ai/deepseek-ai/DeepSeek-V3": { + "input_cost_per_token": 1.25e-06, + "litellm_provider": "together_ai", + "max_input_tokens": 65536, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.25e-06, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true + }, + "together_ai/deepseek-ai/DeepSeek-V3.1": { + "input_cost_per_token": 6e-07, + "litellm_provider": "together_ai", + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.7e-06, + "source": "https://www.together.ai/models/deepseek-v3-1", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "together_ai/meta-llama/Llama-3.2-3B-Instruct-Turbo": { + "litellm_provider": "together_ai", + "mode": "chat", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true + }, + "together_ai/meta-llama/Llama-3.3-70B-Instruct-Turbo": { + "input_cost_per_token": 8.8e-07, + "litellm_provider": "together_ai", + "mode": "chat", + "output_cost_per_token": 8.8e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "together_ai/meta-llama/Llama-3.3-70B-Instruct-Turbo-Free": { + "input_cost_per_token": 0, + "litellm_provider": "together_ai", + "mode": "chat", + "output_cost_per_token": 0, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "together_ai/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8": { + "input_cost_per_token": 2.7e-07, + "litellm_provider": "together_ai", + "mode": "chat", + "output_cost_per_token": 8.5e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true + }, + "together_ai/meta-llama/Llama-4-Scout-17B-16E-Instruct": { + "input_cost_per_token": 1.8e-07, + "litellm_provider": "together_ai", + "mode": "chat", + "output_cost_per_token": 5.9e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true + }, + "together_ai/meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo": { + "input_cost_per_token": 3.5e-06, + "litellm_provider": "together_ai", + "mode": "chat", + "output_cost_per_token": 3.5e-06, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true + }, + "together_ai/meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo": { + "input_cost_per_token": 8.8e-07, + "litellm_provider": "together_ai", + "mode": "chat", + "output_cost_per_token": 8.8e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "together_ai/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo": { + "input_cost_per_token": 1.8e-07, + "litellm_provider": "together_ai", + "mode": "chat", + "output_cost_per_token": 1.8e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "together_ai/mistralai/Mistral-7B-Instruct-v0.1": { + "litellm_provider": "together_ai", + "mode": "chat", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "together_ai/mistralai/Mistral-Small-24B-Instruct-2501": { + "litellm_provider": "together_ai", + "mode": "chat", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true + }, + "together_ai/mistralai/Mixtral-8x7B-Instruct-v0.1": { + "input_cost_per_token": 6e-07, + "litellm_provider": "together_ai", + "mode": "chat", + "output_cost_per_token": 6e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "together_ai/moonshotai/Kimi-K2-Instruct": { + "input_cost_per_token": 1e-06, + "litellm_provider": "together_ai", + "mode": "chat", + "output_cost_per_token": 3e-06, + "source": "https://www.together.ai/models/kimi-k2-instruct", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true + }, + "together_ai/openai/gpt-oss-120b": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "together_ai", + "max_input_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 6e-07, + "source": "https://www.together.ai/models/gpt-oss-120b", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true + }, + "together_ai/openai/gpt-oss-20b": { + "input_cost_per_token": 5e-08, + "litellm_provider": "together_ai", + "max_input_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2e-07, + "source": "https://www.together.ai/models/gpt-oss-20b", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true + }, + "together_ai/togethercomputer/CodeLlama-34b-Instruct": { + "litellm_provider": "together_ai", + "mode": "chat", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true + }, + "together_ai/zai-org/GLM-4.5-Air-FP8": { + "input_cost_per_token": 2e-07, + "litellm_provider": "together_ai", + "max_input_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.1e-06, + "source": "https://www.together.ai/models/glm-4-5-air", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true + }, + "tts-1": { + "input_cost_per_character": 1.5e-05, + "litellm_provider": "openai", + "mode": "audio_speech", + "supported_endpoints": [ + "/v1/audio/speech" + ] + }, + "tts-1-hd": { + "input_cost_per_character": 3e-05, + "litellm_provider": "openai", + "mode": "audio_speech", + "supported_endpoints": [ + "/v1/audio/speech" + ] + }, + "us.amazon.nova-lite-v1:0": { + "input_cost_per_token": 6e-08, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 300000, + "max_output_tokens": 10000, + "max_tokens": 10000, + "mode": "chat", + "output_cost_per_token": 2.4e-07, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_vision": true + }, + "us.amazon.nova-micro-v1:0": { + "input_cost_per_token": 3.5e-08, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 128000, + "max_output_tokens": 10000, + "max_tokens": 10000, + "mode": "chat", + "output_cost_per_token": 1.4e-07, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true + }, + "us.amazon.nova-premier-v1:0": { + "input_cost_per_token": 2.5e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 10000, + "max_tokens": 10000, + "mode": "chat", + "output_cost_per_token": 1.25e-05, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": false, + "supports_response_schema": true, + "supports_vision": true + }, + "us.amazon.nova-pro-v1:0": { + "input_cost_per_token": 8e-07, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 300000, + "max_output_tokens": 10000, + "max_tokens": 10000, + "mode": "chat", + "output_cost_per_token": 3.2e-06, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_vision": true + }, + "us.anthropic.claude-3-5-haiku-20241022-v1:0": { + "cache_creation_input_token_cost": 1e-06, + "cache_read_input_token_cost": 8e-08, + "input_cost_per_token": 8e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 4e-06, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "us.anthropic.claude-3-5-sonnet-20240620-v1:0": { + "input_cost_per_token": 3e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "us.anthropic.claude-3-5-sonnet-20241022-v2:0": { + "cache_creation_input_token_cost": 3.75e-06, + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 3e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "us.anthropic.claude-3-7-sonnet-20250219-v1:0": { + "cache_creation_input_token_cost": 3.75e-06, + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 3e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "us.anthropic.claude-3-haiku-20240307-v1:0": { + "input_cost_per_token": 2.5e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.25e-06, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "us.anthropic.claude-3-opus-20240229-v1:0": { + "input_cost_per_token": 1.5e-05, + "litellm_provider": "bedrock", + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 7.5e-05, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "us.anthropic.claude-3-sonnet-20240229-v1:0": { + "input_cost_per_token": 3e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "us.anthropic.claude-opus-4-1-20250805-v1:0": { + "cache_creation_input_token_cost": 1.875e-05, + "cache_read_input_token_cost": 1.5e-06, + "input_cost_per_token": 1.5e-05, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 200000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 7.5e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "source": "https://endpoints.ai.cloud.ovh.net/models/mistral-small-3-2-24b-instruct-2506" + "tool_use_system_prompt_tokens": 159 }, - "ovhcloud/DeepSeek-R1-Distill-Llama-70B": { - "max_tokens": 131000, - "max_input_tokens": 131000, - "max_output_tokens": 131000, - "input_cost_per_token": 6.7e-07, - "output_cost_per_token": 6.7e-07, - "litellm_provider": "ovhcloud", - "mode": "chat", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "source": "https://endpoints.ai.cloud.ovh.net/models/deepseek-r1-distill-llama-70b" - }, - "ovhcloud/Llama-3.1-8B-Instruct": { - "max_tokens": 131000, - "max_input_tokens": 131000, - "max_output_tokens": 131000, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 1e-07, - "litellm_provider": "ovhcloud", - "mode": "chat", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "source": "https://endpoints.ai.cloud.ovh.net/models/llama-3-1-8b-instruct" - }, - "ovhcloud/Mistral-7B-Instruct-v0.3": { - "max_tokens": 127000, - "max_input_tokens": 127000, - "max_output_tokens": 127000, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 1e-07, - "litellm_provider": "ovhcloud", - "mode": "chat", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "source": "https://endpoints.ai.cloud.ovh.net/models/mistral-7b-instruct-v0-3" - }, - "ovhcloud/gpt-oss-20b": { - "max_tokens": 131000, - "max_input_tokens": 131000, - "max_output_tokens": 131000, - "input_cost_per_token": 4e-08, - "output_cost_per_token": 1.5e-07, - "litellm_provider": "ovhcloud", - "mode": "chat", - "supports_function_calling": false, - "supports_response_schema": true, - "supports_tool_choice": false, - "supports_reasoning": true, - "source": "https://endpoints.ai.cloud.ovh.net/models/gpt-oss-20b" - }, - "ovhcloud/Mistral-Nemo-Instruct-2407": { - "max_tokens": 118000, - "max_input_tokens": 118000, - "max_output_tokens": 118000, - "input_cost_per_token": 1.3e-07, - "output_cost_per_token": 1.3e-07, - "litellm_provider": "ovhcloud", - "mode": "chat", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "source": "https://endpoints.ai.cloud.ovh.net/models/mistral-nemo-instruct-2407" - }, - "ovhcloud/Qwen3-32B": { - "max_tokens": 32000, - "max_input_tokens": 32000, + "us.anthropic.claude-opus-4-20250514-v1:0": { + "cache_creation_input_token_cost": 1.875e-05, + "cache_read_input_token_cost": 1.5e-06, + "input_cost_per_token": 1.5e-05, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 200000, "max_output_tokens": 32000, - "input_cost_per_token": 8e-08, - "output_cost_per_token": 2.3e-07, - "litellm_provider": "ovhcloud", + "max_tokens": 32000, "mode": "chat", + "output_cost_per_token": 7.5e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_reasoning": true, - "source": "https://endpoints.ai.cloud.ovh.net/models/qwen3-32b" + "supports_vision": true, + "tool_use_system_prompt_tokens": 159 }, - "ovhcloud/mamba-codestral-7B-v0.1": { + "us.anthropic.claude-sonnet-4-20250514-v1:0": { + "cache_creation_input_token_cost": 3.75e-06, + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 3e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159 + }, + "us.deepseek.r1-v1:0": { + "input_cost_per_token": 1.35e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 5.4e-06, + "supports_function_calling": false, + "supports_reasoning": true, + "supports_tool_choice": false + }, + "us.meta.llama3-1-405b-instruct-v1:0": { + "input_cost_per_token": 5.32e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.6e-05, + "supports_function_calling": true, + "supports_tool_choice": false + }, + "us.meta.llama3-1-70b-instruct-v1:0": { + "input_cost_per_token": 9.9e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 128000, + "max_output_tokens": 2048, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 9.9e-07, + "supports_function_calling": true, + "supports_tool_choice": false + }, + "us.meta.llama3-1-8b-instruct-v1:0": { + "input_cost_per_token": 2.2e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 128000, + "max_output_tokens": 2048, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2.2e-07, + "supports_function_calling": true, + "supports_tool_choice": false + }, + "us.meta.llama3-2-11b-instruct-v1:0": { + "input_cost_per_token": 3.5e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 3.5e-07, + "supports_function_calling": true, + "supports_tool_choice": false, + "supports_vision": true + }, + "us.meta.llama3-2-1b-instruct-v1:0": { + "input_cost_per_token": 1e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-07, + "supports_function_calling": true, + "supports_tool_choice": false + }, + "us.meta.llama3-2-3b-instruct-v1:0": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.5e-07, + "supports_function_calling": true, + "supports_tool_choice": false + }, + "us.meta.llama3-2-90b-instruct-v1:0": { + "input_cost_per_token": 2e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2e-06, + "supports_function_calling": true, + "supports_tool_choice": false, + "supports_vision": true + }, + "us.meta.llama3-3-70b-instruct-v1:0": { + "input_cost_per_token": 7.2e-07, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 7.2e-07, + "supports_function_calling": true, + "supports_tool_choice": false + }, + "us.meta.llama4-maverick-17b-instruct-v1:0": { + "input_cost_per_token": 2.4e-07, + "input_cost_per_token_batches": 1.2e-07, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 9.7e-07, + "output_cost_per_token_batches": 4.85e-07, + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text", + "code" + ], + "supports_function_calling": true, + "supports_tool_choice": false + }, + "us.meta.llama4-scout-17b-instruct-v1:0": { + "input_cost_per_token": 1.7e-07, + "input_cost_per_token_batches": 8.5e-08, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 6.6e-07, + "output_cost_per_token_batches": 3.3e-07, + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text", + "code" + ], + "supports_function_calling": true, + "supports_tool_choice": false + }, + "us.mistral.pixtral-large-2502-v1:0": { + "input_cost_per_token": 2e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 6e-06, + "supports_function_calling": true, + "supports_tool_choice": false + }, + "v0/v0-1.0-md": { + "input_cost_per_token": 3e-06, + "litellm_provider": "v0", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "v0/v0-1.5-lg": { + "input_cost_per_token": 1.5e-05, + "litellm_provider": "v0", + "max_input_tokens": 512000, + "max_output_tokens": 512000, + "max_tokens": 512000, + "mode": "chat", + "output_cost_per_token": 7.5e-05, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "v0/v0-1.5-md": { + "input_cost_per_token": 3e-06, + "litellm_provider": "v0", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "vercel_ai_gateway/alibaba/qwen-3-14b": { + "input_cost_per_token": 8e-08, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 40960, + "max_output_tokens": 16384, + "max_tokens": 40960, + "mode": "chat", + "output_cost_per_token": 2.4e-07 + }, + "vercel_ai_gateway/alibaba/qwen-3-235b": { + "input_cost_per_token": 2e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 40960, + "max_output_tokens": 16384, + "max_tokens": 40960, + "mode": "chat", + "output_cost_per_token": 6e-07 + }, + "vercel_ai_gateway/alibaba/qwen-3-30b": { + "input_cost_per_token": 1e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 40960, + "max_output_tokens": 16384, + "max_tokens": 40960, + "mode": "chat", + "output_cost_per_token": 3e-07 + }, + "vercel_ai_gateway/alibaba/qwen-3-32b": { + "input_cost_per_token": 1e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 40960, + "max_output_tokens": 16384, + "max_tokens": 40960, + "mode": "chat", + "output_cost_per_token": 3e-07 + }, + "vercel_ai_gateway/alibaba/qwen3-coder": { + "input_cost_per_token": 4e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 262144, + "max_output_tokens": 66536, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 1.6e-06 + }, + "vercel_ai_gateway/amazon/nova-lite": { + "input_cost_per_token": 6e-08, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 300000, + "max_output_tokens": 8192, + "max_tokens": 300000, + "mode": "chat", + "output_cost_per_token": 2.4e-07 + }, + "vercel_ai_gateway/amazon/nova-micro": { + "input_cost_per_token": 3.5e-08, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.4e-07 + }, + "vercel_ai_gateway/amazon/nova-pro": { + "input_cost_per_token": 8e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 300000, + "max_output_tokens": 8192, + "max_tokens": 300000, + "mode": "chat", + "output_cost_per_token": 3.2e-06 + }, + "vercel_ai_gateway/amazon/titan-embed-text-v2": { + "input_cost_per_token": 2e-08, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 0, + "max_output_tokens": 0, + "max_tokens": 0, + "mode": "chat", + "output_cost_per_token": 0.0 + }, + "vercel_ai_gateway/anthropic/claude-3-haiku": { + "cache_creation_input_token_cost": 3e-07, + "cache_read_input_token_cost": 3e-08, + "input_cost_per_token": 2.5e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 200000, + "mode": "chat", + "output_cost_per_token": 1.25e-06 + }, + "vercel_ai_gateway/anthropic/claude-3-opus": { + "cache_creation_input_token_cost": 1.875e-05, + "cache_read_input_token_cost": 1.5e-06, + "input_cost_per_token": 1.5e-05, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 200000, + "mode": "chat", + "output_cost_per_token": 7.5e-05 + }, + "vercel_ai_gateway/anthropic/claude-3.5-haiku": { + "cache_creation_input_token_cost": 1e-06, + "cache_read_input_token_cost": 8e-08, + "input_cost_per_token": 8e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 200000, + "mode": "chat", + "output_cost_per_token": 4e-06 + }, + "vercel_ai_gateway/anthropic/claude-3.5-sonnet": { + "cache_creation_input_token_cost": 3.75e-06, + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 3e-06, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 200000, + "mode": "chat", + "output_cost_per_token": 1.5e-05 + }, + "vercel_ai_gateway/anthropic/claude-3.7-sonnet": { + "cache_creation_input_token_cost": 3.75e-06, + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 3e-06, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 200000, + "mode": "chat", + "output_cost_per_token": 1.5e-05 + }, + "vercel_ai_gateway/anthropic/claude-4-opus": { + "cache_creation_input_token_cost": 1.875e-05, + "cache_read_input_token_cost": 1.5e-06, + "input_cost_per_token": 1.5e-05, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 200000, + "max_output_tokens": 32000, + "max_tokens": 200000, + "mode": "chat", + "output_cost_per_token": 7.5e-05 + }, + "vercel_ai_gateway/anthropic/claude-4-sonnet": { + "cache_creation_input_token_cost": 3.75e-06, + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 3e-06, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 200000, + "mode": "chat", + "output_cost_per_token": 1.5e-05 + }, + "vercel_ai_gateway/cohere/command-a": { + "input_cost_per_token": 2.5e-06, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 256000, + "max_output_tokens": 8000, "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 1e-05 + }, + "vercel_ai_gateway/cohere/command-r": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 6e-07 + }, + "vercel_ai_gateway/cohere/command-r-plus": { + "input_cost_per_token": 2.5e-06, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05 + }, + "vercel_ai_gateway/cohere/embed-v4.0": { + "input_cost_per_token": 1.2e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 0, + "max_output_tokens": 0, + "max_tokens": 0, + "mode": "chat", + "output_cost_per_token": 0.0 + }, + "vercel_ai_gateway/deepseek/deepseek-r1": { + "input_cost_per_token": 5.5e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2.19e-06 + }, + "vercel_ai_gateway/deepseek/deepseek-r1-distill-llama-70b": { + "input_cost_per_token": 7.5e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 9.9e-07 + }, + "vercel_ai_gateway/deepseek/deepseek-v3": { + "input_cost_per_token": 9e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 9e-07 + }, + "vercel_ai_gateway/google/gemini-2.0-flash": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 6e-07 + }, + "vercel_ai_gateway/google/gemini-2.0-flash-lite": { + "input_cost_per_token": 7.5e-08, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 3e-07 + }, + "vercel_ai_gateway/google/gemini-2.5-flash": { + "input_cost_per_token": 3e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 1000000, + "max_output_tokens": 65536, + "max_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 2.5e-06 + }, + "vercel_ai_gateway/google/gemini-2.5-pro": { + "input_cost_per_token": 2.5e-06, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 1e-05 + }, + "vercel_ai_gateway/google/gemini-embedding-001": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 0, + "max_output_tokens": 0, + "max_tokens": 0, + "mode": "embedding", + "output_cost_per_token": 0.0 + }, + "vercel_ai_gateway/google/gemma-2-9b": { + "input_cost_per_token": 2e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 2e-07 + }, + "vercel_ai_gateway/google/text-embedding-005": { + "input_cost_per_token": 2.5e-08, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 0, + "max_output_tokens": 0, + "max_tokens": 0, + "mode": "embedding", + "output_cost_per_token": 0.0 + }, + "vercel_ai_gateway/google/text-multilingual-embedding-002": { + "input_cost_per_token": 2.5e-08, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 0, + "max_output_tokens": 0, + "max_tokens": 0, + "mode": "embedding", + "output_cost_per_token": 0.0 + }, + "vercel_ai_gateway/inception/mercury-coder-small": { + "input_cost_per_token": 2.5e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 32000, + "max_output_tokens": 16384, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 1e-06 + }, + "vercel_ai_gateway/meta/llama-3-70b": { + "input_cost_per_token": 5.9e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 7.9e-07 + }, + "vercel_ai_gateway/meta/llama-3-8b": { + "input_cost_per_token": 5e-08, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 8e-08 + }, + "vercel_ai_gateway/meta/llama-3.1-70b": { + "input_cost_per_token": 7.2e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 7.2e-07 + }, + "vercel_ai_gateway/meta/llama-3.1-8b": { + "input_cost_per_token": 5e-08, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 131000, + "max_output_tokens": 131072, + "max_tokens": 131000, + "mode": "chat", + "output_cost_per_token": 8e-08 + }, + "vercel_ai_gateway/meta/llama-3.2-11b": { + "input_cost_per_token": 1.6e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.6e-07 + }, + "vercel_ai_gateway/meta/llama-3.2-1b": { + "input_cost_per_token": 1e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-07 + }, + "vercel_ai_gateway/meta/llama-3.2-3b": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.5e-07 + }, + "vercel_ai_gateway/meta/llama-3.2-90b": { + "input_cost_per_token": 7.2e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 7.2e-07 + }, + "vercel_ai_gateway/meta/llama-3.3-70b": { + "input_cost_per_token": 7.2e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 7.2e-07 + }, + "vercel_ai_gateway/meta/llama-4-maverick": { + "input_cost_per_token": 2e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 131072, + "max_output_tokens": 8192, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 6e-07 + }, + "vercel_ai_gateway/meta/llama-4-scout": { + "input_cost_per_token": 1e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 131072, + "max_output_tokens": 8192, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 3e-07 + }, + "vercel_ai_gateway/mistral/codestral": { + "input_cost_per_token": 3e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 256000, + "max_output_tokens": 4000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 9e-07 + }, + "vercel_ai_gateway/mistral/codestral-embed": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 0, + "max_output_tokens": 0, + "max_tokens": 0, + "mode": "chat", + "output_cost_per_token": 0.0 + }, + "vercel_ai_gateway/mistral/devstral-small": { + "input_cost_per_token": 7e-08, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2.8e-07 + }, + "vercel_ai_gateway/mistral/magistral-medium": { + "input_cost_per_token": 2e-06, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 128000, + "max_output_tokens": 64000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5e-06 + }, + "vercel_ai_gateway/mistral/magistral-small": { + "input_cost_per_token": 5e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 128000, + "max_output_tokens": 64000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.5e-06 + }, + "vercel_ai_gateway/mistral/ministral-3b": { + "input_cost_per_token": 4e-08, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 128000, + "max_output_tokens": 4000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4e-08 + }, + "vercel_ai_gateway/mistral/ministral-8b": { + "input_cost_per_token": 1e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 128000, + "max_output_tokens": 4000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-07 + }, + "vercel_ai_gateway/mistral/mistral-embed": { + "input_cost_per_token": 1e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 0, + "max_output_tokens": 0, + "max_tokens": 0, + "mode": "chat", + "output_cost_per_token": 0.0 + }, + "vercel_ai_gateway/mistral/mistral-large": { + "input_cost_per_token": 2e-06, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 32000, + "max_output_tokens": 4000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 6e-06 + }, + "vercel_ai_gateway/mistral/mistral-saba-24b": { + "input_cost_per_token": 7.9e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 7.9e-07 + }, + "vercel_ai_gateway/mistral/mistral-small": { + "input_cost_per_token": 1e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 32000, + "max_output_tokens": 4000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 3e-07 + }, + "vercel_ai_gateway/mistral/mixtral-8x22b-instruct": { + "input_cost_per_token": 1.2e-06, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 65536, + "max_output_tokens": 2048, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 1.2e-06 + }, + "vercel_ai_gateway/mistral/pixtral-12b": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 128000, + "max_output_tokens": 4000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.5e-07 + }, + "vercel_ai_gateway/mistral/pixtral-large": { + "input_cost_per_token": 2e-06, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 128000, + "max_output_tokens": 4000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 6e-06 + }, + "vercel_ai_gateway/moonshotai/kimi-k2": { + "input_cost_per_token": 5.5e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 131072, + "max_output_tokens": 16384, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2.2e-06 + }, + "vercel_ai_gateway/morph/morph-v3-fast": { + "input_cost_per_token": 8e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 32768, + "max_output_tokens": 16384, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 1.2e-06 + }, + "vercel_ai_gateway/morph/morph-v3-large": { + "input_cost_per_token": 9e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 32768, + "max_output_tokens": 16384, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 1.9e-06 + }, + "vercel_ai_gateway/openai/gpt-3.5-turbo": { + "input_cost_per_token": 5e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 16385, + "max_output_tokens": 4096, + "max_tokens": 16385, + "mode": "chat", + "output_cost_per_token": 1.5e-06 + }, + "vercel_ai_gateway/openai/gpt-3.5-turbo-instruct": { + "input_cost_per_token": 1.5e-06, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 8192, + "max_output_tokens": 4096, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 2e-06 + }, + "vercel_ai_gateway/openai/gpt-4-turbo": { + "input_cost_per_token": 1e-05, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 3e-05 + }, + "vercel_ai_gateway/openai/gpt-4.1": { + "cache_creation_input_token_cost": 0.0, + "cache_read_input_token_cost": 5e-07, + "input_cost_per_token": 2e-06, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 1047576, + "mode": "chat", + "output_cost_per_token": 8e-06 + }, + "vercel_ai_gateway/openai/gpt-4.1-mini": { + "cache_creation_input_token_cost": 0.0, + "cache_read_input_token_cost": 1e-07, + "input_cost_per_token": 4e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 1047576, + "mode": "chat", + "output_cost_per_token": 1.6e-06 + }, + "vercel_ai_gateway/openai/gpt-4.1-nano": { + "cache_creation_input_token_cost": 0.0, + "cache_read_input_token_cost": 2.5e-08, + "input_cost_per_token": 1e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 1047576, + "mode": "chat", + "output_cost_per_token": 4e-07 + }, + "vercel_ai_gateway/openai/gpt-4o": { + "cache_creation_input_token_cost": 0.0, + "cache_read_input_token_cost": 1.25e-06, + "input_cost_per_token": 2.5e-06, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05 + }, + "vercel_ai_gateway/openai/gpt-4o-mini": { + "cache_creation_input_token_cost": 0.0, + "cache_read_input_token_cost": 7.5e-08, + "input_cost_per_token": 1.5e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 6e-07 + }, + "vercel_ai_gateway/openai/o1": { + "cache_creation_input_token_cost": 0.0, + "cache_read_input_token_cost": 7.5e-06, + "input_cost_per_token": 1.5e-05, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 200000, + "mode": "chat", + "output_cost_per_token": 6e-05 + }, + "vercel_ai_gateway/openai/o3": { + "cache_creation_input_token_cost": 0.0, + "cache_read_input_token_cost": 5e-07, + "input_cost_per_token": 2e-06, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 200000, + "mode": "chat", + "output_cost_per_token": 8e-06 + }, + "vercel_ai_gateway/openai/o3-mini": { + "cache_creation_input_token_cost": 0.0, + "cache_read_input_token_cost": 5.5e-07, + "input_cost_per_token": 1.1e-06, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 200000, + "mode": "chat", + "output_cost_per_token": 4.4e-06 + }, + "vercel_ai_gateway/openai/o4-mini": { + "cache_creation_input_token_cost": 0.0, + "cache_read_input_token_cost": 2.75e-07, + "input_cost_per_token": 1.1e-06, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 200000, + "mode": "chat", + "output_cost_per_token": 4.4e-06 + }, + "vercel_ai_gateway/openai/text-embedding-3-large": { + "input_cost_per_token": 1.3e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 0, + "max_output_tokens": 0, + "max_tokens": 0, + "mode": "embedding", + "output_cost_per_token": 0.0 + }, + "vercel_ai_gateway/openai/text-embedding-3-small": { + "input_cost_per_token": 2e-08, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 0, + "max_output_tokens": 0, + "max_tokens": 0, + "mode": "embedding", + "output_cost_per_token": 0.0 + }, + "vercel_ai_gateway/openai/text-embedding-ada-002": { + "input_cost_per_token": 1e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 0, + "max_output_tokens": 0, + "max_tokens": 0, + "mode": "embedding", + "output_cost_per_token": 0.0 + }, + "vercel_ai_gateway/perplexity/sonar": { + "input_cost_per_token": 1e-06, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 127000, + "max_output_tokens": 8000, + "max_tokens": 127000, + "mode": "chat", + "output_cost_per_token": 1e-06 + }, + "vercel_ai_gateway/perplexity/sonar-pro": { + "input_cost_per_token": 3e-06, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 200000, + "max_output_tokens": 8000, + "max_tokens": 200000, + "mode": "chat", + "output_cost_per_token": 1.5e-05 + }, + "vercel_ai_gateway/perplexity/sonar-reasoning": { + "input_cost_per_token": 1e-06, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 127000, + "max_output_tokens": 8000, + "max_tokens": 127000, + "mode": "chat", + "output_cost_per_token": 5e-06 + }, + "vercel_ai_gateway/perplexity/sonar-reasoning-pro": { + "input_cost_per_token": 2e-06, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 127000, + "max_output_tokens": 8000, + "max_tokens": 127000, + "mode": "chat", + "output_cost_per_token": 8e-06 + }, + "vercel_ai_gateway/vercel/v0-1.0-md": { + "input_cost_per_token": 3e-06, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 128000, + "max_output_tokens": 32000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.5e-05 + }, + "vercel_ai_gateway/vercel/v0-1.5-md": { + "input_cost_per_token": 3e-06, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 128000, + "max_output_tokens": 32768, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.5e-05 + }, + "vercel_ai_gateway/xai/grok-2": { + "input_cost_per_token": 2e-06, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 131072, + "max_output_tokens": 4000, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1e-05 + }, + "vercel_ai_gateway/xai/grok-2-vision": { + "input_cost_per_token": 2e-06, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 1e-05 + }, + "vercel_ai_gateway/xai/grok-3": { + "input_cost_per_token": 3e-06, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.5e-05 + }, + "vercel_ai_gateway/xai/grok-3-fast": { + "input_cost_per_token": 5e-06, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2.5e-05 + }, + "vercel_ai_gateway/xai/grok-3-mini": { + "input_cost_per_token": 3e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 5e-07 + }, + "vercel_ai_gateway/xai/grok-3-mini-fast": { + "input_cost_per_token": 6e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4e-06 + }, + "vercel_ai_gateway/xai/grok-4": { + "input_cost_per_token": 3e-06, + "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 256000, "max_output_tokens": 256000, - "input_cost_per_token": 1.9e-07, - "output_cost_per_token": 1.9e-07, - "litellm_provider": "ovhcloud", + "max_tokens": 256000, "mode": "chat", - "supports_function_calling": false, + "output_cost_per_token": 1.5e-05 + }, + "vercel_ai_gateway/zai/glm-4.5": { + "input_cost_per_token": 6e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2.2e-06 + }, + "vercel_ai_gateway/zai/glm-4.5-air": { + "input_cost_per_token": 2e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 128000, + "max_output_tokens": 96000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.1e-06 + }, + "vertex_ai/claude-3-5-haiku": { + "input_cost_per_token": 1e-06, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 5e-06, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_tool_choice": true + }, + "vertex_ai/claude-3-5-haiku@20241022": { + "input_cost_per_token": 1e-06, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 5e-06, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_tool_choice": true + }, + "vertex_ai/claude-3-5-sonnet": { + "input_cost_per_token": 3e-06, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "vertex_ai/claude-3-5-sonnet-v2": { + "input_cost_per_token": 3e-06, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "vertex_ai/claude-3-5-sonnet-v2@20241022": { + "input_cost_per_token": 3e-06, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "vertex_ai/claude-3-5-sonnet@20240620": { + "input_cost_per_token": 3e-06, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "vertex_ai/claude-3-7-sonnet@20250219": { + "cache_creation_input_token_cost": 3.75e-06, + "cache_read_input_token_cost": 3e-07, + "deprecation_date": "2025-06-01", + "input_cost_per_token": 3e-06, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": false, - "source": "https://endpoints.ai.cloud.ovh.net/models/mamba-codestral-7b-v0-1" + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159 + }, + "vertex_ai/claude-3-haiku": { + "input_cost_per_token": 2.5e-07, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.25e-06, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "vertex_ai/claude-3-haiku@20240307": { + "input_cost_per_token": 2.5e-07, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.25e-06, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "vertex_ai/claude-3-opus": { + "input_cost_per_token": 1.5e-05, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 7.5e-05, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "vertex_ai/claude-3-opus@20240229": { + "input_cost_per_token": 1.5e-05, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 7.5e-05, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "vertex_ai/claude-3-sonnet": { + "input_cost_per_token": 3e-06, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "vertex_ai/claude-3-sonnet@20240229": { + "input_cost_per_token": 3e-06, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "vertex_ai/claude-opus-4": { + "cache_creation_input_token_cost": 1.875e-05, + "cache_read_input_token_cost": 1.5e-06, + "input_cost_per_token": 1.5e-05, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 200000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 7.5e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159 + }, + "vertex_ai/claude-opus-4-1": { + "cache_creation_input_token_cost": 1.875e-05, + "cache_read_input_token_cost": 1.5e-06, + "input_cost_per_token": 1.5e-05, + "input_cost_per_token_batches": 7.5e-06, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 7.5e-05, + "output_cost_per_token_batches": 3.75e-05, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "vertex_ai/claude-opus-4-1@20250805": { + "cache_creation_input_token_cost": 1.875e-05, + "cache_read_input_token_cost": 1.5e-06, + "input_cost_per_token": 1.5e-05, + "input_cost_per_token_batches": 7.5e-06, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 7.5e-05, + "output_cost_per_token_batches": 3.75e-05, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "vertex_ai/claude-opus-4@20250514": { + "cache_creation_input_token_cost": 1.875e-05, + "cache_read_input_token_cost": 1.5e-06, + "input_cost_per_token": 1.5e-05, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 200000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 7.5e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159 + }, + "vertex_ai/claude-sonnet-4": { + "cache_creation_input_token_cost": 3.75e-06, + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 3e-06, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159 + }, + "vertex_ai/claude-sonnet-4@20250514": { + "cache_creation_input_token_cost": 3.75e-06, + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 3e-06, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159 + }, + "vertex_ai/codestral-2501": { + "input_cost_per_token": 2e-07, + "litellm_provider": "vertex_ai-mistral_models", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 6e-07, + "supports_function_calling": true, + "supports_tool_choice": true + }, + "vertex_ai/codestral@2405": { + "input_cost_per_token": 2e-07, + "litellm_provider": "vertex_ai-mistral_models", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 6e-07, + "supports_function_calling": true, + "supports_tool_choice": true + }, + "vertex_ai/codestral@latest": { + "input_cost_per_token": 2e-07, + "litellm_provider": "vertex_ai-mistral_models", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 6e-07, + "supports_function_calling": true, + "supports_tool_choice": true + }, + "vertex_ai/deepseek-ai/deepseek-r1-0528-maas": { + "input_cost_per_token": 1.35e-06, + "litellm_provider": "vertex_ai-deepseek_models", + "max_input_tokens": 65336, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 5.4e-06, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "vertex_ai/imagegeneration@006": { + "litellm_provider": "vertex_ai-image-models", + "mode": "image_generation", + "output_cost_per_image": 0.02, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" + }, + "vertex_ai/imagen-3.0-fast-generate-001": { + "litellm_provider": "vertex_ai-image-models", + "mode": "image_generation", + "output_cost_per_image": 0.02, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" + }, + "vertex_ai/imagen-3.0-generate-001": { + "litellm_provider": "vertex_ai-image-models", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" + }, + "vertex_ai/imagen-3.0-generate-002": { + "litellm_provider": "vertex_ai-image-models", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" + }, + "vertex_ai/imagen-4.0-fast-generate-001": { + "litellm_provider": "vertex_ai-image-models", + "mode": "image_generation", + "output_cost_per_image": 0.02, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" + }, + "vertex_ai/imagen-4.0-generate-001": { + "litellm_provider": "vertex_ai-image-models", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" + }, + "vertex_ai/imagen-4.0-ultra-generate-001": { + "litellm_provider": "vertex_ai-image-models", + "mode": "image_generation", + "output_cost_per_image": 0.06, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" + }, + "vertex_ai/jamba-1.5": { + "input_cost_per_token": 2e-07, + "litellm_provider": "vertex_ai-ai21_models", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 4e-07, + "supports_tool_choice": true + }, + "vertex_ai/jamba-1.5-large": { + "input_cost_per_token": 2e-06, + "litellm_provider": "vertex_ai-ai21_models", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 8e-06, + "supports_tool_choice": true + }, + "vertex_ai/jamba-1.5-large@001": { + "input_cost_per_token": 2e-06, + "litellm_provider": "vertex_ai-ai21_models", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 8e-06, + "supports_tool_choice": true + }, + "vertex_ai/jamba-1.5-mini": { + "input_cost_per_token": 2e-07, + "litellm_provider": "vertex_ai-ai21_models", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 4e-07, + "supports_tool_choice": true + }, + "vertex_ai/jamba-1.5-mini@001": { + "input_cost_per_token": 2e-07, + "litellm_provider": "vertex_ai-ai21_models", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 4e-07, + "supports_tool_choice": true + }, + "vertex_ai/meta/llama-3.1-405b-instruct-maas": { + "input_cost_per_token": 5e-06, + "litellm_provider": "vertex_ai-llama_models", + "max_input_tokens": 128000, + "max_output_tokens": 2048, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.6e-05, + "source": "https://console.cloud.google.com/vertex-ai/publishers/meta/model-garden/llama-3.2-90b-vision-instruct-maas", + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "vertex_ai/meta/llama-3.1-70b-instruct-maas": { + "input_cost_per_token": 0.0, + "litellm_provider": "vertex_ai-llama_models", + "max_input_tokens": 128000, + "max_output_tokens": 2048, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.0, + "source": "https://console.cloud.google.com/vertex-ai/publishers/meta/model-garden/llama-3.2-90b-vision-instruct-maas", + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "vertex_ai/meta/llama-3.1-8b-instruct-maas": { + "input_cost_per_token": 0.0, + "litellm_provider": "vertex_ai-llama_models", + "max_input_tokens": 128000, + "max_output_tokens": 2048, + "max_tokens": 128000, + "metadata": { + "notes": "VertexAI states that The Llama 3.1 API service for llama-3.1-70b-instruct-maas and llama-3.1-8b-instruct-maas are in public preview and at no cost." + }, + "mode": "chat", + "output_cost_per_token": 0.0, + "source": "https://console.cloud.google.com/vertex-ai/publishers/meta/model-garden/llama-3.2-90b-vision-instruct-maas", + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "vertex_ai/meta/llama-3.2-90b-vision-instruct-maas": { + "input_cost_per_token": 0.0, + "litellm_provider": "vertex_ai-llama_models", + "max_input_tokens": 128000, + "max_output_tokens": 2048, + "max_tokens": 128000, + "metadata": { + "notes": "VertexAI states that The Llama 3.2 API service is at no cost during public preview, and will be priced as per dollar-per-1M-tokens at GA." + }, + "mode": "chat", + "output_cost_per_token": 0.0, + "source": "https://console.cloud.google.com/vertex-ai/publishers/meta/model-garden/llama-3.2-90b-vision-instruct-maas", + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "vertex_ai/meta/llama-4-maverick-17b-128e-instruct-maas": { + "input_cost_per_token": 3.5e-07, + "litellm_provider": "vertex_ai-llama_models", + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "max_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 1.15e-06, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text", + "code" + ], + "supports_function_calling": true, + "supports_tool_choice": true + }, + "vertex_ai/meta/llama-4-maverick-17b-16e-instruct-maas": { + "input_cost_per_token": 3.5e-07, + "litellm_provider": "vertex_ai-llama_models", + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "max_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 1.15e-06, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text", + "code" + ], + "supports_function_calling": true, + "supports_tool_choice": true + }, + "vertex_ai/meta/llama-4-scout-17b-128e-instruct-maas": { + "input_cost_per_token": 2.5e-07, + "litellm_provider": "vertex_ai-llama_models", + "max_input_tokens": 10000000, + "max_output_tokens": 10000000, + "max_tokens": 10000000, + "mode": "chat", + "output_cost_per_token": 7e-07, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text", + "code" + ], + "supports_function_calling": true, + "supports_tool_choice": true + }, + "vertex_ai/meta/llama-4-scout-17b-16e-instruct-maas": { + "input_cost_per_token": 2.5e-07, + "litellm_provider": "vertex_ai-llama_models", + "max_input_tokens": 10000000, + "max_output_tokens": 10000000, + "max_tokens": 10000000, + "mode": "chat", + "output_cost_per_token": 7e-07, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text", + "code" + ], + "supports_function_calling": true, + "supports_tool_choice": true + }, + "vertex_ai/meta/llama3-405b-instruct-maas": { + "input_cost_per_token": 0.0, + "litellm_provider": "vertex_ai-llama_models", + "max_input_tokens": 32000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 0.0, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", + "supports_tool_choice": true + }, + "vertex_ai/meta/llama3-70b-instruct-maas": { + "input_cost_per_token": 0.0, + "litellm_provider": "vertex_ai-llama_models", + "max_input_tokens": 32000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 0.0, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", + "supports_tool_choice": true + }, + "vertex_ai/meta/llama3-8b-instruct-maas": { + "input_cost_per_token": 0.0, + "litellm_provider": "vertex_ai-llama_models", + "max_input_tokens": 32000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 0.0, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", + "supports_tool_choice": true + }, + "vertex_ai/mistral-large-2411": { + "input_cost_per_token": 2e-06, + "litellm_provider": "vertex_ai-mistral_models", + "max_input_tokens": 128000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 6e-06, + "supports_function_calling": true, + "supports_tool_choice": true + }, + "vertex_ai/mistral-large@2407": { + "input_cost_per_token": 2e-06, + "litellm_provider": "vertex_ai-mistral_models", + "max_input_tokens": 128000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 6e-06, + "supports_function_calling": true, + "supports_tool_choice": true + }, + "vertex_ai/mistral-large@2411-001": { + "input_cost_per_token": 2e-06, + "litellm_provider": "vertex_ai-mistral_models", + "max_input_tokens": 128000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 6e-06, + "supports_function_calling": true, + "supports_tool_choice": true + }, + "vertex_ai/mistral-large@latest": { + "input_cost_per_token": 2e-06, + "litellm_provider": "vertex_ai-mistral_models", + "max_input_tokens": 128000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 6e-06, + "supports_function_calling": true, + "supports_tool_choice": true + }, + "vertex_ai/mistral-nemo@2407": { + "input_cost_per_token": 3e-06, + "litellm_provider": "vertex_ai-mistral_models", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 3e-06, + "supports_function_calling": true, + "supports_tool_choice": true + }, + "vertex_ai/mistral-nemo@latest": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "vertex_ai-mistral_models", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.5e-07, + "supports_function_calling": true, + "supports_tool_choice": true + }, + "vertex_ai/mistral-small-2503": { + "input_cost_per_token": 1e-06, + "litellm_provider": "vertex_ai-mistral_models", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 3e-06, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "vertex_ai/mistral-small-2503@001": { + "input_cost_per_token": 1e-06, + "litellm_provider": "vertex_ai-mistral_models", + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 3e-06, + "supports_function_calling": true, + "supports_tool_choice": true + }, + "vertex_ai/openai/gpt-oss-120b-maas": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "vertex_ai-openai_models", + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 6e-07, + "source": "https://console.cloud.google.com/vertex-ai/publishers/openai/model-garden/gpt-oss-120b-maas", + "supports_reasoning": true + }, + "vertex_ai/openai/gpt-oss-20b-maas": { + "input_cost_per_token": 7.5e-08, + "litellm_provider": "vertex_ai-openai_models", + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 3e-07, + "source": "https://console.cloud.google.com/vertex-ai/publishers/openai/model-garden/gpt-oss-120b-maas", + "supports_reasoning": true + }, + "vertex_ai/qwen/qwen3-235b-a22b-instruct-2507-maas": { + "input_cost_per_token": 2.5e-07, + "litellm_provider": "vertex_ai-qwen_models", + "max_input_tokens": 262144, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1e-06, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "supports_function_calling": true, + "supports_tool_choice": true + }, + "vertex_ai/qwen/qwen3-coder-480b-a35b-instruct-maas": { + "input_cost_per_token": 1e-06, + "litellm_provider": "vertex_ai-qwen_models", + "max_input_tokens": 262144, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 4e-06, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "supports_function_calling": true, + "supports_tool_choice": true + }, + "vertex_ai/veo-2.0-generate-001": { + "litellm_provider": "vertex_ai-video-models", + "max_input_tokens": 1024, + "max_tokens": 1024, + "mode": "video_generation", + "output_cost_per_second": 0.35, + "source": "https://ai.google.dev/gemini-api/docs/video", + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "vertex_ai/veo-3.0-fast-generate-preview": { + "litellm_provider": "vertex_ai-video-models", + "max_input_tokens": 1024, + "max_tokens": 1024, + "mode": "video_generation", + "output_cost_per_second": 0.4, + "source": "https://ai.google.dev/gemini-api/docs/video", + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "vertex_ai/veo-3.0-generate-preview": { + "litellm_provider": "vertex_ai-video-models", + "max_input_tokens": 1024, + "max_tokens": 1024, + "mode": "video_generation", + "output_cost_per_second": 0.75, + "source": "https://ai.google.dev/gemini-api/docs/video", + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "voyage/rerank-2": { + "input_cost_per_query": 5e-08, + "input_cost_per_token": 5e-08, + "litellm_provider": "voyage", + "max_input_tokens": 16000, + "max_output_tokens": 16000, + "max_query_tokens": 16000, + "max_tokens": 16000, + "mode": "rerank", + "output_cost_per_token": 0.0 + }, + "voyage/rerank-2-lite": { + "input_cost_per_query": 2e-08, + "input_cost_per_token": 2e-08, + "litellm_provider": "voyage", + "max_input_tokens": 8000, + "max_output_tokens": 8000, + "max_query_tokens": 8000, + "max_tokens": 8000, + "mode": "rerank", + "output_cost_per_token": 0.0 + }, + "voyage/voyage-2": { + "input_cost_per_token": 1e-07, + "litellm_provider": "voyage", + "max_input_tokens": 4000, + "max_tokens": 4000, + "mode": "embedding", + "output_cost_per_token": 0.0 + }, + "voyage/voyage-3": { + "input_cost_per_token": 6e-08, + "litellm_provider": "voyage", + "max_input_tokens": 32000, + "max_tokens": 32000, + "mode": "embedding", + "output_cost_per_token": 0.0 + }, + "voyage/voyage-3-large": { + "input_cost_per_token": 1.8e-07, + "litellm_provider": "voyage", + "max_input_tokens": 32000, + "max_tokens": 32000, + "mode": "embedding", + "output_cost_per_token": 0.0 + }, + "voyage/voyage-3-lite": { + "input_cost_per_token": 2e-08, + "litellm_provider": "voyage", + "max_input_tokens": 32000, + "max_tokens": 32000, + "mode": "embedding", + "output_cost_per_token": 0.0 + }, + "voyage/voyage-code-2": { + "input_cost_per_token": 1.2e-07, + "litellm_provider": "voyage", + "max_input_tokens": 16000, + "max_tokens": 16000, + "mode": "embedding", + "output_cost_per_token": 0.0 + }, + "voyage/voyage-code-3": { + "input_cost_per_token": 1.8e-07, + "litellm_provider": "voyage", + "max_input_tokens": 32000, + "max_tokens": 32000, + "mode": "embedding", + "output_cost_per_token": 0.0 + }, + "voyage/voyage-context-3": { + "input_cost_per_token": 1.8e-07, + "litellm_provider": "voyage", + "max_input_tokens": 120000, + "max_tokens": 120000, + "mode": "embedding", + "output_cost_per_token": 0.0 + }, + "voyage/voyage-finance-2": { + "input_cost_per_token": 1.2e-07, + "litellm_provider": "voyage", + "max_input_tokens": 32000, + "max_tokens": 32000, + "mode": "embedding", + "output_cost_per_token": 0.0 + }, + "voyage/voyage-large-2": { + "input_cost_per_token": 1.2e-07, + "litellm_provider": "voyage", + "max_input_tokens": 16000, + "max_tokens": 16000, + "mode": "embedding", + "output_cost_per_token": 0.0 + }, + "voyage/voyage-law-2": { + "input_cost_per_token": 1.2e-07, + "litellm_provider": "voyage", + "max_input_tokens": 16000, + "max_tokens": 16000, + "mode": "embedding", + "output_cost_per_token": 0.0 + }, + "voyage/voyage-lite-01": { + "input_cost_per_token": 1e-07, + "litellm_provider": "voyage", + "max_input_tokens": 4096, + "max_tokens": 4096, + "mode": "embedding", + "output_cost_per_token": 0.0 + }, + "voyage/voyage-lite-02-instruct": { + "input_cost_per_token": 1e-07, + "litellm_provider": "voyage", + "max_input_tokens": 4000, + "max_tokens": 4000, + "mode": "embedding", + "output_cost_per_token": 0.0 + }, + "voyage/voyage-multimodal-3": { + "input_cost_per_token": 1.2e-07, + "litellm_provider": "voyage", + "max_input_tokens": 32000, + "max_tokens": 32000, + "mode": "embedding", + "output_cost_per_token": 0.0 + }, + "watsonx/ibm/granite-3-8b-instruct": { + "input_cost_per_token": 0.0002, + "litellm_provider": "watsonx", + "max_input_tokens": 8192, + "max_output_tokens": 1024, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.0002, + "supports_audio_input": false, + "supports_audio_output": false, + "supports_function_calling": true, + "supports_parallel_function_calling": false, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "watsonx/mistralai/mistral-large": { + "input_cost_per_token": 3e-06, + "litellm_provider": "watsonx", + "max_input_tokens": 131072, + "max_output_tokens": 16384, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1e-05, + "supports_audio_input": false, + "supports_audio_output": false, + "supports_function_calling": true, + "supports_parallel_function_calling": false, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "whisper-1": { + "input_cost_per_second": 0.0001, + "litellm_provider": "openai", + "mode": "audio_transcription", + "output_cost_per_second": 0.0001, + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "xai/grok-2": { + "input_cost_per_token": 2e-06, + "litellm_provider": "xai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1e-05, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_web_search": true + }, + "xai/grok-2-1212": { + "input_cost_per_token": 2e-06, + "litellm_provider": "xai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1e-05, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_web_search": true + }, + "xai/grok-2-latest": { + "input_cost_per_token": 2e-06, + "litellm_provider": "xai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1e-05, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_web_search": true + }, + "xai/grok-2-vision": { + "input_cost_per_image": 2e-06, + "input_cost_per_token": 2e-06, + "litellm_provider": "xai", + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 1e-05, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "xai/grok-2-vision-1212": { + "input_cost_per_image": 2e-06, + "input_cost_per_token": 2e-06, + "litellm_provider": "xai", + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 1e-05, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "xai/grok-2-vision-latest": { + "input_cost_per_image": 2e-06, + "input_cost_per_token": 2e-06, + "litellm_provider": "xai", + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 1e-05, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "xai/grok-3": { + "input_cost_per_token": 3e-06, + "litellm_provider": "xai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "source": "https://x.ai/api#pricing", + "supports_function_calling": true, + "supports_response_schema": false, + "supports_tool_choice": true, + "supports_web_search": true + }, + "xai/grok-3-beta": { + "input_cost_per_token": 3e-06, + "litellm_provider": "xai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "source": "https://x.ai/api#pricing", + "supports_function_calling": true, + "supports_response_schema": false, + "supports_tool_choice": true, + "supports_web_search": true + }, + "xai/grok-3-fast-beta": { + "input_cost_per_token": 5e-06, + "litellm_provider": "xai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2.5e-05, + "source": "https://x.ai/api#pricing", + "supports_function_calling": true, + "supports_response_schema": false, + "supports_tool_choice": true, + "supports_web_search": true + }, + "xai/grok-3-fast-latest": { + "input_cost_per_token": 5e-06, + "litellm_provider": "xai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2.5e-05, + "source": "https://x.ai/api#pricing", + "supports_function_calling": true, + "supports_response_schema": false, + "supports_tool_choice": true, + "supports_web_search": true + }, + "xai/grok-3-latest": { + "input_cost_per_token": 3e-06, + "litellm_provider": "xai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "source": "https://x.ai/api#pricing", + "supports_function_calling": true, + "supports_response_schema": false, + "supports_tool_choice": true, + "supports_web_search": true + }, + "xai/grok-3-mini": { + "input_cost_per_token": 3e-07, + "litellm_provider": "xai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 5e-07, + "source": "https://x.ai/api#pricing", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": false, + "supports_tool_choice": true, + "supports_web_search": true + }, + "xai/grok-3-mini-beta": { + "input_cost_per_token": 3e-07, + "litellm_provider": "xai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 5e-07, + "source": "https://x.ai/api#pricing", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": false, + "supports_tool_choice": true, + "supports_web_search": true + }, + "xai/grok-3-mini-fast": { + "input_cost_per_token": 6e-07, + "litellm_provider": "xai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4e-06, + "source": "https://x.ai/api#pricing", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": false, + "supports_tool_choice": true, + "supports_web_search": true + }, + "xai/grok-3-mini-fast-beta": { + "input_cost_per_token": 6e-07, + "litellm_provider": "xai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4e-06, + "source": "https://x.ai/api#pricing", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": false, + "supports_tool_choice": true, + "supports_web_search": true + }, + "xai/grok-3-mini-fast-latest": { + "input_cost_per_token": 6e-07, + "litellm_provider": "xai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4e-06, + "source": "https://x.ai/api#pricing", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": false, + "supports_tool_choice": true, + "supports_web_search": true + }, + "xai/grok-3-mini-latest": { + "input_cost_per_token": 3e-07, + "litellm_provider": "xai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 5e-07, + "source": "https://x.ai/api#pricing", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": false, + "supports_tool_choice": true, + "supports_web_search": true + }, + "xai/grok-4": { + "input_cost_per_token": 3e-06, + "litellm_provider": "xai", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "source": "https://docs.x.ai/docs/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_web_search": true + }, + "xai/grok-4-0709": { + "input_cost_per_token": 3e-06, + "litellm_provider": "xai", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "source": "https://docs.x.ai/docs/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_web_search": true + }, + "xai/grok-4-latest": { + "input_cost_per_token": 3e-06, + "litellm_provider": "xai", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "source": "https://docs.x.ai/docs/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_web_search": true + }, + "xai/grok-beta": { + "input_cost_per_token": 5e-06, + "litellm_provider": "xai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "xai/grok-code-fast": { + "cache_read_input_token_cost": 2e-08, + "input_cost_per_token": 2e-07, + "litellm_provider": "xai", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 1.5e-06, + "source": "https://docs.x.ai/docs/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "xai/grok-code-fast-1": { + "cache_read_input_token_cost": 2e-08, + "input_cost_per_token": 2e-07, + "litellm_provider": "xai", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 1.5e-06, + "source": "https://docs.x.ai/docs/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "xai/grok-code-fast-1-0825": { + "cache_read_input_token_cost": 2e-08, + "input_cost_per_token": 2e-07, + "litellm_provider": "xai", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 1.5e-06, + "source": "https://docs.x.ai/docs/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "xai/grok-vision-beta": { + "input_cost_per_image": 5e-06, + "input_cost_per_token": 5e-06, + "litellm_provider": "xai", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true } -} +} \ No newline at end of file diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 4394cef383..1452f1465d 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -1,2570 +1,821 @@ { - "sample_spec": { - "max_tokens": "LEGACY parameter. set to max_output_tokens if provider specifies it. IF not set to max_input_tokens, if provider specifies it.", - "max_input_tokens": "max input tokens, if the provider specifies it. if not default to max_tokens", - "max_output_tokens": "max output tokens, if the provider specifies it. if not default to max_tokens", - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "output_cost_per_reasoning_token": 0.0, - "input_cost_per_audio_token": 0.0, - "litellm_provider": "one of https://docs.litellm.ai/docs/providers", - "mode": "one of: chat, embedding, completion, image_generation, audio_transcription, audio_speech, image_generation, moderation, rerank", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_vision": true, - "supports_audio_input": true, - "supports_audio_output": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_reasoning": true, - "supports_web_search": true, - "search_context_cost_per_query": { - "search_context_size_low": 0.0, - "search_context_size_medium": 0.0, - "search_context_size_high": 0.0 - }, - "file_search_cost_per_1k_calls": 0.0, - "file_search_cost_per_gb_per_day": 0.0, - "vector_store_cost_per_gb_per_day": 0.0, - "computer_use_input_cost_per_1k_tokens": 0.0, - "computer_use_output_cost_per_1k_tokens": 0.0, - "code_interpreter_cost_per_session": 0.0, - "supported_regions": [ - "global", - "us-west-2", - "eu-west-1", - "ap-southeast-1", - "ap-northeast-1" - ], - "deprecation_date": "date when the model becomes deprecated in the format YYYY-MM-DD" - }, - "omni-moderation-latest": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 0, - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "openai", - "mode": "moderation" - }, - "omni-moderation-latest-intents": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 0, - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "openai", - "mode": "moderation" - }, - "omni-moderation-2024-09-26": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 0, - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "openai", - "mode": "moderation" - }, - "gpt-4": { - "max_tokens": 4096, - "max_input_tokens": 8192, - "max_output_tokens": 4096, - "input_cost_per_token": 3e-05, - "output_cost_per_token": 6e-05, - "litellm_provider": "openai", - "mode": "chat", - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "gpt-4.1": { - "max_tokens": 32768, - "max_input_tokens": 1047576, - "max_output_tokens": 32768, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 8e-06, - "input_cost_per_token_batches": 1e-06, - "output_cost_per_token_batches": 4e-06, - "cache_read_input_token_cost": 5e-07, - "litellm_provider": "openai", - "mode": "chat", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_pdf_input": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_native_streaming": true - }, - "gpt-4.1-2025-04-14": { - "max_tokens": 32768, - "max_input_tokens": 1047576, - "max_output_tokens": 32768, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 8e-06, - "input_cost_per_token_batches": 1e-06, - "output_cost_per_token_batches": 4e-06, - "cache_read_input_token_cost": 5e-07, - "litellm_provider": "openai", - "mode": "chat", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_pdf_input": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_native_streaming": true - }, - "gpt-4.1-mini": { - "max_tokens": 32768, - "max_input_tokens": 1047576, - "max_output_tokens": 32768, - "input_cost_per_token": 4e-07, - "output_cost_per_token": 1.6e-06, - "input_cost_per_token_batches": 2e-07, - "output_cost_per_token_batches": 8e-07, - "cache_read_input_token_cost": 1e-07, - "litellm_provider": "openai", - "mode": "chat", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_pdf_input": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_native_streaming": true - }, - "gpt-4.1-mini-2025-04-14": { - "max_tokens": 32768, - "max_input_tokens": 1047576, - "max_output_tokens": 32768, - "input_cost_per_token": 4e-07, - "output_cost_per_token": 1.6e-06, - "input_cost_per_token_batches": 2e-07, - "output_cost_per_token_batches": 8e-07, - "cache_read_input_token_cost": 1e-07, - "litellm_provider": "openai", - "mode": "chat", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_pdf_input": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_native_streaming": true - }, - "gpt-4.1-nano": { - "max_tokens": 32768, - "max_input_tokens": 1047576, - "max_output_tokens": 32768, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 4e-07, - "input_cost_per_token_batches": 5e-08, - "output_cost_per_token_batches": 2e-07, - "cache_read_input_token_cost": 2.5e-08, - "litellm_provider": "openai", - "mode": "chat", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_pdf_input": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_native_streaming": true - }, - "gpt-4.1-nano-2025-04-14": { - "max_tokens": 32768, - "max_input_tokens": 1047576, - "max_output_tokens": 32768, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 4e-07, - "input_cost_per_token_batches": 5e-08, - "output_cost_per_token_batches": 2e-07, - "cache_read_input_token_cost": 2.5e-08, - "litellm_provider": "openai", - "mode": "chat", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_pdf_input": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_native_streaming": true - }, - "gpt-4o": { - "max_tokens": 16384, - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "input_cost_per_token": 2.5e-06, - "output_cost_per_token": 1e-05, - "input_cost_per_token_batches": 1.25e-06, - "output_cost_per_token_batches": 5e-06, - "cache_read_input_token_cost": 1.25e-06, - "litellm_provider": "openai", - "mode": "chat", - "supports_pdf_input": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "watsonx/ibm/granite-3-8b-instruct": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 1024, - "input_cost_per_token": 0.0002, - "output_cost_per_token": 0.0002, - "litellm_provider": "watsonx", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_parallel_function_calling": false, - "supports_vision": false, - "supports_audio_input": false, - "supports_audio_output": false, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_system_messages": true - }, - "watsonx/mistralai/mistral-large": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 16384, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1e-05, - "litellm_provider": "watsonx", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_parallel_function_calling": false, - "supports_vision": false, - "supports_audio_input": false, - "supports_audio_output": false, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_system_messages": true - }, - "gpt-4o-search-preview-2025-03-11": { - "max_tokens": 16384, - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "input_cost_per_token": 2.5e-06, - "output_cost_per_token": 1e-05, - "input_cost_per_token_batches": 1.25e-06, - "output_cost_per_token_batches": 5e-06, - "cache_read_input_token_cost": 1.25e-06, - "litellm_provider": "openai", - "mode": "chat", - "supports_pdf_input": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "gpt-4o-search-preview": { - "max_tokens": 16384, - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "input_cost_per_token": 2.5e-06, - "output_cost_per_token": 1e-05, - "input_cost_per_token_batches": 1.25e-06, - "output_cost_per_token_batches": 5e-06, - "cache_read_input_token_cost": 1.25e-06, - "litellm_provider": "openai", - "mode": "chat", - "supports_pdf_input": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_web_search": true, - "search_context_cost_per_query": { - "search_context_size_low": 0.03, - "search_context_size_medium": 0.035, - "search_context_size_high": 0.05 - } - }, - "gpt-4.5-preview": { - "max_tokens": 16384, - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "input_cost_per_token": 7.5e-05, - "output_cost_per_token": 0.00015, - "input_cost_per_token_batches": 3.75e-05, - "output_cost_per_token_batches": 7.5e-05, - "cache_read_input_token_cost": 3.75e-05, - "litellm_provider": "openai", - "mode": "chat", - "supports_pdf_input": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "gpt-4.5-preview-2025-02-27": { - "max_tokens": 16384, - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "input_cost_per_token": 7.5e-05, - "output_cost_per_token": 0.00015, - "input_cost_per_token_batches": 3.75e-05, - "output_cost_per_token_batches": 7.5e-05, - "cache_read_input_token_cost": 3.75e-05, - "litellm_provider": "openai", - "mode": "chat", - "supports_pdf_input": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "deprecation_date": "2025-07-14" - }, - "gpt-4o-audio-preview": { - "max_tokens": 16384, - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "input_cost_per_token": 2.5e-06, - "input_cost_per_audio_token": 0.0001, - "output_cost_per_token": 1e-05, - "output_cost_per_audio_token": 0.0002, - "litellm_provider": "openai", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_audio_input": true, - "supports_audio_output": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "gpt-4o-audio-preview-2024-12-17": { - "max_tokens": 16384, - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "input_cost_per_token": 2.5e-06, - "input_cost_per_audio_token": 4e-05, - "output_cost_per_token": 1e-05, - "output_cost_per_audio_token": 8e-05, - "litellm_provider": "openai", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_audio_input": true, - "supports_audio_output": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "gpt-4o-audio-preview-2024-10-01": { - "max_tokens": 16384, - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "input_cost_per_token": 2.5e-06, - "input_cost_per_audio_token": 0.0001, - "output_cost_per_token": 1e-05, - "output_cost_per_audio_token": 0.0002, - "litellm_provider": "openai", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_audio_input": true, - "supports_audio_output": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "gpt-4o-audio-preview-2025-06-03": { - "max_tokens": 16384, - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "input_cost_per_token": 2.5e-06, - "input_cost_per_audio_token": 4e-05, - "output_cost_per_token": 1e-05, - "output_cost_per_audio_token": 8e-05, - "litellm_provider": "openai", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_audio_input": true, - "supports_audio_output": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "gpt-4o-mini-audio-preview": { - "max_tokens": 16384, - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "input_cost_per_token": 1.5e-07, - "input_cost_per_audio_token": 1e-05, - "output_cost_per_token": 6e-07, - "output_cost_per_audio_token": 2e-05, - "litellm_provider": "openai", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_audio_input": true, - "supports_audio_output": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "gpt-4o-mini-audio-preview-2024-12-17": { - "max_tokens": 16384, - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "input_cost_per_token": 1.5e-07, - "input_cost_per_audio_token": 1e-05, - "output_cost_per_token": 6e-07, - "output_cost_per_audio_token": 2e-05, - "litellm_provider": "openai", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_audio_input": true, - "supports_audio_output": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "gpt-4o-mini": { - "max_tokens": 16384, - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 6e-07, - "input_cost_per_token_batches": 7.5e-08, - "output_cost_per_token_batches": 3e-07, - "cache_read_input_token_cost": 7.5e-08, - "litellm_provider": "openai", - "mode": "chat", - "supports_pdf_input": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "gpt-4o-mini-search-preview-2025-03-11": { - "max_tokens": 16384, - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 6e-07, - "input_cost_per_token_batches": 7.5e-08, - "output_cost_per_token_batches": 3e-07, - "cache_read_input_token_cost": 7.5e-08, - "litellm_provider": "openai", - "mode": "chat", - "supports_pdf_input": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "gpt-4o-mini-search-preview": { - "max_tokens": 16384, - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 6e-07, - "input_cost_per_token_batches": 7.5e-08, - "output_cost_per_token_batches": 3e-07, - "cache_read_input_token_cost": 7.5e-08, - "litellm_provider": "openai", - "mode": "chat", - "supports_pdf_input": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_web_search": true, - "search_context_cost_per_query": { - "search_context_size_low": 0.025, - "search_context_size_medium": 0.0275, - "search_context_size_high": 0.03 - } - }, - "gpt-4o-mini-2024-07-18": { - "max_tokens": 16384, - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 6e-07, - "input_cost_per_token_batches": 7.5e-08, - "output_cost_per_token_batches": 3e-07, - "cache_read_input_token_cost": 7.5e-08, - "litellm_provider": "openai", - "mode": "chat", - "supports_pdf_input": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "search_context_cost_per_query": { - "search_context_size_low": 0.025, - "search_context_size_medium": 0.0275, - "search_context_size_high": 0.03 - } - }, - "gpt-5": { - "max_tokens": 128000, - "max_input_tokens": 400000, - "max_output_tokens": 128000, - "input_cost_per_token": 1.25e-06, - "output_cost_per_token": 1e-05, - "cache_read_input_token_cost": 1.25e-07, - "litellm_provider": "openai", - "mode": "chat", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_pdf_input": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_native_streaming": true, - "supports_reasoning": true - }, - "gpt-5-mini": { - "max_tokens": 128000, - "max_input_tokens": 400000, - "max_output_tokens": 128000, - "input_cost_per_token": 2.5e-07, - "output_cost_per_token": 2e-06, - "cache_read_input_token_cost": 2.5e-08, - "litellm_provider": "openai", - "mode": "chat", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_pdf_input": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_native_streaming": true, - "supports_reasoning": true - }, - "gpt-5-nano": { - "max_tokens": 128000, - "max_input_tokens": 400000, - "max_output_tokens": 128000, - "input_cost_per_token": 5e-08, - "output_cost_per_token": 4e-07, - "cache_read_input_token_cost": 5e-09, - "litellm_provider": "openai", - "mode": "chat", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_pdf_input": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_native_streaming": true, - "supports_reasoning": true - }, - "gpt-5-chat": { - "max_tokens": 128000, - "max_input_tokens": 400000, - "max_output_tokens": 128000, - "input_cost_per_token": 1.25e-06, - "output_cost_per_token": 1e-05, - "cache_read_input_token_cost": 1.25e-07, - "litellm_provider": "openai", - "mode": "chat", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_pdf_input": true, - "supports_function_calling": false, - "supports_parallel_function_calling": false, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": false, - "supports_native_streaming": true, - "supports_reasoning": true - }, - "gpt-5-chat-latest": { - "max_tokens": 128000, - "max_input_tokens": 400000, - "max_output_tokens": 128000, - "input_cost_per_token": 1.25e-06, - "output_cost_per_token": 1e-05, - "cache_read_input_token_cost": 1.25e-07, - "litellm_provider": "openai", - "mode": "chat", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_pdf_input": true, - "supports_function_calling": false, - "supports_parallel_function_calling": false, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": false, - "supports_native_streaming": true, - "supports_reasoning": true - }, - "gpt-5-2025-08-07": { - "max_tokens": 128000, - "max_input_tokens": 400000, - "max_output_tokens": 128000, - "input_cost_per_token": 1.25e-06, - "output_cost_per_token": 1e-05, - "cache_read_input_token_cost": 1.25e-07, - "litellm_provider": "openai", - "mode": "chat", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_pdf_input": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_native_streaming": true, - "supports_reasoning": true - }, - "gpt-5-mini-2025-08-07": { - "max_tokens": 128000, - "max_input_tokens": 400000, - "max_output_tokens": 128000, - "input_cost_per_token": 2.5e-07, - "output_cost_per_token": 2e-06, - "cache_read_input_token_cost": 2.5e-08, - "litellm_provider": "openai", - "mode": "chat", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_pdf_input": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_native_streaming": true, - "supports_reasoning": true - }, - "gpt-5-nano-2025-08-07": { - "max_tokens": 128000, - "max_input_tokens": 400000, - "max_output_tokens": 128000, - "input_cost_per_token": 5e-08, - "output_cost_per_token": 4e-07, - "cache_read_input_token_cost": 5e-09, - "litellm_provider": "openai", - "mode": "chat", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_pdf_input": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_native_streaming": true, - "supports_reasoning": true - }, - "codex-mini-latest": { - "max_tokens": 100000, - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "input_cost_per_token": 1.5e-06, - "output_cost_per_token": 6e-06, - "cache_read_input_token_cost": 3.75e-07, - "litellm_provider": "openai", - "mode": "responses", - "supports_pdf_input": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supported_endpoints": [ - "/v1/responses" - ] - }, - "o1-pro": { - "max_tokens": 100000, - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "input_cost_per_token": 0.00015, - "output_cost_per_token": 0.0006, - "input_cost_per_token_batches": 7.5e-05, - "output_cost_per_token_batches": 0.0003, - "litellm_provider": "openai", - "mode": "responses", - "supports_pdf_input": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_native_streaming": false, - "supports_reasoning": true, - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supported_endpoints": [ - "/v1/responses", - "/v1/batch" - ] - }, - "o1-pro-2025-03-19": { - "max_tokens": 100000, - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "input_cost_per_token": 0.00015, - "output_cost_per_token": 0.0006, - "input_cost_per_token_batches": 7.5e-05, - "output_cost_per_token_batches": 0.0003, - "litellm_provider": "openai", - "mode": "responses", - "supports_pdf_input": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_native_streaming": false, - "supports_reasoning": true, - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supported_endpoints": [ - "/v1/responses", - "/v1/batch" - ] - }, - "o1": { - "max_tokens": 100000, - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "input_cost_per_token": 1.5e-05, - "output_cost_per_token": 6e-05, - "cache_read_input_token_cost": 7.5e-06, - "litellm_provider": "openai", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_response_schema": true, - "supports_reasoning": true, - "supports_tool_choice": true - }, - "o1-mini": { - "max_tokens": 65536, - "max_input_tokens": 128000, - "max_output_tokens": 65536, - "input_cost_per_token": 1.1e-06, - "output_cost_per_token": 4.4e-06, - "cache_read_input_token_cost": 5.5e-07, - "litellm_provider": "openai", - "mode": "chat", - "supports_vision": true, - "supports_pdf_input": true, - "supports_prompt_caching": true - }, - "computer-use-preview": { - "max_tokens": 1024, - "max_input_tokens": 8192, - "max_output_tokens": 1024, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.2e-05, - "litellm_provider": "azure", - "mode": "chat", - "supported_endpoints": [ - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": false, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_reasoning": true - }, - "o3-deep-research": { - "max_tokens": 100000, - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "input_cost_per_token": 1e-05, - "output_cost_per_token": 4e-05, - "input_cost_per_token_batches": 5e-06, - "output_cost_per_token_batches": 2e-05, - "cache_read_input_token_cost": 2.5e-06, - "litellm_provider": "openai", - "mode": "responses", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_pdf_input": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_native_streaming": true - }, - "o3-deep-research-2025-06-26": { - "max_tokens": 100000, - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "input_cost_per_token": 1e-05, - "output_cost_per_token": 4e-05, - "input_cost_per_token_batches": 5e-06, - "output_cost_per_token_batches": 2e-05, - "cache_read_input_token_cost": 2.5e-06, - "litellm_provider": "openai", - "mode": "responses", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_pdf_input": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_native_streaming": true - }, - "o3-pro": { - "max_tokens": 100000, - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "input_cost_per_token": 2e-05, - "input_cost_per_token_batches": 1e-05, - "output_cost_per_token_batches": 4e-05, - "output_cost_per_token": 8e-05, - "litellm_provider": "openai", - "mode": "responses", - "supports_function_calling": true, - "supports_parallel_function_calling": false, - "supports_vision": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_reasoning": true, - "supports_tool_choice": true, - "supported_endpoints": [ - "/v1/responses", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ] - }, - "o3-pro-2025-06-10": { - "max_tokens": 100000, - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "input_cost_per_token": 2e-05, - "input_cost_per_token_batches": 1e-05, - "output_cost_per_token_batches": 4e-05, - "output_cost_per_token": 8e-05, - "litellm_provider": "openai", - "mode": "responses", - "supports_function_calling": true, - "supports_parallel_function_calling": false, - "supports_vision": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_reasoning": true, - "supports_tool_choice": true, - "supported_endpoints": [ - "/v1/responses", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ] - }, - "o3": { - "max_tokens": 100000, - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 8e-06, - "cache_read_input_token_cost": 5e-07, - "litellm_provider": "openai", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": false, - "supports_vision": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_reasoning": true, - "supports_tool_choice": true, - "supported_endpoints": [ - "/v1/responses", - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ] - }, - "o3-2025-04-16": { - "max_tokens": 100000, - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 8e-06, - "cache_read_input_token_cost": 5e-07, - "litellm_provider": "openai", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": false, - "supports_vision": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_reasoning": true, - "supports_tool_choice": true, - "supported_endpoints": [ - "/v1/responses", - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ] - }, - "o3-mini": { - "max_tokens": 100000, - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "input_cost_per_token": 1.1e-06, - "output_cost_per_token": 4.4e-06, - "cache_read_input_token_cost": 5.5e-07, - "litellm_provider": "openai", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": false, - "supports_vision": false, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_reasoning": true, - "supports_tool_choice": true - }, - "o3-mini-2025-01-31": { - "max_tokens": 100000, - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "input_cost_per_token": 1.1e-06, - "output_cost_per_token": 4.4e-06, - "cache_read_input_token_cost": 5.5e-07, - "litellm_provider": "openai", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": false, - "supports_vision": false, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_reasoning": true, - "supports_tool_choice": true - }, - "o4-mini": { - "max_tokens": 100000, - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "input_cost_per_token": 1.1e-06, - "output_cost_per_token": 4.4e-06, - "cache_read_input_token_cost": 2.75e-07, - "litellm_provider": "openai", - "mode": "chat", - "supports_pdf_input": true, - "supports_function_calling": true, - "supports_parallel_function_calling": false, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_reasoning": true, - "supports_tool_choice": true - }, - "o4-mini-deep-research": { - "max_tokens": 100000, - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 8e-06, - "input_cost_per_token_batches": 1e-06, - "output_cost_per_token_batches": 4e-06, - "cache_read_input_token_cost": 5e-07, - "litellm_provider": "openai", - "mode": "responses", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_pdf_input": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_native_streaming": true - }, - "o4-mini-deep-research-2025-06-26": { - "max_tokens": 100000, - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 8e-06, - "input_cost_per_token_batches": 1e-06, - "output_cost_per_token_batches": 4e-06, - "cache_read_input_token_cost": 5e-07, - "litellm_provider": "openai", - "mode": "responses", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_pdf_input": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_native_streaming": true - }, - "o4-mini-2025-04-16": { - "max_tokens": 100000, - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "input_cost_per_token": 1.1e-06, - "output_cost_per_token": 4.4e-06, - "cache_read_input_token_cost": 2.75e-07, - "litellm_provider": "openai", - "mode": "chat", - "supports_pdf_input": true, - "supports_function_calling": true, - "supports_parallel_function_calling": false, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_reasoning": true, - "supports_tool_choice": true - }, - "o1-mini-2024-09-12": { - "max_tokens": 65536, - "max_input_tokens": 128000, - "max_output_tokens": 65536, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.2e-05, - "cache_read_input_token_cost": 1.5e-06, - "litellm_provider": "openai", - "mode": "chat", - "supports_pdf_input": true, - "supports_vision": true, - "supports_reasoning": true, - "supports_prompt_caching": true - }, - "o1-preview": { - "max_tokens": 32768, - "max_input_tokens": 128000, - "max_output_tokens": 32768, - "input_cost_per_token": 1.5e-05, - "output_cost_per_token": 6e-05, - "cache_read_input_token_cost": 7.5e-06, - "litellm_provider": "openai", - "mode": "chat", - "supports_pdf_input": true, - "supports_vision": true, - "supports_reasoning": true, - "supports_prompt_caching": true - }, - "o1-preview-2024-09-12": { - "max_tokens": 32768, - "max_input_tokens": 128000, - "max_output_tokens": 32768, - "input_cost_per_token": 1.5e-05, - "output_cost_per_token": 6e-05, - "cache_read_input_token_cost": 7.5e-06, - "litellm_provider": "openai", - "mode": "chat", - "supports_pdf_input": true, - "supports_vision": true, - "supports_reasoning": true, - "supports_prompt_caching": true - }, - "o1-2024-12-17": { - "max_tokens": 100000, - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "input_cost_per_token": 1.5e-05, - "output_cost_per_token": 6e-05, - "cache_read_input_token_cost": 7.5e-06, - "litellm_provider": "openai", - "mode": "chat", - "supports_pdf_input": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_response_schema": true, - "supports_reasoning": true, - "supports_tool_choice": true - }, - "chatgpt-4o-latest": { - "max_tokens": 4096, - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 5e-06, - "output_cost_per_token": 1.5e-05, - "litellm_provider": "openai", - "mode": "chat", - "supports_pdf_input": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "gpt-4o-2024-05-13": { - "max_tokens": 4096, - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 5e-06, - "output_cost_per_token": 1.5e-05, - "input_cost_per_token_batches": 2.5e-06, - "output_cost_per_token_batches": 7.5e-06, - "litellm_provider": "openai", - "mode": "chat", - "supports_pdf_input": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "gpt-4o-2024-08-06": { - "max_tokens": 16384, - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "input_cost_per_token": 2.5e-06, - "output_cost_per_token": 1e-05, - "input_cost_per_token_batches": 1.25e-06, - "output_cost_per_token_batches": 5e-06, - "cache_read_input_token_cost": 1.25e-06, - "litellm_provider": "openai", - "mode": "chat", - "supports_pdf_input": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "gpt-4o-2024-11-20": { - "max_tokens": 16384, - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "input_cost_per_token": 2.5e-06, - "output_cost_per_token": 1e-05, - "input_cost_per_token_batches": 1.25e-06, - "output_cost_per_token_batches": 5e-06, - "cache_read_input_token_cost": 1.25e-06, - "litellm_provider": "openai", - "mode": "chat", - "supports_pdf_input": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "gpt-realtime": { - "max_tokens": 4096, - "max_input_tokens": 32000, - "max_output_tokens": 4096, - "input_cost_per_token": 4e-06, - "cache_read_input_token_cost": 0.4e-06, - "output_cost_per_token": 16e-06, - "input_cost_per_audio_token": 32e-06, - "output_cost_per_audio_token": 64e-06, - "cache_creation_input_audio_token_cost": 0.4e-06, - "input_cost_per_image": 5e-06, - "litellm_provider": "openai", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_audio_input": true, - "supports_audio_output": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supported_endpoints": [ - "/v1/realtime" - ], - "supported_modalities": [ - "text", - "image", - "audio" - ], - "supported_output_modalities": [ - "text", - "audio" - ] - }, - "gpt-realtime-2025-08-28": { - "max_tokens": 4096, - "max_input_tokens": 32000, - "max_output_tokens": 4096, - "input_cost_per_token": 4e-06, - "cache_read_input_token_cost": 0.4e-06, - "output_cost_per_token": 16e-06, - "input_cost_per_audio_token": 32e-06, - "output_cost_per_audio_token": 64e-06, - "cache_creation_input_audio_token_cost": 0.4e-06, - "input_cost_per_image": 5e-06, - "litellm_provider": "openai", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_audio_input": true, - "supports_audio_output": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supported_endpoints": [ - "/v1/realtime" - ], - "supported_modalities": [ - "text", - "image", - "audio" - ], - "supported_output_modalities": [ - "text", - "audio" - ] - }, - "gpt-4o-realtime-preview-2024-10-01": { - "max_tokens": 4096, - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 5e-06, - "input_cost_per_audio_token": 0.0001, - "cache_read_input_token_cost": 2.5e-06, - "cache_creation_input_audio_token_cost": 2e-05, - "output_cost_per_token": 2e-05, - "output_cost_per_audio_token": 0.0002, - "litellm_provider": "openai", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_audio_input": true, - "supports_audio_output": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "gpt-4o-realtime-preview": { - "max_tokens": 4096, - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 5e-06, - "input_cost_per_audio_token": 4e-05, - "cache_read_input_token_cost": 2.5e-06, - "output_cost_per_token": 2e-05, - "output_cost_per_audio_token": 8e-05, - "litellm_provider": "openai", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_audio_input": true, - "supports_audio_output": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "gpt-4o-realtime-preview-2024-12-17": { - "max_tokens": 4096, - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 5e-06, - "input_cost_per_audio_token": 4e-05, - "cache_read_input_token_cost": 2.5e-06, - "output_cost_per_token": 2e-05, - "output_cost_per_audio_token": 8e-05, - "litellm_provider": "openai", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_audio_input": true, - "supports_audio_output": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "gpt-4o-realtime-preview-2025-06-03": { - "max_tokens": 4096, - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 5e-06, - "input_cost_per_audio_token": 4e-05, - "cache_read_input_token_cost": 2.5e-06, - "output_cost_per_token": 2e-05, - "output_cost_per_audio_token": 8e-05, - "litellm_provider": "openai", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_audio_input": true, - "supports_audio_output": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "gpt-4o-mini-realtime-preview": { - "max_tokens": 4096, - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 6e-07, - "input_cost_per_audio_token": 1e-05, - "cache_read_input_token_cost": 3e-07, - "cache_creation_input_audio_token_cost": 3e-07, - "output_cost_per_token": 2.4e-06, - "output_cost_per_audio_token": 2e-05, - "litellm_provider": "openai", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_audio_input": true, - "supports_audio_output": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "gpt-4o-mini-realtime-preview-2024-12-17": { - "max_tokens": 4096, - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 6e-07, - "input_cost_per_audio_token": 1e-05, - "cache_read_input_token_cost": 3e-07, - "cache_creation_input_audio_token_cost": 3e-07, - "output_cost_per_token": 2.4e-06, - "output_cost_per_audio_token": 2e-05, - "litellm_provider": "openai", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_audio_input": true, - "supports_audio_output": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "gpt-4-turbo-preview": { - "max_tokens": 4096, - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 1e-05, - "output_cost_per_token": 3e-05, - "litellm_provider": "openai", - "mode": "chat", - "supports_pdf_input": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "gpt-4-0314": { - "max_tokens": 4096, - "max_input_tokens": 8192, - "max_output_tokens": 4096, - "input_cost_per_token": 3e-05, - "output_cost_per_token": 6e-05, - "litellm_provider": "openai", - "mode": "chat", - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "gpt-4-0613": { - "max_tokens": 4096, - "max_input_tokens": 8192, - "max_output_tokens": 4096, - "input_cost_per_token": 3e-05, - "output_cost_per_token": 6e-05, - "litellm_provider": "openai", - "mode": "chat", - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "deprecation_date": "2025-06-06", - "supports_tool_choice": true - }, - "gpt-4-32k": { - "max_tokens": 4096, - "max_input_tokens": 32768, - "max_output_tokens": 4096, - "input_cost_per_token": 6e-05, - "output_cost_per_token": 0.00012, - "litellm_provider": "openai", - "mode": "chat", - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "gpt-4-32k-0314": { - "max_tokens": 4096, - "max_input_tokens": 32768, - "max_output_tokens": 4096, - "input_cost_per_token": 6e-05, - "output_cost_per_token": 0.00012, - "litellm_provider": "openai", - "mode": "chat", - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "gpt-4-32k-0613": { - "max_tokens": 4096, - "max_input_tokens": 32768, - "max_output_tokens": 4096, - "input_cost_per_token": 6e-05, - "output_cost_per_token": 0.00012, - "litellm_provider": "openai", - "mode": "chat", - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "gpt-4-turbo": { - "max_tokens": 4096, - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 1e-05, - "output_cost_per_token": 3e-05, - "litellm_provider": "openai", - "mode": "chat", - "supports_pdf_input": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "gpt-4-turbo-2024-04-09": { - "max_tokens": 4096, - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 1e-05, - "output_cost_per_token": 3e-05, - "litellm_provider": "openai", - "mode": "chat", - "supports_pdf_input": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "gpt-4-1106-preview": { - "max_tokens": 4096, - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 1e-05, - "output_cost_per_token": 3e-05, - "litellm_provider": "openai", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "gpt-4-0125-preview": { - "max_tokens": 4096, - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 1e-05, - "output_cost_per_token": 3e-05, - "litellm_provider": "openai", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "gpt-4-vision-preview": { - "max_tokens": 4096, - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 1e-05, - "output_cost_per_token": 3e-05, - "litellm_provider": "openai", - "mode": "chat", - "supports_vision": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "deprecation_date": "2024-12-06", - "supports_tool_choice": true - }, - "gpt-4-1106-vision-preview": { - "max_tokens": 4096, - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 1e-05, - "output_cost_per_token": 3e-05, - "litellm_provider": "openai", - "mode": "chat", - "supports_vision": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "deprecation_date": "2024-12-06", - "supports_tool_choice": true - }, - "gpt-3.5-turbo": { - "max_tokens": 4097, - "max_input_tokens": 16385, - "max_output_tokens": 4096, - "input_cost_per_token": 1.5e-06, - "output_cost_per_token": 2e-06, - "litellm_provider": "openai", - "mode": "chat", - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "gpt-3.5-turbo-0301": { - "max_tokens": 4097, - "max_input_tokens": 4097, - "max_output_tokens": 4096, - "input_cost_per_token": 1.5e-06, - "output_cost_per_token": 2e-06, - "litellm_provider": "openai", - "mode": "chat", - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "gpt-3.5-turbo-0613": { - "max_tokens": 4097, - "max_input_tokens": 4097, - "max_output_tokens": 4096, - "input_cost_per_token": 1.5e-06, - "output_cost_per_token": 2e-06, - "litellm_provider": "openai", - "mode": "chat", - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "gpt-3.5-turbo-1106": { - "max_tokens": 16385, - "max_input_tokens": 16385, - "max_output_tokens": 4096, - "input_cost_per_token": 1e-06, - "output_cost_per_token": 2e-06, - "litellm_provider": "openai", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "gpt-3.5-turbo-0125": { - "max_tokens": 16385, - "max_input_tokens": 16385, - "max_output_tokens": 4096, - "input_cost_per_token": 5e-07, - "output_cost_per_token": 1.5e-06, - "litellm_provider": "openai", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "gpt-3.5-turbo-16k": { - "max_tokens": 16385, - "max_input_tokens": 16385, - "max_output_tokens": 4096, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 4e-06, - "litellm_provider": "openai", - "mode": "chat", - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "gpt-3.5-turbo-16k-0613": { - "max_tokens": 16385, - "max_input_tokens": 16385, - "max_output_tokens": 4096, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 4e-06, - "litellm_provider": "openai", - "mode": "chat", - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "ft:gpt-3.5-turbo": { - "max_tokens": 4096, - "max_input_tokens": 16385, - "max_output_tokens": 4096, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 6e-06, - "input_cost_per_token_batches": 1.5e-06, - "output_cost_per_token_batches": 3e-06, - "litellm_provider": "openai", - "mode": "chat", - "supports_system_messages": true, - "supports_tool_choice": true - }, - "ft:gpt-3.5-turbo-0125": { - "max_tokens": 4096, - "max_input_tokens": 16385, - "max_output_tokens": 4096, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 6e-06, - "litellm_provider": "openai", - "mode": "chat", - "supports_system_messages": true, - "supports_tool_choice": true - }, - "ft:gpt-3.5-turbo-1106": { - "max_tokens": 4096, - "max_input_tokens": 16385, - "max_output_tokens": 4096, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 6e-06, - "litellm_provider": "openai", - "mode": "chat", - "supports_system_messages": true, - "supports_tool_choice": true - }, - "ft:gpt-3.5-turbo-0613": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 6e-06, - "litellm_provider": "openai", - "mode": "chat", - "supports_system_messages": true, - "supports_tool_choice": true - }, - "ft:gpt-4-0613": { - "max_tokens": 4096, - "max_input_tokens": 8192, - "max_output_tokens": 4096, - "input_cost_per_token": 3e-05, - "output_cost_per_token": 6e-05, - "litellm_provider": "openai", - "mode": "chat", - "supports_function_calling": true, - "source": "OpenAI needs to add pricing for this ft model, will be updated when added by OpenAI. Defaulting to base model pricing", - "supports_system_messages": true, - "supports_tool_choice": true - }, - "ft:gpt-4o-2024-08-06": { - "max_tokens": 16384, - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "input_cost_per_token": 3.75e-06, - "output_cost_per_token": 1.5e-05, - "input_cost_per_token_batches": 1.875e-06, - "output_cost_per_token_batches": 7.5e-06, - "litellm_provider": "openai", - "mode": "chat", - "supports_pdf_input": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "ft:gpt-4o-2024-11-20": { - "max_tokens": 16384, - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "input_cost_per_token": 3.75e-06, - "cache_creation_input_token_cost": 1.875e-06, - "output_cost_per_token": 1.5e-05, - "litellm_provider": "openai", - "mode": "chat", - "supports_pdf_input": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "ft:gpt-4o-mini-2024-07-18": { - "max_tokens": 16384, - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "input_cost_per_token": 3e-07, - "output_cost_per_token": 1.2e-06, - "input_cost_per_token_batches": 1.5e-07, - "output_cost_per_token_batches": 6e-07, - "cache_read_input_token_cost": 1.5e-07, - "litellm_provider": "openai", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "ft:davinci-002": { - "max_tokens": 16384, - "max_input_tokens": 16384, - "max_output_tokens": 4096, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 2e-06, - "input_cost_per_token_batches": 1e-06, - "output_cost_per_token_batches": 1e-06, - "litellm_provider": "text-completion-openai", - "mode": "completion" - }, - "ft:babbage-002": { - "max_tokens": 16384, - "max_input_tokens": 16384, - "max_output_tokens": 4096, - "input_cost_per_token": 4e-07, - "output_cost_per_token": 4e-07, - "input_cost_per_token_batches": 2e-07, - "output_cost_per_token_batches": 2e-07, - "litellm_provider": "text-completion-openai", - "mode": "completion" - }, - "text-embedding-3-large": { - "max_tokens": 8191, - "max_input_tokens": 8191, - "output_vector_size": 3072, - "input_cost_per_token": 1.3e-07, - "output_cost_per_token": 0.0, - "input_cost_per_token_batches": 6.5e-08, - "output_cost_per_token_batches": 0.0, - "litellm_provider": "openai", - "mode": "embedding" - }, - "text-embedding-3-small": { - "max_tokens": 8191, - "max_input_tokens": 8191, - "output_vector_size": 1536, - "input_cost_per_token": 2e-08, - "output_cost_per_token": 0.0, - "input_cost_per_token_batches": 1e-08, - "output_cost_per_token_batches": 0.0, - "litellm_provider": "openai", - "mode": "embedding" - }, - "text-embedding-ada-002": { - "max_tokens": 8191, - "max_input_tokens": 8191, - "output_vector_size": 1536, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 0.0, - "litellm_provider": "openai", - "mode": "embedding" - }, - "text-embedding-ada-002-v2": { - "max_tokens": 8191, - "max_input_tokens": 8191, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 0.0, - "input_cost_per_token_batches": 5e-08, - "output_cost_per_token_batches": 0.0, - "litellm_provider": "openai", - "mode": "embedding" - }, - "text-moderation-stable": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 0, - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "openai", - "mode": "moderation" - }, - "text-moderation-007": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 0, - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "openai", - "mode": "moderation" - }, - "text-moderation-latest": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 0, - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "openai", - "mode": "moderation" - }, - "256-x-256/dall-e-2": { + "1024-x-1024/50-steps/bedrock/amazon.nova-canvas-v1:0": { + "litellm_provider": "bedrock", + "max_input_tokens": 2600, "mode": "image_generation", - "input_cost_per_pixel": 2.4414e-07, - "output_cost_per_pixel": 0.0, - "litellm_provider": "openai" + "output_cost_per_image": 0.06 }, - "512-x-512/dall-e-2": { + "1024-x-1024/50-steps/stability.stable-diffusion-xl-v1": { + "litellm_provider": "bedrock", + "max_input_tokens": 77, + "max_tokens": 77, "mode": "image_generation", - "input_cost_per_pixel": 6.86e-08, - "output_cost_per_pixel": 0.0, - "litellm_provider": "openai" + "output_cost_per_image": 0.04 }, "1024-x-1024/dall-e-2": { - "mode": "image_generation", "input_cost_per_pixel": 1.9e-08, - "output_cost_per_pixel": 0.0, - "litellm_provider": "openai" - }, - "hd/1024-x-1792/dall-e-3": { - "mode": "image_generation", - "input_cost_per_pixel": 6.539e-08, - "output_cost_per_pixel": 0.0, - "litellm_provider": "openai" - }, - "hd/1792-x-1024/dall-e-3": { - "mode": "image_generation", - "input_cost_per_pixel": 6.539e-08, - "output_cost_per_pixel": 0.0, - "litellm_provider": "openai" - }, - "hd/1024-x-1024/dall-e-3": { - "mode": "image_generation", - "input_cost_per_pixel": 7.629e-08, - "output_cost_per_pixel": 0.0, - "litellm_provider": "openai" - }, - "standard/1024-x-1792/dall-e-3": { - "mode": "image_generation", - "input_cost_per_pixel": 4.359e-08, - "output_cost_per_pixel": 0.0, - "litellm_provider": "openai" - }, - "standard/1792-x-1024/dall-e-3": { - "mode": "image_generation", - "input_cost_per_pixel": 4.359e-08, - "output_cost_per_pixel": 0.0, - "litellm_provider": "openai" - }, - "standard/1024-x-1024/dall-e-3": { - "mode": "image_generation", - "input_cost_per_pixel": 3.81469e-08, - "output_cost_per_pixel": 0.0, - "litellm_provider": "openai" - }, - "gpt-image-1": { - "mode": "image_generation", - "input_cost_per_pixel": 4.0054321e-08, - "output_cost_per_pixel": 0.0, "litellm_provider": "openai", - "supported_endpoints": [ - "/v1/images/generations" - ] - }, - "low/1024-x-1024/gpt-image-1": { "mode": "image_generation", - "input_cost_per_pixel": 1.0490417e-08, - "output_cost_per_pixel": 0.0, - "litellm_provider": "openai", - "supported_endpoints": [ - "/v1/images/generations" - ] + "output_cost_per_pixel": 0.0 }, - "medium/1024-x-1024/gpt-image-1": { + "1024-x-1024/max-steps/stability.stable-diffusion-xl-v1": { + "litellm_provider": "bedrock", + "max_input_tokens": 77, + "max_tokens": 77, "mode": "image_generation", - "input_cost_per_pixel": 4.0054321e-08, - "output_cost_per_pixel": 0.0, - "litellm_provider": "openai", - "supported_endpoints": [ - "/v1/images/generations" - ] + "output_cost_per_image": 0.08 }, - "high/1024-x-1024/gpt-image-1": { + "256-x-256/dall-e-2": { + "input_cost_per_pixel": 2.4414e-07, + "litellm_provider": "openai", "mode": "image_generation", - "input_cost_per_pixel": 1.59263611e-07, - "output_cost_per_pixel": 0.0, - "litellm_provider": "openai", - "supported_endpoints": [ - "/v1/images/generations" - ] + "output_cost_per_pixel": 0.0 }, - "low/1024-x-1536/gpt-image-1": { + "512-x-512/50-steps/stability.stable-diffusion-xl-v0": { + "litellm_provider": "bedrock", + "max_input_tokens": 77, + "max_tokens": 77, "mode": "image_generation", - "input_cost_per_pixel": 1.0172526e-08, - "output_cost_per_pixel": 0.0, - "litellm_provider": "openai", - "supported_endpoints": [ - "/v1/images/generations" - ] + "output_cost_per_image": 0.018 }, - "medium/1024-x-1536/gpt-image-1": { + "512-x-512/dall-e-2": { + "input_cost_per_pixel": 6.86e-08, + "litellm_provider": "openai", "mode": "image_generation", - "input_cost_per_pixel": 4.0054321e-08, - "output_cost_per_pixel": 0.0, - "litellm_provider": "openai", - "supported_endpoints": [ - "/v1/images/generations" - ] + "output_cost_per_pixel": 0.0 }, - "high/1024-x-1536/gpt-image-1": { + "512-x-512/max-steps/stability.stable-diffusion-xl-v0": { + "litellm_provider": "bedrock", + "max_input_tokens": 77, + "max_tokens": 77, "mode": "image_generation", - "input_cost_per_pixel": 1.58945719e-07, - "output_cost_per_pixel": 0.0, - "litellm_provider": "openai", - "supported_endpoints": [ - "/v1/images/generations" - ] + "output_cost_per_image": 0.036 }, - "low/1536-x-1024/gpt-image-1": { - "mode": "image_generation", - "input_cost_per_pixel": 1.0172526e-08, - "output_cost_per_pixel": 0.0, - "litellm_provider": "openai", - "supported_endpoints": [ - "/v1/images/generations" - ] - }, - "medium/1536-x-1024/gpt-image-1": { - "mode": "image_generation", - "input_cost_per_pixel": 4.0054321e-08, - "output_cost_per_pixel": 0.0, - "litellm_provider": "openai", - "supported_endpoints": [ - "/v1/images/generations" - ] - }, - "high/1536-x-1024/gpt-image-1": { - "mode": "image_generation", - "input_cost_per_pixel": 1.58945719e-07, - "output_cost_per_pixel": 0.0, - "litellm_provider": "openai", - "supported_endpoints": [ - "/v1/images/generations" - ] - }, - "gpt-4o-transcribe": { - "mode": "audio_transcription", - "max_input_tokens": 16000, - "max_output_tokens": 2000, - "input_cost_per_token": 2.5e-06, - "input_cost_per_audio_token": 6e-06, - "output_cost_per_token": 1e-05, - "litellm_provider": "openai", - "supported_endpoints": [ - "/v1/audio/transcriptions" - ] - }, - "gpt-4o-mini-transcribe": { - "mode": "audio_transcription", - "max_input_tokens": 16000, - "max_output_tokens": 2000, - "input_cost_per_token": 1.25e-06, - "input_cost_per_audio_token": 3e-06, - "output_cost_per_token": 5e-06, - "litellm_provider": "openai", - "supported_endpoints": [ - "/v1/audio/transcriptions" - ] - }, - "whisper-1": { - "mode": "audio_transcription", - "input_cost_per_second": 0.0001, - "output_cost_per_second": 0.0001, - "litellm_provider": "openai", - "supported_endpoints": [ - "/v1/audio/transcriptions" - ] - }, - "tts-1": { - "mode": "audio_speech", - "input_cost_per_character": 1.5e-05, - "litellm_provider": "openai", - "supported_endpoints": [ - "/v1/audio/speech" - ] - }, - "tts-1-hd": { - "mode": "audio_speech", - "input_cost_per_character": 3e-05, - "litellm_provider": "openai", - "supported_endpoints": [ - "/v1/audio/speech" - ] - }, - "gpt-4o-mini-tts": { - "mode": "audio_speech", - "input_cost_per_token": 2.5e-06, - "output_cost_per_token": 1e-05, - "output_cost_per_audio_token": 1.2e-05, - "output_cost_per_second": 0.00025, - "litellm_provider": "openai", - "supported_modalities": [ - "text", - "audio" - ], - "supported_output_modalities": [ - "audio" - ], - "supported_endpoints": [ - "/v1/audio/speech" - ] - }, - "azure/gpt-5": { - "max_tokens": 128000, - "max_input_tokens": 272000, - "max_output_tokens": 128000, - "input_cost_per_token": 1.25e-06, - "output_cost_per_token": 1e-05, - "cache_read_input_token_cost": 1.25e-07, - "litellm_provider": "azure", + "ai21.j2-mid-v1": { + "input_cost_per_token": 1.25e-05, + "litellm_provider": "bedrock", + "max_input_tokens": 8191, + "max_output_tokens": 8191, + "max_tokens": 8191, "mode": "chat", + "output_cost_per_token": 1.25e-05 + }, + "ai21.j2-ultra-v1": { + "input_cost_per_token": 1.88e-05, + "litellm_provider": "bedrock", + "max_input_tokens": 8191, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 1.88e-05 + }, + "ai21.jamba-1-5-large-v1:0": { + "input_cost_per_token": 2e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 8e-06 + }, + "ai21.jamba-1-5-mini-v1:0": { + "input_cost_per_token": 2e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 4e-07 + }, + "ai21.jamba-instruct-v1:0": { + "input_cost_per_token": 5e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 70000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 7e-07, + "supports_system_messages": true + }, + "aiml/dall-e-2": { + "litellm_provider": "aiml", + "metadata": { + "notes": "DALL-E 2 via AI/ML API - Reliable text-to-image generation" + }, + "mode": "image_generation", + "output_cost_per_image": 0.021, + "source": "https://docs.aimlapi.com/", "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_pdf_input": true, + "/v1/images/generations" + ] + }, + "aiml/dall-e-3": { + "litellm_provider": "aiml", + "metadata": { + "notes": "DALL-E 3 via AI/ML API - High-quality text-to-image generation" + }, + "mode": "image_generation", + "output_cost_per_image": 0.042, + "source": "https://docs.aimlapi.com/", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "aiml/flux-pro": { + "litellm_provider": "aiml", + "metadata": { + "notes": "Flux Dev - Development version optimized for experimentation" + }, + "mode": "image_generation", + "output_cost_per_image": 0.053, + "source": "https://docs.aimlapi.com/", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "aiml/flux-pro/v1.1": { + "litellm_provider": "aiml", + "mode": "image_generation", + "output_cost_per_image": 0.042, + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "aiml/flux-pro/v1.1-ultra": { + "litellm_provider": "aiml", + "mode": "image_generation", + "output_cost_per_image": 0.063, + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "aiml/flux-realism": { + "litellm_provider": "aiml", + "metadata": { + "notes": "Flux Pro - Professional-grade image generation model" + }, + "mode": "image_generation", + "output_cost_per_image": 0.037, + "source": "https://docs.aimlapi.com/", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "aiml/flux/dev": { + "litellm_provider": "aiml", + "metadata": { + "notes": "Flux Dev - Development version optimized for experimentation" + }, + "mode": "image_generation", + "output_cost_per_image": 0.026, + "source": "https://docs.aimlapi.com/", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "aiml/flux/kontext-max/text-to-image": { + "litellm_provider": "aiml", + "metadata": { + "notes": "Flux Pro v1.1 - Enhanced version with improved capabilities and 6x faster inference speed" + }, + "mode": "image_generation", + "output_cost_per_image": 0.084, + "source": "https://docs.aimlapi.com/", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "aiml/flux/kontext-pro/text-to-image": { + "litellm_provider": "aiml", + "metadata": { + "notes": "Flux Pro v1.1 - Enhanced version with improved capabilities and 6x faster inference speed" + }, + "mode": "image_generation", + "output_cost_per_image": 0.042, + "source": "https://docs.aimlapi.com/", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "aiml/flux/schnell": { + "litellm_provider": "aiml", + "metadata": { + "notes": "Flux Schnell - Fast generation model optimized for speed" + }, + "mode": "image_generation", + "output_cost_per_image": 0.003, + "source": "https://docs.aimlapi.com/", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "amazon.nova-lite-v1:0": { + "input_cost_per_token": 6e-08, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 300000, + "max_output_tokens": 10000, + "max_tokens": 10000, + "mode": "chat", + "output_cost_per_token": 2.4e-07, "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, + "supports_pdf_input": true, "supports_prompt_caching": true, - "supports_system_messages": true, + "supports_response_schema": true, + "supports_vision": true + }, + "amazon.nova-micro-v1:0": { + "input_cost_per_token": 3.5e-08, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 128000, + "max_output_tokens": 10000, + "max_tokens": 10000, + "mode": "chat", + "output_cost_per_token": 1.4e-07, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true + }, + "amazon.nova-pro-v1:0": { + "input_cost_per_token": 8e-07, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 300000, + "max_output_tokens": 10000, + "max_tokens": 10000, + "mode": "chat", + "output_cost_per_token": 3.2e-06, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_vision": true + }, + "amazon.rerank-v1:0": { + "input_cost_per_query": 0.001, + "input_cost_per_token": 0.0, + "litellm_provider": "bedrock", + "max_document_chunks_per_query": 100, + "max_input_tokens": 32000, + "max_output_tokens": 32000, + "max_query_tokens": 32000, + "max_tokens": 32000, + "max_tokens_per_document_chunk": 512, + "mode": "rerank", + "output_cost_per_token": 0.0 + }, + "amazon.titan-embed-image-v1": { + "input_cost_per_image": 6e-05, + "input_cost_per_token": 8e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 128, + "max_tokens": 128, + "metadata": { + "notes": "'supports_image_input' is a deprecated field. Use 'supports_embedding_image_input' instead." + }, + "mode": "embedding", + "output_cost_per_token": 0.0, + "output_vector_size": 1024, + "source": "https://us-east-1.console.aws.amazon.com/bedrock/home?region=us-east-1#/providers?model=amazon.titan-image-generator-v1", + "supports_embedding_image_input": true, + "supports_image_input": true + }, + "amazon.titan-embed-text-v1": { + "input_cost_per_token": 1e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 8192, + "max_tokens": 8192, + "mode": "embedding", + "output_cost_per_token": 0.0, + "output_vector_size": 1536 + }, + "amazon.titan-embed-text-v2:0": { + "input_cost_per_token": 2e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 8192, + "max_tokens": 8192, + "mode": "embedding", + "output_cost_per_token": 0.0, + "output_vector_size": 1024 + }, + "amazon.titan-text-express-v1": { + "input_cost_per_token": 1.3e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 42000, + "max_output_tokens": 8000, + "max_tokens": 8000, + "mode": "chat", + "output_cost_per_token": 1.7e-06 + }, + "amazon.titan-text-lite-v1": { + "input_cost_per_token": 3e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 42000, + "max_output_tokens": 4000, + "max_tokens": 4000, + "mode": "chat", + "output_cost_per_token": 4e-07 + }, + "amazon.titan-text-premier-v1:0": { + "input_cost_per_token": 5e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 42000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 1.5e-06 + }, + "anthropic.claude-3-5-haiku-20241022-v1:0": { + "cache_creation_input_token_cost": 1e-06, + "cache_read_input_token_cost": 8e-08, + "input_cost_per_token": 8e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 4e-06, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "anthropic.claude-3-5-sonnet-20240620-v1:0": { + "input_cost_per_token": 3e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_response_schema": true, "supports_tool_choice": true, - "supports_native_streaming": true, - "supports_reasoning": true + "supports_vision": true }, - "azure/gpt-5-2025-08-07": { - "max_tokens": 128000, - "max_input_tokens": 272000, - "max_output_tokens": 128000, - "input_cost_per_token": 1.25e-06, - "output_cost_per_token": 1e-05, - "cache_read_input_token_cost": 1.25e-07, - "litellm_provider": "azure", + "anthropic.claude-3-5-sonnet-20241022-v2:0": { + "cache_creation_input_token_cost": 3.75e-06, + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 3e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_pdf_input": true, + "output_cost_per_token": 1.5e-05, + "supports_assistant_prefill": true, + "supports_computer_use": true, "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, + "supports_pdf_input": true, "supports_prompt_caching": true, - "supports_system_messages": true, + "supports_response_schema": true, "supports_tool_choice": true, - "supports_native_streaming": true, - "supports_reasoning": true + "supports_vision": true }, - "azure/gpt-5-mini": { - "max_tokens": 128000, - "max_input_tokens": 272000, - "max_output_tokens": 128000, - "input_cost_per_token": 2.5e-07, - "output_cost_per_token": 2e-06, - "cache_read_input_token_cost": 2.5e-08, - "litellm_provider": "azure", + "anthropic.claude-3-7-sonnet-20250219-v1:0": { + "cache_creation_input_token_cost": 3.75e-06, + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 3e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_pdf_input": true, + "output_cost_per_token": 1.5e-05, + "supports_assistant_prefill": true, + "supports_computer_use": true, "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_native_streaming": true, - "supports_reasoning": true - }, - "azure/gpt-5-mini-2025-08-07": { - "max_tokens": 128000, - "max_input_tokens": 272000, - "max_output_tokens": 128000, - "input_cost_per_token": 2.5e-07, - "output_cost_per_token": 2e-06, - "cache_read_input_token_cost": 2.5e-08, - "litellm_provider": "azure", - "mode": "chat", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], "supports_pdf_input": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_native_streaming": true, - "supports_reasoning": true - }, - "azure/gpt-5-nano-2025-08-07": { - "max_tokens": 128000, - "max_input_tokens": 272000, - "max_output_tokens": 128000, - "input_cost_per_token": 5e-08, - "output_cost_per_token": 4e-07, - "cache_read_input_token_cost": 5e-09, - "litellm_provider": "azure", - "mode": "chat", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_pdf_input": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_native_streaming": true, - "supports_reasoning": true - }, - "azure/gpt-5-nano": { - "max_tokens": 128000, - "max_input_tokens": 272000, - "max_output_tokens": 128000, - "input_cost_per_token": 5e-08, - "output_cost_per_token": 4e-07, - "cache_read_input_token_cost": 5e-09, - "litellm_provider": "azure", - "mode": "chat", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_pdf_input": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_native_streaming": true, - "supports_reasoning": true - }, - "azure/gpt-5-chat": { - "max_tokens": 128000, - "max_input_tokens": 272000, - "max_output_tokens": 128000, - "input_cost_per_token": 1.25e-06, - "output_cost_per_token": 1e-05, - "cache_read_input_token_cost": 1.25e-07, - "litellm_provider": "azure", - "mode": "chat", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_pdf_input": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": false, - "supports_native_streaming": true, "supports_reasoning": true, - "source": "https://azure.microsoft.com/en-us/blog/gpt-5-in-azure-ai-foundry-the-future-of-ai-apps-and-agents-starts-here/" + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true }, - "azure/gpt-5-chat-latest": { - "max_tokens": 128000, - "max_input_tokens": 272000, - "max_output_tokens": 128000, - "input_cost_per_token": 1.25e-06, - "output_cost_per_token": 1e-05, - "cache_read_input_token_cost": 1.25e-07, - "litellm_provider": "azure", + "anthropic.claude-3-haiku-20240307-v1:0": { + "input_cost_per_token": 2.5e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", + "output_cost_per_token": 1.25e-06, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "anthropic.claude-3-opus-20240229-v1:0": { + "input_cost_per_token": 1.5e-05, + "litellm_provider": "bedrock", + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 7.5e-05, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "anthropic.claude-3-sonnet-20240229-v1:0": { + "input_cost_per_token": 3e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "anthropic.claude-instant-v1": { + "input_cost_per_token": 8e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 2.4e-06, + "supports_tool_choice": true + }, + "anthropic.claude-opus-4-1-20250805-v1:0": { + "cache_creation_input_token_cost": 1.875e-05, + "cache_read_input_token_cost": 1.5e-06, + "input_cost_per_token": 1.5e-05, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 200000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 7.5e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159 + }, + "anthropic.claude-opus-4-20250514-v1:0": { + "cache_creation_input_token_cost": 1.875e-05, + "cache_read_input_token_cost": 1.5e-06, + "input_cost_per_token": 1.5e-05, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 200000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 7.5e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159 + }, + "anthropic.claude-sonnet-4-20250514-v1:0": { + "cache_creation_input_token_cost": 3.75e-06, + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 3e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159 + }, + "anthropic.claude-v1": { + "input_cost_per_token": 8e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 2.4e-05 + }, + "anthropic.claude-v2:1": { + "input_cost_per_token": 8e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 2.4e-05, + "supports_tool_choice": true + }, + "anyscale/HuggingFaceH4/zephyr-7b-beta": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "anyscale", + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1.5e-07 + }, + "anyscale/codellama/CodeLlama-34b-Instruct-hf": { + "input_cost_per_token": 1e-06, + "litellm_provider": "anyscale", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1e-06 + }, + "anyscale/codellama/CodeLlama-70b-Instruct-hf": { + "input_cost_per_token": 1e-06, + "litellm_provider": "anyscale", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1e-06, + "source": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/codellama-CodeLlama-70b-Instruct-hf" + }, + "anyscale/google/gemma-7b-it": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "anyscale", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.5e-07, + "source": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/google-gemma-7b-it" + }, + "anyscale/meta-llama/Llama-2-13b-chat-hf": { + "input_cost_per_token": 2.5e-07, + "litellm_provider": "anyscale", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 2.5e-07 + }, + "anyscale/meta-llama/Llama-2-70b-chat-hf": { + "input_cost_per_token": 1e-06, + "litellm_provider": "anyscale", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1e-06 + }, + "anyscale/meta-llama/Llama-2-7b-chat-hf": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "anyscale", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.5e-07 + }, + "anyscale/meta-llama/Meta-Llama-3-70B-Instruct": { + "input_cost_per_token": 1e-06, + "litellm_provider": "anyscale", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1e-06, + "source": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/meta-llama-Meta-Llama-3-70B-Instruct" + }, + "anyscale/meta-llama/Meta-Llama-3-8B-Instruct": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "anyscale", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.5e-07, + "source": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/meta-llama-Meta-Llama-3-8B-Instruct" + }, + "anyscale/mistralai/Mistral-7B-Instruct-v0.1": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "anyscale", + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1.5e-07, + "source": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/mistralai-Mistral-7B-Instruct-v0.1", + "supports_function_calling": true + }, + "anyscale/mistralai/Mixtral-8x22B-Instruct-v0.1": { + "input_cost_per_token": 9e-07, + "litellm_provider": "anyscale", + "max_input_tokens": 65536, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 9e-07, + "source": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/mistralai-Mixtral-8x22B-Instruct-v0.1", + "supports_function_calling": true + }, + "anyscale/mistralai/Mixtral-8x7B-Instruct-v0.1": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "anyscale", + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1.5e-07, + "source": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/mistralai-Mixtral-8x7B-Instruct-v0.1", + "supports_function_calling": true + }, + "apac.amazon.nova-lite-v1:0": { + "input_cost_per_token": 6.3e-08, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 300000, + "max_output_tokens": 10000, + "max_tokens": 10000, + "mode": "chat", + "output_cost_per_token": 2.52e-07, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_vision": true + }, + "apac.amazon.nova-micro-v1:0": { + "input_cost_per_token": 3.7e-08, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 128000, + "max_output_tokens": 10000, + "max_tokens": 10000, + "mode": "chat", + "output_cost_per_token": 1.48e-07, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true + }, + "apac.amazon.nova-pro-v1:0": { + "input_cost_per_token": 8.4e-07, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 300000, + "max_output_tokens": 10000, + "max_tokens": 10000, + "mode": "chat", + "output_cost_per_token": 3.36e-06, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_vision": true + }, + "apac.anthropic.claude-3-5-sonnet-20240620-v1:0": { + "input_cost_per_token": 3e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "apac.anthropic.claude-3-5-sonnet-20241022-v2:0": { + "cache_creation_input_token_cost": 3.75e-06, + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 3e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "apac.anthropic.claude-3-haiku-20240307-v1:0": { + "input_cost_per_token": 2.5e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.25e-06, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "apac.anthropic.claude-3-sonnet-20240229-v1:0": { + "input_cost_per_token": 3e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "apac.anthropic.claude-sonnet-4-20250514-v1:0": { + "cache_creation_input_token_cost": 3.75e-06, + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 3e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159 + }, + "assemblyai/best": { + "input_cost_per_second": 3.333e-05, + "litellm_provider": "assemblyai", + "mode": "audio_transcription", + "output_cost_per_second": 0.0 + }, + "assemblyai/nano": { + "input_cost_per_second": 0.00010278, + "litellm_provider": "assemblyai", + "mode": "audio_transcription", + "output_cost_per_second": 0.0 + }, + "azure/ada": { + "input_cost_per_token": 1e-07, + "litellm_provider": "azure", + "max_input_tokens": 8191, + "max_tokens": 8191, + "mode": "embedding", + "output_cost_per_token": 0.0 + }, + "azure/codex-mini": { + "cache_read_input_token_cost": 3.75e-07, + "input_cost_per_token": 1.5e-06, + "litellm_provider": "azure", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "responses", + "output_cost_per_token": 6e-06, "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", "/v1/responses" ], "supported_modalities": [ @@ -2574,43 +825,34 @@ "supported_output_modalities": [ "text" ], - "supports_pdf_input": true, "supports_function_calling": true, "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, + "supports_pdf_input": true, "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, "supports_system_messages": true, - "supports_tool_choice": false, - "supports_native_streaming": true, - "supports_reasoning": true + "supports_tool_choice": true, + "supports_vision": true }, - "azure/gpt-4o-mini-tts": { - "mode": "audio_speech", - "input_cost_per_token": 2.5e-06, - "output_cost_per_token": 1e-05, - "output_cost_per_audio_token": 1.2e-05, - "output_cost_per_second": 0.00025, + "azure/command-r-plus": { + "input_cost_per_token": 3e-06, "litellm_provider": "azure", - "supported_modalities": [ - "text", - "audio" - ], - "supported_output_modalities": [ - "audio" - ], - "supported_endpoints": [ - "/v1/audio/speech" - ] + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "supports_function_calling": true }, "azure/computer-use-preview": { - "max_tokens": 1024, + "input_cost_per_token": 3e-06, + "litellm_provider": "azure", "max_input_tokens": 8192, "max_output_tokens": 1024, - "input_cost_per_token": 3e-06, + "max_tokens": 1024, + "mode": "chat", "output_cost_per_token": 1.2e-05, - "litellm_provider": "azure", - "mode": "chat", "supported_endpoints": [ "/v1/responses" ], @@ -2623,2209 +865,2284 @@ ], "supports_function_calling": true, "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_reasoning": true + "supports_vision": true }, - "azure/gpt-4o-audio-preview-2024-12-17": { - "max_tokens": 16384, + "azure/eu/gpt-4o-2024-08-06": { + "cache_read_input_token_cost": 1.375e-06, + "input_cost_per_token": 2.75e-06, + "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, - "input_cost_per_token": 2.5e-06, - "input_cost_per_audio_token": 4e-05, - "output_cost_per_token": 1e-05, - "output_cost_per_audio_token": 8e-05, - "litellm_provider": "azure", + "max_tokens": 16384, "mode": "chat", - "supported_endpoints": [ - "/v1/chat/completions" - ], - "supported_modalities": [ - "text", - "audio" - ], - "supported_output_modalities": [ - "text", - "audio" - ], + "output_cost_per_token": 1.1e-05, "supports_function_calling": true, "supports_parallel_function_calling": true, - "supports_response_schema": false, - "supports_vision": false, - "supports_prompt_caching": false, - "supports_system_messages": true, + "supports_prompt_caching": true, + "supports_response_schema": true, "supports_tool_choice": true, - "supports_native_streaming": true, - "supports_reasoning": false + "supports_vision": true }, - "azure/gpt-4o-mini-audio-preview-2024-12-17": { - "max_tokens": 16384, + "azure/eu/gpt-4o-2024-11-20": { + "cache_creation_input_token_cost": 1.38e-06, + "input_cost_per_token": 2.75e-06, + "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, - "input_cost_per_token": 2.5e-06, - "input_cost_per_audio_token": 4e-05, - "output_cost_per_token": 1e-05, - "output_cost_per_audio_token": 8e-05, - "litellm_provider": "azure", + "max_tokens": 16384, "mode": "chat", - "supported_endpoints": [ - "/v1/chat/completions" - ], - "supported_modalities": [ - "text", - "audio" - ], - "supported_output_modalities": [ - "text", - "audio" - ], - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": false, - "supports_vision": false, - "supports_prompt_caching": false, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_native_streaming": true, - "supports_reasoning": false - }, - "azure/gpt-4.1": { - "max_tokens": 32768, - "max_input_tokens": 1047576, - "max_output_tokens": 32768, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 8e-06, - "input_cost_per_token_batches": 1e-06, - "output_cost_per_token_batches": 4e-06, - "cache_read_input_token_cost": 5e-07, - "litellm_provider": "azure", - "mode": "chat", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], + "output_cost_per_token": 1.1e-05, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, "supports_tool_choice": true, - "supports_native_streaming": true, - "supports_web_search": false + "supports_vision": true }, - "azure/gpt-4.1-2025-04-14": { - "max_tokens": 32768, - "max_input_tokens": 1047576, - "max_output_tokens": 32768, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 8e-06, - "input_cost_per_token_batches": 1e-06, - "output_cost_per_token_batches": 4e-06, - "cache_read_input_token_cost": 5e-07, + "azure/eu/gpt-4o-mini-2024-07-18": { + "cache_read_input_token_cost": 8.3e-08, + "input_cost_per_token": 1.65e-07, "litellm_provider": "azure", - "mode": "chat", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_native_streaming": true, - "supports_web_search": false - }, - "azure/gpt-4.1-mini": { - "max_tokens": 32768, - "max_input_tokens": 1047576, - "max_output_tokens": 32768, - "input_cost_per_token": 4e-07, - "output_cost_per_token": 1.6e-06, - "input_cost_per_token_batches": 2e-07, - "output_cost_per_token_batches": 8e-07, - "cache_read_input_token_cost": 1e-07, - "litellm_provider": "azure", - "mode": "chat", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_native_streaming": true, - "supports_web_search": false - }, - "azure/gpt-4.1-mini-2025-04-14": { - "max_tokens": 32768, - "max_input_tokens": 1047576, - "max_output_tokens": 32768, - "input_cost_per_token": 4e-07, - "output_cost_per_token": 1.6e-06, - "input_cost_per_token_batches": 2e-07, - "output_cost_per_token_batches": 8e-07, - "cache_read_input_token_cost": 1e-07, - "litellm_provider": "azure", - "mode": "chat", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_native_streaming": true, - "supports_web_search": false - }, - "azure/gpt-4.1-nano": { - "max_tokens": 32768, - "max_input_tokens": 1047576, - "max_output_tokens": 32768, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 4e-07, - "input_cost_per_token_batches": 5e-08, - "output_cost_per_token_batches": 2e-07, - "cache_read_input_token_cost": 2.5e-08, - "litellm_provider": "azure", - "mode": "chat", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_native_streaming": true - }, - "azure/gpt-4.1-nano-2025-04-14": { - "max_tokens": 32768, - "max_input_tokens": 1047576, - "max_output_tokens": 32768, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 4e-07, - "input_cost_per_token_batches": 5e-08, - "output_cost_per_token_batches": 2e-07, - "cache_read_input_token_cost": 2.5e-08, - "litellm_provider": "azure", - "mode": "chat", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_native_streaming": true - }, - "azure/o3-pro": { - "max_tokens": 100000, - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "input_cost_per_token": 2e-05, - "output_cost_per_token": 8e-05, - "input_cost_per_token_batches": 1e-05, - "output_cost_per_token_batches": 4e-05, - "litellm_provider": "azure", - "mode": "responses", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": true, - "supports_parallel_function_calling": false, - "supports_vision": true, - "supports_prompt_caching": false, - "supports_response_schema": true, - "supports_reasoning": true, - "supports_tool_choice": true - }, - "azure/o3-pro-2025-06-10": { - "max_tokens": 100000, - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "input_cost_per_token": 2e-05, - "output_cost_per_token": 8e-05, - "input_cost_per_token_batches": 1e-05, - "output_cost_per_token_batches": 4e-05, - "litellm_provider": "azure", - "mode": "responses", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": true, - "supports_parallel_function_calling": false, - "supports_vision": true, - "supports_prompt_caching": false, - "supports_response_schema": true, - "supports_reasoning": true, - "supports_tool_choice": true - }, - "azure/o3": { - "max_tokens": 100000, - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 8e-06, - "cache_read_input_token_cost": 5e-07, - "litellm_provider": "azure", - "mode": "chat", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": true, - "supports_parallel_function_calling": false, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_reasoning": true, - "supports_tool_choice": true - }, - "azure/o3-2025-04-16": { - "max_tokens": 100000, - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "input_cost_per_token": 1e-05, - "output_cost_per_token": 4e-05, - "cache_read_input_token_cost": 2.5e-06, - "litellm_provider": "azure", - "mode": "chat", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": true, - "supports_parallel_function_calling": false, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_reasoning": true, - "supports_tool_choice": true - }, - "azure/o3-deep-research": { - "max_tokens": 100000, - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "input_cost_per_token": 1e-05, - "output_cost_per_token": 4e-05, - "cache_read_input_token_cost": 2.5e-06, - "litellm_provider": "azure", - "mode": "responses", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_pdf_input": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_web_search": true - }, - "azure/o4-mini": { - "max_tokens": 100000, - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "input_cost_per_token": 1.1e-06, - "output_cost_per_token": 4.4e-06, - "cache_read_input_token_cost": 2.75e-07, - "litellm_provider": "azure", - "mode": "chat", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/batch", - "/v1/responses" - ], - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_function_calling": true, - "supports_parallel_function_calling": false, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_reasoning": true, - "supports_tool_choice": true - }, - "azure/gpt-4o-mini-realtime-preview-2024-12-17": { - "max_tokens": 4096, "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 6e-07, - "input_cost_per_audio_token": 1e-05, - "cache_read_input_token_cost": 3e-07, - "cache_creation_input_audio_token_cost": 3e-07, - "output_cost_per_token": 2.4e-06, - "output_cost_per_audio_token": 2e-05, - "litellm_provider": "azure", + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", + "output_cost_per_token": 6.6e-07, "supports_function_calling": true, "supports_parallel_function_calling": true, - "supports_audio_input": true, - "supports_audio_output": true, - "supports_system_messages": true, - "supports_tool_choice": true + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true }, "azure/eu/gpt-4o-mini-realtime-preview-2024-12-17": { - "max_tokens": 4096, - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 6.6e-07, - "input_cost_per_audio_token": 1.1e-05, - "cache_read_input_token_cost": 3.3e-07, "cache_creation_input_audio_token_cost": 3.3e-07, - "output_cost_per_token": 2.64e-06, - "output_cost_per_audio_token": 2.2e-05, - "litellm_provider": "azure", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_audio_input": true, - "supports_audio_output": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "azure/us/gpt-4o-mini-realtime-preview-2024-12-17": { - "max_tokens": 4096, - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 6.6e-07, - "input_cost_per_audio_token": 1.1e-05, "cache_read_input_token_cost": 3.3e-07, - "cache_creation_input_audio_token_cost": 3.3e-07, - "output_cost_per_token": 2.64e-06, + "input_cost_per_audio_token": 1.1e-05, + "input_cost_per_token": 6.6e-07, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", "output_cost_per_audio_token": 2.2e-05, - "litellm_provider": "azure", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, + "output_cost_per_token": 2.64e-06, "supports_audio_input": true, "supports_audio_output": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "azure/gpt-4o-realtime-preview-2024-12-17": { - "max_tokens": 4096, - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 5e-06, - "input_cost_per_audio_token": 4e-05, - "cache_read_input_token_cost": 2.5e-06, - "output_cost_per_token": 2e-05, - "output_cost_per_audio_token": 8e-05, - "litellm_provider": "azure", - "mode": "chat", - "supported_modalities": [ - "text", - "audio" - ], - "supported_output_modalities": [ - "text", - "audio" - ], "supports_function_calling": true, "supports_parallel_function_calling": true, - "supports_audio_input": true, - "supports_audio_output": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "azure/us/gpt-4o-realtime-preview-2024-12-17": { - "max_tokens": 4096, - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 5.5e-06, - "input_cost_per_audio_token": 4.4e-05, - "cache_read_input_token_cost": 2.75e-06, - "cache_read_input_audio_token_cost": 2.5e-06, - "output_cost_per_token": 2.2e-05, - "output_cost_per_audio_token": 8e-05, - "litellm_provider": "azure", - "mode": "chat", - "supported_modalities": [ - "text", - "audio" - ], - "supported_output_modalities": [ - "text", - "audio" - ], - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_audio_input": true, - "supports_audio_output": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "azure/eu/gpt-4o-realtime-preview-2024-12-17": { - "max_tokens": 4096, - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 5.5e-06, - "input_cost_per_audio_token": 4.4e-05, - "cache_read_input_token_cost": 2.75e-06, - "cache_read_input_audio_token_cost": 2.5e-06, - "output_cost_per_token": 2.2e-05, - "output_cost_per_audio_token": 8e-05, - "litellm_provider": "azure", - "mode": "chat", - "supported_modalities": [ - "text", - "audio" - ], - "supported_output_modalities": [ - "text", - "audio" - ], - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_audio_input": true, - "supports_audio_output": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "azure/gpt-4o-realtime-preview-2024-10-01": { - "max_tokens": 4096, - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 5e-06, - "input_cost_per_audio_token": 0.0001, - "cache_read_input_token_cost": 2.5e-06, - "cache_creation_input_audio_token_cost": 2e-05, - "output_cost_per_token": 2e-05, - "output_cost_per_audio_token": 0.0002, - "litellm_provider": "azure", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_audio_input": true, - "supports_audio_output": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "azure/us/gpt-4o-realtime-preview-2024-10-01": { - "max_tokens": 4096, - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 5.5e-06, - "input_cost_per_audio_token": 0.00011, - "cache_read_input_token_cost": 2.75e-06, - "cache_creation_input_audio_token_cost": 2.2e-05, - "output_cost_per_token": 2.2e-05, - "output_cost_per_audio_token": 0.00022, - "litellm_provider": "azure", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_audio_input": true, - "supports_audio_output": true, "supports_system_messages": true, "supports_tool_choice": true }, "azure/eu/gpt-4o-realtime-preview-2024-10-01": { - "max_tokens": 4096, + "cache_creation_input_audio_token_cost": 2.2e-05, + "cache_read_input_token_cost": 2.75e-06, + "input_cost_per_audio_token": 0.00011, + "input_cost_per_token": 5.5e-06, + "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 4096, - "input_cost_per_token": 5.5e-06, - "input_cost_per_audio_token": 0.00011, - "cache_read_input_token_cost": 2.75e-06, - "cache_creation_input_audio_token_cost": 2.2e-05, - "output_cost_per_token": 2.2e-05, - "output_cost_per_audio_token": 0.00022, - "litellm_provider": "azure", + "max_tokens": 4096, "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, + "output_cost_per_audio_token": 0.00022, + "output_cost_per_token": 2.2e-05, "supports_audio_input": true, "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true }, - "azure/o4-mini-2025-04-16": { - "max_tokens": 100000, - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "input_cost_per_token": 1.1e-06, - "output_cost_per_token": 4.4e-06, - "cache_read_input_token_cost": 2.75e-07, + "azure/eu/gpt-4o-realtime-preview-2024-12-17": { + "cache_read_input_audio_token_cost": 2.5e-06, + "cache_read_input_token_cost": 2.75e-06, + "input_cost_per_audio_token": 4.4e-05, + "input_cost_per_token": 5.5e-06, "litellm_provider": "azure", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": false, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_reasoning": true, - "supports_tool_choice": true - }, - "azure/o3-mini-2025-01-31": { - "max_tokens": 100000, - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "input_cost_per_token": 1.1e-06, - "output_cost_per_token": 4.4e-06, - "cache_read_input_token_cost": 5.5e-07, - "litellm_provider": "azure", - "mode": "chat", - "supports_reasoning": true, - "supports_vision": false, - "supports_prompt_caching": true, - "supports_tool_choice": true - }, - "azure/us/o3-mini-2025-01-31": { - "max_tokens": 100000, - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "input_cost_per_token": 1.21e-06, - "input_cost_per_token_batches": 6.05e-07, - "output_cost_per_token": 4.84e-06, - "output_cost_per_token_batches": 2.42e-06, - "cache_read_input_token_cost": 6.05e-07, - "litellm_provider": "azure", - "mode": "chat", - "supports_vision": false, - "supports_reasoning": true, - "supports_prompt_caching": true, - "supports_tool_choice": true - }, - "azure/eu/o3-mini-2025-01-31": { - "max_tokens": 100000, - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "input_cost_per_token": 1.21e-06, - "input_cost_per_token_batches": 6.05e-07, - "output_cost_per_token": 4.84e-06, - "output_cost_per_token_batches": 2.42e-06, - "cache_read_input_token_cost": 6.05e-07, - "litellm_provider": "azure", - "mode": "chat", - "supports_vision": false, - "supports_reasoning": true, - "supports_prompt_caching": true, - "supports_tool_choice": true - }, - "azure/tts-1": { - "mode": "audio_speech", - "input_cost_per_character": 1.5e-05, - "litellm_provider": "azure" - }, - "azure/tts-1-hd": { - "mode": "audio_speech", - "input_cost_per_character": 3e-05, - "litellm_provider": "azure" - }, - "azure/whisper-1": { - "mode": "audio_transcription", - "input_cost_per_second": 0.0001, - "output_cost_per_second": 0.0001, - "litellm_provider": "azure" - }, - "azure/gpt-4o-transcribe": { - "mode": "audio_transcription", - "max_input_tokens": 16000, - "max_output_tokens": 2000, - "input_cost_per_token": 2.5e-06, - "input_cost_per_audio_token": 6e-06, - "output_cost_per_token": 1e-05, - "litellm_provider": "azure", - "supported_endpoints": [ - "/v1/audio/transcriptions" - ] - }, - "azure/gpt-4o-mini-transcribe": { - "mode": "audio_transcription", - "max_input_tokens": 16000, - "max_output_tokens": 2000, - "input_cost_per_token": 1.25e-06, - "input_cost_per_audio_token": 3e-06, - "output_cost_per_token": 5e-06, - "litellm_provider": "azure", - "supported_endpoints": [ - "/v1/audio/transcriptions" - ] - }, - "azure/o3-mini": { - "max_tokens": 100000, - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "input_cost_per_token": 1.1e-06, - "output_cost_per_token": 4.4e-06, - "cache_read_input_token_cost": 5.5e-07, - "litellm_provider": "azure", - "mode": "chat", - "supports_vision": false, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "azure/o1-mini": { - "max_tokens": 65536, "max_input_tokens": 128000, - "max_output_tokens": 65536, - "input_cost_per_token": 1.21e-06, - "output_cost_per_token": 4.84e-06, - "cache_read_input_token_cost": 6.05e-07, - "litellm_provider": "azure", + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", + "output_cost_per_audio_token": 8e-05, + "output_cost_per_token": 2.2e-05, + "supported_modalities": [ + "text", + "audio" + ], + "supported_output_modalities": [ + "text", + "audio" + ], + "supports_audio_input": true, + "supports_audio_output": true, "supports_function_calling": true, "supports_parallel_function_calling": true, - "supports_vision": false, - "supports_reasoning": true, - "supports_prompt_caching": true - }, - "azure/o1-mini-2024-09-12": { - "max_tokens": 65536, - "max_input_tokens": 128000, - "max_output_tokens": 65536, - "input_cost_per_token": 1.1e-06, - "output_cost_per_token": 4.4e-06, - "cache_read_input_token_cost": 5.5e-07, - "litellm_provider": "azure", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_vision": false, - "supports_reasoning": true, - "supports_prompt_caching": true - }, - "azure/us/o1-mini-2024-09-12": { - "max_tokens": 65536, - "max_input_tokens": 128000, - "max_output_tokens": 65536, - "input_cost_per_token": 1.21e-06, - "input_cost_per_token_batches": 6.05e-07, - "output_cost_per_token": 4.84e-06, - "output_cost_per_token_batches": 2.42e-06, - "cache_read_input_token_cost": 6.05e-07, - "litellm_provider": "azure", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_vision": false, - "supports_prompt_caching": true - }, - "azure/eu/o1-mini-2024-09-12": { - "max_tokens": 65536, - "max_input_tokens": 128000, - "max_output_tokens": 65536, - "input_cost_per_token": 1.21e-06, - "input_cost_per_token_batches": 6.05e-07, - "output_cost_per_token": 4.84e-06, - "output_cost_per_token_batches": 2.42e-06, - "cache_read_input_token_cost": 6.05e-07, - "litellm_provider": "azure", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_vision": false, - "supports_prompt_caching": true - }, - "azure/o1": { - "max_tokens": 100000, - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "input_cost_per_token": 1.5e-05, - "output_cost_per_token": 6e-05, - "cache_read_input_token_cost": 7.5e-06, - "litellm_provider": "azure", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_vision": true, - "supports_reasoning": true, - "supports_prompt_caching": true, - "supports_tool_choice": true - }, - "azure/o1-2024-12-17": { - "max_tokens": 100000, - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "input_cost_per_token": 1.5e-05, - "output_cost_per_token": 6e-05, - "cache_read_input_token_cost": 7.5e-06, - "litellm_provider": "azure", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_vision": true, - "supports_reasoning": true, - "supports_prompt_caching": true, - "supports_tool_choice": true - }, - "azure/us/o1-2024-12-17": { - "max_tokens": 100000, - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "input_cost_per_token": 1.65e-05, - "output_cost_per_token": 6.6e-05, - "cache_read_input_token_cost": 8.25e-06, - "litellm_provider": "azure", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_vision": true, - "supports_prompt_caching": true, + "supports_system_messages": true, "supports_tool_choice": true }, "azure/eu/o1-2024-12-17": { - "max_tokens": 100000, - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "input_cost_per_token": 1.65e-05, - "output_cost_per_token": 6.6e-05, "cache_read_input_token_cost": 8.25e-06, + "input_cost_per_token": 1.65e-05, "litellm_provider": "azure", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_tool_choice": true - }, - "azure/codex-mini": { - "max_tokens": 100000, "max_input_tokens": 200000, "max_output_tokens": 100000, - "input_cost_per_token": 1.5e-06, - "output_cost_per_token": 6e-06, - "cache_read_input_token_cost": 3.75e-07, - "litellm_provider": "azure", - "mode": "responses", - "supports_pdf_input": true, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 6.6e-05, "supports_function_calling": true, "supports_parallel_function_calling": true, - "supports_vision": true, "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_response_schema": true, "supports_tool_choice": true, - "supports_reasoning": true, - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supported_endpoints": [ - "/v1/responses" - ] + "supports_vision": true }, - "azure/o1-preview": { - "max_tokens": 32768, - "max_input_tokens": 128000, - "max_output_tokens": 32768, - "input_cost_per_token": 1.5e-05, - "output_cost_per_token": 6e-05, - "cache_read_input_token_cost": 7.5e-06, + "azure/eu/o1-mini-2024-09-12": { + "cache_read_input_token_cost": 6.05e-07, + "input_cost_per_token": 1.21e-06, + "input_cost_per_token_batches": 6.05e-07, "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 65536, + "max_tokens": 65536, "mode": "chat", + "output_cost_per_token": 4.84e-06, + "output_cost_per_token_batches": 2.42e-06, "supports_function_calling": true, "supports_parallel_function_calling": true, - "supports_vision": false, - "supports_reasoning": true, - "supports_prompt_caching": true - }, - "azure/o1-preview-2024-09-12": { - "max_tokens": 32768, - "max_input_tokens": 128000, - "max_output_tokens": 32768, - "input_cost_per_token": 1.5e-05, - "output_cost_per_token": 6e-05, - "cache_read_input_token_cost": 7.5e-06, - "litellm_provider": "azure", - "mode": "chat", - "supports_pdf_input": true, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_vision": false, - "supports_reasoning": true, - "supports_prompt_caching": true - }, - "azure/us/o1-preview-2024-09-12": { - "max_tokens": 32768, - "max_input_tokens": 128000, - "max_output_tokens": 32768, - "input_cost_per_token": 1.65e-05, - "output_cost_per_token": 6.6e-05, - "cache_read_input_token_cost": 8.25e-06, - "litellm_provider": "azure", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_vision": false, - "supports_prompt_caching": true + "supports_prompt_caching": true, + "supports_vision": false }, "azure/eu/o1-preview-2024-09-12": { - "max_tokens": 32768, + "cache_read_input_token_cost": 8.25e-06, + "input_cost_per_token": 1.65e-05, + "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 32768, - "input_cost_per_token": 1.65e-05, + "max_tokens": 32768, + "mode": "chat", "output_cost_per_token": 6.6e-05, - "cache_read_input_token_cost": 8.25e-06, - "litellm_provider": "azure", - "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true, - "supports_vision": false, - "supports_prompt_caching": true - }, - "azure/gpt-4.5-preview": { - "max_tokens": 16384, - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "input_cost_per_token": 7.5e-05, - "output_cost_per_token": 0.00015, - "input_cost_per_token_batches": 3.75e-05, - "output_cost_per_token_batches": 7.5e-05, - "cache_read_input_token_cost": 3.75e-05, - "litellm_provider": "azure", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true + "supports_vision": false }, - "azure/gpt-4o": { - "max_tokens": 16384, - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "input_cost_per_token": 2.5e-06, - "output_cost_per_token": 1e-05, - "cache_read_input_token_cost": 1.25e-06, + "azure/eu/o3-mini-2025-01-31": { + "cache_read_input_token_cost": 6.05e-07, + "input_cost_per_token": 1.21e-06, + "input_cost_per_token_batches": 6.05e-07, "litellm_provider": "azure", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, + "output_cost_per_token": 4.84e-06, + "output_cost_per_token_batches": 2.42e-06, "supports_prompt_caching": true, - "supports_tool_choice": true - }, - "azure/global/gpt-4o-2024-11-20": { - "max_tokens": 16384, - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "input_cost_per_token": 2.5e-06, - "output_cost_per_token": 1e-05, - "cache_read_input_token_cost": 1.25e-06, - "litellm_provider": "azure", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_tool_choice": true - }, - "azure/gpt-4o-2024-08-06": { - "max_tokens": 16384, - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "input_cost_per_token": 2.5e-06, - "output_cost_per_token": 1e-05, - "cache_read_input_token_cost": 1.25e-06, - "litellm_provider": "azure", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_tool_choice": true - }, - "azure/global/gpt-4o-2024-08-06": { - "max_tokens": 16384, - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "input_cost_per_token": 2.5e-06, - "output_cost_per_token": 1e-05, - "cache_read_input_token_cost": 1.25e-06, - "litellm_provider": "azure", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_tool_choice": true - }, - "azure/gpt-4o-2024-11-20": { - "max_tokens": 16384, - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "input_cost_per_token": 2.75e-06, - "output_cost_per_token": 1.1e-05, - "cache_read_input_token_cost": 1.25e-06, - "litellm_provider": "azure", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_tool_choice": true - }, - "azure/us/gpt-4o-2024-11-20": { - "max_tokens": 16384, - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "input_cost_per_token": 2.75e-06, - "cache_creation_input_token_cost": 1.38e-06, - "output_cost_per_token": 1.1e-05, - "litellm_provider": "azure", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_tool_choice": true - }, - "azure/eu/gpt-4o-2024-11-20": { - "max_tokens": 16384, - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "input_cost_per_token": 2.75e-06, - "cache_creation_input_token_cost": 1.38e-06, - "output_cost_per_token": 1.1e-05, - "litellm_provider": "azure", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_tool_choice": true - }, - "azure/gpt-4o-2024-05-13": { - "max_tokens": 4096, - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 5e-06, - "output_cost_per_token": 1.5e-05, - "litellm_provider": "azure", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_tool_choice": true + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false }, "azure/global-standard/gpt-4o-2024-08-06": { - "max_tokens": 16384, - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "input_cost_per_token": 2.5e-06, - "output_cost_per_token": 1e-05, "cache_read_input_token_cost": 1.25e-06, + "deprecation_date": "2025-08-20", + "input_cost_per_token": 2.5e-06, "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", + "output_cost_per_token": 1e-05, "supports_function_calling": true, "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, "supports_prompt_caching": true, + "supports_response_schema": true, "supports_tool_choice": true, - "deprecation_date": "2025-08-20" - }, - "azure/us/gpt-4o-2024-08-06": { - "max_tokens": 16384, - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "input_cost_per_token": 2.75e-06, - "output_cost_per_token": 1.1e-05, - "cache_read_input_token_cost": 1.375e-06, - "litellm_provider": "azure", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_tool_choice": true - }, - "azure/eu/gpt-4o-2024-08-06": { - "max_tokens": 16384, - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "input_cost_per_token": 2.75e-06, - "output_cost_per_token": 1.1e-05, - "cache_read_input_token_cost": 1.375e-06, - "litellm_provider": "azure", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_tool_choice": true + "supports_vision": true }, "azure/global-standard/gpt-4o-2024-11-20": { - "max_tokens": 16384, + "cache_read_input_token_cost": 1.25e-06, + "deprecation_date": "2025-12-20", + "input_cost_per_token": 2.5e-06, + "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, - "input_cost_per_token": 2.5e-06, - "output_cost_per_token": 1e-05, - "cache_read_input_token_cost": 1.25e-06, - "litellm_provider": "azure", + "max_tokens": 16384, "mode": "chat", + "output_cost_per_token": 1e-05, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, - "supports_vision": true, "supports_tool_choice": true, - "deprecation_date": "2025-12-20" + "supports_vision": true }, "azure/global-standard/gpt-4o-mini": { - "max_tokens": 16384, - "max_input_tokens": 128000, - "max_output_tokens": 16384, "input_cost_per_token": 1.5e-07, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", "output_cost_per_token": 6e-07, - "litellm_provider": "azure", - "mode": "chat", "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, - "supports_vision": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_vision": true }, - "azure/gpt-4o-mini": { - "max_tokens": 16384, + "azure/global/gpt-4o-2024-08-06": { + "cache_read_input_token_cost": 1.25e-06, + "input_cost_per_token": 2.5e-06, + "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, - "input_cost_per_token": 1.65e-07, - "output_cost_per_token": 6.6e-07, - "cache_read_input_token_cost": 7.5e-08, - "litellm_provider": "azure", + "max_tokens": 16384, "mode": "chat", + "output_cost_per_token": 1e-05, "supports_function_calling": true, "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, "supports_prompt_caching": true, - "supports_tool_choice": true + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true }, - "azure/gpt-4o-mini-2024-07-18": { - "max_tokens": 16384, + "azure/global/gpt-4o-2024-11-20": { + "cache_read_input_token_cost": 1.25e-06, + "input_cost_per_token": 2.5e-06, + "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 16384, - "input_cost_per_token": 1.65e-07, - "output_cost_per_token": 6.6e-07, - "cache_read_input_token_cost": 7.5e-08, - "litellm_provider": "azure", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_tool_choice": true - }, - "azure/us/gpt-4o-mini-2024-07-18": { "max_tokens": 16384, - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "input_cost_per_token": 1.65e-07, - "output_cost_per_token": 6.6e-07, - "cache_read_input_token_cost": 8.3e-08, - "litellm_provider": "azure", "mode": "chat", + "output_cost_per_token": 1e-05, "supports_function_calling": true, "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, "supports_prompt_caching": true, - "supports_tool_choice": true + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true }, - "azure/eu/gpt-4o-mini-2024-07-18": { - "max_tokens": 16384, - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "input_cost_per_token": 1.65e-07, - "output_cost_per_token": 6.6e-07, - "cache_read_input_token_cost": 8.3e-08, + "azure/gpt-3.5-turbo": { + "input_cost_per_token": 5e-07, "litellm_provider": "azure", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_tool_choice": true - }, - "azure/gpt-4-turbo-2024-04-09": { - "max_tokens": 4096, - "max_input_tokens": 128000, + "max_input_tokens": 4097, "max_output_tokens": 4096, - "input_cost_per_token": 1e-05, - "output_cost_per_token": 3e-05, - "litellm_provider": "azure", + "max_tokens": 4096, "mode": "chat", + "output_cost_per_token": 1.5e-06, + "supports_function_calling": true, + "supports_tool_choice": true + }, + "azure/gpt-3.5-turbo-0125": { + "deprecation_date": "2025-03-31", + "input_cost_per_token": 5e-07, + "litellm_provider": "azure", + "max_input_tokens": 16384, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.5e-06, "supports_function_calling": true, "supports_parallel_function_calling": true, - "supports_vision": true, + "supports_tool_choice": true + }, + "azure/gpt-3.5-turbo-instruct-0914": { + "input_cost_per_token": 1.5e-06, + "litellm_provider": "azure_text", + "max_input_tokens": 4097, + "max_tokens": 4097, + "mode": "completion", + "output_cost_per_token": 2e-06 + }, + "azure/gpt-35-turbo": { + "input_cost_per_token": 5e-07, + "litellm_provider": "azure", + "max_input_tokens": 4097, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.5e-06, + "supports_function_calling": true, + "supports_tool_choice": true + }, + "azure/gpt-35-turbo-0125": { + "deprecation_date": "2025-05-31", + "input_cost_per_token": 5e-07, + "litellm_provider": "azure", + "max_input_tokens": 16384, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.5e-06, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true + }, + "azure/gpt-35-turbo-0301": { + "deprecation_date": "2025-02-13", + "input_cost_per_token": 2e-07, + "litellm_provider": "azure", + "max_input_tokens": 4097, + "max_output_tokens": 4096, + "max_tokens": 4097, + "mode": "chat", + "output_cost_per_token": 2e-06, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true + }, + "azure/gpt-35-turbo-0613": { + "deprecation_date": "2025-02-13", + "input_cost_per_token": 1.5e-06, + "litellm_provider": "azure", + "max_input_tokens": 4097, + "max_output_tokens": 4096, + "max_tokens": 4097, + "mode": "chat", + "output_cost_per_token": 2e-06, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true + }, + "azure/gpt-35-turbo-1106": { + "deprecation_date": "2025-03-31", + "input_cost_per_token": 1e-06, + "litellm_provider": "azure", + "max_input_tokens": 16384, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 2e-06, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true + }, + "azure/gpt-35-turbo-16k": { + "input_cost_per_token": 3e-06, + "litellm_provider": "azure", + "max_input_tokens": 16385, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 4e-06, + "supports_tool_choice": true + }, + "azure/gpt-35-turbo-16k-0613": { + "input_cost_per_token": 3e-06, + "litellm_provider": "azure", + "max_input_tokens": 16385, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 4e-06, + "supports_function_calling": true, + "supports_tool_choice": true + }, + "azure/gpt-35-turbo-instruct": { + "input_cost_per_token": 1.5e-06, + "litellm_provider": "azure_text", + "max_input_tokens": 4097, + "max_tokens": 4097, + "mode": "completion", + "output_cost_per_token": 2e-06 + }, + "azure/gpt-35-turbo-instruct-0914": { + "input_cost_per_token": 1.5e-06, + "litellm_provider": "azure_text", + "max_input_tokens": 4097, + "max_tokens": 4097, + "mode": "completion", + "output_cost_per_token": 2e-06 + }, + "azure/gpt-4": { + "input_cost_per_token": 3e-05, + "litellm_provider": "azure", + "max_input_tokens": 8192, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 6e-05, + "supports_function_calling": true, "supports_tool_choice": true }, "azure/gpt-4-0125-preview": { - "max_tokens": 4096, + "input_cost_per_token": 1e-05, + "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 4096, - "input_cost_per_token": 1e-05, - "output_cost_per_token": 3e-05, - "litellm_provider": "azure", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_tool_choice": true - }, - "azure/gpt-4-1106-preview": { "max_tokens": 4096, - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 1e-05, - "output_cost_per_token": 3e-05, - "litellm_provider": "azure", "mode": "chat", + "output_cost_per_token": 3e-05, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true }, "azure/gpt-4-0613": { - "max_tokens": 4096, + "input_cost_per_token": 3e-05, + "litellm_provider": "azure", "max_input_tokens": 8192, "max_output_tokens": 4096, - "input_cost_per_token": 3e-05, - "output_cost_per_token": 6e-05, - "litellm_provider": "azure", + "max_tokens": 4096, "mode": "chat", + "output_cost_per_token": 6e-05, "supports_function_calling": true, "supports_tool_choice": true }, - "azure/gpt-4-32k-0613": { - "max_tokens": 4096, - "max_input_tokens": 32768, - "max_output_tokens": 4096, - "input_cost_per_token": 6e-05, - "output_cost_per_token": 0.00012, + "azure/gpt-4-1106-preview": { + "input_cost_per_token": 1e-05, "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", + "output_cost_per_token": 3e-05, + "supports_function_calling": true, + "supports_parallel_function_calling": true, "supports_tool_choice": true }, "azure/gpt-4-32k": { - "max_tokens": 4096, + "input_cost_per_token": 6e-05, + "litellm_provider": "azure", "max_input_tokens": 32768, "max_output_tokens": 4096, - "input_cost_per_token": 6e-05, - "output_cost_per_token": 0.00012, - "litellm_provider": "azure", + "max_tokens": 4096, "mode": "chat", + "output_cost_per_token": 0.00012, "supports_tool_choice": true }, - "azure/gpt-4": { - "max_tokens": 4096, - "max_input_tokens": 8192, - "max_output_tokens": 4096, - "input_cost_per_token": 3e-05, - "output_cost_per_token": 6e-05, + "azure/gpt-4-32k-0613": { + "input_cost_per_token": 6e-05, "litellm_provider": "azure", + "max_input_tokens": 32768, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", - "supports_function_calling": true, + "output_cost_per_token": 0.00012, "supports_tool_choice": true }, "azure/gpt-4-turbo": { - "max_tokens": 4096, + "input_cost_per_token": 1e-05, + "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 4096, - "input_cost_per_token": 1e-05, - "output_cost_per_token": 3e-05, - "litellm_provider": "azure", + "max_tokens": 4096, "mode": "chat", + "output_cost_per_token": 3e-05, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true }, + "azure/gpt-4-turbo-2024-04-09": { + "input_cost_per_token": 1e-05, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 3e-05, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true + }, "azure/gpt-4-turbo-vision-preview": { - "max_tokens": 4096, - "max_input_tokens": 128000, - "max_output_tokens": 4096, "input_cost_per_token": 1e-05, - "output_cost_per_token": 3e-05, "litellm_provider": "azure", - "mode": "chat", - "supports_vision": true, - "supports_tool_choice": true - }, - "azure/gpt-35-turbo-16k-0613": { - "max_tokens": 4096, - "max_input_tokens": 16385, - "max_output_tokens": 4096, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 4e-06, - "litellm_provider": "azure", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true - }, - "azure/gpt-35-turbo-1106": { - "max_tokens": 4096, - "max_input_tokens": 16384, - "max_output_tokens": 4096, - "input_cost_per_token": 1e-06, - "output_cost_per_token": 2e-06, - "litellm_provider": "azure", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "deprecation_date": "2025-03-31", - "supports_tool_choice": true - }, - "azure/gpt-35-turbo-0613": { - "max_tokens": 4097, - "max_input_tokens": 4097, - "max_output_tokens": 4096, - "input_cost_per_token": 1.5e-06, - "output_cost_per_token": 2e-06, - "litellm_provider": "azure", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "deprecation_date": "2025-02-13", - "supports_tool_choice": true - }, - "azure/gpt-35-turbo-0301": { - "max_tokens": 4097, - "max_input_tokens": 4097, - "max_output_tokens": 4096, - "input_cost_per_token": 2e-07, - "output_cost_per_token": 2e-06, - "litellm_provider": "azure", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "deprecation_date": "2025-02-13", - "supports_tool_choice": true - }, - "azure/gpt-35-turbo-0125": { - "max_tokens": 4096, - "max_input_tokens": 16384, - "max_output_tokens": 4096, - "input_cost_per_token": 5e-07, - "output_cost_per_token": 1.5e-06, - "litellm_provider": "azure", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "deprecation_date": "2025-05-31", - "supports_tool_choice": true - }, - "azure/gpt-3.5-turbo-0125": { - "max_tokens": 4096, - "max_input_tokens": 16384, - "max_output_tokens": 4096, - "input_cost_per_token": 5e-07, - "output_cost_per_token": 1.5e-06, - "litellm_provider": "azure", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "deprecation_date": "2025-03-31", - "supports_tool_choice": true - }, - "azure/gpt-35-turbo-16k": { - "max_tokens": 4096, - "max_input_tokens": 16385, - "max_output_tokens": 4096, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 4e-06, - "litellm_provider": "azure", - "mode": "chat", - "supports_tool_choice": true - }, - "azure/gpt-35-turbo": { - "max_tokens": 4096, - "max_input_tokens": 4097, - "max_output_tokens": 4096, - "input_cost_per_token": 5e-07, - "output_cost_per_token": 1.5e-06, - "litellm_provider": "azure", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true - }, - "azure/gpt-3.5-turbo": { - "max_tokens": 4096, - "max_input_tokens": 4097, - "max_output_tokens": 4096, - "input_cost_per_token": 5e-07, - "output_cost_per_token": 1.5e-06, - "litellm_provider": "azure", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true - }, - "azure/gpt-3.5-turbo-instruct-0914": { - "max_tokens": 4097, - "max_input_tokens": 4097, - "input_cost_per_token": 1.5e-06, - "output_cost_per_token": 2e-06, - "litellm_provider": "azure_text", - "mode": "completion" - }, - "azure/gpt-35-turbo-instruct": { - "max_tokens": 4097, - "max_input_tokens": 4097, - "input_cost_per_token": 1.5e-06, - "output_cost_per_token": 2e-06, - "litellm_provider": "azure_text", - "mode": "completion" - }, - "azure/gpt-35-turbo-instruct-0914": { - "max_tokens": 4097, - "max_input_tokens": 4097, - "input_cost_per_token": 1.5e-06, - "output_cost_per_token": 2e-06, - "litellm_provider": "azure_text", - "mode": "completion" - }, - "azure/mistral-large-latest": { - "max_tokens": 32000, - "max_input_tokens": 32000, - "input_cost_per_token": 8e-06, - "output_cost_per_token": 2.4e-05, - "litellm_provider": "azure", - "mode": "chat", - "supports_function_calling": true - }, - "azure/mistral-large-2402": { - "max_tokens": 32000, - "max_input_tokens": 32000, - "input_cost_per_token": 8e-06, - "output_cost_per_token": 2.4e-05, - "litellm_provider": "azure", - "mode": "chat", - "supports_function_calling": true - }, - "azure/command-r-plus": { - "max_tokens": 4096, "max_input_tokens": 128000, "max_output_tokens": 4096, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "litellm_provider": "azure", + "max_tokens": 4096, "mode": "chat", - "supports_function_calling": true + "output_cost_per_token": 3e-05, + "supports_tool_choice": true, + "supports_vision": true }, - "azure/ada": { - "max_tokens": 8191, - "max_input_tokens": 8191, + "azure/gpt-4.1": { + "cache_read_input_token_cost": 5e-07, + "input_cost_per_token": 2e-06, + "input_cost_per_token_batches": 1e-06, + "litellm_provider": "azure", + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 8e-06, + "output_cost_per_token_batches": 4e-06, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": false + }, + "azure/gpt-4.1-2025-04-14": { + "cache_read_input_token_cost": 5e-07, + "input_cost_per_token": 2e-06, + "input_cost_per_token_batches": 1e-06, + "litellm_provider": "azure", + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 8e-06, + "output_cost_per_token_batches": 4e-06, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": false + }, + "azure/gpt-4.1-mini": { + "cache_read_input_token_cost": 1e-07, + "input_cost_per_token": 4e-07, + "input_cost_per_token_batches": 2e-07, + "litellm_provider": "azure", + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 1.6e-06, + "output_cost_per_token_batches": 8e-07, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": false + }, + "azure/gpt-4.1-mini-2025-04-14": { + "cache_read_input_token_cost": 1e-07, + "input_cost_per_token": 4e-07, + "input_cost_per_token_batches": 2e-07, + "litellm_provider": "azure", + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 1.6e-06, + "output_cost_per_token_batches": 8e-07, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": false + }, + "azure/gpt-4.1-nano": { + "cache_read_input_token_cost": 2.5e-08, "input_cost_per_token": 1e-07, - "output_cost_per_token": 0.0, + "input_cost_per_token_batches": 5e-08, "litellm_provider": "azure", - "mode": "embedding" + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 4e-07, + "output_cost_per_token_batches": 2e-07, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true }, - "azure/text-embedding-ada-002": { - "max_tokens": 8191, - "max_input_tokens": 8191, + "azure/gpt-4.1-nano-2025-04-14": { + "cache_read_input_token_cost": 2.5e-08, "input_cost_per_token": 1e-07, - "output_cost_per_token": 0.0, + "input_cost_per_token_batches": 5e-08, "litellm_provider": "azure", - "mode": "embedding" + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 4e-07, + "output_cost_per_token_batches": 2e-07, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true }, - "azure/text-embedding-3-large": { - "max_tokens": 8191, - "max_input_tokens": 8191, - "input_cost_per_token": 1.3e-07, - "output_cost_per_token": 0.0, + "azure/gpt-4.5-preview": { + "cache_read_input_token_cost": 3.75e-05, + "input_cost_per_token": 7.5e-05, + "input_cost_per_token_batches": 3.75e-05, "litellm_provider": "azure", - "mode": "embedding" + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 0.00015, + "output_cost_per_token_batches": 7.5e-05, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true }, - "azure/text-embedding-3-small": { - "max_tokens": 8191, - "max_input_tokens": 8191, - "input_cost_per_token": 2e-08, - "output_cost_per_token": 0.0, + "azure/gpt-4o": { + "cache_read_input_token_cost": 1.25e-06, + "input_cost_per_token": 2.5e-06, "litellm_provider": "azure", - "mode": "embedding" + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1e-05, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "azure/gpt-4o-2024-05-13": { + "input_cost_per_token": 5e-06, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "azure/gpt-4o-2024-08-06": { + "cache_read_input_token_cost": 1.25e-06, + "input_cost_per_token": 2.5e-06, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1e-05, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "azure/gpt-4o-2024-11-20": { + "cache_read_input_token_cost": 1.25e-06, + "input_cost_per_token": 2.75e-06, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1.1e-05, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "azure/gpt-4o-audio-preview-2024-12-17": { + "input_cost_per_audio_token": 4e-05, + "input_cost_per_token": 2.5e-06, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_audio_token": 8e-05, + "output_cost_per_token": 1e-05, + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supported_modalities": [ + "text", + "audio" + ], + "supported_output_modalities": [ + "text", + "audio" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": false, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "azure/gpt-4o-mini": { + "cache_read_input_token_cost": 7.5e-08, + "input_cost_per_token": 1.65e-07, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 6.6e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "azure/gpt-4o-mini-2024-07-18": { + "cache_read_input_token_cost": 7.5e-08, + "input_cost_per_token": 1.65e-07, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 6.6e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "azure/gpt-4o-mini-audio-preview-2024-12-17": { + "input_cost_per_audio_token": 4e-05, + "input_cost_per_token": 2.5e-06, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_audio_token": 8e-05, + "output_cost_per_token": 1e-05, + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supported_modalities": [ + "text", + "audio" + ], + "supported_output_modalities": [ + "text", + "audio" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": false, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "azure/gpt-4o-mini-realtime-preview-2024-12-17": { + "cache_creation_input_audio_token_cost": 3e-07, + "cache_read_input_token_cost": 3e-07, + "input_cost_per_audio_token": 1e-05, + "input_cost_per_token": 6e-07, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_audio_token": 2e-05, + "output_cost_per_token": 2.4e-06, + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "azure/gpt-4o-mini-transcribe": { + "input_cost_per_audio_token": 3e-06, + "input_cost_per_token": 1.25e-06, + "litellm_provider": "azure", + "max_input_tokens": 16000, + "max_output_tokens": 2000, + "mode": "audio_transcription", + "output_cost_per_token": 5e-06, + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "azure/gpt-4o-mini-tts": { + "input_cost_per_token": 2.5e-06, + "litellm_provider": "azure", + "mode": "audio_speech", + "output_cost_per_audio_token": 1.2e-05, + "output_cost_per_second": 0.00025, + "output_cost_per_token": 1e-05, + "supported_endpoints": [ + "/v1/audio/speech" + ], + "supported_modalities": [ + "text", + "audio" + ], + "supported_output_modalities": [ + "audio" + ] + }, + "azure/gpt-4o-realtime-preview-2024-10-01": { + "cache_creation_input_audio_token_cost": 2e-05, + "cache_read_input_token_cost": 2.5e-06, + "input_cost_per_audio_token": 0.0001, + "input_cost_per_token": 5e-06, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_audio_token": 0.0002, + "output_cost_per_token": 2e-05, + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "azure/gpt-4o-realtime-preview-2024-12-17": { + "cache_read_input_token_cost": 2.5e-06, + "input_cost_per_audio_token": 4e-05, + "input_cost_per_token": 5e-06, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_audio_token": 8e-05, + "output_cost_per_token": 2e-05, + "supported_modalities": [ + "text", + "audio" + ], + "supported_output_modalities": [ + "text", + "audio" + ], + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "azure/gpt-4o-transcribe": { + "input_cost_per_audio_token": 6e-06, + "input_cost_per_token": 2.5e-06, + "litellm_provider": "azure", + "max_input_tokens": 16000, + "max_output_tokens": 2000, + "mode": "audio_transcription", + "output_cost_per_token": 1e-05, + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "azure/gpt-5": { + "cache_read_input_token_cost": 1.25e-07, + "input_cost_per_token": 1.25e-06, + "litellm_provider": "azure", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "azure/gpt-5-2025-08-07": { + "cache_read_input_token_cost": 1.25e-07, + "input_cost_per_token": 1.25e-06, + "litellm_provider": "azure", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "azure/gpt-5-chat": { + "cache_read_input_token_cost": 1.25e-07, + "input_cost_per_token": 1.25e-06, + "litellm_provider": "azure", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "source": "https://azure.microsoft.com/en-us/blog/gpt-5-in-azure-ai-foundry-the-future-of-ai-apps-and-agents-starts-here/", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": false, + "supports_vision": true + }, + "azure/gpt-5-chat-latest": { + "cache_read_input_token_cost": 1.25e-07, + "input_cost_per_token": 1.25e-06, + "litellm_provider": "azure", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": false, + "supports_vision": true + }, + "azure/gpt-5-mini": { + "cache_read_input_token_cost": 2.5e-08, + "input_cost_per_token": 2.5e-07, + "litellm_provider": "azure", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2e-06, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "azure/gpt-5-mini-2025-08-07": { + "cache_read_input_token_cost": 2.5e-08, + "input_cost_per_token": 2.5e-07, + "litellm_provider": "azure", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2e-06, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "azure/gpt-5-nano": { + "cache_read_input_token_cost": 5e-09, + "input_cost_per_token": 5e-08, + "litellm_provider": "azure", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4e-07, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "azure/gpt-5-nano-2025-08-07": { + "cache_read_input_token_cost": 5e-09, + "input_cost_per_token": 5e-08, + "litellm_provider": "azure", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4e-07, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true }, "azure/gpt-image-1": { - "mode": "image_generation", "input_cost_per_pixel": 4.0054321e-08, - "output_cost_per_pixel": 0.0, "litellm_provider": "azure", + "mode": "image_generation", + "output_cost_per_pixel": 0.0, "supported_endpoints": [ "/v1/images/generations" ] }, - "azure/low/1024-x-1024/gpt-image-1": { - "mode": "image_generation", - "input_cost_per_pixel": 1.0490417e-08, - "output_cost_per_pixel": 0.0, + "azure/hd/1024-x-1024/dall-e-3": { + "input_cost_per_pixel": 7.629e-08, "litellm_provider": "azure", - "supported_endpoints": [ - "/v1/images/generations" - ] + "mode": "image_generation", + "output_cost_per_token": 0.0 }, - "azure/medium/1024-x-1024/gpt-image-1": { - "mode": "image_generation", - "input_cost_per_pixel": 4.0054321e-08, - "output_cost_per_pixel": 0.0, + "azure/hd/1024-x-1792/dall-e-3": { + "input_cost_per_pixel": 6.539e-08, "litellm_provider": "azure", - "supported_endpoints": [ - "/v1/images/generations" - ] + "mode": "image_generation", + "output_cost_per_token": 0.0 + }, + "azure/hd/1792-x-1024/dall-e-3": { + "input_cost_per_pixel": 6.539e-08, + "litellm_provider": "azure", + "mode": "image_generation", + "output_cost_per_token": 0.0 }, "azure/high/1024-x-1024/gpt-image-1": { - "mode": "image_generation", "input_cost_per_pixel": 1.59263611e-07, - "output_cost_per_pixel": 0.0, "litellm_provider": "azure", - "supported_endpoints": [ - "/v1/images/generations" - ] - }, - "azure/low/1024-x-1536/gpt-image-1": { "mode": "image_generation", - "input_cost_per_pixel": 1.0172526e-08, "output_cost_per_pixel": 0.0, - "litellm_provider": "azure", - "supported_endpoints": [ - "/v1/images/generations" - ] - }, - "azure/medium/1024-x-1536/gpt-image-1": { - "mode": "image_generation", - "input_cost_per_pixel": 4.0054321e-08, - "output_cost_per_pixel": 0.0, - "litellm_provider": "azure", "supported_endpoints": [ "/v1/images/generations" ] }, "azure/high/1024-x-1536/gpt-image-1": { - "mode": "image_generation", "input_cost_per_pixel": 1.58945719e-07, - "output_cost_per_pixel": 0.0, "litellm_provider": "azure", - "supported_endpoints": [ - "/v1/images/generations" - ] - }, - "azure/low/1536-x-1024/gpt-image-1": { "mode": "image_generation", - "input_cost_per_pixel": 1.0172526e-08, "output_cost_per_pixel": 0.0, - "litellm_provider": "azure", - "supported_endpoints": [ - "/v1/images/generations" - ] - }, - "azure/medium/1536-x-1024/gpt-image-1": { - "mode": "image_generation", - "input_cost_per_pixel": 4.0054321e-08, - "output_cost_per_pixel": 0.0, - "litellm_provider": "azure", "supported_endpoints": [ "/v1/images/generations" ] }, "azure/high/1536-x-1024/gpt-image-1": { - "mode": "image_generation", "input_cost_per_pixel": 1.58945719e-07, - "output_cost_per_pixel": 0.0, "litellm_provider": "azure", + "mode": "image_generation", + "output_cost_per_pixel": 0.0, "supported_endpoints": [ "/v1/images/generations" ] }, - "azure/standard/1024-x-1024/dall-e-3": { - "input_cost_per_pixel": 3.81469e-08, - "output_cost_per_token": 0.0, + "azure/low/1024-x-1024/gpt-image-1": { + "input_cost_per_pixel": 1.0490417e-08, "litellm_provider": "azure", - "mode": "image_generation" + "mode": "image_generation", + "output_cost_per_pixel": 0.0, + "supported_endpoints": [ + "/v1/images/generations" + ] }, - "azure/hd/1024-x-1024/dall-e-3": { - "input_cost_per_pixel": 7.629e-08, - "output_cost_per_token": 0.0, + "azure/low/1024-x-1536/gpt-image-1": { + "input_cost_per_pixel": 1.0172526e-08, "litellm_provider": "azure", - "mode": "image_generation" + "mode": "image_generation", + "output_cost_per_pixel": 0.0, + "supported_endpoints": [ + "/v1/images/generations" + ] }, - "azure/standard/1024-x-1792/dall-e-3": { - "input_cost_per_pixel": 4.359e-08, - "output_cost_per_token": 0.0, + "azure/low/1536-x-1024/gpt-image-1": { + "input_cost_per_pixel": 1.0172526e-08, "litellm_provider": "azure", - "mode": "image_generation" + "mode": "image_generation", + "output_cost_per_pixel": 0.0, + "supported_endpoints": [ + "/v1/images/generations" + ] }, - "azure/standard/1792-x-1024/dall-e-3": { - "input_cost_per_pixel": 4.359e-08, - "output_cost_per_token": 0.0, + "azure/medium/1024-x-1024/gpt-image-1": { + "input_cost_per_pixel": 4.0054321e-08, "litellm_provider": "azure", - "mode": "image_generation" + "mode": "image_generation", + "output_cost_per_pixel": 0.0, + "supported_endpoints": [ + "/v1/images/generations" + ] }, - "azure/hd/1024-x-1792/dall-e-3": { - "input_cost_per_pixel": 6.539e-08, - "output_cost_per_token": 0.0, + "azure/medium/1024-x-1536/gpt-image-1": { + "input_cost_per_pixel": 4.0054321e-08, "litellm_provider": "azure", - "mode": "image_generation" + "mode": "image_generation", + "output_cost_per_pixel": 0.0, + "supported_endpoints": [ + "/v1/images/generations" + ] }, - "azure/hd/1792-x-1024/dall-e-3": { - "input_cost_per_pixel": 6.539e-08, - "output_cost_per_token": 0.0, + "azure/medium/1536-x-1024/gpt-image-1": { + "input_cost_per_pixel": 4.0054321e-08, "litellm_provider": "azure", - "mode": "image_generation" + "mode": "image_generation", + "output_cost_per_pixel": 0.0, + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "azure/mistral-large-2402": { + "input_cost_per_token": 8e-06, + "litellm_provider": "azure", + "max_input_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 2.4e-05, + "supports_function_calling": true + }, + "azure/mistral-large-latest": { + "input_cost_per_token": 8e-06, + "litellm_provider": "azure", + "max_input_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 2.4e-05, + "supports_function_calling": true + }, + "azure/o1": { + "cache_read_input_token_cost": 7.5e-06, + "input_cost_per_token": 1.5e-05, + "litellm_provider": "azure", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 6e-05, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "azure/o1-2024-12-17": { + "cache_read_input_token_cost": 7.5e-06, + "input_cost_per_token": 1.5e-05, + "litellm_provider": "azure", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 6e-05, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "azure/o1-mini": { + "cache_read_input_token_cost": 6.05e-07, + "input_cost_per_token": 1.21e-06, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 4.84e-06, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_vision": false + }, + "azure/o1-mini-2024-09-12": { + "cache_read_input_token_cost": 5.5e-07, + "input_cost_per_token": 1.1e-06, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_vision": false + }, + "azure/o1-preview": { + "cache_read_input_token_cost": 7.5e-06, + "input_cost_per_token": 1.5e-05, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 6e-05, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_vision": false + }, + "azure/o1-preview-2024-09-12": { + "cache_read_input_token_cost": 7.5e-06, + "input_cost_per_token": 1.5e-05, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 6e-05, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_vision": false + }, + "azure/o3": { + "cache_read_input_token_cost": 5e-07, + "input_cost_per_token": 2e-06, + "litellm_provider": "azure", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 8e-06, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "azure/o3-2025-04-16": { + "cache_read_input_token_cost": 2.5e-06, + "input_cost_per_token": 1e-05, + "litellm_provider": "azure", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 4e-05, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "azure/o3-deep-research": { + "cache_read_input_token_cost": 2.5e-06, + "input_cost_per_token": 1e-05, + "litellm_provider": "azure", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "responses", + "output_cost_per_token": 4e-05, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "azure/o3-mini": { + "cache_read_input_token_cost": 5.5e-07, + "input_cost_per_token": 1.1e-06, + "litellm_provider": "azure", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "azure/o3-mini-2025-01-31": { + "cache_read_input_token_cost": 5.5e-07, + "input_cost_per_token": 1.1e-06, + "litellm_provider": "azure", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "azure/o3-pro": { + "input_cost_per_token": 2e-05, + "input_cost_per_token_batches": 1e-05, + "litellm_provider": "azure", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "responses", + "output_cost_per_token": 8e-05, + "output_cost_per_token_batches": 4e-05, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": false, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "azure/o3-pro-2025-06-10": { + "input_cost_per_token": 2e-05, + "input_cost_per_token_batches": 1e-05, + "litellm_provider": "azure", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "responses", + "output_cost_per_token": 8e-05, + "output_cost_per_token_batches": 4e-05, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": false, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "azure/o4-mini": { + "cache_read_input_token_cost": 2.75e-07, + "input_cost_per_token": 1.1e-06, + "litellm_provider": "azure", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "azure/o4-mini-2025-04-16": { + "cache_read_input_token_cost": 2.75e-07, + "input_cost_per_token": 1.1e-06, + "litellm_provider": "azure", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "supports_function_calling": true, + "supports_parallel_function_calling": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true }, "azure/standard/1024-x-1024/dall-e-2": { "input_cost_per_pixel": 0.0, - "output_cost_per_token": 0.0, "litellm_provider": "azure", - "mode": "image_generation" + "mode": "image_generation", + "output_cost_per_token": 0.0 }, - "azure_ai/grok-3": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 3.3e-06, - "output_cost_per_token": 1.65e-05, - "litellm_provider": "azure_ai", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": false, - "source": "https://devblogs.microsoft.com/foundry/announcing-grok-3-and-grok-3-mini-on-azure-ai-foundry/", - "supports_web_search": true + "azure/standard/1024-x-1024/dall-e-3": { + "input_cost_per_pixel": 3.81469e-08, + "litellm_provider": "azure", + "mode": "image_generation", + "output_cost_per_token": 0.0 }, - "azure_ai/global/grok-3": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "litellm_provider": "azure_ai", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": false, - "source": "https://devblogs.microsoft.com/foundry/announcing-grok-3-and-grok-3-mini-on-azure-ai-foundry/", - "supports_web_search": true + "azure/standard/1024-x-1792/dall-e-3": { + "input_cost_per_pixel": 4.359e-08, + "litellm_provider": "azure", + "mode": "image_generation", + "output_cost_per_token": 0.0 }, - "azure_ai/global/grok-3-mini": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 2.5e-07, - "output_cost_per_token": 1.27e-06, - "litellm_provider": "azure_ai", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": false, - "source": "https://devblogs.microsoft.com/foundry/announcing-grok-3-and-grok-3-mini-on-azure-ai-foundry/", - "supports_web_search": true + "azure/standard/1792-x-1024/dall-e-3": { + "input_cost_per_pixel": 4.359e-08, + "litellm_provider": "azure", + "mode": "image_generation", + "output_cost_per_token": 0.0 }, - "azure_ai/grok-3-mini": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 2.75e-07, - "output_cost_per_token": 1.38e-06, - "litellm_provider": "azure_ai", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": false, - "source": "https://devblogs.microsoft.com/foundry/announcing-grok-3-and-grok-3-mini-on-azure-ai-foundry/", - "supports_web_search": true - }, - "azure_ai/deepseek-r1": { - "max_tokens": 8192, - "max_input_tokens": 128000, - "max_output_tokens": 8192, - "input_cost_per_token": 1.35e-06, - "output_cost_per_token": 5.4e-06, - "litellm_provider": "azure_ai", - "mode": "chat", - "supports_tool_choice": true, - "supports_reasoning": true, - "source": "https://techcommunity.microsoft.com/blog/machinelearningblog/deepseek-r1-improved-performance-higher-limits-and-transparent-pricing/4386367" - }, - "azure_ai/deepseek-v3": { - "max_tokens": 8192, - "max_input_tokens": 128000, - "max_output_tokens": 8192, - "input_cost_per_token": 1.14e-06, - "output_cost_per_token": 4.56e-06, - "litellm_provider": "azure_ai", - "mode": "chat", - "supports_tool_choice": true, - "source": "https://techcommunity.microsoft.com/blog/machinelearningblog/announcing-deepseek-v3-on-azure-ai-foundry-and-github/4390438" - }, - "azure_ai/deepseek-v3-0324": { - "max_tokens": 8192, - "max_input_tokens": 128000, - "max_output_tokens": 8192, - "input_cost_per_token": 1.14e-06, - "output_cost_per_token": 4.56e-06, - "litellm_provider": "azure_ai", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true, - "source": "https://techcommunity.microsoft.com/blog/machinelearningblog/announcing-deepseek-v3-on-azure-ai-foundry-and-github/4390438" - }, - "azure_ai/jamba-instruct": { - "max_tokens": 4096, - "max_input_tokens": 70000, - "max_output_tokens": 4096, - "input_cost_per_token": 5e-07, - "output_cost_per_token": 7e-07, - "litellm_provider": "azure_ai", - "mode": "chat", - "supports_tool_choice": true - }, - "azure_ai/jais-30b-chat": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 0.0032, - "output_cost_per_token": 0.00971, - "litellm_provider": "azure_ai", - "mode": "chat", - "source": "https://azure.microsoft.com/en-us/products/ai-services/ai-foundry/models/jais-30b-chat" - }, - "azure_ai/mistral-nemo": { - "max_tokens": 4096, - "max_input_tokens": 131072, - "max_output_tokens": 4096, - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 1.5e-07, - "litellm_provider": "azure_ai", - "mode": "chat", - "supports_function_calling": true, - "source": "https://azuremarketplace.microsoft.com/en/marketplace/apps/000-000.mistral-nemo-12b-2407?tab=PlansAndPrice" - }, - "azure_ai/mistral-medium-2505": { + "azure/text-embedding-3-large": { + "input_cost_per_token": 1.3e-07, + "litellm_provider": "azure", + "max_input_tokens": 8191, "max_tokens": 8191, - "max_input_tokens": 131072, - "max_output_tokens": 8191, - "input_cost_per_token": 4e-07, - "output_cost_per_token": 2e-06, - "litellm_provider": "azure_ai", - "mode": "chat", - "supports_function_calling": true, - "supports_assistant_prefill": true, - "supports_tool_choice": true + "mode": "embedding", + "output_cost_per_token": 0.0 }, - "azure_ai/mistral-large": { + "azure/text-embedding-3-small": { + "input_cost_per_token": 2e-08, + "litellm_provider": "azure", + "max_input_tokens": 8191, "max_tokens": 8191, - "max_input_tokens": 32000, - "max_output_tokens": 8191, - "input_cost_per_token": 4e-06, - "output_cost_per_token": 1.2e-05, - "litellm_provider": "azure_ai", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true + "mode": "embedding", + "output_cost_per_token": 0.0 }, - "azure_ai/mistral-small": { + "azure/text-embedding-ada-002": { + "input_cost_per_token": 1e-07, + "litellm_provider": "azure", + "max_input_tokens": 8191, "max_tokens": 8191, - "max_input_tokens": 32000, - "max_output_tokens": 8191, - "input_cost_per_token": 1e-06, - "output_cost_per_token": 3e-06, - "litellm_provider": "azure_ai", - "supports_function_calling": true, - "mode": "chat", - "supports_tool_choice": true + "mode": "embedding", + "output_cost_per_token": 0.0 }, - "azure_ai/mistral-small-2503": { - "max_tokens": 128000, + "azure/tts-1": { + "input_cost_per_character": 1.5e-05, + "litellm_provider": "azure", + "mode": "audio_speech" + }, + "azure/tts-1-hd": { + "input_cost_per_character": 3e-05, + "litellm_provider": "azure", + "mode": "audio_speech" + }, + "azure/us/gpt-4o-2024-08-06": { + "cache_read_input_token_cost": 1.375e-06, + "input_cost_per_token": 2.75e-06, + "litellm_provider": "azure", "max_input_tokens": 128000, - "max_output_tokens": 128000, - "input_cost_per_token": 1e-06, - "output_cost_per_token": 3e-06, - "litellm_provider": "azure_ai", + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", + "output_cost_per_token": 1.1e-05, "supports_function_calling": true, - "supports_vision": true, - "supports_tool_choice": true + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true }, - "azure_ai/mistral-large-2407": { - "max_tokens": 4096, + "azure/us/gpt-4o-2024-11-20": { + "cache_creation_input_token_cost": 1.38e-06, + "input_cost_per_token": 2.75e-06, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1.1e-05, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "azure/us/gpt-4o-mini-2024-07-18": { + "cache_read_input_token_cost": 8.3e-08, + "input_cost_per_token": 1.65e-07, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 6.6e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "azure/us/gpt-4o-mini-realtime-preview-2024-12-17": { + "cache_creation_input_audio_token_cost": 3.3e-07, + "cache_read_input_token_cost": 3.3e-07, + "input_cost_per_audio_token": 1.1e-05, + "input_cost_per_token": 6.6e-07, + "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 4096, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 6e-06, - "litellm_provider": "azure_ai", - "supports_function_calling": true, + "max_tokens": 4096, "mode": "chat", - "source": "https://azuremarketplace.microsoft.com/en/marketplace/apps/000-000.mistral-ai-large-2407-offer?tab=Overview", + "output_cost_per_audio_token": 2.2e-05, + "output_cost_per_token": 2.64e-06, + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, "supports_tool_choice": true }, - "azure_ai/mistral-large-latest": { - "max_tokens": 4096, + "azure/us/gpt-4o-realtime-preview-2024-10-01": { + "cache_creation_input_audio_token_cost": 2.2e-05, + "cache_read_input_token_cost": 2.75e-06, + "input_cost_per_audio_token": 0.00011, + "input_cost_per_token": 5.5e-06, + "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 4096, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 6e-06, - "litellm_provider": "azure_ai", - "supports_function_calling": true, + "max_tokens": 4096, "mode": "chat", - "source": "https://azuremarketplace.microsoft.com/en/marketplace/apps/000-000.mistral-ai-large-2407-offer?tab=Overview", + "output_cost_per_audio_token": 0.00022, + "output_cost_per_token": 2.2e-05, + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, "supports_tool_choice": true }, - "azure_ai/ministral-3b": { - "max_tokens": 4096, + "azure/us/gpt-4o-realtime-preview-2024-12-17": { + "cache_read_input_audio_token_cost": 2.5e-06, + "cache_read_input_token_cost": 2.75e-06, + "input_cost_per_audio_token": 4.4e-05, + "input_cost_per_token": 5.5e-06, + "litellm_provider": "azure", "max_input_tokens": 128000, "max_output_tokens": 4096, - "input_cost_per_token": 4e-08, - "output_cost_per_token": 4e-08, - "litellm_provider": "azure_ai", - "supports_function_calling": true, + "max_tokens": 4096, "mode": "chat", - "source": "https://azuremarketplace.microsoft.com/en/marketplace/apps/000-000.ministral-3b-2410-offer?tab=Overview", + "output_cost_per_audio_token": 8e-05, + "output_cost_per_token": 2.2e-05, + "supported_modalities": [ + "text", + "audio" + ], + "supported_output_modalities": [ + "text", + "audio" + ], + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, "supports_tool_choice": true }, + "azure/us/o1-2024-12-17": { + "cache_read_input_token_cost": 8.25e-06, + "input_cost_per_token": 1.65e-05, + "litellm_provider": "azure", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 6.6e-05, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "azure/us/o1-mini-2024-09-12": { + "cache_read_input_token_cost": 6.05e-07, + "input_cost_per_token": 1.21e-06, + "input_cost_per_token_batches": 6.05e-07, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 4.84e-06, + "output_cost_per_token_batches": 2.42e-06, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_vision": false + }, + "azure/us/o1-preview-2024-09-12": { + "cache_read_input_token_cost": 8.25e-06, + "input_cost_per_token": 1.65e-05, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 6.6e-05, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_vision": false + }, + "azure/us/o3-mini-2025-01-31": { + "cache_read_input_token_cost": 6.05e-07, + "input_cost_per_token": 1.21e-06, + "input_cost_per_token_batches": 6.05e-07, + "litellm_provider": "azure", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 4.84e-06, + "output_cost_per_token_batches": 2.42e-06, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "azure/whisper-1": { + "input_cost_per_second": 0.0001, + "litellm_provider": "azure", + "mode": "audio_transcription", + "output_cost_per_second": 0.0001 + }, + "azure_ai/Cohere-embed-v3-english": { + "input_cost_per_token": 1e-07, + "litellm_provider": "azure_ai", + "max_input_tokens": 512, + "max_tokens": 512, + "mode": "embedding", + "output_cost_per_token": 0.0, + "output_vector_size": 1024, + "source": "https://azuremarketplace.microsoft.com/en-us/marketplace/apps/cohere.cohere-embed-v3-english-offer?tab=PlansAndPrice", + "supports_embedding_image_input": true + }, + "azure_ai/Cohere-embed-v3-multilingual": { + "input_cost_per_token": 1e-07, + "litellm_provider": "azure_ai", + "max_input_tokens": 512, + "max_tokens": 512, + "mode": "embedding", + "output_cost_per_token": 0.0, + "output_vector_size": 1024, + "source": "https://azuremarketplace.microsoft.com/en-us/marketplace/apps/cohere.cohere-embed-v3-english-offer?tab=PlansAndPrice", + "supports_embedding_image_input": true + }, + "azure_ai/FLUX-1.1-pro": { + "litellm_provider": "azure_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/black-forest-labs-flux-1-kontext-pro-and-flux1-1-pro-now-available-in-azure-ai-f/4434659", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "azure_ai/FLUX.1-Kontext-pro": { + "litellm_provider": "azure_ai", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://azuremarketplace.microsoft.com/pt-br/marketplace/apps/cohere.cohere-embed-4-offer?tab=PlansAndPrice", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, "azure_ai/Llama-3.2-11B-Vision-Instruct": { - "max_tokens": 2048, + "input_cost_per_token": 3.7e-07, + "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 2048, - "input_cost_per_token": 3.7e-07, - "output_cost_per_token": 3.7e-07, - "litellm_provider": "azure_ai", - "supports_function_calling": true, - "supports_vision": true, + "max_tokens": 2048, "mode": "chat", + "output_cost_per_token": 3.7e-07, "source": "https://azuremarketplace.microsoft.com/en/marketplace/apps/metagenai.meta-llama-3-2-11b-vision-instruct-offer?tab=Overview", - "supports_tool_choice": true + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "azure_ai/Llama-3.2-90B-Vision-Instruct": { + "input_cost_per_token": 2.04e-06, + "litellm_provider": "azure_ai", + "max_input_tokens": 128000, + "max_output_tokens": 2048, + "max_tokens": 2048, + "mode": "chat", + "output_cost_per_token": 2.04e-06, + "source": "https://azuremarketplace.microsoft.com/en/marketplace/apps/metagenai.meta-llama-3-2-90b-vision-instruct-offer?tab=Overview", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true }, "azure_ai/Llama-3.3-70B-Instruct": { - "max_tokens": 2048, + "input_cost_per_token": 7.1e-07, + "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 2048, - "input_cost_per_token": 7.1e-07, + "max_tokens": 2048, + "mode": "chat", "output_cost_per_token": 7.1e-07, - "litellm_provider": "azure_ai", - "supports_function_calling": true, - "mode": "chat", "source": "https://azuremarketplace.microsoft.com/en/marketplace/apps/metagenai.llama-3-3-70b-instruct-offer?tab=Overview", - "supports_tool_choice": true - }, - "azure_ai/Llama-4-Scout-17B-16E-Instruct": { - "max_tokens": 16384, - "max_input_tokens": 10000000, - "max_output_tokens": 16384, - "input_cost_per_token": 2e-07, - "output_cost_per_token": 7.8e-07, - "litellm_provider": "azure_ai", "supports_function_calling": true, - "supports_vision": true, - "mode": "chat", - "source": "https://azure.microsoft.com/en-us/blog/introducing-the-llama-4-herd-in-azure-ai-foundry-and-azure-databricks/", "supports_tool_choice": true }, "azure_ai/Llama-4-Maverick-17B-128E-Instruct-FP8": { - "max_tokens": 16384, + "input_cost_per_token": 1.41e-06, + "litellm_provider": "azure_ai", "max_input_tokens": 1000000, "max_output_tokens": 16384, - "input_cost_per_token": 1.41e-06, + "max_tokens": 16384, + "mode": "chat", "output_cost_per_token": 3.5e-07, - "litellm_provider": "azure_ai", - "supports_function_calling": true, - "supports_vision": true, - "mode": "chat", "source": "https://azure.microsoft.com/en-us/blog/introducing-the-llama-4-herd-in-azure-ai-foundry-and-azure-databricks/", - "supports_tool_choice": true - }, - "azure_ai/Llama-3.2-90B-Vision-Instruct": { - "max_tokens": 2048, - "max_input_tokens": 128000, - "max_output_tokens": 2048, - "input_cost_per_token": 2.04e-06, - "output_cost_per_token": 2.04e-06, - "litellm_provider": "azure_ai", "supports_function_calling": true, - "supports_vision": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "azure_ai/Llama-4-Scout-17B-16E-Instruct": { + "input_cost_per_token": 2e-07, + "litellm_provider": "azure_ai", + "max_input_tokens": 10000000, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", - "source": "https://azuremarketplace.microsoft.com/en/marketplace/apps/metagenai.meta-llama-3-2-90b-vision-instruct-offer?tab=Overview", - "supports_tool_choice": true + "output_cost_per_token": 7.8e-07, + "source": "https://azure.microsoft.com/en-us/blog/introducing-the-llama-4-herd-in-azure-ai-foundry-and-azure-databricks/", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true }, "azure_ai/Meta-Llama-3-70B-Instruct": { - "max_tokens": 2048, + "input_cost_per_token": 1.1e-06, + "litellm_provider": "azure_ai", "max_input_tokens": 8192, "max_output_tokens": 2048, - "input_cost_per_token": 1.1e-06, + "max_tokens": 2048, + "mode": "chat", "output_cost_per_token": 3.7e-07, - "litellm_provider": "azure_ai", - "mode": "chat", - "supports_tool_choice": true - }, - "azure_ai/Meta-Llama-3.1-8B-Instruct": { - "max_tokens": 2048, - "max_input_tokens": 128000, - "max_output_tokens": 2048, - "input_cost_per_token": 3e-07, - "output_cost_per_token": 6.1e-07, - "litellm_provider": "azure_ai", - "mode": "chat", - "source": "https://azuremarketplace.microsoft.com/en-us/marketplace/apps/metagenai.meta-llama-3-1-8b-instruct-offer?tab=PlansAndPrice", - "supports_tool_choice": true - }, - "azure_ai/Meta-Llama-3.1-70B-Instruct": { - "max_tokens": 2048, - "max_input_tokens": 128000, - "max_output_tokens": 2048, - "input_cost_per_token": 2.68e-06, - "output_cost_per_token": 3.54e-06, - "litellm_provider": "azure_ai", - "mode": "chat", - "source": "https://azuremarketplace.microsoft.com/en-us/marketplace/apps/metagenai.meta-llama-3-1-70b-instruct-offer?tab=PlansAndPrice", "supports_tool_choice": true }, "azure_ai/Meta-Llama-3.1-405B-Instruct": { - "max_tokens": 2048, + "input_cost_per_token": 5.33e-06, + "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 2048, - "input_cost_per_token": 5.33e-06, - "output_cost_per_token": 1.6e-05, - "litellm_provider": "azure_ai", + "max_tokens": 2048, "mode": "chat", + "output_cost_per_token": 1.6e-05, "source": "https://azuremarketplace.microsoft.com/en-us/marketplace/apps/metagenai.meta-llama-3-1-405b-instruct-offer?tab=PlansAndPrice", "supports_tool_choice": true }, - "azure_ai/Phi-4-mini-instruct": { - "max_tokens": 4096, - "max_input_tokens": 131072, - "max_output_tokens": 4096, - "input_cost_per_token": 7.5e-08, - "output_cost_per_token": 3e-07, + "azure_ai/Meta-Llama-3.1-70B-Instruct": { + "input_cost_per_token": 2.68e-06, "litellm_provider": "azure_ai", - "mode": "chat", - "supports_function_calling": true, - "source": "https://techcommunity.microsoft.com/blog/Azure-AI-Services-blog/announcing-new-phi-pricing-empowering-your-business-with-small-language-models/4395112" - }, - "azure_ai/Phi-4-multimodal-instruct": { - "max_tokens": 4096, - "max_input_tokens": 131072, - "max_output_tokens": 4096, - "input_cost_per_token": 8e-08, - "input_cost_per_audio_token": 4e-06, - "output_cost_per_token": 3.2e-07, - "litellm_provider": "azure_ai", - "mode": "chat", - "supports_audio_input": true, - "supports_function_calling": true, - "supports_vision": true, - "source": "https://techcommunity.microsoft.com/blog/Azure-AI-Services-blog/announcing-new-phi-pricing-empowering-your-business-with-small-language-models/4395112" - }, - "azure_ai/Phi-4": { - "max_tokens": 16384, - "max_input_tokens": 16384, - "max_output_tokens": 16384, - "input_cost_per_token": 1.25e-07, - "output_cost_per_token": 5e-07, - "litellm_provider": "azure_ai", - "mode": "chat", - "supports_vision": false, - "source": "https://techcommunity.microsoft.com/blog/machinelearningblog/affordable-innovation-unveiling-the-pricing-of-phi-3-slms-on-models-as-a-service/4156495", - "supports_function_calling": true, - "supports_tool_choice": true - }, - "azure_ai/Phi-3.5-mini-instruct": { - "max_tokens": 4096, "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 1.3e-07, - "output_cost_per_token": 5.2e-07, - "litellm_provider": "azure_ai", + "max_output_tokens": 2048, + "max_tokens": 2048, "mode": "chat", - "supports_vision": false, - "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", + "output_cost_per_token": 3.54e-06, + "source": "https://azuremarketplace.microsoft.com/en-us/marketplace/apps/metagenai.meta-llama-3-1-70b-instruct-offer?tab=PlansAndPrice", "supports_tool_choice": true }, - "azure_ai/Phi-3.5-vision-instruct": { - "max_tokens": 4096, + "azure_ai/Meta-Llama-3.1-8B-Instruct": { + "input_cost_per_token": 3e-07, + "litellm_provider": "azure_ai", "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 1.3e-07, - "output_cost_per_token": 5.2e-07, - "litellm_provider": "azure_ai", + "max_output_tokens": 2048, + "max_tokens": 2048, "mode": "chat", - "supports_vision": true, - "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", - "supports_tool_choice": true - }, - "azure_ai/Phi-3.5-MoE-instruct": { - "max_tokens": 4096, - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 1.6e-07, - "output_cost_per_token": 6.4e-07, - "litellm_provider": "azure_ai", - "mode": "chat", - "supports_vision": false, - "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", - "supports_tool_choice": true - }, - "azure_ai/Phi-3-mini-4k-instruct": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 1.3e-07, - "output_cost_per_token": 5.2e-07, - "litellm_provider": "azure_ai", - "mode": "chat", - "supports_vision": false, - "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", - "supports_tool_choice": true - }, - "azure_ai/Phi-3-mini-128k-instruct": { - "max_tokens": 4096, - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 1.3e-07, - "output_cost_per_token": 5.2e-07, - "litellm_provider": "azure_ai", - "mode": "chat", - "supports_vision": false, - "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", - "supports_tool_choice": true - }, - "azure_ai/Phi-3-small-8k-instruct": { - "max_tokens": 4096, - "max_input_tokens": 8192, - "max_output_tokens": 4096, - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 6e-07, - "litellm_provider": "azure_ai", - "mode": "chat", - "supports_vision": false, - "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", - "supports_tool_choice": true - }, - "azure_ai/Phi-3-small-128k-instruct": { - "max_tokens": 4096, - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 6e-07, - "litellm_provider": "azure_ai", - "mode": "chat", - "supports_vision": false, - "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", - "supports_tool_choice": true - }, - "azure_ai/Phi-3-medium-4k-instruct": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 1.7e-07, - "output_cost_per_token": 6.8e-07, - "litellm_provider": "azure_ai", - "mode": "chat", - "supports_vision": false, - "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", + "output_cost_per_token": 6.1e-07, + "source": "https://azuremarketplace.microsoft.com/en-us/marketplace/apps/metagenai.meta-llama-3-1-8b-instruct-offer?tab=PlansAndPrice", "supports_tool_choice": true }, "azure_ai/Phi-3-medium-128k-instruct": { - "max_tokens": 4096, + "input_cost_per_token": 1.7e-07, + "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 4096, - "input_cost_per_token": 1.7e-07, - "output_cost_per_token": 6.8e-07, - "litellm_provider": "azure_ai", + "max_tokens": 4096, "mode": "chat", - "supports_vision": false, + "output_cost_per_token": 6.8e-07, "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_vision": false }, - "azure_ai/cohere-rerank-v3.5": { - "max_tokens": 4096, + "azure_ai/Phi-3-medium-4k-instruct": { + "input_cost_per_token": 1.7e-07, + "litellm_provider": "azure_ai", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_query_tokens": 2048, - "input_cost_per_token": 0.0, - "input_cost_per_query": 0.002, - "output_cost_per_token": 0.0, - "litellm_provider": "azure_ai", - "mode": "rerank" - }, - "azure_ai/cohere-rerank-v3-multilingual": { "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 6.8e-07, + "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", + "supports_tool_choice": true, + "supports_vision": false + }, + "azure_ai/Phi-3-mini-128k-instruct": { + "input_cost_per_token": 1.3e-07, + "litellm_provider": "azure_ai", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 5.2e-07, + "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", + "supports_tool_choice": true, + "supports_vision": false + }, + "azure_ai/Phi-3-mini-4k-instruct": { + "input_cost_per_token": 1.3e-07, + "litellm_provider": "azure_ai", "max_input_tokens": 4096, "max_output_tokens": 4096, - "max_query_tokens": 2048, - "input_cost_per_token": 0.0, - "input_cost_per_query": 0.002, - "output_cost_per_token": 0.0, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 5.2e-07, + "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", + "supports_tool_choice": true, + "supports_vision": false + }, + "azure_ai/Phi-3-small-128k-instruct": { + "input_cost_per_token": 1.5e-07, "litellm_provider": "azure_ai", - "mode": "rerank" + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 6e-07, + "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", + "supports_tool_choice": true, + "supports_vision": false + }, + "azure_ai/Phi-3-small-8k-instruct": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "azure_ai", + "max_input_tokens": 8192, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 6e-07, + "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", + "supports_tool_choice": true, + "supports_vision": false + }, + "azure_ai/Phi-3.5-MoE-instruct": { + "input_cost_per_token": 1.6e-07, + "litellm_provider": "azure_ai", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 6.4e-07, + "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", + "supports_tool_choice": true, + "supports_vision": false + }, + "azure_ai/Phi-3.5-mini-instruct": { + "input_cost_per_token": 1.3e-07, + "litellm_provider": "azure_ai", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 5.2e-07, + "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", + "supports_tool_choice": true, + "supports_vision": false + }, + "azure_ai/Phi-3.5-vision-instruct": { + "input_cost_per_token": 1.3e-07, + "litellm_provider": "azure_ai", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 5.2e-07, + "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/", + "supports_tool_choice": true, + "supports_vision": true + }, + "azure_ai/Phi-4": { + "input_cost_per_token": 1.25e-07, + "litellm_provider": "azure_ai", + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 5e-07, + "source": "https://techcommunity.microsoft.com/blog/machinelearningblog/affordable-innovation-unveiling-the-pricing-of-phi-3-slms-on-models-as-a-service/4156495", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "azure_ai/Phi-4-mini-instruct": { + "input_cost_per_token": 7.5e-08, + "litellm_provider": "azure_ai", + "max_input_tokens": 131072, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 3e-07, + "source": "https://techcommunity.microsoft.com/blog/Azure-AI-Services-blog/announcing-new-phi-pricing-empowering-your-business-with-small-language-models/4395112", + "supports_function_calling": true + }, + "azure_ai/Phi-4-multimodal-instruct": { + "input_cost_per_audio_token": 4e-06, + "input_cost_per_token": 8e-08, + "litellm_provider": "azure_ai", + "max_input_tokens": 131072, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 3.2e-07, + "source": "https://techcommunity.microsoft.com/blog/Azure-AI-Services-blog/announcing-new-phi-pricing-empowering-your-business-with-small-language-models/4395112", + "supports_audio_input": true, + "supports_function_calling": true, + "supports_vision": true }, "azure_ai/cohere-rerank-v3-english": { - "max_tokens": 4096, + "input_cost_per_query": 0.002, + "input_cost_per_token": 0.0, + "litellm_provider": "azure_ai", "max_input_tokens": 4096, "max_output_tokens": 4096, "max_query_tokens": 2048, - "input_cost_per_token": 0.0, + "max_tokens": 4096, + "mode": "rerank", + "output_cost_per_token": 0.0 + }, + "azure_ai/cohere-rerank-v3-multilingual": { "input_cost_per_query": 0.002, - "output_cost_per_token": 0.0, + "input_cost_per_token": 0.0, "litellm_provider": "azure_ai", - "mode": "rerank" + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_query_tokens": 2048, + "max_tokens": 4096, + "mode": "rerank", + "output_cost_per_token": 0.0 }, - "azure_ai/Cohere-embed-v3-english": { - "max_tokens": 512, - "max_input_tokens": 512, - "output_vector_size": 1024, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 0.0, + "azure_ai/cohere-rerank-v3.5": { + "input_cost_per_query": 0.002, + "input_cost_per_token": 0.0, "litellm_provider": "azure_ai", - "mode": "embedding", - "supports_embedding_image_input": true, - "source": "https://azuremarketplace.microsoft.com/en-us/marketplace/apps/cohere.cohere-embed-v3-english-offer?tab=PlansAndPrice" + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_query_tokens": 2048, + "max_tokens": 4096, + "mode": "rerank", + "output_cost_per_token": 0.0 }, - "azure_ai/Cohere-embed-v3-multilingual": { - "max_tokens": 512, - "max_input_tokens": 512, - "output_vector_size": 1024, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 0.0, + "azure_ai/deepseek-r1": { + "input_cost_per_token": 1.35e-06, "litellm_provider": "azure_ai", - "mode": "embedding", - "supports_embedding_image_input": true, - "source": "https://azuremarketplace.microsoft.com/en-us/marketplace/apps/cohere.cohere-embed-v3-english-offer?tab=PlansAndPrice" + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 5.4e-06, + "source": "https://techcommunity.microsoft.com/blog/machinelearningblog/deepseek-r1-improved-performance-higher-limits-and-transparent-pricing/4386367", + "supports_reasoning": true, + "supports_tool_choice": true + }, + "azure_ai/deepseek-v3": { + "input_cost_per_token": 1.14e-06, + "litellm_provider": "azure_ai", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 4.56e-06, + "source": "https://techcommunity.microsoft.com/blog/machinelearningblog/announcing-deepseek-v3-on-azure-ai-foundry-and-github/4390438", + "supports_tool_choice": true + }, + "azure_ai/deepseek-v3-0324": { + "input_cost_per_token": 1.14e-06, + "litellm_provider": "azure_ai", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 4.56e-06, + "source": "https://techcommunity.microsoft.com/blog/machinelearningblog/announcing-deepseek-v3-on-azure-ai-foundry-and-github/4390438", + "supports_function_calling": true, + "supports_tool_choice": true }, "azure_ai/embed-v-4-0": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "output_vector_size": 3072, "input_cost_per_token": 1.2e-07, - "output_cost_per_token": 0.0, "litellm_provider": "azure_ai", + "max_input_tokens": 128000, + "max_tokens": 128000, "mode": "embedding", - "supports_embedding_image_input": true, + "output_cost_per_token": 0.0, + "output_vector_size": 3072, + "source": "https://azuremarketplace.microsoft.com/pt-br/marketplace/apps/cohere.cohere-embed-4-offer?tab=PlansAndPrice", "supported_endpoints": [ "/v1/embeddings" ], @@ -4833,3767 +3150,5449 @@ "text", "image" ], - "source": "https://azuremarketplace.microsoft.com/pt-br/marketplace/apps/cohere.cohere-embed-4-offer?tab=PlansAndPrice" + "supports_embedding_image_input": true }, - "azure_ai/FLUX-1.1-pro": { - "output_cost_per_image": 0.04, + "azure_ai/global/grok-3": { + "input_cost_per_token": 3e-06, "litellm_provider": "azure_ai", - "mode": "image_generation", - "supported_endpoints": [ - "/v1/images/generations" - ], - "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/black-forest-labs-flux-1-kontext-pro-and-flux1-1-pro-now-available-in-azure-ai-f/4434659" + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "source": "https://devblogs.microsoft.com/foundry/announcing-grok-3-and-grok-3-mini-on-azure-ai-foundry/", + "supports_function_calling": true, + "supports_response_schema": false, + "supports_tool_choice": true, + "supports_web_search": true }, - "azure_ai/FLUX.1-Kontext-pro": { - "output_cost_per_image": 0.04, + "azure_ai/global/grok-3-mini": { + "input_cost_per_token": 2.5e-07, "litellm_provider": "azure_ai", - "mode": "image_generation", - "supported_endpoints": [ - "/v1/images/generations" - ], - "source": "https://azuremarketplace.microsoft.com/pt-br/marketplace/apps/cohere.cohere-embed-4-offer?tab=PlansAndPrice" + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.27e-06, + "source": "https://devblogs.microsoft.com/foundry/announcing-grok-3-and-grok-3-mini-on-azure-ai-foundry/", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": false, + "supports_tool_choice": true, + "supports_web_search": true + }, + "azure_ai/grok-3": { + "input_cost_per_token": 3.3e-06, + "litellm_provider": "azure_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.65e-05, + "source": "https://devblogs.microsoft.com/foundry/announcing-grok-3-and-grok-3-mini-on-azure-ai-foundry/", + "supports_function_calling": true, + "supports_response_schema": false, + "supports_tool_choice": true, + "supports_web_search": true + }, + "azure_ai/grok-3-mini": { + "input_cost_per_token": 2.75e-07, + "litellm_provider": "azure_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.38e-06, + "source": "https://devblogs.microsoft.com/foundry/announcing-grok-3-and-grok-3-mini-on-azure-ai-foundry/", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": false, + "supports_tool_choice": true, + "supports_web_search": true + }, + "azure_ai/jais-30b-chat": { + "input_cost_per_token": 0.0032, + "litellm_provider": "azure_ai", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.00971, + "source": "https://azure.microsoft.com/en-us/products/ai-services/ai-foundry/models/jais-30b-chat" + }, + "azure_ai/jamba-instruct": { + "input_cost_per_token": 5e-07, + "litellm_provider": "azure_ai", + "max_input_tokens": 70000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 7e-07, + "supports_tool_choice": true + }, + "azure_ai/ministral-3b": { + "input_cost_per_token": 4e-08, + "litellm_provider": "azure_ai", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 4e-08, + "source": "https://azuremarketplace.microsoft.com/en/marketplace/apps/000-000.ministral-3b-2410-offer?tab=Overview", + "supports_function_calling": true, + "supports_tool_choice": true + }, + "azure_ai/mistral-large": { + "input_cost_per_token": 4e-06, + "litellm_provider": "azure_ai", + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 1.2e-05, + "supports_function_calling": true, + "supports_tool_choice": true + }, + "azure_ai/mistral-large-2407": { + "input_cost_per_token": 2e-06, + "litellm_provider": "azure_ai", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 6e-06, + "source": "https://azuremarketplace.microsoft.com/en/marketplace/apps/000-000.mistral-ai-large-2407-offer?tab=Overview", + "supports_function_calling": true, + "supports_tool_choice": true + }, + "azure_ai/mistral-large-latest": { + "input_cost_per_token": 2e-06, + "litellm_provider": "azure_ai", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 6e-06, + "source": "https://azuremarketplace.microsoft.com/en/marketplace/apps/000-000.mistral-ai-large-2407-offer?tab=Overview", + "supports_function_calling": true, + "supports_tool_choice": true + }, + "azure_ai/mistral-medium-2505": { + "input_cost_per_token": 4e-07, + "litellm_provider": "azure_ai", + "max_input_tokens": 131072, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 2e-06, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_tool_choice": true + }, + "azure_ai/mistral-nemo": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "azure_ai", + "max_input_tokens": 131072, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.5e-07, + "source": "https://azuremarketplace.microsoft.com/en/marketplace/apps/000-000.mistral-nemo-12b-2407?tab=PlansAndPrice", + "supports_function_calling": true + }, + "azure_ai/mistral-small": { + "input_cost_per_token": 1e-06, + "litellm_provider": "azure_ai", + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 3e-06, + "supports_function_calling": true, + "supports_tool_choice": true + }, + "azure_ai/mistral-small-2503": { + "input_cost_per_token": 1e-06, + "litellm_provider": "azure_ai", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 3e-06, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true }, "babbage-002": { - "max_tokens": 16384, + "input_cost_per_token": 4e-07, + "litellm_provider": "text-completion-openai", "max_input_tokens": 16384, "max_output_tokens": 4096, - "input_cost_per_token": 4e-07, - "output_cost_per_token": 4e-07, - "litellm_provider": "text-completion-openai", - "mode": "completion" - }, - "davinci-002": { "max_tokens": 16384, - "max_input_tokens": 16384, - "max_output_tokens": 4096, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 2e-06, - "litellm_provider": "text-completion-openai", - "mode": "completion" - }, - "gpt-3.5-turbo-instruct": { - "max_tokens": 4096, - "max_input_tokens": 8192, - "max_output_tokens": 4096, - "input_cost_per_token": 1.5e-06, - "output_cost_per_token": 2e-06, - "litellm_provider": "text-completion-openai", - "mode": "completion" - }, - "gpt-3.5-turbo-instruct-0914": { - "max_tokens": 4097, - "max_input_tokens": 8192, - "max_output_tokens": 4097, - "input_cost_per_token": 1.5e-06, - "output_cost_per_token": 2e-06, - "litellm_provider": "text-completion-openai", - "mode": "completion" - }, - "mistral/mistral-tiny": { - "max_tokens": 8191, - "max_input_tokens": 32000, - "max_output_tokens": 8191, - "input_cost_per_token": 2.5e-07, - "output_cost_per_token": 2.5e-07, - "litellm_provider": "mistral", - "mode": "chat", - "supports_assistant_prefill": true, - "supports_tool_choice": true, - "supports_response_schema": true - }, - "mistral/mistral-small": { - "max_tokens": 8191, - "max_input_tokens": 32000, - "max_output_tokens": 8191, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 3e-07, - "litellm_provider": "mistral", - "supports_function_calling": true, - "mode": "chat", - "supports_assistant_prefill": true, - "supports_tool_choice": true, - "supports_response_schema": true - }, - "mistral/mistral-small-latest": { - "max_tokens": 8191, - "max_input_tokens": 32000, - "max_output_tokens": 8191, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 3e-07, - "litellm_provider": "mistral", - "supports_function_calling": true, - "mode": "chat", - "supports_assistant_prefill": true, - "supports_tool_choice": true, - "supports_response_schema": true - }, - "mistral/mistral-medium": { - "max_tokens": 8191, - "max_input_tokens": 32000, - "max_output_tokens": 8191, - "input_cost_per_token": 2.7e-06, - "output_cost_per_token": 8.1e-06, - "litellm_provider": "mistral", - "mode": "chat", - "supports_assistant_prefill": true, - "supports_tool_choice": true, - "supports_response_schema": true - }, - "mistral/mistral-medium-latest": { - "max_tokens": 8191, - "max_input_tokens": 131072, - "max_output_tokens": 8191, - "input_cost_per_token": 4e-07, - "output_cost_per_token": 2e-06, - "litellm_provider": "mistral", - "mode": "chat", - "supports_function_calling": true, - "supports_assistant_prefill": true, - "supports_tool_choice": true, - "supports_response_schema": true - }, - "mistral/mistral-medium-2505": { - "max_tokens": 8191, - "max_input_tokens": 131072, - "max_output_tokens": 8191, - "input_cost_per_token": 4e-07, - "output_cost_per_token": 2e-06, - "litellm_provider": "mistral", - "mode": "chat", - "supports_function_calling": true, - "supports_assistant_prefill": true, - "supports_tool_choice": true, - "supports_response_schema": true - }, - "mistral/mistral-medium-2312": { - "max_tokens": 8191, - "max_input_tokens": 32000, - "max_output_tokens": 8191, - "input_cost_per_token": 2.7e-06, - "output_cost_per_token": 8.1e-06, - "litellm_provider": "mistral", - "mode": "chat", - "supports_assistant_prefill": true, - "supports_tool_choice": true, - "supports_response_schema": true - }, - "mistral/mistral-large-latest": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 6e-06, - "litellm_provider": "mistral", - "mode": "chat", - "supports_function_calling": true, - "supports_assistant_prefill": true, - "supports_tool_choice": true, - "supports_response_schema": true - }, - "mistral/mistral-large-2411": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 6e-06, - "litellm_provider": "mistral", - "mode": "chat", - "supports_function_calling": true, - "supports_assistant_prefill": true, - "supports_tool_choice": true, - "supports_response_schema": true - }, - "mistral/mistral-large-2402": { - "max_tokens": 8191, - "max_input_tokens": 32000, - "max_output_tokens": 8191, - "input_cost_per_token": 4e-06, - "output_cost_per_token": 1.2e-05, - "litellm_provider": "mistral", - "mode": "chat", - "supports_function_calling": true, - "supports_assistant_prefill": true, - "supports_tool_choice": true, - "supports_response_schema": true - }, - "mistral/mistral-large-2407": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 9e-06, - "litellm_provider": "mistral", - "mode": "chat", - "supports_function_calling": true, - "supports_assistant_prefill": true, - "supports_tool_choice": true, - "supports_response_schema": true - }, - "mistral/pixtral-large-latest": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 6e-06, - "litellm_provider": "mistral", - "mode": "chat", - "supports_function_calling": true, - "supports_assistant_prefill": true, - "supports_vision": true, - "supports_tool_choice": true, - "supports_response_schema": true - }, - "mistral/pixtral-large-2411": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 6e-06, - "litellm_provider": "mistral", - "mode": "chat", - "supports_function_calling": true, - "supports_assistant_prefill": true, - "supports_vision": true, - "supports_tool_choice": true, - "supports_response_schema": true - }, - "mistral/pixtral-12b-2409": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 1.5e-07, - "litellm_provider": "mistral", - "mode": "chat", - "supports_function_calling": true, - "supports_assistant_prefill": true, - "supports_vision": true, - "supports_tool_choice": true, - "supports_response_schema": true - }, - "mistral/open-mistral-7b": { - "max_tokens": 8191, - "max_input_tokens": 32000, - "max_output_tokens": 8191, - "input_cost_per_token": 2.5e-07, - "output_cost_per_token": 2.5e-07, - "litellm_provider": "mistral", - "mode": "chat", - "supports_assistant_prefill": true, - "supports_tool_choice": true, - "supports_response_schema": true - }, - "mistral/open-mixtral-8x7b": { - "max_tokens": 8191, - "max_input_tokens": 32000, - "max_output_tokens": 8191, - "input_cost_per_token": 7e-07, - "output_cost_per_token": 7e-07, - "litellm_provider": "mistral", - "mode": "chat", - "supports_function_calling": true, - "supports_assistant_prefill": true, - "supports_tool_choice": true, - "supports_response_schema": true - }, - "mistral/open-mixtral-8x22b": { - "max_tokens": 8191, - "max_input_tokens": 65336, - "max_output_tokens": 8191, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 6e-06, - "litellm_provider": "mistral", - "mode": "chat", - "supports_function_calling": true, - "supports_assistant_prefill": true, - "supports_tool_choice": true, - "supports_response_schema": true - }, - "mistral/codestral-latest": { - "max_tokens": 8191, - "max_input_tokens": 32000, - "max_output_tokens": 8191, - "input_cost_per_token": 1e-06, - "output_cost_per_token": 3e-06, - "litellm_provider": "mistral", - "mode": "chat", - "supports_assistant_prefill": true, - "supports_tool_choice": true, - "supports_response_schema": true - }, - "mistral/codestral-2405": { - "max_tokens": 8191, - "max_input_tokens": 32000, - "max_output_tokens": 8191, - "input_cost_per_token": 1e-06, - "output_cost_per_token": 3e-06, - "litellm_provider": "mistral", - "mode": "chat", - "supports_assistant_prefill": true, - "supports_tool_choice": true, - "supports_response_schema": true - }, - "mistral/open-mistral-nemo": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "input_cost_per_token": 3e-07, - "output_cost_per_token": 3e-07, - "litellm_provider": "mistral", - "mode": "chat", - "source": "https://mistral.ai/technology/", - "supports_assistant_prefill": true, - "supports_tool_choice": true, - "supports_response_schema": true - }, - "mistral/open-mistral-nemo-2407": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "input_cost_per_token": 3e-07, - "output_cost_per_token": 3e-07, - "litellm_provider": "mistral", - "mode": "chat", - "source": "https://mistral.ai/technology/", - "supports_assistant_prefill": true, - "supports_tool_choice": true, - "supports_response_schema": true - }, - "mistral/open-codestral-mamba": { - "max_tokens": 256000, - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "input_cost_per_token": 2.5e-07, - "output_cost_per_token": 2.5e-07, - "litellm_provider": "mistral", - "mode": "chat", - "source": "https://mistral.ai/technology/", - "supports_assistant_prefill": true, - "supports_tool_choice": true - }, - "mistral/codestral-mamba-latest": { - "max_tokens": 256000, - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "input_cost_per_token": 2.5e-07, - "output_cost_per_token": 2.5e-07, - "litellm_provider": "mistral", - "mode": "chat", - "source": "https://mistral.ai/technology/", - "supports_assistant_prefill": true, - "supports_tool_choice": true - }, - "mistral/devstral-small-2505": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 3e-07, - "litellm_provider": "mistral", - "mode": "chat", - "source": "https://mistral.ai/news/devstral", - "supports_function_calling": true, - "supports_assistant_prefill": true, - "supports_tool_choice": true, - "supports_response_schema": true - }, - "mistral/devstral-small-2507": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 3e-07, - "litellm_provider": "mistral", - "mode": "chat", - "source": "https://mistral.ai/news/devstral", - "supports_function_calling": true, - "supports_assistant_prefill": true, - "supports_tool_choice": true, - "supports_response_schema": true - }, - "mistral/devstral-medium-2507": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "input_cost_per_token": 4e-07, - "output_cost_per_token": 2e-06, - "litellm_provider": "mistral", - "mode": "chat", - "source": "https://mistral.ai/news/devstral", - "supports_function_calling": true, - "supports_assistant_prefill": true, - "supports_tool_choice": true, - "supports_response_schema": true - }, - "mistral/magistral-medium-latest": { - "max_tokens": 40000, - "max_input_tokens": 40000, - "max_output_tokens": 40000, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 5e-06, - "litellm_provider": "mistral", - "mode": "chat", - "source": "https://mistral.ai/news/magistral", - "supports_function_calling": true, - "supports_assistant_prefill": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true - }, - "mistral/magistral-medium-2506": { - "max_tokens": 40000, - "max_input_tokens": 40000, - "max_output_tokens": 40000, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 5e-06, - "litellm_provider": "mistral", - "mode": "chat", - "source": "https://mistral.ai/news/magistral", - "supports_function_calling": true, - "supports_assistant_prefill": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true - }, - "mistral/magistral-small-latest": { - "max_tokens": 40000, - "max_input_tokens": 40000, - "max_output_tokens": 40000, - "input_cost_per_token": 5e-07, - "output_cost_per_token": 1.5e-06, - "litellm_provider": "mistral", - "mode": "chat", - "source": "https://mistral.ai/pricing#api-pricing", - "supports_function_calling": true, - "supports_assistant_prefill": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true - }, - "mistral/magistral-small-2506": { - "max_tokens": 40000, - "max_input_tokens": 40000, - "max_output_tokens": 40000, - "input_cost_per_token": 5e-07, - "output_cost_per_token": 1.5e-06, - "litellm_provider": "mistral", - "mode": "chat", - "source": "https://mistral.ai/pricing#api-pricing", - "supports_function_calling": true, - "supports_assistant_prefill": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": true - }, - "mistral/mistral-embed": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "input_cost_per_token": 1e-07, - "litellm_provider": "mistral", - "mode": "embedding" - }, - "deepseek/deepseek-reasoner": { - "max_tokens": 8192, - "max_input_tokens": 65536, - "max_output_tokens": 8192, - "input_cost_per_token": 5.5e-07, - "input_cost_per_token_cache_hit": 1.4e-07, - "output_cost_per_token": 2.19e-06, - "litellm_provider": "deepseek", - "mode": "chat", - "supports_function_calling": true, - "supports_assistant_prefill": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_prompt_caching": true - }, - "deepseek/deepseek-chat": { - "max_tokens": 8192, - "max_input_tokens": 65536, - "max_output_tokens": 8192, - "input_cost_per_token": 2.7e-07, - "input_cost_per_token_cache_hit": 7e-08, - "cache_read_input_token_cost": 7e-08, - "cache_creation_input_token_cost": 0.0, - "output_cost_per_token": 1.1e-06, - "litellm_provider": "deepseek", - "mode": "chat", - "supports_function_calling": true, - "supports_assistant_prefill": true, - "supports_tool_choice": true, - "supports_prompt_caching": true - }, - "deepseek/deepseek-r1": { - "max_tokens": 8192, - "max_input_tokens": 65536, - "max_output_tokens": 8192, - "input_cost_per_token": 5.5e-07, - "input_cost_per_token_cache_hit": 1.4e-07, - "output_cost_per_token": 2.19e-06, - "litellm_provider": "deepseek", - "mode": "chat", - "supports_function_calling": true, - "supports_assistant_prefill": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_prompt_caching": true - }, - "deepseek/deepseek-v3": { - "max_tokens": 8192, - "max_input_tokens": 65536, - "max_output_tokens": 8192, - "input_cost_per_token": 2.7e-07, - "input_cost_per_token_cache_hit": 7e-08, - "cache_read_input_token_cost": 7e-08, - "cache_creation_input_token_cost": 0.0, - "output_cost_per_token": 1.1e-06, - "litellm_provider": "deepseek", - "mode": "chat", - "supports_function_calling": true, - "supports_assistant_prefill": true, - "supports_tool_choice": true, - "supports_prompt_caching": true - }, - "codestral/codestral-latest": { - "max_tokens": 8191, - "max_input_tokens": 32000, - "max_output_tokens": 8191, - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "codestral", - "mode": "chat", - "source": "https://docs.mistral.ai/capabilities/code_generation/", - "supports_assistant_prefill": true, - "supports_tool_choice": true - }, - "codestral/codestral-2405": { - "max_tokens": 8191, - "max_input_tokens": 32000, - "max_output_tokens": 8191, - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "codestral", - "mode": "chat", - "source": "https://docs.mistral.ai/capabilities/code_generation/", - "supports_assistant_prefill": true, - "supports_tool_choice": true - }, - "text-completion-codestral/codestral-latest": { - "max_tokens": 8191, - "max_input_tokens": 32000, - "max_output_tokens": 8191, - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "text-completion-codestral", "mode": "completion", - "source": "https://docs.mistral.ai/capabilities/code_generation/" + "output_cost_per_token": 4e-07 }, - "text-completion-codestral/codestral-2405": { - "max_tokens": 8191, - "max_input_tokens": 32000, - "max_output_tokens": 8191, - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "text-completion-codestral", - "mode": "completion", - "source": "https://docs.mistral.ai/capabilities/code_generation/" - }, - "xai/grok-beta": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 5e-06, - "output_cost_per_token": 1.5e-05, - "litellm_provider": "xai", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "supports_tool_choice": true, - "supports_web_search": true - }, - "xai/grok-2-vision-1212": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "input_cost_per_token": 2e-06, - "input_cost_per_image": 2e-06, - "output_cost_per_token": 1e-05, - "litellm_provider": "xai", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "supports_tool_choice": true, - "supports_web_search": true - }, - "xai/grok-2-vision-latest": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "input_cost_per_token": 2e-06, - "input_cost_per_image": 2e-06, - "output_cost_per_token": 1e-05, - "litellm_provider": "xai", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "supports_tool_choice": true, - "supports_web_search": true - }, - "xai/grok-2-vision": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "input_cost_per_token": 2e-06, - "input_cost_per_image": 2e-06, - "output_cost_per_token": 1e-05, - "litellm_provider": "xai", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "supports_tool_choice": true, - "supports_web_search": true - }, - "xai/grok-3": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "litellm_provider": "xai", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": false, - "source": "https://x.ai/api#pricing", - "supports_web_search": true - }, - "xai/grok-3-latest": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "litellm_provider": "xai", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": false, - "source": "https://x.ai/api#pricing", - "supports_web_search": true - }, - "xai/grok-3-beta": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "litellm_provider": "xai", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": false, - "source": "https://x.ai/api#pricing", - "supports_web_search": true - }, - "xai/grok-3-fast-beta": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 5e-06, - "output_cost_per_token": 2.5e-05, - "litellm_provider": "xai", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": false, - "source": "https://x.ai/api#pricing", - "supports_web_search": true - }, - "xai/grok-3-fast-latest": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 5e-06, - "output_cost_per_token": 2.5e-05, - "litellm_provider": "xai", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": false, - "source": "https://x.ai/api#pricing", - "supports_web_search": true - }, - "xai/grok-3-mini": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 3e-07, - "output_cost_per_token": 5e-07, - "litellm_provider": "xai", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": false, - "source": "https://x.ai/api#pricing", - "supports_web_search": true - }, - "xai/grok-3-mini-latest": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 3e-07, - "output_cost_per_token": 5e-07, - "litellm_provider": "xai", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": false, - "source": "https://x.ai/api#pricing", - "supports_web_search": true - }, - "xai/grok-3-mini-fast": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 6e-07, - "output_cost_per_token": 4e-06, - "litellm_provider": "xai", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": false, - "source": "https://x.ai/api#pricing", - "supports_web_search": true - }, - "xai/grok-3-mini-fast-latest": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 6e-07, - "output_cost_per_token": 4e-06, - "litellm_provider": "xai", - "mode": "chat", - "supports_reasoning": true, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": false, - "source": "https://x.ai/api#pricing", - "supports_web_search": true - }, - "xai/grok-3-mini-beta": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 3e-07, - "output_cost_per_token": 5e-07, - "litellm_provider": "xai", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": false, - "source": "https://x.ai/api#pricing", - "supports_web_search": true - }, - "xai/grok-3-mini-fast-beta": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 6e-07, - "output_cost_per_token": 4e-06, - "litellm_provider": "xai", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_response_schema": false, - "source": "https://x.ai/api#pricing", - "supports_web_search": true - }, - "xai/grok-vision-beta": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 5e-06, - "input_cost_per_image": 5e-06, - "output_cost_per_token": 1.5e-05, - "litellm_provider": "xai", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "supports_tool_choice": true, - "supports_web_search": true - }, - "xai/grok-2-1212": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 1e-05, - "litellm_provider": "xai", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_web_search": true - }, - "xai/grok-2": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 1e-05, - "litellm_provider": "xai", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_web_search": true - }, - "xai/grok-2-latest": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 1e-05, - "litellm_provider": "xai", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_web_search": true - }, - "xai/grok-code-fast-1": { - "max_tokens": 256000, - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "input_cost_per_token": 0.2e-06, - "output_cost_per_token": 1.5e-06, - "cache_read_input_token_cost": 0.02e-06, - "litellm_provider": "xai", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "source": "https://docs.x.ai/docs/models" - }, - "xai/grok-code-fast": { - "max_tokens": 256000, - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "input_cost_per_token": 0.2e-06, - "output_cost_per_token": 1.5e-06, - "cache_read_input_token_cost": 0.02e-06, - "litellm_provider": "xai", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "source": "https://docs.x.ai/docs/models" - }, - "xai/grok-code-fast-1-0825": { - "max_tokens": 256000, - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "input_cost_per_token": 0.2e-06, - "output_cost_per_token": 1.5e-06, - "cache_read_input_token_cost": 0.02e-06, - "litellm_provider": "xai", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "source": "https://docs.x.ai/docs/models" - }, - "xai/grok-4": { - "max_tokens": 256000, - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "litellm_provider": "xai", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "source": "https://docs.x.ai/docs/models", - "supports_web_search": true - }, - "xai/grok-4-0709": { - "max_tokens": 256000, - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "litellm_provider": "xai", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "source": "https://docs.x.ai/docs/models", - "supports_web_search": true - }, - "xai/grok-4-latest": { - "max_tokens": 256000, - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "litellm_provider": "xai", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "source": "https://docs.x.ai/docs/models", - "supports_web_search": true - }, - "deepseek/deepseek-coder": { - "max_tokens": 4096, - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 1.4e-07, - "input_cost_per_token_cache_hit": 1.4e-08, - "output_cost_per_token": 2.8e-07, - "litellm_provider": "deepseek", - "mode": "chat", - "supports_function_calling": true, - "supports_assistant_prefill": true, - "supports_tool_choice": true, - "supports_prompt_caching": true - }, - "groq/deepseek-r1-distill-llama-70b": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "input_cost_per_token": 7.5e-07, - "output_cost_per_token": 9.9e-07, - "litellm_provider": "groq", - "mode": "chat", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_reasoning": true, - "supports_tool_choice": true - }, - "groq/llama-3.3-70b-versatile": { - "max_tokens": 32768, - "max_input_tokens": 128000, - "max_output_tokens": 32768, - "input_cost_per_token": 5.9e-07, - "output_cost_per_token": 7.9e-07, - "litellm_provider": "groq", - "mode": "chat", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "groq/llama-3.3-70b-specdec": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 5.9e-07, - "output_cost_per_token": 9.9e-07, - "litellm_provider": "groq", - "mode": "chat", - "supports_tool_choice": true, - "deprecation_date": "2025-04-14" - }, - "groq/llama-guard-3-8b": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 2e-07, - "output_cost_per_token": 2e-07, - "litellm_provider": "groq", - "mode": "chat" - }, - "groq/llama2-70b-4096": { - "max_tokens": 4096, + "bedrock/*/1-month-commitment/cohere.command-light-text-v14": { + "input_cost_per_second": 0.001902, + "litellm_provider": "bedrock", "max_input_tokens": 4096, "max_output_tokens": 4096, - "input_cost_per_token": 7e-07, - "output_cost_per_token": 8e-07, - "litellm_provider": "groq", + "max_tokens": 4096, "mode": "chat", - "supports_function_calling": true, - "supports_response_schema": true, + "output_cost_per_second": 0.001902, "supports_tool_choice": true }, - "groq/llama-3.2-1b-preview": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 4e-08, - "output_cost_per_token": 4e-08, - "litellm_provider": "groq", + "bedrock/*/1-month-commitment/cohere.command-text-v14": { + "input_cost_per_second": 0.011, + "litellm_provider": "bedrock", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "deprecation_date": "2025-04-14" - }, - "groq/llama-3.2-3b-preview": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 6e-08, - "output_cost_per_token": 6e-08, - "litellm_provider": "groq", - "mode": "chat", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "deprecation_date": "2025-04-14" - }, - "groq/llama-3.2-11b-text-preview": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 1.8e-07, - "output_cost_per_token": 1.8e-07, - "litellm_provider": "groq", - "mode": "chat", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "deprecation_date": "2024-10-28" - }, - "groq/llama-3.2-11b-vision-preview": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 1.8e-07, - "output_cost_per_token": 1.8e-07, - "litellm_provider": "groq", - "mode": "chat", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_tool_choice": true, - "deprecation_date": "2025-04-14" - }, - "groq/llama-3.2-90b-text-preview": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 9e-07, - "output_cost_per_token": 9e-07, - "litellm_provider": "groq", - "mode": "chat", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "deprecation_date": "2024-11-25" - }, - "groq/llama-3.2-90b-vision-preview": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 9e-07, - "output_cost_per_token": 9e-07, - "litellm_provider": "groq", - "mode": "chat", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_tool_choice": true, - "deprecation_date": "2025-04-14" - }, - "groq/llama-3.1-8b-instant": { - "max_tokens": 8192, - "max_input_tokens": 128000, - "max_output_tokens": 8192, - "input_cost_per_token": 5e-08, - "output_cost_per_token": 8e-08, - "litellm_provider": "groq", - "mode": "chat", - "supports_function_calling": true, - "supports_response_schema": true, + "output_cost_per_second": 0.011, "supports_tool_choice": true }, - "groq/llama-3.1-70b-versatile": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 5.9e-07, - "output_cost_per_token": 7.9e-07, - "litellm_provider": "groq", + "bedrock/*/6-month-commitment/cohere.command-light-text-v14": { + "input_cost_per_second": 0.0011416, + "litellm_provider": "bedrock", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "deprecation_date": "2025-01-24" - }, - "groq/llama-3.1-405b-reasoning": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 5.9e-07, - "output_cost_per_token": 7.9e-07, - "litellm_provider": "groq", - "mode": "chat", - "supports_function_calling": true, - "supports_response_schema": true, + "output_cost_per_second": 0.0011416, "supports_tool_choice": true }, - "groq/meta-llama/llama-4-scout-17b-16e-instruct": { - "max_tokens": 8192, - "max_input_tokens": 131072, - "max_output_tokens": 8192, - "input_cost_per_token": 1.1e-07, - "output_cost_per_token": 3.4e-07, - "litellm_provider": "groq", + "bedrock/*/6-month-commitment/cohere.command-text-v14": { + "input_cost_per_second": 0.0066027, + "litellm_provider": "bedrock", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, "mode": "chat", - "supports_function_calling": true, - "supports_response_schema": true, + "output_cost_per_second": 0.0066027, "supports_tool_choice": true }, - "groq/meta-llama/llama-4-maverick-17b-128e-instruct": { - "max_tokens": 8192, - "max_input_tokens": 131072, + "bedrock/ap-northeast-1/1-month-commitment/anthropic.claude-instant-v1": { + "input_cost_per_second": 0.01475, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_second": 0.01475, + "supports_tool_choice": true + }, + "bedrock/ap-northeast-1/1-month-commitment/anthropic.claude-v1": { + "input_cost_per_second": 0.0455, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_second": 0.0455 + }, + "bedrock/ap-northeast-1/1-month-commitment/anthropic.claude-v2:1": { + "input_cost_per_second": 0.0455, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_second": 0.0455, + "supports_tool_choice": true + }, + "bedrock/ap-northeast-1/6-month-commitment/anthropic.claude-instant-v1": { + "input_cost_per_second": 0.008194, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_second": 0.008194, + "supports_tool_choice": true + }, + "bedrock/ap-northeast-1/6-month-commitment/anthropic.claude-v1": { + "input_cost_per_second": 0.02527, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_second": 0.02527 + }, + "bedrock/ap-northeast-1/6-month-commitment/anthropic.claude-v2:1": { + "input_cost_per_second": 0.02527, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_second": 0.02527, + "supports_tool_choice": true + }, + "bedrock/ap-northeast-1/anthropic.claude-instant-v1": { + "input_cost_per_token": 2.23e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 7.55e-06, + "supports_tool_choice": true + }, + "bedrock/ap-northeast-1/anthropic.claude-v1": { + "input_cost_per_token": 8e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 2.4e-05, + "supports_tool_choice": true + }, + "bedrock/ap-northeast-1/anthropic.claude-v2:1": { + "input_cost_per_token": 8e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 2.4e-05, + "supports_tool_choice": true + }, + "bedrock/ap-south-1/meta.llama3-70b-instruct-v1:0": { + "input_cost_per_token": 3.18e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 8192, "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 4.2e-06 + }, + "bedrock/ap-south-1/meta.llama3-8b-instruct-v1:0": { + "input_cost_per_token": 3.6e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 7.2e-07 + }, + "bedrock/ca-central-1/meta.llama3-70b-instruct-v1:0": { + "input_cost_per_token": 3.05e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 4.03e-06 + }, + "bedrock/ca-central-1/meta.llama3-8b-instruct-v1:0": { + "input_cost_per_token": 3.5e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 6.9e-07 + }, + "bedrock/eu-central-1/1-month-commitment/anthropic.claude-instant-v1": { + "input_cost_per_second": 0.01635, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_second": 0.01635, + "supports_tool_choice": true + }, + "bedrock/eu-central-1/1-month-commitment/anthropic.claude-v1": { + "input_cost_per_second": 0.0415, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_second": 0.0415 + }, + "bedrock/eu-central-1/1-month-commitment/anthropic.claude-v2:1": { + "input_cost_per_second": 0.0415, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_second": 0.0415, + "supports_tool_choice": true + }, + "bedrock/eu-central-1/6-month-commitment/anthropic.claude-instant-v1": { + "input_cost_per_second": 0.009083, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_second": 0.009083, + "supports_tool_choice": true + }, + "bedrock/eu-central-1/6-month-commitment/anthropic.claude-v1": { + "input_cost_per_second": 0.02305, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_second": 0.02305 + }, + "bedrock/eu-central-1/6-month-commitment/anthropic.claude-v2:1": { + "input_cost_per_second": 0.02305, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_second": 0.02305, + "supports_tool_choice": true + }, + "bedrock/eu-central-1/anthropic.claude-instant-v1": { + "input_cost_per_token": 2.48e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 8.38e-06, + "supports_tool_choice": true + }, + "bedrock/eu-central-1/anthropic.claude-v1": { + "input_cost_per_token": 8e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 2.4e-05 + }, + "bedrock/eu-central-1/anthropic.claude-v2:1": { + "input_cost_per_token": 8e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 2.4e-05, + "supports_tool_choice": true + }, + "bedrock/eu-west-1/meta.llama3-70b-instruct-v1:0": { + "input_cost_per_token": 2.86e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 3.78e-06 + }, + "bedrock/eu-west-1/meta.llama3-8b-instruct-v1:0": { + "input_cost_per_token": 3.2e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 6.5e-07 + }, + "bedrock/eu-west-2/meta.llama3-70b-instruct-v1:0": { + "input_cost_per_token": 3.45e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 4.55e-06 + }, + "bedrock/eu-west-2/meta.llama3-8b-instruct-v1:0": { + "input_cost_per_token": 3.9e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 7.8e-07 + }, + "bedrock/eu-west-3/mistral.mistral-7b-instruct-v0:2": { "input_cost_per_token": 2e-07, - "output_cost_per_token": 6e-07, - "litellm_provider": "groq", - "mode": "chat", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "groq/mistral-saba-24b": { - "max_tokens": 32000, + "litellm_provider": "bedrock", "max_input_tokens": 32000, - "max_output_tokens": 32000, - "input_cost_per_token": 7.9e-07, - "output_cost_per_token": 7.9e-07, - "litellm_provider": "groq", - "mode": "chat" - }, - "groq/mixtral-8x7b-32768": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "input_cost_per_token": 2.4e-07, - "output_cost_per_token": 2.4e-07, - "litellm_provider": "groq", + "max_output_tokens": 8191, + "max_tokens": 8191, "mode": "chat", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "deprecation_date": "2025-03-20" - }, - "groq/gemma-7b-it": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 7e-08, - "output_cost_per_token": 7e-08, - "litellm_provider": "groq", - "mode": "chat", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "deprecation_date": "2024-12-18" - }, - "groq/gemma2-9b-it": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 2e-07, - "output_cost_per_token": 2e-07, - "litellm_provider": "groq", - "mode": "chat", - "supports_function_calling": false, - "supports_response_schema": true, - "supports_tool_choice": false - }, - "groq/llama3-groq-70b-8192-tool-use-preview": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 8.9e-07, - "output_cost_per_token": 8.9e-07, - "litellm_provider": "groq", - "mode": "chat", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "deprecation_date": "2025-01-06" - }, - "groq/llama3-groq-8b-8192-tool-use-preview": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 1.9e-07, - "output_cost_per_token": 1.9e-07, - "litellm_provider": "groq", - "mode": "chat", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "deprecation_date": "2025-01-06" - }, - "groq/qwen/qwen3-32b": { - "max_tokens": 131000, - "max_input_tokens": 131000, - "max_output_tokens": 131000, - "input_cost_per_token": 2.9e-07, - "output_cost_per_token": 5.9e-07, - "litellm_provider": "groq", - "mode": "chat", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_reasoning": true, + "output_cost_per_token": 2.6e-07, "supports_tool_choice": true }, - "groq/moonshotai/kimi-k2-instruct": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 16384, - "input_cost_per_token": 1e-06, - "output_cost_per_token": 3e-06, - "litellm_provider": "groq", + "bedrock/eu-west-3/mistral.mistral-large-2402-v1:0": { + "input_cost_per_token": 1.04e-05, + "litellm_provider": "bedrock", + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, "mode": "chat", - "supports_function_calling": true, - "supports_response_schema": true, + "output_cost_per_token": 3.12e-05, + "supports_function_calling": true + }, + "bedrock/eu-west-3/mistral.mixtral-8x7b-instruct-v0:1": { + "input_cost_per_token": 5.9e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 9.1e-07, "supports_tool_choice": true }, - "groq/playai-tts": { - "max_tokens": 10000, - "max_input_tokens": 10000, - "max_output_tokens": 10000, - "input_cost_per_character": 5e-05, - "litellm_provider": "groq", - "mode": "audio_speech" - }, - "groq/whisper-large-v3": { - "input_cost_per_second": 3.083e-05, - "output_cost_per_second": 0.0, - "litellm_provider": "groq", - "mode": "audio_transcription" - }, - "groq/whisper-large-v3-turbo": { - "input_cost_per_second": 1.111e-05, - "output_cost_per_second": 0.0, - "litellm_provider": "groq", - "mode": "audio_transcription" - }, - "groq/distil-whisper-large-v3-en": { - "input_cost_per_second": 5.56e-06, - "output_cost_per_second": 0.0, - "litellm_provider": "groq", - "mode": "audio_transcription" - }, - "groq/openai/gpt-oss-20b": { - "max_tokens": 32768, - "max_input_tokens": 131072, - "max_output_tokens": 32768, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 5e-07, - "litellm_provider": "groq", + "bedrock/invoke/anthropic.claude-3-5-sonnet-20240620-v1:0": { + "input_cost_per_token": 3e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "metadata": { + "notes": "Anthropic via Invoke route does not currently support pdf input." + }, "mode": "chat", + "output_cost_per_token": 1.5e-05, "supports_function_calling": true, - "supports_parallel_function_calling": true, "supports_response_schema": true, - "supports_reasoning": true, "supports_tool_choice": true, - "supports_web_search": true + "supports_vision": true }, - "groq/openai/gpt-oss-120b": { - "max_tokens": 32766, - "max_input_tokens": 131072, - "max_output_tokens": 32766, + "bedrock/sa-east-1/meta.llama3-70b-instruct-v1:0": { + "input_cost_per_token": 4.45e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 5.88e-06 + }, + "bedrock/sa-east-1/meta.llama3-8b-instruct-v1:0": { + "input_cost_per_token": 5e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.01e-06 + }, + "bedrock/us-east-1/1-month-commitment/anthropic.claude-instant-v1": { + "input_cost_per_second": 0.011, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_second": 0.011, + "supports_tool_choice": true + }, + "bedrock/us-east-1/1-month-commitment/anthropic.claude-v1": { + "input_cost_per_second": 0.0175, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_second": 0.0175 + }, + "bedrock/us-east-1/1-month-commitment/anthropic.claude-v2:1": { + "input_cost_per_second": 0.0175, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_second": 0.0175, + "supports_tool_choice": true + }, + "bedrock/us-east-1/6-month-commitment/anthropic.claude-instant-v1": { + "input_cost_per_second": 0.00611, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_second": 0.00611, + "supports_tool_choice": true + }, + "bedrock/us-east-1/6-month-commitment/anthropic.claude-v1": { + "input_cost_per_second": 0.00972, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_second": 0.00972 + }, + "bedrock/us-east-1/6-month-commitment/anthropic.claude-v2:1": { + "input_cost_per_second": 0.00972, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_second": 0.00972, + "supports_tool_choice": true + }, + "bedrock/us-east-1/anthropic.claude-instant-v1": { + "input_cost_per_token": 8e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 2.4e-06, + "supports_tool_choice": true + }, + "bedrock/us-east-1/anthropic.claude-v1": { + "input_cost_per_token": 8e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 2.4e-05, + "supports_tool_choice": true + }, + "bedrock/us-east-1/anthropic.claude-v2:1": { + "input_cost_per_token": 8e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 2.4e-05, + "supports_tool_choice": true + }, + "bedrock/us-east-1/meta.llama3-70b-instruct-v1:0": { + "input_cost_per_token": 2.65e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 3.5e-06 + }, + "bedrock/us-east-1/meta.llama3-8b-instruct-v1:0": { + "input_cost_per_token": 3e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 6e-07 + }, + "bedrock/us-east-1/mistral.mistral-7b-instruct-v0:2": { "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 7.5e-07, - "litellm_provider": "groq", + "litellm_provider": "bedrock", + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_reasoning": true, - "supports_tool_choice": true, - "supports_web_search": true + "output_cost_per_token": 2e-07, + "supports_tool_choice": true }, - "cerebras/llama3.1-8b": { - "max_tokens": 128000, + "bedrock/us-east-1/mistral.mistral-large-2402-v1:0": { + "input_cost_per_token": 8e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 2.4e-05, + "supports_function_calling": true + }, + "bedrock/us-east-1/mistral.mixtral-8x7b-instruct-v0:1": { + "input_cost_per_token": 4.5e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 7e-07, + "supports_tool_choice": true + }, + "bedrock/us-gov-east-1/amazon.nova-pro-v1:0": { + "input_cost_per_token": 9.6e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 300000, + "max_output_tokens": 10000, + "max_tokens": 10000, + "mode": "chat", + "output_cost_per_token": 3.84e-06, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_vision": true + }, + "bedrock/us-gov-east-1/amazon.titan-embed-text-v1": { + "input_cost_per_token": 1e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 8192, + "max_tokens": 8192, + "mode": "embedding", + "output_cost_per_token": 0.0, + "output_vector_size": 1536 + }, + "bedrock/us-gov-east-1/amazon.titan-embed-text-v2:0": { + "input_cost_per_token": 2e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 8192, + "max_tokens": 8192, + "mode": "embedding", + "output_cost_per_token": 0.0, + "output_vector_size": 1024 + }, + "bedrock/us-gov-east-1/amazon.titan-text-express-v1": { + "input_cost_per_token": 1.3e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 42000, + "max_output_tokens": 8000, + "max_tokens": 8000, + "mode": "chat", + "output_cost_per_token": 1.7e-06 + }, + "bedrock/us-gov-east-1/amazon.titan-text-lite-v1": { + "input_cost_per_token": 3e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 42000, + "max_output_tokens": 4000, + "max_tokens": 4000, + "mode": "chat", + "output_cost_per_token": 4e-07 + }, + "bedrock/us-gov-east-1/amazon.titan-text-premier-v1:0": { + "input_cost_per_token": 5e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 42000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 1.5e-06 + }, + "bedrock/us-gov-east-1/anthropic.claude-3-5-sonnet-20240620-v1:0": { + "input_cost_per_token": 3.6e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.8e-05, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "bedrock/us-gov-east-1/anthropic.claude-3-haiku-20240307-v1:0": { + "input_cost_per_token": 3e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.5e-06, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "bedrock/us-gov-east-1/meta.llama3-70b-instruct-v1:0": { + "input_cost_per_token": 2.65e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 8000, + "max_output_tokens": 2048, + "max_tokens": 2048, + "mode": "chat", + "output_cost_per_token": 3.5e-06, + "supports_pdf_input": true + }, + "bedrock/us-gov-east-1/meta.llama3-8b-instruct-v1:0": { + "input_cost_per_token": 3e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 8000, + "max_output_tokens": 2048, + "max_tokens": 2048, + "mode": "chat", + "output_cost_per_token": 2.65e-06, + "supports_pdf_input": true + }, + "bedrock/us-gov-west-1/amazon.nova-pro-v1:0": { + "input_cost_per_token": 9.6e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 300000, + "max_output_tokens": 10000, + "max_tokens": 10000, + "mode": "chat", + "output_cost_per_token": 3.84e-06, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_vision": true + }, + "bedrock/us-gov-west-1/amazon.titan-embed-text-v1": { + "input_cost_per_token": 1e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 8192, + "max_tokens": 8192, + "mode": "embedding", + "output_cost_per_token": 0.0, + "output_vector_size": 1536 + }, + "bedrock/us-gov-west-1/amazon.titan-embed-text-v2:0": { + "input_cost_per_token": 2e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 8192, + "max_tokens": 8192, + "mode": "embedding", + "output_cost_per_token": 0.0, + "output_vector_size": 1024 + }, + "bedrock/us-gov-west-1/amazon.titan-text-express-v1": { + "input_cost_per_token": 1.3e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 42000, + "max_output_tokens": 8000, + "max_tokens": 8000, + "mode": "chat", + "output_cost_per_token": 1.7e-06 + }, + "bedrock/us-gov-west-1/amazon.titan-text-lite-v1": { + "input_cost_per_token": 3e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 42000, + "max_output_tokens": 4000, + "max_tokens": 4000, + "mode": "chat", + "output_cost_per_token": 4e-07 + }, + "bedrock/us-gov-west-1/amazon.titan-text-premier-v1:0": { + "input_cost_per_token": 5e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 42000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 1.5e-06 + }, + "bedrock/us-gov-west-1/anthropic.claude-3-5-sonnet-20240620-v1:0": { + "input_cost_per_token": 3.6e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.8e-05, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "bedrock/us-gov-west-1/anthropic.claude-3-haiku-20240307-v1:0": { + "input_cost_per_token": 3e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.5e-06, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "bedrock/us-gov-west-1/meta.llama3-70b-instruct-v1:0": { + "input_cost_per_token": 2.65e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 8000, + "max_output_tokens": 2048, + "max_tokens": 2048, + "mode": "chat", + "output_cost_per_token": 3.5e-06, + "supports_pdf_input": true + }, + "bedrock/us-gov-west-1/meta.llama3-8b-instruct-v1:0": { + "input_cost_per_token": 3e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 8000, + "max_output_tokens": 2048, + "max_tokens": 2048, + "mode": "chat", + "output_cost_per_token": 2.65e-06, + "supports_pdf_input": true + }, + "bedrock/us-west-1/meta.llama3-70b-instruct-v1:0": { + "input_cost_per_token": 2.65e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 3.5e-06 + }, + "bedrock/us-west-1/meta.llama3-8b-instruct-v1:0": { + "input_cost_per_token": 3e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 6e-07 + }, + "bedrock/us-west-2/1-month-commitment/anthropic.claude-instant-v1": { + "input_cost_per_second": 0.011, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_second": 0.011, + "supports_tool_choice": true + }, + "bedrock/us-west-2/1-month-commitment/anthropic.claude-v1": { + "input_cost_per_second": 0.0175, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_second": 0.0175 + }, + "bedrock/us-west-2/1-month-commitment/anthropic.claude-v2:1": { + "input_cost_per_second": 0.0175, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_second": 0.0175, + "supports_tool_choice": true + }, + "bedrock/us-west-2/6-month-commitment/anthropic.claude-instant-v1": { + "input_cost_per_second": 0.00611, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_second": 0.00611, + "supports_tool_choice": true + }, + "bedrock/us-west-2/6-month-commitment/anthropic.claude-v1": { + "input_cost_per_second": 0.00972, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_second": 0.00972 + }, + "bedrock/us-west-2/6-month-commitment/anthropic.claude-v2:1": { + "input_cost_per_second": 0.00972, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_second": 0.00972, + "supports_tool_choice": true + }, + "bedrock/us-west-2/anthropic.claude-instant-v1": { + "input_cost_per_token": 8e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 2.4e-06, + "supports_tool_choice": true + }, + "bedrock/us-west-2/anthropic.claude-v1": { + "input_cost_per_token": 8e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 2.4e-05, + "supports_tool_choice": true + }, + "bedrock/us-west-2/anthropic.claude-v2:1": { + "input_cost_per_token": 8e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 100000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 2.4e-05, + "supports_tool_choice": true + }, + "bedrock/us-west-2/mistral.mistral-7b-instruct-v0:2": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 2e-07, + "supports_tool_choice": true + }, + "bedrock/us-west-2/mistral.mistral-large-2402-v1:0": { + "input_cost_per_token": 8e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 2.4e-05, + "supports_function_calling": true + }, + "bedrock/us-west-2/mistral.mixtral-8x7b-instruct-v0:1": { + "input_cost_per_token": 4.5e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 7e-07, + "supports_tool_choice": true + }, + "bedrock/us.anthropic.claude-3-5-haiku-20241022-v1:0": { + "cache_creation_input_token_cost": 1e-06, + "cache_read_input_token_cost": 8e-08, + "input_cost_per_token": 8e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 4e-06, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "cerebras/llama-3.3-70b": { + "input_cost_per_token": 8.5e-07, + "litellm_provider": "cerebras", "max_input_tokens": 128000, "max_output_tokens": 128000, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 1e-07, - "litellm_provider": "cerebras", + "max_tokens": 128000, "mode": "chat", + "output_cost_per_token": 1.2e-06, "supports_function_calling": true, "supports_tool_choice": true }, "cerebras/llama3.1-70b": { - "max_tokens": 128000, + "input_cost_per_token": 6e-07, + "litellm_provider": "cerebras", "max_input_tokens": 128000, "max_output_tokens": 128000, - "input_cost_per_token": 6e-07, - "output_cost_per_token": 6e-07, - "litellm_provider": "cerebras", + "max_tokens": 128000, "mode": "chat", + "output_cost_per_token": 6e-07, "supports_function_calling": true, "supports_tool_choice": true }, - "cerebras/llama-3.3-70b": { - "max_tokens": 128000, + "cerebras/llama3.1-8b": { + "input_cost_per_token": 1e-07, + "litellm_provider": "cerebras", "max_input_tokens": 128000, "max_output_tokens": 128000, - "input_cost_per_token": 8.5e-07, - "output_cost_per_token": 1.2e-06, - "litellm_provider": "cerebras", + "max_tokens": 128000, "mode": "chat", + "output_cost_per_token": 1e-07, "supports_function_calling": true, "supports_tool_choice": true }, + "cerebras/openai/gpt-oss-120b": { + "input_cost_per_token": 2.5e-07, + "litellm_provider": "cerebras", + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 6.9e-07, + "source": "https://www.cerebras.ai/blog/openai-gpt-oss-120b-runs-fastest-on-cerebras", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, "cerebras/qwen-3-32b": { - "max_tokens": 128000, + "input_cost_per_token": 4e-07, + "litellm_provider": "cerebras", "max_input_tokens": 128000, "max_output_tokens": 128000, - "input_cost_per_token": 4e-07, + "max_tokens": 128000, + "mode": "chat", "output_cost_per_token": 8e-07, - "litellm_provider": "cerebras", - "mode": "chat", + "source": "https://inference-docs.cerebras.ai/support/pricing", "supports_function_calling": true, - "supports_tool_choice": true, - "source": "https://inference-docs.cerebras.ai/support/pricing" - }, - - "cerebras/openai/gpt-oss-120b": { - "max_tokens": 32768, - "max_input_tokens": 131072, - "max_output_tokens": 32768, - "input_cost_per_token": 2.5e-07, - "output_cost_per_token": 6.9e-07, - "litellm_provider": "cerebras", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_reasoning": true, - "supports_tool_choice": true, - "source": "https://www.cerebras.ai/blog/openai-gpt-oss-120b-runs-fastest-on-cerebras" - }, - "friendliai/meta-llama-3.1-8b-instruct": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 1e-07, - "litellm_provider": "friendliai", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_response_schema": true, "supports_tool_choice": true }, - "friendliai/meta-llama-3.1-70b-instruct": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 6e-07, - "output_cost_per_token": 6e-07, - "litellm_provider": "friendliai", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "claude-3-haiku-20240307": { - "max_tokens": 4096, - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "input_cost_per_token": 2.5e-07, - "output_cost_per_token": 1.25e-06, - "cache_creation_input_token_cost": 3e-07, - "cache_read_input_token_cost": 3e-08, - "litellm_provider": "anthropic", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 264, - "supports_assistant_prefill": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "deprecation_date": "2025-03-01", - "supports_tool_choice": true - }, - "claude-3-5-haiku-20241022": { - "max_tokens": 8192, - "max_input_tokens": 200000, - "max_output_tokens": 8192, - "input_cost_per_token": 8e-07, - "output_cost_per_token": 4e-06, - "cache_creation_input_token_cost": 1e-06, - "cache_creation_input_token_cost_above_1hr": 1.6e-06, - "cache_read_input_token_cost": 8e-08, - "search_context_cost_per_query": { - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01, - "search_context_size_high": 0.01 - }, - "litellm_provider": "anthropic", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 264, - "supports_assistant_prefill": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "deprecation_date": "2025-10-01", - "supports_tool_choice": true, - "supports_web_search": true - }, - "claude-3-5-haiku-latest": { - "max_tokens": 8192, - "max_input_tokens": 200000, - "max_output_tokens": 8192, - "input_cost_per_token": 1e-06, - "output_cost_per_token": 5e-06, - "cache_creation_input_token_cost": 1.25e-06, - "cache_read_input_token_cost": 1e-07, - "search_context_cost_per_query": { - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01, - "search_context_size_high": 0.01 - }, - "litellm_provider": "anthropic", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 264, - "supports_assistant_prefill": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "deprecation_date": "2025-10-01", - "supports_tool_choice": true, - "supports_web_search": true - }, - "claude-3-opus-latest": { - "max_tokens": 4096, - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "input_cost_per_token": 1.5e-05, - "output_cost_per_token": 7.5e-05, - "cache_creation_input_token_cost": 1.875e-05, - "cache_read_input_token_cost": 1.5e-06, - "litellm_provider": "anthropic", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 395, - "supports_assistant_prefill": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "deprecation_date": "2025-03-01", - "supports_tool_choice": true - }, - "claude-3-opus-20240229": { - "max_tokens": 4096, - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "input_cost_per_token": 1.5e-05, - "output_cost_per_token": 7.5e-05, - "cache_creation_input_token_cost": 1.875e-05, - "cache_read_input_token_cost": 1.5e-06, - "litellm_provider": "anthropic", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 395, - "supports_assistant_prefill": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "deprecation_date": "2025-03-01", - "supports_tool_choice": true - }, - "claude-3-5-sonnet-latest": { - "supports_computer_use": true, - "max_tokens": 8192, - "max_input_tokens": 200000, - "max_output_tokens": 8192, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "cache_creation_input_token_cost": 3.75e-06, - "cache_read_input_token_cost": 3e-07, - "search_context_cost_per_query": { - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01, - "search_context_size_high": 0.01 - }, - "litellm_provider": "anthropic", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 159, - "supports_assistant_prefill": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "deprecation_date": "2025-06-01", - "supports_tool_choice": true, - "supports_web_search": true - }, - "claude-3-5-sonnet-20240620": { - "max_tokens": 8192, - "max_input_tokens": 200000, - "max_output_tokens": 8192, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "cache_creation_input_token_cost": 3.75e-06, - "cache_read_input_token_cost": 3e-07, - "litellm_provider": "anthropic", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 159, - "supports_assistant_prefill": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "deprecation_date": "2025-06-01", - "supports_tool_choice": true - }, - "claude-opus-4-20250514": { - "max_tokens": 32000, - "max_input_tokens": 200000, - "max_output_tokens": 32000, - "input_cost_per_token": 1.5e-05, - "output_cost_per_token": 7.5e-05, - "search_context_cost_per_query": { - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01, - "search_context_size_high": 0.01 - }, - "cache_creation_input_token_cost": 1.875e-05, - "cache_read_input_token_cost": 1.5e-06, - "litellm_provider": "anthropic", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 159, - "supports_assistant_prefill": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_computer_use": true - }, - "claude-opus-4-1": { - "max_tokens": 32000, - "max_input_tokens": 200000, - "max_output_tokens": 32000, - "input_cost_per_token": 1.5e-05, - "output_cost_per_token": 7.5e-05, - "search_context_cost_per_query": { - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01, - "search_context_size_high": 0.01 - }, - "cache_creation_input_token_cost": 1.875e-05, - "cache_read_input_token_cost": 1.5e-06, - "litellm_provider": "anthropic", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 159, - "supports_assistant_prefill": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_computer_use": true - }, - "claude-opus-4-1-20250805": { - "max_tokens": 32000, - "max_input_tokens": 200000, - "max_output_tokens": 32000, - "input_cost_per_token": 1.5e-05, - "output_cost_per_token": 7.5e-05, - "search_context_cost_per_query": { - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01, - "search_context_size_high": 0.01 - }, - "cache_creation_input_token_cost": 1.875e-05, - "cache_read_input_token_cost": 1.5e-06, - "litellm_provider": "anthropic", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 159, - "supports_assistant_prefill": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_computer_use": true - }, - "claude-sonnet-4-20250514": { - "max_tokens": 64000, - "max_input_tokens": 200000, - "max_output_tokens": 64000, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "search_context_cost_per_query": { - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01, - "search_context_size_high": 0.01 - }, - "cache_creation_input_token_cost": 3.75e-06, - "cache_read_input_token_cost": 3e-07, - "litellm_provider": "anthropic", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 159, - "supports_assistant_prefill": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_computer_use": true - }, - "claude-4-opus-20250514": { - "max_tokens": 32000, - "max_input_tokens": 200000, - "max_output_tokens": 32000, - "input_cost_per_token": 1.5e-05, - "output_cost_per_token": 7.5e-05, - "search_context_cost_per_query": { - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01, - "search_context_size_high": 0.01 - }, - "cache_creation_input_token_cost": 1.875e-05, - "cache_read_input_token_cost": 1.5e-06, - "litellm_provider": "anthropic", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 159, - "supports_assistant_prefill": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_computer_use": true - }, - "claude-4-sonnet-20250514": { - "max_tokens": 1000000, - "max_input_tokens": 1000000, - "max_output_tokens": 1000000, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "input_cost_per_token_above_200k_tokens": 6e-06, - "output_cost_per_token_above_200k_tokens": 2.25e-05, - "search_context_cost_per_query": { - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01, - "search_context_size_high": 0.01 - }, - "cache_creation_input_token_cost": 3.75e-06, - "cache_read_input_token_cost": 3e-07, - "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, - "cache_read_input_token_cost_above_200k_tokens": 6e-07, - "litellm_provider": "anthropic", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 159, - "supports_assistant_prefill": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_computer_use": true - }, - "claude-3-7-sonnet-latest": { - "supports_computer_use": true, - "max_tokens": 128000, - "max_input_tokens": 200000, - "max_output_tokens": 128000, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "search_context_cost_per_query": { - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01, - "search_context_size_high": 0.01 - }, - "cache_creation_input_token_cost": 3.75e-06, - "cache_read_input_token_cost": 3e-07, - "litellm_provider": "anthropic", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 159, - "supports_assistant_prefill": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "deprecation_date": "2025-06-01", - "supports_tool_choice": true, - "supports_reasoning": true - }, - "claude-3-7-sonnet-20250219": { - "supports_computer_use": true, - "max_tokens": 128000, - "max_input_tokens": 200000, - "max_output_tokens": 128000, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "cache_creation_input_token_cost": 3.75e-06, - "cache_read_input_token_cost": 3e-07, - "search_context_cost_per_query": { - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01, - "search_context_size_high": 0.01 - }, - "litellm_provider": "anthropic", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 159, - "supports_assistant_prefill": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "deprecation_date": "2026-02-01", - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_web_search": true - }, - "claude-3-5-sonnet-20241022": { - "supports_computer_use": true, - "max_tokens": 8192, - "max_input_tokens": 200000, - "max_output_tokens": 8192, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "cache_creation_input_token_cost": 3.75e-06, - "cache_read_input_token_cost": 3e-07, - "search_context_cost_per_query": { - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01, - "search_context_size_high": 0.01 - }, - "litellm_provider": "anthropic", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 159, - "supports_assistant_prefill": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "deprecation_date": "2025-10-01", - "supports_tool_choice": true, - "supports_web_search": true - }, - "text-bison": { - "max_tokens": 2048, - "max_input_tokens": 8192, - "max_output_tokens": 2048, - "input_cost_per_character": 2.5e-07, - "output_cost_per_character": 5e-07, - "litellm_provider": "vertex_ai-text-models", - "mode": "completion", - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" - }, - "text-bison@001": { - "max_tokens": 1024, - "max_input_tokens": 8192, - "max_output_tokens": 1024, - "input_cost_per_character": 2.5e-07, - "output_cost_per_character": 5e-07, - "litellm_provider": "vertex_ai-text-models", - "mode": "completion", - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" - }, - "text-bison@002": { - "max_tokens": 1024, - "max_input_tokens": 8192, - "max_output_tokens": 1024, - "input_cost_per_character": 2.5e-07, - "output_cost_per_character": 5e-07, - "litellm_provider": "vertex_ai-text-models", - "mode": "completion", - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" - }, - "text-bison32k": { - "max_tokens": 1024, - "max_input_tokens": 8192, - "max_output_tokens": 1024, - "input_cost_per_token": 1.25e-07, - "output_cost_per_token": 1.25e-07, - "input_cost_per_character": 2.5e-07, - "output_cost_per_character": 5e-07, - "litellm_provider": "vertex_ai-text-models", - "mode": "completion", - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" - }, - "text-bison32k@002": { - "max_tokens": 1024, - "max_input_tokens": 8192, - "max_output_tokens": 1024, - "input_cost_per_token": 1.25e-07, - "output_cost_per_token": 1.25e-07, - "input_cost_per_character": 2.5e-07, - "output_cost_per_character": 5e-07, - "litellm_provider": "vertex_ai-text-models", - "mode": "completion", - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" - }, - "text-unicorn": { - "max_tokens": 1024, - "max_input_tokens": 8192, - "max_output_tokens": 1024, - "input_cost_per_token": 1e-05, - "output_cost_per_token": 2.8e-05, - "litellm_provider": "vertex_ai-text-models", - "mode": "completion", - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" - }, - "text-unicorn@001": { - "max_tokens": 1024, - "max_input_tokens": 8192, - "max_output_tokens": 1024, - "input_cost_per_token": 1e-05, - "output_cost_per_token": 2.8e-05, - "litellm_provider": "vertex_ai-text-models", - "mode": "completion", - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" - }, "chat-bison": { - "max_tokens": 4096, + "input_cost_per_character": 2.5e-07, + "input_cost_per_token": 1.25e-07, + "litellm_provider": "vertex_ai-chat-models", "max_input_tokens": 8192, "max_output_tokens": 4096, - "input_cost_per_token": 1.25e-07, - "output_cost_per_token": 1.25e-07, - "input_cost_per_character": 2.5e-07, - "output_cost_per_character": 5e-07, - "litellm_provider": "vertex_ai-chat-models", - "mode": "chat", - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", - "supports_tool_choice": true - }, - "chat-bison@001": { "max_tokens": 4096, - "max_input_tokens": 8192, - "max_output_tokens": 4096, - "input_cost_per_token": 1.25e-07, - "output_cost_per_token": 1.25e-07, - "input_cost_per_character": 2.5e-07, - "output_cost_per_character": 5e-07, - "litellm_provider": "vertex_ai-chat-models", "mode": "chat", - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", - "supports_tool_choice": true - }, - "chat-bison@002": { - "max_tokens": 4096, - "max_input_tokens": 8192, - "max_output_tokens": 4096, - "input_cost_per_token": 1.25e-07, - "output_cost_per_token": 1.25e-07, - "input_cost_per_character": 2.5e-07, "output_cost_per_character": 5e-07, - "litellm_provider": "vertex_ai-chat-models", - "mode": "chat", + "output_cost_per_token": 1.25e-07, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", - "deprecation_date": "2025-04-09", "supports_tool_choice": true }, "chat-bison-32k": { - "max_tokens": 8192, + "input_cost_per_character": 2.5e-07, + "input_cost_per_token": 1.25e-07, + "litellm_provider": "vertex_ai-chat-models", "max_input_tokens": 32000, "max_output_tokens": 8192, - "input_cost_per_token": 1.25e-07, - "output_cost_per_token": 1.25e-07, - "input_cost_per_character": 2.5e-07, - "output_cost_per_character": 5e-07, - "litellm_provider": "vertex_ai-chat-models", + "max_tokens": 8192, "mode": "chat", + "output_cost_per_character": 5e-07, + "output_cost_per_token": 1.25e-07, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", "supports_tool_choice": true }, "chat-bison-32k@002": { - "max_tokens": 8192, + "input_cost_per_character": 2.5e-07, + "input_cost_per_token": 1.25e-07, + "litellm_provider": "vertex_ai-chat-models", "max_input_tokens": 32000, "max_output_tokens": 8192, - "input_cost_per_token": 1.25e-07, - "output_cost_per_token": 1.25e-07, - "input_cost_per_character": 2.5e-07, - "output_cost_per_character": 5e-07, - "litellm_provider": "vertex_ai-chat-models", + "max_tokens": 8192, "mode": "chat", + "output_cost_per_character": 5e-07, + "output_cost_per_token": 1.25e-07, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", "supports_tool_choice": true }, + "chat-bison@001": { + "input_cost_per_character": 2.5e-07, + "input_cost_per_token": 1.25e-07, + "litellm_provider": "vertex_ai-chat-models", + "max_input_tokens": 8192, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_character": 5e-07, + "output_cost_per_token": 1.25e-07, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "supports_tool_choice": true + }, + "chat-bison@002": { + "deprecation_date": "2025-04-09", + "input_cost_per_character": 2.5e-07, + "input_cost_per_token": 1.25e-07, + "litellm_provider": "vertex_ai-chat-models", + "max_input_tokens": 8192, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_character": 5e-07, + "output_cost_per_token": 1.25e-07, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "supports_tool_choice": true + }, + "chatdolphin": { + "input_cost_per_token": 5e-07, + "litellm_provider": "nlp_cloud", + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 5e-07 + }, + "chatgpt-4o-latest": { + "input_cost_per_token": 5e-06, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "claude-3-5-haiku-20241022": { + "cache_creation_input_token_cost": 1e-06, + "cache_creation_input_token_cost_above_1hr": 1.6e-06, + "cache_read_input_token_cost": 8e-08, + "deprecation_date": "2025-10-01", + "input_cost_per_token": 8e-07, + "litellm_provider": "anthropic", + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 4e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "tool_use_system_prompt_tokens": 264 + }, + "claude-3-5-haiku-latest": { + "cache_creation_input_token_cost": 1.25e-06, + "cache_read_input_token_cost": 1e-07, + "deprecation_date": "2025-10-01", + "input_cost_per_token": 1e-06, + "litellm_provider": "anthropic", + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 5e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "tool_use_system_prompt_tokens": 264 + }, + "claude-3-5-sonnet-20240620": { + "cache_creation_input_token_cost": 3.75e-06, + "cache_creation_input_token_cost_above_1hr": 1.6e-06, + "cache_read_input_token_cost": 3e-07, + "deprecation_date": "2025-06-01", + "input_cost_per_token": 3e-06, + "litellm_provider": "anthropic", + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159 + }, + "claude-3-5-sonnet-20241022": { + "cache_creation_input_token_cost": 3.75e-06, + "cache_creation_input_token_cost_above_1hr": 1.6e-06, + "cache_read_input_token_cost": 3e-07, + "deprecation_date": "2025-10-01", + "input_cost_per_token": 3e-06, + "litellm_provider": "anthropic", + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "tool_use_system_prompt_tokens": 159 + }, + "claude-3-5-sonnet-latest": { + "cache_creation_input_token_cost": 3.75e-06, + "cache_creation_input_token_cost_above_1hr": 1.6e-06, + "cache_read_input_token_cost": 3e-07, + "deprecation_date": "2025-06-01", + "input_cost_per_token": 3e-06, + "litellm_provider": "anthropic", + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "tool_use_system_prompt_tokens": 159 + }, + "claude-3-7-sonnet-20250219": { + "cache_creation_input_token_cost": 3.75e-06, + "cache_read_input_token_cost": 3e-07, + "deprecation_date": "2026-02-01", + "input_cost_per_token": 3e-06, + "litellm_provider": "anthropic", + "max_input_tokens": 200000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "tool_use_system_prompt_tokens": 159 + }, + "claude-3-7-sonnet-latest": { + "cache_creation_input_token_cost": 3.75e-06, + "cache_read_input_token_cost": 3e-07, + "deprecation_date": "2025-06-01", + "input_cost_per_token": 3e-06, + "litellm_provider": "anthropic", + "max_input_tokens": 200000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159 + }, + "claude-3-haiku-20240307": { + "cache_creation_input_token_cost": 3e-07, + "cache_read_input_token_cost": 3e-08, + "deprecation_date": "2025-03-01", + "input_cost_per_token": 2.5e-07, + "litellm_provider": "anthropic", + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.25e-06, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 264 + }, + "claude-3-opus-20240229": { + "cache_creation_input_token_cost": 1.875e-05, + "cache_read_input_token_cost": 1.5e-06, + "deprecation_date": "2025-03-01", + "input_cost_per_token": 1.5e-05, + "litellm_provider": "anthropic", + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 7.5e-05, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 395 + }, + "claude-3-opus-latest": { + "cache_creation_input_token_cost": 1.875e-05, + "cache_read_input_token_cost": 1.5e-06, + "deprecation_date": "2025-03-01", + "input_cost_per_token": 1.5e-05, + "litellm_provider": "anthropic", + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 7.5e-05, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 395 + }, + "claude-4-opus-20250514": { + "cache_creation_input_token_cost": 1.875e-05, + "cache_read_input_token_cost": 1.5e-06, + "input_cost_per_token": 1.5e-05, + "litellm_provider": "anthropic", + "max_input_tokens": 200000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 7.5e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159 + }, + "claude-4-sonnet-20250514": { + "cache_creation_input_token_cost": 3.75e-06, + "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, + "cache_read_input_token_cost": 3e-07, + "cache_read_input_token_cost_above_200k_tokens": 6e-07, + "input_cost_per_token": 3e-06, + "input_cost_per_token_above_200k_tokens": 6e-06, + "litellm_provider": "anthropic", + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "max_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "output_cost_per_token_above_200k_tokens": 2.25e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159 + }, + "claude-opus-4-1": { + "cache_creation_input_token_cost": 1.875e-05, + "cache_read_input_token_cost": 1.5e-06, + "input_cost_per_token": 1.5e-05, + "litellm_provider": "anthropic", + "max_input_tokens": 200000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 7.5e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159 + }, + "claude-opus-4-1-20250805": { + "cache_creation_input_token_cost": 1.875e-05, + "cache_read_input_token_cost": 1.5e-06, + "input_cost_per_token": 1.5e-05, + "litellm_provider": "anthropic", + "max_input_tokens": 200000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 7.5e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159 + }, + "claude-opus-4-20250514": { + "cache_creation_input_token_cost": 1.875e-05, + "cache_read_input_token_cost": 1.5e-06, + "input_cost_per_token": 1.5e-05, + "litellm_provider": "anthropic", + "max_input_tokens": 200000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 7.5e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159 + }, + "claude-sonnet-4-20250514": { + "cache_creation_input_token_cost": 3.75e-06, + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 3e-06, + "litellm_provider": "anthropic", + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159 + }, + "cloudflare/@cf/meta/llama-2-7b-chat-fp16": { + "input_cost_per_token": 1.923e-06, + "litellm_provider": "cloudflare", + "max_input_tokens": 3072, + "max_output_tokens": 3072, + "max_tokens": 3072, + "mode": "chat", + "output_cost_per_token": 1.923e-06 + }, + "cloudflare/@cf/meta/llama-2-7b-chat-int8": { + "input_cost_per_token": 1.923e-06, + "litellm_provider": "cloudflare", + "max_input_tokens": 2048, + "max_output_tokens": 2048, + "max_tokens": 2048, + "mode": "chat", + "output_cost_per_token": 1.923e-06 + }, + "cloudflare/@cf/mistral/mistral-7b-instruct-v0.1": { + "input_cost_per_token": 1.923e-06, + "litellm_provider": "cloudflare", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.923e-06 + }, + "cloudflare/@hf/thebloke/codellama-7b-instruct-awq": { + "input_cost_per_token": 1.923e-06, + "litellm_provider": "cloudflare", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.923e-06 + }, "code-bison": { - "max_tokens": 1024, + "input_cost_per_character": 2.5e-07, + "input_cost_per_token": 1.25e-07, + "litellm_provider": "vertex_ai-code-text-models", "max_input_tokens": 6144, "max_output_tokens": 1024, - "input_cost_per_token": 1.25e-07, - "output_cost_per_token": 1.25e-07, - "input_cost_per_character": 2.5e-07, - "output_cost_per_character": 5e-07, - "litellm_provider": "vertex_ai-code-text-models", + "max_tokens": 1024, "mode": "chat", + "output_cost_per_character": 5e-07, + "output_cost_per_token": 1.25e-07, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", "supports_tool_choice": true }, - "code-bison@001": { - "max_tokens": 1024, + "code-bison-32k@002": { + "input_cost_per_character": 2.5e-07, + "input_cost_per_token": 1.25e-07, + "litellm_provider": "vertex_ai-code-text-models", "max_input_tokens": 6144, "max_output_tokens": 1024, - "input_cost_per_token": 1.25e-07, - "output_cost_per_token": 1.25e-07, - "input_cost_per_character": 2.5e-07, - "output_cost_per_character": 5e-07, - "litellm_provider": "vertex_ai-code-text-models", - "mode": "completion", - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" - }, - "code-bison@002": { "max_tokens": 1024, - "max_input_tokens": 6144, - "max_output_tokens": 1024, - "input_cost_per_token": 1.25e-07, - "output_cost_per_token": 1.25e-07, - "input_cost_per_character": 2.5e-07, - "output_cost_per_character": 5e-07, - "litellm_provider": "vertex_ai-code-text-models", "mode": "completion", + "output_cost_per_character": 5e-07, + "output_cost_per_token": 1.25e-07, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" }, "code-bison32k": { - "max_tokens": 1024, + "input_cost_per_character": 2.5e-07, + "input_cost_per_token": 1.25e-07, + "litellm_provider": "vertex_ai-code-text-models", "max_input_tokens": 6144, "max_output_tokens": 1024, - "input_cost_per_token": 1.25e-07, - "output_cost_per_token": 1.25e-07, - "input_cost_per_character": 2.5e-07, - "output_cost_per_character": 5e-07, - "litellm_provider": "vertex_ai-code-text-models", + "max_tokens": 1024, "mode": "completion", + "output_cost_per_character": 5e-07, + "output_cost_per_token": 1.25e-07, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" }, - "code-bison-32k@002": { - "max_tokens": 1024, + "code-bison@001": { + "input_cost_per_character": 2.5e-07, + "input_cost_per_token": 1.25e-07, + "litellm_provider": "vertex_ai-code-text-models", "max_input_tokens": 6144, "max_output_tokens": 1024, - "input_cost_per_token": 1.25e-07, - "output_cost_per_token": 1.25e-07, - "input_cost_per_character": 2.5e-07, + "max_tokens": 1024, + "mode": "completion", "output_cost_per_character": 5e-07, - "litellm_provider": "vertex_ai-code-text-models", - "mode": "completion", + "output_cost_per_token": 1.25e-07, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" }, - "code-gecko@001": { - "max_tokens": 64, - "max_input_tokens": 2048, - "max_output_tokens": 64, + "code-bison@002": { + "input_cost_per_character": 2.5e-07, "input_cost_per_token": 1.25e-07, - "output_cost_per_token": 1.25e-07, "litellm_provider": "vertex_ai-code-text-models", + "max_input_tokens": 6144, + "max_output_tokens": 1024, + "max_tokens": 1024, "mode": "completion", - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" - }, - "code-gecko@002": { - "max_tokens": 64, - "max_input_tokens": 2048, - "max_output_tokens": 64, - "input_cost_per_token": 1.25e-07, + "output_cost_per_character": 5e-07, "output_cost_per_token": 1.25e-07, - "litellm_provider": "vertex_ai-code-text-models", - "mode": "completion", "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" }, "code-gecko": { - "max_tokens": 64, + "input_cost_per_token": 1.25e-07, + "litellm_provider": "vertex_ai-code-text-models", "max_input_tokens": 2048, "max_output_tokens": 64, - "input_cost_per_token": 1.25e-07, - "output_cost_per_token": 1.25e-07, - "litellm_provider": "vertex_ai-code-text-models", + "max_tokens": 64, "mode": "completion", + "output_cost_per_token": 1.25e-07, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" }, "code-gecko-latest": { - "max_tokens": 64, + "input_cost_per_token": 1.25e-07, + "litellm_provider": "vertex_ai-code-text-models", "max_input_tokens": 2048, "max_output_tokens": 64, - "input_cost_per_token": 1.25e-07, - "output_cost_per_token": 1.25e-07, - "litellm_provider": "vertex_ai-code-text-models", + "max_tokens": 64, "mode": "completion", + "output_cost_per_token": 1.25e-07, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" }, - "codechat-bison@latest": { - "max_tokens": 1024, - "max_input_tokens": 6144, - "max_output_tokens": 1024, + "code-gecko@001": { "input_cost_per_token": 1.25e-07, + "litellm_provider": "vertex_ai-code-text-models", + "max_input_tokens": 2048, + "max_output_tokens": 64, + "max_tokens": 64, + "mode": "completion", "output_cost_per_token": 1.25e-07, - "input_cost_per_character": 2.5e-07, - "output_cost_per_character": 5e-07, - "litellm_provider": "vertex_ai-code-chat-models", - "mode": "chat", - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", - "supports_tool_choice": true + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" + }, + "code-gecko@002": { + "input_cost_per_token": 1.25e-07, + "litellm_provider": "vertex_ai-code-text-models", + "max_input_tokens": 2048, + "max_output_tokens": 64, + "max_tokens": 64, + "mode": "completion", + "output_cost_per_token": 1.25e-07, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" }, "codechat-bison": { - "max_tokens": 1024, + "input_cost_per_character": 2.5e-07, + "input_cost_per_token": 1.25e-07, + "litellm_provider": "vertex_ai-code-chat-models", "max_input_tokens": 6144, "max_output_tokens": 1024, - "input_cost_per_token": 1.25e-07, - "output_cost_per_token": 1.25e-07, - "input_cost_per_character": 2.5e-07, - "output_cost_per_character": 5e-07, - "litellm_provider": "vertex_ai-code-chat-models", - "mode": "chat", - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", - "supports_tool_choice": true - }, - "codechat-bison@001": { "max_tokens": 1024, - "max_input_tokens": 6144, - "max_output_tokens": 1024, - "input_cost_per_token": 1.25e-07, - "output_cost_per_token": 1.25e-07, - "input_cost_per_character": 2.5e-07, - "output_cost_per_character": 5e-07, - "litellm_provider": "vertex_ai-code-chat-models", "mode": "chat", - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", - "supports_tool_choice": true - }, - "codechat-bison@002": { - "max_tokens": 1024, - "max_input_tokens": 6144, - "max_output_tokens": 1024, - "input_cost_per_token": 1.25e-07, - "output_cost_per_token": 1.25e-07, - "input_cost_per_character": 2.5e-07, "output_cost_per_character": 5e-07, - "litellm_provider": "vertex_ai-code-chat-models", - "mode": "chat", + "output_cost_per_token": 1.25e-07, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", "supports_tool_choice": true }, "codechat-bison-32k": { - "max_tokens": 8192, + "input_cost_per_character": 2.5e-07, + "input_cost_per_token": 1.25e-07, + "litellm_provider": "vertex_ai-code-chat-models", "max_input_tokens": 32000, "max_output_tokens": 8192, - "input_cost_per_token": 1.25e-07, - "output_cost_per_token": 1.25e-07, - "input_cost_per_character": 2.5e-07, - "output_cost_per_character": 5e-07, - "litellm_provider": "vertex_ai-code-chat-models", + "max_tokens": 8192, "mode": "chat", + "output_cost_per_character": 5e-07, + "output_cost_per_token": 1.25e-07, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", "supports_tool_choice": true }, "codechat-bison-32k@002": { - "max_tokens": 8192, + "input_cost_per_character": 2.5e-07, + "input_cost_per_token": 1.25e-07, + "litellm_provider": "vertex_ai-code-chat-models", "max_input_tokens": 32000, "max_output_tokens": 8192, - "input_cost_per_token": 1.25e-07, - "output_cost_per_token": 1.25e-07, - "input_cost_per_character": 2.5e-07, - "output_cost_per_character": 5e-07, - "litellm_provider": "vertex_ai-code-chat-models", + "max_tokens": 8192, "mode": "chat", + "output_cost_per_character": 5e-07, + "output_cost_per_token": 1.25e-07, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", "supports_tool_choice": true }, - "meta_llama/Llama-4-Scout-17B-16E-Instruct-FP8": { - "max_tokens": 128000, - "max_input_tokens": 10000000, - "max_output_tokens": 4028, - "litellm_provider": "meta_llama", + "codechat-bison@001": { + "input_cost_per_character": 2.5e-07, + "input_cost_per_token": 1.25e-07, + "litellm_provider": "vertex_ai-code-chat-models", + "max_input_tokens": 6144, + "max_output_tokens": 1024, + "max_tokens": 1024, "mode": "chat", - "supports_function_calling": true, - "source": "https://llama.developer.meta.com/docs/models", - "supports_tool_choice": true, - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ] - }, - "meta_llama/Llama-4-Maverick-17B-128E-Instruct-FP8": { - "max_tokens": 128000, - "max_input_tokens": 1000000, - "max_output_tokens": 4028, - "litellm_provider": "meta_llama", - "mode": "chat", - "supports_function_calling": true, - "source": "https://llama.developer.meta.com/docs/models", - "supports_tool_choice": true, - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ] - }, - "meta_llama/Llama-3.3-70B-Instruct": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 4028, - "litellm_provider": "meta_llama", - "mode": "chat", - "supports_function_calling": true, - "source": "https://llama.developer.meta.com/docs/models", - "supports_tool_choice": true, - "supported_modalities": [ - "text" - ], - "supported_output_modalities": [ - "text" - ] - }, - "meta_llama/Llama-3.3-8B-Instruct": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 4028, - "litellm_provider": "meta_llama", - "mode": "chat", - "supports_function_calling": true, - "source": "https://llama.developer.meta.com/docs/models", - "supports_tool_choice": true, - "supported_modalities": [ - "text" - ], - "supported_output_modalities": [ - "text" - ] - }, - "gemini-pro": { - "max_tokens": 8192, - "max_input_tokens": 32760, - "max_output_tokens": 8192, - "input_cost_per_image": 0.0025, - "input_cost_per_video_per_second": 0.002, - "input_cost_per_token": 5e-07, - "input_cost_per_character": 1.25e-07, - "output_cost_per_token": 1.5e-06, - "output_cost_per_character": 3.75e-07, - "litellm_provider": "vertex_ai-language-models", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "output_cost_per_character": 5e-07, + "output_cost_per_token": 1.25e-07, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", "supports_tool_choice": true }, - "gemini-1.0-pro": { - "max_tokens": 8192, - "max_input_tokens": 32760, - "max_output_tokens": 8192, - "input_cost_per_image": 0.0025, - "input_cost_per_video_per_second": 0.002, - "input_cost_per_token": 5e-07, - "input_cost_per_character": 1.25e-07, - "output_cost_per_token": 1.5e-06, - "output_cost_per_character": 3.75e-07, - "litellm_provider": "vertex_ai-language-models", + "codechat-bison@002": { + "input_cost_per_character": 2.5e-07, + "input_cost_per_token": 1.25e-07, + "litellm_provider": "vertex_ai-code-chat-models", + "max_input_tokens": 6144, + "max_output_tokens": 1024, + "max_tokens": 1024, "mode": "chat", + "output_cost_per_character": 5e-07, + "output_cost_per_token": 1.25e-07, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "supports_tool_choice": true + }, + "codechat-bison@latest": { + "input_cost_per_character": 2.5e-07, + "input_cost_per_token": 1.25e-07, + "litellm_provider": "vertex_ai-code-chat-models", + "max_input_tokens": 6144, + "max_output_tokens": 1024, + "max_tokens": 1024, + "mode": "chat", + "output_cost_per_character": 5e-07, + "output_cost_per_token": 1.25e-07, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "supports_tool_choice": true + }, + "codestral/codestral-2405": { + "input_cost_per_token": 0.0, + "litellm_provider": "codestral", + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 0.0, + "source": "https://docs.mistral.ai/capabilities/code_generation/", + "supports_assistant_prefill": true, + "supports_tool_choice": true + }, + "codestral/codestral-latest": { + "input_cost_per_token": 0.0, + "litellm_provider": "codestral", + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 0.0, + "source": "https://docs.mistral.ai/capabilities/code_generation/", + "supports_assistant_prefill": true, + "supports_tool_choice": true + }, + "codex-mini-latest": { + "cache_read_input_token_cost": 3.75e-07, + "input_cost_per_token": 1.5e-06, + "litellm_provider": "openai", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "responses", + "output_cost_per_token": 6e-06, + "supported_endpoints": [ + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], "supports_function_calling": true, "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "cohere.command-light-text-v14": { + "input_cost_per_token": 3e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 6e-07, + "supports_tool_choice": true + }, + "cohere.command-r-plus-v1:0": { + "input_cost_per_token": 3e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "supports_tool_choice": true + }, + "cohere.command-r-v1:0": { + "input_cost_per_token": 5e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.5e-06, + "supports_tool_choice": true + }, + "cohere.command-text-v14": { + "input_cost_per_token": 1.5e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 2e-06, + "supports_tool_choice": true + }, + "cohere.embed-english-v3": { + "input_cost_per_token": 1e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 512, + "max_tokens": 512, + "mode": "embedding", + "output_cost_per_token": 0.0, + "supports_embedding_image_input": true + }, + "cohere.embed-multilingual-v3": { + "input_cost_per_token": 1e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 512, + "max_tokens": 512, + "mode": "embedding", + "output_cost_per_token": 0.0, + "supports_embedding_image_input": true + }, + "cohere.rerank-v3-5:0": { + "input_cost_per_query": 0.002, + "input_cost_per_token": 0.0, + "litellm_provider": "bedrock", + "max_document_chunks_per_query": 100, + "max_input_tokens": 32000, + "max_output_tokens": 32000, + "max_query_tokens": 32000, + "max_tokens": 32000, + "max_tokens_per_document_chunk": 512, + "mode": "rerank", + "output_cost_per_token": 0.0 + }, + "command": { + "input_cost_per_token": 1e-06, + "litellm_provider": "cohere", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "completion", + "output_cost_per_token": 2e-06 + }, + "command-a-03-2025": { + "input_cost_per_token": 2.5e-06, + "litellm_provider": "cohere_chat", + "max_input_tokens": 256000, + "max_output_tokens": 8000, + "max_tokens": 8000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "supports_function_calling": true, + "supports_tool_choice": true + }, + "command-light": { + "input_cost_per_token": 3e-07, + "litellm_provider": "cohere_chat", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 6e-07, + "supports_tool_choice": true + }, + "command-nightly": { + "input_cost_per_token": 1e-06, + "litellm_provider": "cohere", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "completion", + "output_cost_per_token": 2e-06 + }, + "command-r": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "cohere_chat", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 6e-07, + "supports_function_calling": true, + "supports_tool_choice": true + }, + "command-r-08-2024": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "cohere_chat", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 6e-07, + "supports_function_calling": true, + "supports_tool_choice": true + }, + "command-r-plus": { + "input_cost_per_token": 2.5e-06, + "litellm_provider": "cohere_chat", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1e-05, + "supports_function_calling": true, + "supports_tool_choice": true + }, + "command-r-plus-08-2024": { + "input_cost_per_token": 2.5e-06, + "litellm_provider": "cohere_chat", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1e-05, + "supports_function_calling": true, + "supports_tool_choice": true + }, + "command-r7b-12-2024": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "cohere_chat", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 3.75e-08, + "source": "https://docs.cohere.com/v2/docs/command-r7b", + "supports_function_calling": true, + "supports_tool_choice": true + }, + "computer-use-preview": { + "input_cost_per_token": 3e-06, + "litellm_provider": "azure", + "max_input_tokens": 8192, + "max_output_tokens": 1024, + "max_tokens": 1024, + "mode": "chat", + "output_cost_per_token": 1.2e-05, + "supported_endpoints": [ + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "dashscope/qwen-coder": { + "input_cost_per_token": 3e-07, + "litellm_provider": "dashscope", + "max_input_tokens": 1000000, + "max_output_tokens": 16384, + "max_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 1.5e-06, + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "dashscope/qwen-flash": { + "litellm_provider": "dashscope", + "max_input_tokens": 997952, + "max_output_tokens": 32768, + "max_tokens": 1000000, + "mode": "chat", + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "tiered_pricing": [ + { + "input_cost_per_token": 5e-08, + "output_cost_per_token": 4e-07, + "range": [ + 0, + 256000.0 + ] + }, + { + "input_cost_per_token": 2.5e-07, + "output_cost_per_token": 2e-06, + "range": [ + 256000.0, + 1000000.0 + ] + } + ] + }, + "dashscope/qwen-flash-2025-07-28": { + "litellm_provider": "dashscope", + "max_input_tokens": 997952, + "max_output_tokens": 32768, + "max_tokens": 1000000, + "mode": "chat", + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "tiered_pricing": [ + { + "input_cost_per_token": 5e-08, + "output_cost_per_token": 4e-07, + "range": [ + 0, + 256000.0 + ] + }, + { + "input_cost_per_token": 2.5e-07, + "output_cost_per_token": 2e-06, + "range": [ + 256000.0, + 1000000.0 + ] + } + ] + }, + "dashscope/qwen-max": { + "input_cost_per_token": 1.6e-06, + "litellm_provider": "dashscope", + "max_input_tokens": 30720, + "max_output_tokens": 8192, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 6.4e-06, + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "dashscope/qwen-plus": { + "input_cost_per_token": 4e-07, + "litellm_provider": "dashscope", + "max_input_tokens": 129024, + "max_output_tokens": 16384, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "dashscope/qwen-plus-2025-01-25": { + "input_cost_per_token": 4e-07, + "litellm_provider": "dashscope", + "max_input_tokens": 129024, + "max_output_tokens": 8192, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "dashscope/qwen-plus-2025-04-28": { + "input_cost_per_token": 4e-07, + "litellm_provider": "dashscope", + "max_input_tokens": 129024, + "max_output_tokens": 16384, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_reasoning_token": 4e-06, + "output_cost_per_token": 1.2e-06, + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "dashscope/qwen-plus-2025-07-14": { + "input_cost_per_token": 4e-07, + "litellm_provider": "dashscope", + "max_input_tokens": 129024, + "max_output_tokens": 16384, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_reasoning_token": 4e-06, + "output_cost_per_token": 1.2e-06, + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "dashscope/qwen-plus-2025-07-28": { + "litellm_provider": "dashscope", + "max_input_tokens": 997952, + "max_output_tokens": 32768, + "max_tokens": 1000000, + "mode": "chat", + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "tiered_pricing": [ + { + "input_cost_per_token": 4e-07, + "output_cost_per_reasoning_token": 4e-06, + "output_cost_per_token": 1.2e-06, + "range": [ + 0, + 256000.0 + ] + }, + { + "input_cost_per_token": 1.2e-06, + "output_cost_per_reasoning_token": 1.2e-05, + "output_cost_per_token": 3.6e-06, + "range": [ + 256000.0, + 1000000.0 + ] + } + ] + }, + "dashscope/qwen-plus-2025-09-11": { + "litellm_provider": "dashscope", + "max_input_tokens": 997952, + "max_output_tokens": 32768, + "max_tokens": 1000000, + "mode": "chat", + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "tiered_pricing": [ + { + "input_cost_per_token": 4e-07, + "output_cost_per_reasoning_token": 4e-06, + "output_cost_per_token": 1.2e-06, + "range": [ + 0, + 256000.0 + ] + }, + { + "input_cost_per_token": 1.2e-06, + "output_cost_per_reasoning_token": 1.2e-05, + "output_cost_per_token": 3.6e-06, + "range": [ + 256000.0, + 1000000.0 + ] + } + ] + }, + "dashscope/qwen-plus-latest": { + "litellm_provider": "dashscope", + "max_input_tokens": 997952, + "max_output_tokens": 32768, + "max_tokens": 1000000, + "mode": "chat", + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "tiered_pricing": [ + { + "input_cost_per_token": 4e-07, + "output_cost_per_reasoning_token": 4e-06, + "output_cost_per_token": 1.2e-06, + "range": [ + 0, + 256000.0 + ] + }, + { + "input_cost_per_token": 1.2e-06, + "output_cost_per_reasoning_token": 1.2e-05, + "output_cost_per_token": 3.6e-06, + "range": [ + 256000.0, + 1000000.0 + ] + } + ] + }, + "dashscope/qwen-turbo": { + "input_cost_per_token": 5e-08, + "litellm_provider": "dashscope", + "max_input_tokens": 129024, + "max_output_tokens": 16384, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_reasoning_token": 5e-07, + "output_cost_per_token": 2e-07, + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "dashscope/qwen-turbo-2024-11-01": { + "input_cost_per_token": 5e-08, + "litellm_provider": "dashscope", + "max_input_tokens": 1000000, + "max_output_tokens": 8192, + "max_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 2e-07, + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "dashscope/qwen-turbo-2025-04-28": { + "input_cost_per_token": 5e-08, + "litellm_provider": "dashscope", + "max_input_tokens": 1000000, + "max_output_tokens": 16384, + "max_tokens": 1000000, + "mode": "chat", + "output_cost_per_reasoning_token": 5e-07, + "output_cost_per_token": 2e-07, + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "dashscope/qwen-turbo-latest": { + "input_cost_per_token": 5e-08, + "litellm_provider": "dashscope", + "max_input_tokens": 1000000, + "max_output_tokens": 16384, + "max_tokens": 1000000, + "mode": "chat", + "output_cost_per_reasoning_token": 5e-07, + "output_cost_per_token": 2e-07, + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "dashscope/qwen3-30b-a3b": { + "litellm_provider": "dashscope", + "max_input_tokens": 129024, + "max_output_tokens": 16384, + "max_tokens": 131072, + "mode": "chat", + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "dashscope/qwen3-coder-flash": { + "litellm_provider": "dashscope", + "max_input_tokens": 997952, + "max_output_tokens": 65536, + "max_tokens": 1000000, + "mode": "chat", + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "tiered_pricing": [ + { + "cache_read_input_token_cost": 8e-08, + "input_cost_per_token": 3e-07, + "output_cost_per_token": 1.5e-06, + "range": [ + 0, + 32000.0 + ] + }, + { + "cache_read_input_token_cost": 1.2e-07, + "input_cost_per_token": 5e-07, + "output_cost_per_token": 2.5e-06, + "range": [ + 32000.0, + 128000.0 + ] + }, + { + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 8e-07, + "output_cost_per_token": 4e-06, + "range": [ + 128000.0, + 256000.0 + ] + }, + { + "cache_read_input_token_cost": 4e-07, + "input_cost_per_token": 1.6e-06, + "output_cost_per_token": 9.6e-06, + "range": [ + 256000.0, + 1000000.0 + ] + } + ] + }, + "dashscope/qwen3-coder-flash-2025-07-28": { + "litellm_provider": "dashscope", + "max_input_tokens": 997952, + "max_output_tokens": 65536, + "max_tokens": 1000000, + "mode": "chat", + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "tiered_pricing": [ + { + "input_cost_per_token": 3e-07, + "output_cost_per_token": 1.5e-06, + "range": [ + 0, + 32000.0 + ] + }, + { + "input_cost_per_token": 5e-07, + "output_cost_per_token": 2.5e-06, + "range": [ + 32000.0, + 128000.0 + ] + }, + { + "input_cost_per_token": 8e-07, + "output_cost_per_token": 4e-06, + "range": [ + 128000.0, + 256000.0 + ] + }, + { + "input_cost_per_token": 1.6e-06, + "output_cost_per_token": 9.6e-06, + "range": [ + 256000.0, + 1000000.0 + ] + } + ] + }, + "dashscope/qwen3-coder-plus": { + "litellm_provider": "dashscope", + "max_input_tokens": 997952, + "max_output_tokens": 65536, + "max_tokens": 1000000, + "mode": "chat", + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "tiered_pricing": [ + { + "cache_read_input_token_cost": 1e-07, + "input_cost_per_token": 1e-06, + "output_cost_per_token": 5e-06, + "range": [ + 0, + 32000.0 + ] + }, + { + "cache_read_input_token_cost": 1.8e-07, + "input_cost_per_token": 1.8e-06, + "output_cost_per_token": 9e-06, + "range": [ + 32000.0, + 128000.0 + ] + }, + { + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 3e-06, + "output_cost_per_token": 1.5e-05, + "range": [ + 128000.0, + 256000.0 + ] + }, + { + "cache_read_input_token_cost": 6e-07, + "input_cost_per_token": 6e-06, + "output_cost_per_token": 6e-05, + "range": [ + 256000.0, + 1000000.0 + ] + } + ] + }, + "dashscope/qwen3-coder-plus-2025-07-22": { + "litellm_provider": "dashscope", + "max_input_tokens": 997952, + "max_output_tokens": 65536, + "max_tokens": 1000000, + "mode": "chat", + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "tiered_pricing": [ + { + "input_cost_per_token": 1e-06, + "output_cost_per_token": 5e-06, + "range": [ + 0, + 32000.0 + ] + }, + { + "input_cost_per_token": 1.8e-06, + "output_cost_per_token": 9e-06, + "range": [ + 32000.0, + 128000.0 + ] + }, + { + "input_cost_per_token": 3e-06, + "output_cost_per_token": 1.5e-05, + "range": [ + 128000.0, + 256000.0 + ] + }, + { + "input_cost_per_token": 6e-06, + "output_cost_per_token": 6e-05, + "range": [ + 256000.0, + 1000000.0 + ] + } + ] + }, + "dashscope/qwen3-max-preview": { + "litellm_provider": "dashscope", + "max_input_tokens": 258048, + "max_output_tokens": 65536, + "max_tokens": 262144, + "mode": "chat", + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "tiered_pricing": [ + { + "input_cost_per_token": 1.2e-06, + "output_cost_per_token": 6e-06, + "range": [ + 0, + 32000.0 + ] + }, + { + "input_cost_per_token": 2.4e-06, + "output_cost_per_token": 1.2e-05, + "range": [ + 32000.0, + 128000.0 + ] + }, + { + "input_cost_per_token": 3e-06, + "output_cost_per_token": 1.5e-05, + "range": [ + 128000.0, + 252000.0 + ] + } + ] + }, + "dashscope/qwq-plus": { + "input_cost_per_token": 8e-07, + "litellm_provider": "dashscope", + "max_input_tokens": 98304, + "max_output_tokens": 8192, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2.4e-06, + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "databricks/databricks-bge-large-en": { + "input_cost_per_token": 1.0003e-07, + "input_dbu_cost_per_token": 1.429e-06, + "litellm_provider": "databricks", + "max_input_tokens": 512, + "max_tokens": 512, + "metadata": { + "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." + }, + "mode": "embedding", + "output_cost_per_token": 0.0, + "output_dbu_cost_per_token": 0.0, + "output_vector_size": 1024, + "source": "https://www.databricks.com/product/pricing/foundation-model-serving" + }, + "databricks/databricks-claude-3-7-sonnet": { + "input_cost_per_token": 2.5e-06, + "input_dbu_cost_per_token": 3.571e-05, + "litellm_provider": "databricks", + "max_input_tokens": 200000, + "max_output_tokens": 128000, + "max_tokens": 200000, + "metadata": { + "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Claude 3.7 conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." + }, + "mode": "chat", + "output_cost_per_token": 1.7857e-05, + "output_db_cost_per_token": 0.000214286, + "source": "https://www.databricks.com/product/pricing/foundation-model-serving", + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "databricks/databricks-gte-large-en": { + "input_cost_per_token": 1.2999e-07, + "input_dbu_cost_per_token": 1.857e-06, + "litellm_provider": "databricks", + "max_input_tokens": 8192, + "max_tokens": 8192, + "metadata": { + "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." + }, + "mode": "embedding", + "output_cost_per_token": 0.0, + "output_dbu_cost_per_token": 0.0, + "output_vector_size": 1024, + "source": "https://www.databricks.com/product/pricing/foundation-model-serving" + }, + "databricks/databricks-llama-2-70b-chat": { + "input_cost_per_token": 5.0001e-07, + "input_dbu_cost_per_token": 7.143e-06, + "litellm_provider": "databricks", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "metadata": { + "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." + }, + "mode": "chat", + "output_cost_per_token": 1.5e-06, + "output_dbu_cost_per_token": 2.1429e-05, + "source": "https://www.databricks.com/product/pricing/foundation-model-serving", + "supports_tool_choice": true + }, + "databricks/databricks-llama-4-maverick": { + "input_cost_per_token": 5e-06, + "input_dbu_cost_per_token": 7.143e-05, + "litellm_provider": "databricks", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "metadata": { + "notes": "Databricks documentation now provides both DBU costs (_dbu_cost_per_token) and dollar costs(_cost_per_token)." + }, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "output_dbu_cost_per_token": 0.00021429, + "source": "https://www.databricks.com/product/pricing/foundation-model-serving", + "supports_tool_choice": true + }, + "databricks/databricks-meta-llama-3-1-405b-instruct": { + "input_cost_per_token": 5e-06, + "input_dbu_cost_per_token": 7.1429e-05, + "litellm_provider": "databricks", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "metadata": { + "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." + }, + "mode": "chat", + "output_cost_per_token": 1.500002e-05, + "output_db_cost_per_token": 0.000214286, + "source": "https://www.databricks.com/product/pricing/foundation-model-serving", + "supports_tool_choice": true + }, + "databricks/databricks-meta-llama-3-3-70b-instruct": { + "input_cost_per_token": 1.00002e-06, + "input_dbu_cost_per_token": 1.4286e-05, + "litellm_provider": "databricks", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "metadata": { + "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." + }, + "mode": "chat", + "output_cost_per_token": 2.99999e-06, + "output_dbu_cost_per_token": 4.2857e-05, + "source": "https://www.databricks.com/product/pricing/foundation-model-serving", + "supports_tool_choice": true + }, + "databricks/databricks-meta-llama-3-70b-instruct": { + "input_cost_per_token": 1.00002e-06, + "input_dbu_cost_per_token": 1.4286e-05, + "litellm_provider": "databricks", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "metadata": { + "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." + }, + "mode": "chat", + "output_cost_per_token": 2.99999e-06, + "output_dbu_cost_per_token": 4.2857e-05, + "source": "https://www.databricks.com/product/pricing/foundation-model-serving", + "supports_tool_choice": true + }, + "databricks/databricks-mixtral-8x7b-instruct": { + "input_cost_per_token": 5.0001e-07, + "input_dbu_cost_per_token": 7.143e-06, + "litellm_provider": "databricks", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "metadata": { + "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." + }, + "mode": "chat", + "output_cost_per_token": 9.9902e-07, + "output_dbu_cost_per_token": 1.4286e-05, + "source": "https://www.databricks.com/product/pricing/foundation-model-serving", + "supports_tool_choice": true + }, + "databricks/databricks-mpt-30b-instruct": { + "input_cost_per_token": 9.9902e-07, + "input_dbu_cost_per_token": 1.4286e-05, + "litellm_provider": "databricks", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "metadata": { + "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." + }, + "mode": "chat", + "output_cost_per_token": 9.9902e-07, + "output_dbu_cost_per_token": 1.4286e-05, + "source": "https://www.databricks.com/product/pricing/foundation-model-serving", + "supports_tool_choice": true + }, + "databricks/databricks-mpt-7b-instruct": { + "input_cost_per_token": 5.0001e-07, + "input_dbu_cost_per_token": 7.143e-06, + "litellm_provider": "databricks", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "metadata": { + "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." + }, + "mode": "chat", + "output_cost_per_token": 0.0, + "output_dbu_cost_per_token": 0.0, + "source": "https://www.databricks.com/product/pricing/foundation-model-serving", + "supports_tool_choice": true + }, + "davinci-002": { + "input_cost_per_token": 2e-06, + "litellm_provider": "text-completion-openai", + "max_input_tokens": 16384, + "max_output_tokens": 4096, + "max_tokens": 16384, + "mode": "completion", + "output_cost_per_token": 2e-06 + }, + "deepgram/base": { + "input_cost_per_second": 0.00020833, + "litellm_provider": "deepgram", + "metadata": { + "calculation": "$0.0125/60 seconds = $0.00020833 per second", + "original_pricing_per_minute": 0.0125 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "deepgram/base-conversationalai": { + "input_cost_per_second": 0.00020833, + "litellm_provider": "deepgram", + "metadata": { + "calculation": "$0.0125/60 seconds = $0.00020833 per second", + "original_pricing_per_minute": 0.0125 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "deepgram/base-finance": { + "input_cost_per_second": 0.00020833, + "litellm_provider": "deepgram", + "metadata": { + "calculation": "$0.0125/60 seconds = $0.00020833 per second", + "original_pricing_per_minute": 0.0125 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "deepgram/base-general": { + "input_cost_per_second": 0.00020833, + "litellm_provider": "deepgram", + "metadata": { + "calculation": "$0.0125/60 seconds = $0.00020833 per second", + "original_pricing_per_minute": 0.0125 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "deepgram/base-meeting": { + "input_cost_per_second": 0.00020833, + "litellm_provider": "deepgram", + "metadata": { + "calculation": "$0.0125/60 seconds = $0.00020833 per second", + "original_pricing_per_minute": 0.0125 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "deepgram/base-phonecall": { + "input_cost_per_second": 0.00020833, + "litellm_provider": "deepgram", + "metadata": { + "calculation": "$0.0125/60 seconds = $0.00020833 per second", + "original_pricing_per_minute": 0.0125 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "deepgram/base-video": { + "input_cost_per_second": 0.00020833, + "litellm_provider": "deepgram", + "metadata": { + "calculation": "$0.0125/60 seconds = $0.00020833 per second", + "original_pricing_per_minute": 0.0125 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "deepgram/base-voicemail": { + "input_cost_per_second": 0.00020833, + "litellm_provider": "deepgram", + "metadata": { + "calculation": "$0.0125/60 seconds = $0.00020833 per second", + "original_pricing_per_minute": 0.0125 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "deepgram/enhanced": { + "input_cost_per_second": 0.00024167, + "litellm_provider": "deepgram", + "metadata": { + "calculation": "$0.0145/60 seconds = $0.00024167 per second", + "original_pricing_per_minute": 0.0145 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "deepgram/enhanced-finance": { + "input_cost_per_second": 0.00024167, + "litellm_provider": "deepgram", + "metadata": { + "calculation": "$0.0145/60 seconds = $0.00024167 per second", + "original_pricing_per_minute": 0.0145 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "deepgram/enhanced-general": { + "input_cost_per_second": 0.00024167, + "litellm_provider": "deepgram", + "metadata": { + "calculation": "$0.0145/60 seconds = $0.00024167 per second", + "original_pricing_per_minute": 0.0145 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "deepgram/enhanced-meeting": { + "input_cost_per_second": 0.00024167, + "litellm_provider": "deepgram", + "metadata": { + "calculation": "$0.0145/60 seconds = $0.00024167 per second", + "original_pricing_per_minute": 0.0145 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "deepgram/enhanced-phonecall": { + "input_cost_per_second": 0.00024167, + "litellm_provider": "deepgram", + "metadata": { + "calculation": "$0.0145/60 seconds = $0.00024167 per second", + "original_pricing_per_minute": 0.0145 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "deepgram/nova": { + "input_cost_per_second": 7.167e-05, + "litellm_provider": "deepgram", + "metadata": { + "calculation": "$0.0043/60 seconds = $0.00007167 per second", + "original_pricing_per_minute": 0.0043 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "deepgram/nova-2": { + "input_cost_per_second": 7.167e-05, + "litellm_provider": "deepgram", + "metadata": { + "calculation": "$0.0043/60 seconds = $0.00007167 per second", + "original_pricing_per_minute": 0.0043 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "deepgram/nova-2-atc": { + "input_cost_per_second": 7.167e-05, + "litellm_provider": "deepgram", + "metadata": { + "calculation": "$0.0043/60 seconds = $0.00007167 per second", + "original_pricing_per_minute": 0.0043 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "deepgram/nova-2-automotive": { + "input_cost_per_second": 7.167e-05, + "litellm_provider": "deepgram", + "metadata": { + "calculation": "$0.0043/60 seconds = $0.00007167 per second", + "original_pricing_per_minute": 0.0043 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "deepgram/nova-2-conversationalai": { + "input_cost_per_second": 7.167e-05, + "litellm_provider": "deepgram", + "metadata": { + "calculation": "$0.0043/60 seconds = $0.00007167 per second", + "original_pricing_per_minute": 0.0043 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "deepgram/nova-2-drivethru": { + "input_cost_per_second": 7.167e-05, + "litellm_provider": "deepgram", + "metadata": { + "calculation": "$0.0043/60 seconds = $0.00007167 per second", + "original_pricing_per_minute": 0.0043 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "deepgram/nova-2-finance": { + "input_cost_per_second": 7.167e-05, + "litellm_provider": "deepgram", + "metadata": { + "calculation": "$0.0043/60 seconds = $0.00007167 per second", + "original_pricing_per_minute": 0.0043 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "deepgram/nova-2-general": { + "input_cost_per_second": 7.167e-05, + "litellm_provider": "deepgram", + "metadata": { + "calculation": "$0.0043/60 seconds = $0.00007167 per second", + "original_pricing_per_minute": 0.0043 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "deepgram/nova-2-meeting": { + "input_cost_per_second": 7.167e-05, + "litellm_provider": "deepgram", + "metadata": { + "calculation": "$0.0043/60 seconds = $0.00007167 per second", + "original_pricing_per_minute": 0.0043 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "deepgram/nova-2-phonecall": { + "input_cost_per_second": 7.167e-05, + "litellm_provider": "deepgram", + "metadata": { + "calculation": "$0.0043/60 seconds = $0.00007167 per second", + "original_pricing_per_minute": 0.0043 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "deepgram/nova-2-video": { + "input_cost_per_second": 7.167e-05, + "litellm_provider": "deepgram", + "metadata": { + "calculation": "$0.0043/60 seconds = $0.00007167 per second", + "original_pricing_per_minute": 0.0043 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "deepgram/nova-2-voicemail": { + "input_cost_per_second": 7.167e-05, + "litellm_provider": "deepgram", + "metadata": { + "calculation": "$0.0043/60 seconds = $0.00007167 per second", + "original_pricing_per_minute": 0.0043 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "deepgram/nova-3": { + "input_cost_per_second": 7.167e-05, + "litellm_provider": "deepgram", + "metadata": { + "calculation": "$0.0043/60 seconds = $0.00007167 per second", + "original_pricing_per_minute": 0.0043 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "deepgram/nova-3-general": { + "input_cost_per_second": 7.167e-05, + "litellm_provider": "deepgram", + "metadata": { + "calculation": "$0.0043/60 seconds = $0.00007167 per second", + "original_pricing_per_minute": 0.0043 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "deepgram/nova-3-medical": { + "input_cost_per_second": 8.667e-05, + "litellm_provider": "deepgram", + "metadata": { + "calculation": "$0.0052/60 seconds = $0.00008667 per second (multilingual)", + "original_pricing_per_minute": 0.0052 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "deepgram/nova-general": { + "input_cost_per_second": 7.167e-05, + "litellm_provider": "deepgram", + "metadata": { + "calculation": "$0.0043/60 seconds = $0.00007167 per second", + "original_pricing_per_minute": 0.0043 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "deepgram/nova-phonecall": { + "input_cost_per_second": 7.167e-05, + "litellm_provider": "deepgram", + "metadata": { + "calculation": "$0.0043/60 seconds = $0.00007167 per second", + "original_pricing_per_minute": 0.0043 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "deepgram/whisper": { + "input_cost_per_second": 0.0001, + "litellm_provider": "deepgram", + "metadata": { + "notes": "Deepgram's hosted OpenAI Whisper models - pricing may differ from native Deepgram models" + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "deepgram/whisper-base": { + "input_cost_per_second": 0.0001, + "litellm_provider": "deepgram", + "metadata": { + "notes": "Deepgram's hosted OpenAI Whisper models - pricing may differ from native Deepgram models" + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "deepgram/whisper-large": { + "input_cost_per_second": 0.0001, + "litellm_provider": "deepgram", + "metadata": { + "notes": "Deepgram's hosted OpenAI Whisper models - pricing may differ from native Deepgram models" + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "deepgram/whisper-medium": { + "input_cost_per_second": 0.0001, + "litellm_provider": "deepgram", + "metadata": { + "notes": "Deepgram's hosted OpenAI Whisper models - pricing may differ from native Deepgram models" + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "deepgram/whisper-small": { + "input_cost_per_second": 0.0001, + "litellm_provider": "deepgram", + "metadata": { + "notes": "Deepgram's hosted OpenAI Whisper models - pricing may differ from native Deepgram models" + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "deepgram/whisper-tiny": { + "input_cost_per_second": 0.0001, + "litellm_provider": "deepgram", + "metadata": { + "notes": "Deepgram's hosted OpenAI Whisper models - pricing may differ from native Deepgram models" + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://deepgram.com/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "deepinfra/Gryphe/MythoMax-L2-13b": { + "input_cost_per_token": 7.2e-08, + "litellm_provider": "deepinfra", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 7.2e-08, + "supports_tool_choice": true + }, + "deepinfra/NousResearch/Hermes-3-Llama-3.1-405B": { + "input_cost_per_token": 7e-07, + "litellm_provider": "deepinfra", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 8e-07, + "supports_tool_choice": true + }, + "deepinfra/NousResearch/Hermes-3-Llama-3.1-70B": { + "input_cost_per_token": 1e-07, + "litellm_provider": "deepinfra", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2.8e-07, + "supports_tool_choice": false + }, + "deepinfra/Qwen/QwQ-32B": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "deepinfra", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4e-07, + "supports_tool_choice": true + }, + "deepinfra/Qwen/Qwen2.5-72B-Instruct": { + "input_cost_per_token": 1.2e-07, + "litellm_provider": "deepinfra", + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 3.9e-07, + "supports_tool_choice": true + }, + "deepinfra/Qwen/Qwen2.5-7B-Instruct": { + "input_cost_per_token": 4e-08, + "litellm_provider": "deepinfra", + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 1e-07, + "supports_tool_choice": false + }, + "deepinfra/Qwen/Qwen2.5-VL-32B-Instruct": { + "input_cost_per_token": 2e-07, + "litellm_provider": "deepinfra", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 6e-07, + "supports_tool_choice": true + }, + "deepinfra/Qwen/Qwen3-14B": { + "input_cost_per_token": 6e-08, + "litellm_provider": "deepinfra", + "max_input_tokens": 40960, + "max_output_tokens": 40960, + "max_tokens": 40960, + "mode": "chat", + "output_cost_per_token": 2.4e-07, + "supports_tool_choice": true + }, + "deepinfra/Qwen/Qwen3-235B-A22B": { + "input_cost_per_token": 1.3e-07, + "litellm_provider": "deepinfra", + "max_input_tokens": 40960, + "max_output_tokens": 40960, + "max_tokens": 40960, + "mode": "chat", + "output_cost_per_token": 6e-07, + "supports_tool_choice": true + }, + "deepinfra/Qwen/Qwen3-235B-A22B-Instruct-2507": { + "input_cost_per_token": 1.3e-07, + "litellm_provider": "deepinfra", + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 6e-07, + "supports_tool_choice": true + }, + "deepinfra/Qwen/Qwen3-235B-A22B-Thinking-2507": { + "input_cost_per_token": 1.3e-07, + "litellm_provider": "deepinfra", + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 6e-07, + "supports_tool_choice": true + }, + "deepinfra/Qwen/Qwen3-30B-A3B": { + "input_cost_per_token": 8e-08, + "litellm_provider": "deepinfra", + "max_input_tokens": 40960, + "max_output_tokens": 40960, + "max_tokens": 40960, + "mode": "chat", + "output_cost_per_token": 2.9e-07, + "supports_tool_choice": true + }, + "deepinfra/Qwen/Qwen3-32B": { + "input_cost_per_token": 1e-07, + "litellm_provider": "deepinfra", + "max_input_tokens": 40960, + "max_output_tokens": 40960, + "max_tokens": 40960, + "mode": "chat", + "output_cost_per_token": 3e-07, + "supports_tool_choice": true + }, + "deepinfra/Qwen/Qwen3-Coder-480B-A35B-Instruct": { + "input_cost_per_token": 4e-07, + "litellm_provider": "deepinfra", + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 1.6e-06, + "supports_tool_choice": true + }, + "deepinfra/Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo": { + "cache_read_input_token_cost": 2.4e-07, + "input_cost_per_token": 3e-07, + "litellm_provider": "deepinfra", + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "supports_tool_choice": true + }, + "deepinfra/Sao10K/L3-8B-Lunaris-v1-Turbo": { + "input_cost_per_token": 2e-08, + "litellm_provider": "deepinfra", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 5e-08, + "supports_tool_choice": false + }, + "deepinfra/Sao10K/L3.1-70B-Euryale-v2.2": { + "input_cost_per_token": 6.5e-07, + "litellm_provider": "deepinfra", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 7.5e-07, + "supports_tool_choice": false + }, + "deepinfra/Sao10K/L3.3-70B-Euryale-v2.3": { + "input_cost_per_token": 6.5e-07, + "litellm_provider": "deepinfra", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 7.5e-07, + "supports_tool_choice": false + }, + "deepinfra/allenai/olmOCR-7B-0725-FP8": { + "input_cost_per_token": 2.7e-07, + "litellm_provider": "deepinfra", + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1.5e-06, + "supports_tool_choice": false + }, + "deepinfra/anthropic/claude-3-7-sonnet-latest": { + "cache_read_input_token_cost": 3.3e-07, + "input_cost_per_token": 3.3e-06, + "litellm_provider": "deepinfra", + "max_input_tokens": 200000, + "max_output_tokens": 200000, + "max_tokens": 200000, + "mode": "chat", + "output_cost_per_token": 1.65e-05, + "supports_tool_choice": true + }, + "deepinfra/anthropic/claude-4-opus": { + "input_cost_per_token": 1.65e-05, + "litellm_provider": "deepinfra", + "max_input_tokens": 200000, + "max_output_tokens": 200000, + "max_tokens": 200000, + "mode": "chat", + "output_cost_per_token": 8.25e-05, + "supports_tool_choice": true + }, + "deepinfra/anthropic/claude-4-sonnet": { + "input_cost_per_token": 3.3e-06, + "litellm_provider": "deepinfra", + "max_input_tokens": 200000, + "max_output_tokens": 200000, + "max_tokens": 200000, + "mode": "chat", + "output_cost_per_token": 1.65e-05, + "supports_tool_choice": true + }, + "deepinfra/deepseek-ai/DeepSeek-R1": { + "input_cost_per_token": 7e-07, + "litellm_provider": "deepinfra", + "max_input_tokens": 163840, + "max_output_tokens": 163840, + "max_tokens": 163840, + "mode": "chat", + "output_cost_per_token": 2.4e-06, + "supports_tool_choice": true + }, + "deepinfra/deepseek-ai/DeepSeek-R1-0528": { + "cache_read_input_token_cost": 4e-07, + "input_cost_per_token": 5e-07, + "litellm_provider": "deepinfra", + "max_input_tokens": 163840, + "max_output_tokens": 163840, + "max_tokens": 163840, + "mode": "chat", + "output_cost_per_token": 2.15e-06, + "supports_tool_choice": true + }, + "deepinfra/deepseek-ai/DeepSeek-R1-0528-Turbo": { + "input_cost_per_token": 1e-06, + "litellm_provider": "deepinfra", + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 3e-06, + "supports_tool_choice": true + }, + "deepinfra/deepseek-ai/DeepSeek-R1-Distill-Llama-70B": { + "input_cost_per_token": 1e-07, + "litellm_provider": "deepinfra", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4e-07, + "supports_tool_choice": false + }, + "deepinfra/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B": { + "input_cost_per_token": 7.5e-08, + "litellm_provider": "deepinfra", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.5e-07, + "supports_tool_choice": true + }, + "deepinfra/deepseek-ai/DeepSeek-R1-Turbo": { + "input_cost_per_token": 1e-06, + "litellm_provider": "deepinfra", + "max_input_tokens": 40960, + "max_output_tokens": 40960, + "max_tokens": 40960, + "mode": "chat", + "output_cost_per_token": 3e-06, + "supports_tool_choice": true + }, + "deepinfra/deepseek-ai/DeepSeek-V3": { + "input_cost_per_token": 3.8e-07, + "litellm_provider": "deepinfra", + "max_input_tokens": 163840, + "max_output_tokens": 163840, + "max_tokens": 163840, + "mode": "chat", + "output_cost_per_token": 8.9e-07, + "supports_tool_choice": true + }, + "deepinfra/deepseek-ai/DeepSeek-V3-0324": { + "cache_read_input_token_cost": 2.24e-07, + "input_cost_per_token": 2.8e-07, + "litellm_provider": "deepinfra", + "max_input_tokens": 163840, + "max_output_tokens": 163840, + "max_tokens": 163840, + "mode": "chat", + "output_cost_per_token": 8.8e-07, + "supports_tool_choice": true + }, + "deepinfra/deepseek-ai/DeepSeek-V3.1": { + "cache_read_input_token_cost": 2.16e-07, + "input_cost_per_token": 2.7e-07, + "litellm_provider": "deepinfra", + "max_input_tokens": 163840, + "max_output_tokens": 163840, + "max_tokens": 163840, + "mode": "chat", + "output_cost_per_token": 1e-06, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "deepinfra/google/gemini-2.0-flash-001": { + "input_cost_per_token": 1e-07, + "litellm_provider": "deepinfra", + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "max_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 4e-07, + "supports_tool_choice": true + }, + "deepinfra/google/gemini-2.5-flash": { + "input_cost_per_token": 2.1e-07, + "litellm_provider": "deepinfra", + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "max_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 1.75e-06, + "supports_tool_choice": true + }, + "deepinfra/google/gemini-2.5-pro": { + "input_cost_per_token": 8.75e-07, + "litellm_provider": "deepinfra", + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "max_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 7e-06, + "supports_tool_choice": true + }, + "deepinfra/google/gemma-3-12b-it": { + "input_cost_per_token": 5e-08, + "litellm_provider": "deepinfra", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1e-07, + "supports_tool_choice": true + }, + "deepinfra/google/gemma-3-27b-it": { + "input_cost_per_token": 9e-08, + "litellm_provider": "deepinfra", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.7e-07, + "supports_tool_choice": true + }, + "deepinfra/google/gemma-3-4b-it": { + "input_cost_per_token": 4e-08, + "litellm_provider": "deepinfra", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 8e-08, + "supports_tool_choice": true + }, + "deepinfra/meta-llama/Llama-3.2-11B-Vision-Instruct": { + "input_cost_per_token": 4.9e-08, + "litellm_provider": "deepinfra", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4.9e-08, + "supports_tool_choice": false + }, + "deepinfra/meta-llama/Llama-3.2-3B-Instruct": { + "input_cost_per_token": 1.2e-08, + "litellm_provider": "deepinfra", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2.4e-08, + "supports_tool_choice": true + }, + "deepinfra/meta-llama/Llama-3.3-70B-Instruct": { + "input_cost_per_token": 2.3e-07, + "litellm_provider": "deepinfra", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4e-07, + "supports_tool_choice": true + }, + "deepinfra/meta-llama/Llama-3.3-70B-Instruct-Turbo": { + "input_cost_per_token": 3.8e-08, + "litellm_provider": "deepinfra", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.2e-07, + "supports_tool_choice": true + }, + "deepinfra/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "deepinfra", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 6e-07, + "supports_tool_choice": true + }, + "deepinfra/meta-llama/Llama-4-Scout-17B-16E-Instruct": { + "input_cost_per_token": 8e-08, + "litellm_provider": "deepinfra", + "max_input_tokens": 327680, + "max_output_tokens": 327680, + "max_tokens": 327680, + "mode": "chat", + "output_cost_per_token": 3e-07, + "supports_tool_choice": true + }, + "deepinfra/meta-llama/Llama-Guard-3-8B": { + "input_cost_per_token": 5.5e-08, + "litellm_provider": "deepinfra", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 5.5e-08, + "supports_tool_choice": false + }, + "deepinfra/meta-llama/Llama-Guard-4-12B": { + "input_cost_per_token": 1.8e-07, + "litellm_provider": "deepinfra", + "max_input_tokens": 163840, + "max_output_tokens": 163840, + "max_tokens": 163840, + "mode": "chat", + "output_cost_per_token": 1.8e-07, + "supports_tool_choice": false + }, + "deepinfra/meta-llama/Meta-Llama-3-8B-Instruct": { + "input_cost_per_token": 3e-08, + "litellm_provider": "deepinfra", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 6e-08, + "supports_tool_choice": true + }, + "deepinfra/meta-llama/Meta-Llama-3.1-70B-Instruct": { + "input_cost_per_token": 2.3e-07, + "litellm_provider": "deepinfra", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4e-07, + "supports_tool_choice": true + }, + "deepinfra/meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo": { + "input_cost_per_token": 1e-07, + "litellm_provider": "deepinfra", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2.8e-07, + "supports_tool_choice": true + }, + "deepinfra/meta-llama/Meta-Llama-3.1-8B-Instruct": { + "input_cost_per_token": 3e-08, + "litellm_provider": "deepinfra", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 5e-08, + "supports_tool_choice": true + }, + "deepinfra/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo": { + "input_cost_per_token": 1.5e-08, + "litellm_provider": "deepinfra", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2e-08, + "supports_tool_choice": true + }, + "deepinfra/microsoft/WizardLM-2-8x22B": { + "input_cost_per_token": 4.8e-07, + "litellm_provider": "deepinfra", + "max_input_tokens": 65536, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 4.8e-07, + "supports_tool_choice": false + }, + "deepinfra/microsoft/phi-4": { + "input_cost_per_token": 7e-08, + "litellm_provider": "deepinfra", + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1.4e-07, + "supports_tool_choice": true + }, + "deepinfra/mistralai/Mistral-Nemo-Instruct-2407": { + "input_cost_per_token": 2e-08, + "litellm_provider": "deepinfra", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4e-08, + "supports_tool_choice": true + }, + "deepinfra/mistralai/Mistral-Small-24B-Instruct-2501": { + "input_cost_per_token": 5e-08, + "litellm_provider": "deepinfra", + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 8e-08, + "supports_tool_choice": true + }, + "deepinfra/mistralai/Mistral-Small-3.2-24B-Instruct-2506": { + "input_cost_per_token": 5e-08, + "litellm_provider": "deepinfra", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-07, + "supports_tool_choice": true + }, + "deepinfra/mistralai/Mixtral-8x7B-Instruct-v0.1": { + "input_cost_per_token": 8e-08, + "litellm_provider": "deepinfra", + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 2.4e-07, + "supports_tool_choice": true + }, + "deepinfra/moonshotai/Kimi-K2-Instruct": { + "input_cost_per_token": 5e-07, + "litellm_provider": "deepinfra", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2e-06, + "supports_tool_choice": true + }, + "deepinfra/nvidia/Llama-3.1-Nemotron-70B-Instruct": { + "input_cost_per_token": 1.2e-07, + "litellm_provider": "deepinfra", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 3e-07, + "supports_tool_choice": true + }, + "deepinfra/openai/gpt-oss-120b": { + "input_cost_per_token": 9e-08, + "litellm_provider": "deepinfra", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4.5e-07, + "supports_tool_choice": true + }, + "deepinfra/openai/gpt-oss-20b": { + "input_cost_per_token": 4e-08, + "litellm_provider": "deepinfra", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.6e-07, + "supports_tool_choice": true + }, + "deepinfra/zai-org/GLM-4.5": { + "input_cost_per_token": 5.5e-07, + "litellm_provider": "deepinfra", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2e-06, + "supports_tool_choice": true + }, + "deepinfra/zai-org/GLM-4.5-Air": { + "input_cost_per_token": 2e-07, + "litellm_provider": "deepinfra", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.1e-06, + "supports_tool_choice": true + }, + "deepseek/deepseek-chat": { + "cache_creation_input_token_cost": 0.0, + "cache_read_input_token_cost": 7e-08, + "input_cost_per_token": 2.7e-07, + "input_cost_per_token_cache_hit": 7e-08, + "litellm_provider": "deepseek", + "max_input_tokens": 65536, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.1e-06, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_tool_choice": true + }, + "deepseek/deepseek-coder": { + "input_cost_per_token": 1.4e-07, + "input_cost_per_token_cache_hit": 1.4e-08, + "litellm_provider": "deepseek", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 2.8e-07, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_tool_choice": true + }, + "deepseek/deepseek-r1": { + "input_cost_per_token": 5.5e-07, + "input_cost_per_token_cache_hit": 1.4e-07, + "litellm_provider": "deepseek", + "max_input_tokens": 65536, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 2.19e-06, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "deepseek/deepseek-reasoner": { + "input_cost_per_token": 5.5e-07, + "input_cost_per_token_cache_hit": 1.4e-07, + "litellm_provider": "deepseek", + "max_input_tokens": 65536, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 2.19e-06, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "deepseek/deepseek-v3": { + "cache_creation_input_token_cost": 0.0, + "cache_read_input_token_cost": 7e-08, + "input_cost_per_token": 2.7e-07, + "input_cost_per_token_cache_hit": 7e-08, + "litellm_provider": "deepseek", + "max_input_tokens": 65536, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.1e-06, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_tool_choice": true + }, + "dolphin": { + "input_cost_per_token": 5e-07, + "litellm_provider": "nlp_cloud", + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "completion", + "output_cost_per_token": 5e-07 + }, + "doubao-embedding": { + "input_cost_per_token": 0.0, + "litellm_provider": "volcengine", + "max_input_tokens": 4096, + "max_tokens": 4096, + "metadata": { + "notes": "Volcengine Doubao embedding model - standard version with 2560 dimensions" + }, + "mode": "embedding", + "output_cost_per_token": 0.0, + "output_vector_size": 2560 + }, + "doubao-embedding-large": { + "input_cost_per_token": 0.0, + "litellm_provider": "volcengine", + "max_input_tokens": 4096, + "max_tokens": 4096, + "metadata": { + "notes": "Volcengine Doubao embedding model - large version with 2048 dimensions" + }, + "mode": "embedding", + "output_cost_per_token": 0.0, + "output_vector_size": 2048 + }, + "doubao-embedding-large-text-240915": { + "input_cost_per_token": 0.0, + "litellm_provider": "volcengine", + "max_input_tokens": 4096, + "max_tokens": 4096, + "metadata": { + "notes": "Volcengine Doubao embedding model - text-240915 version with 4096 dimensions" + }, + "mode": "embedding", + "output_cost_per_token": 0.0, + "output_vector_size": 4096 + }, + "doubao-embedding-large-text-250515": { + "input_cost_per_token": 0.0, + "litellm_provider": "volcengine", + "max_input_tokens": 4096, + "max_tokens": 4096, + "metadata": { + "notes": "Volcengine Doubao embedding model - text-250515 version with 2048 dimensions" + }, + "mode": "embedding", + "output_cost_per_token": 0.0, + "output_vector_size": 2048 + }, + "doubao-embedding-text-240715": { + "input_cost_per_token": 0.0, + "litellm_provider": "volcengine", + "max_input_tokens": 4096, + "max_tokens": 4096, + "metadata": { + "notes": "Volcengine Doubao embedding model - text-240715 version with 2560 dimensions" + }, + "mode": "embedding", + "output_cost_per_token": 0.0, + "output_vector_size": 2560 + }, + "elevenlabs/scribe_v1": { + "input_cost_per_second": 6.11e-05, + "litellm_provider": "elevenlabs", + "metadata": { + "calculation": "$0.22/hour = $0.00366/minute = $0.0000611 per second (enterprise pricing)", + "notes": "ElevenLabs Scribe v1 - state-of-the-art speech recognition model with 99 language support", + "original_pricing_per_hour": 0.22 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://elevenlabs.io/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "elevenlabs/scribe_v1_experimental": { + "input_cost_per_second": 6.11e-05, + "litellm_provider": "elevenlabs", + "metadata": { + "calculation": "$0.22/hour = $0.00366/minute = $0.0000611 per second (enterprise pricing)", + "notes": "ElevenLabs Scribe v1 experimental - enhanced version of the main Scribe model", + "original_pricing_per_hour": 0.22 + }, + "mode": "audio_transcription", + "output_cost_per_second": 0.0, + "source": "https://elevenlabs.io/pricing", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "embed-english-light-v2.0": { + "input_cost_per_token": 1e-07, + "litellm_provider": "cohere", + "max_input_tokens": 1024, + "max_tokens": 1024, + "mode": "embedding", + "output_cost_per_token": 0.0 + }, + "embed-english-light-v3.0": { + "input_cost_per_token": 1e-07, + "litellm_provider": "cohere", + "max_input_tokens": 1024, + "max_tokens": 1024, + "mode": "embedding", + "output_cost_per_token": 0.0 + }, + "embed-english-v2.0": { + "input_cost_per_token": 1e-07, + "litellm_provider": "cohere", + "max_input_tokens": 4096, + "max_tokens": 4096, + "mode": "embedding", + "output_cost_per_token": 0.0 + }, + "embed-english-v3.0": { + "input_cost_per_image": 0.0001, + "input_cost_per_token": 1e-07, + "litellm_provider": "cohere", + "max_input_tokens": 1024, + "max_tokens": 1024, + "metadata": { + "notes": "'supports_image_input' is a deprecated field. Use 'supports_embedding_image_input' instead." + }, + "mode": "embedding", + "output_cost_per_token": 0.0, + "supports_embedding_image_input": true, + "supports_image_input": true + }, + "embed-multilingual-v2.0": { + "input_cost_per_token": 1e-07, + "litellm_provider": "cohere", + "max_input_tokens": 768, + "max_tokens": 768, + "mode": "embedding", + "output_cost_per_token": 0.0 + }, + "embed-multilingual-v3.0": { + "input_cost_per_token": 1e-07, + "litellm_provider": "cohere", + "max_input_tokens": 1024, + "max_tokens": 1024, + "mode": "embedding", + "output_cost_per_token": 0.0, + "supports_embedding_image_input": true + }, + "eu.amazon.nova-lite-v1:0": { + "input_cost_per_token": 7.8e-08, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 300000, + "max_output_tokens": 10000, + "max_tokens": 10000, + "mode": "chat", + "output_cost_per_token": 3.12e-07, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_vision": true + }, + "eu.amazon.nova-micro-v1:0": { + "input_cost_per_token": 4.6e-08, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 128000, + "max_output_tokens": 10000, + "max_tokens": 10000, + "mode": "chat", + "output_cost_per_token": 1.84e-07, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true + }, + "eu.amazon.nova-pro-v1:0": { + "input_cost_per_token": 1.05e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 300000, + "max_output_tokens": 10000, + "max_tokens": 10000, + "mode": "chat", + "output_cost_per_token": 4.2e-06, + "source": "https://aws.amazon.com/bedrock/pricing/", + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_vision": true + }, + "eu.anthropic.claude-3-5-haiku-20241022-v1:0": { + "input_cost_per_token": 2.5e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.25e-06, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "eu.anthropic.claude-3-5-sonnet-20240620-v1:0": { + "input_cost_per_token": 3e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "eu.anthropic.claude-3-5-sonnet-20241022-v2:0": { + "input_cost_per_token": 3e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "eu.anthropic.claude-3-7-sonnet-20250219-v1:0": { + "input_cost_per_token": 3e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "eu.anthropic.claude-3-haiku-20240307-v1:0": { + "input_cost_per_token": 2.5e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.25e-06, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "eu.anthropic.claude-3-opus-20240229-v1:0": { + "input_cost_per_token": 1.5e-05, + "litellm_provider": "bedrock", + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 7.5e-05, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "eu.anthropic.claude-3-sonnet-20240229-v1:0": { + "input_cost_per_token": 3e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "eu.anthropic.claude-opus-4-1-20250805-v1:0": { + "cache_creation_input_token_cost": 1.875e-05, + "cache_read_input_token_cost": 1.5e-06, + "input_cost_per_token": 1.5e-05, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 200000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 7.5e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159 + }, + "eu.anthropic.claude-opus-4-20250514-v1:0": { + "cache_creation_input_token_cost": 1.875e-05, + "cache_read_input_token_cost": 1.5e-06, + "input_cost_per_token": 1.5e-05, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 200000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 7.5e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159 + }, + "eu.anthropic.claude-sonnet-4-20250514-v1:0": { + "cache_creation_input_token_cost": 3.75e-06, + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 3e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159 + }, + "eu.meta.llama3-2-1b-instruct-v1:0": { + "input_cost_per_token": 1.3e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.3e-07, + "supports_function_calling": true, + "supports_tool_choice": false + }, + "eu.meta.llama3-2-3b-instruct-v1:0": { + "input_cost_per_token": 1.9e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.9e-07, + "supports_function_calling": true, + "supports_tool_choice": false + }, + "eu.mistral.pixtral-large-2502-v1:0": { + "input_cost_per_token": 2e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 6e-06, + "supports_function_calling": true, + "supports_tool_choice": false + }, + "featherless_ai/featherless-ai/Qwerky-72B": { + "litellm_provider": "featherless_ai", + "max_input_tokens": 32768, + "max_output_tokens": 4096, + "max_tokens": 32768, + "mode": "chat" + }, + "featherless_ai/featherless-ai/Qwerky-QwQ-32B": { + "litellm_provider": "featherless_ai", + "max_input_tokens": 32768, + "max_output_tokens": 4096, + "max_tokens": 32768, + "mode": "chat" + }, + "fireworks-ai-4.1b-to-16b": { + "input_cost_per_token": 2e-07, + "litellm_provider": "fireworks_ai", + "output_cost_per_token": 2e-07 + }, + "fireworks-ai-56b-to-176b": { + "input_cost_per_token": 1.2e-06, + "litellm_provider": "fireworks_ai", + "output_cost_per_token": 1.2e-06 + }, + "fireworks-ai-above-16b": { + "input_cost_per_token": 9e-07, + "litellm_provider": "fireworks_ai", + "output_cost_per_token": 9e-07 + }, + "fireworks-ai-default": { + "input_cost_per_token": 0.0, + "litellm_provider": "fireworks_ai", + "output_cost_per_token": 0.0 + }, + "fireworks-ai-embedding-150m-to-350m": { + "input_cost_per_token": 1.6e-08, + "litellm_provider": "fireworks_ai-embedding-models", + "output_cost_per_token": 0.0 + }, + "fireworks-ai-embedding-up-to-150m": { + "input_cost_per_token": 8e-09, + "litellm_provider": "fireworks_ai-embedding-models", + "output_cost_per_token": 0.0 + }, + "fireworks-ai-moe-up-to-56b": { + "input_cost_per_token": 5e-07, + "litellm_provider": "fireworks_ai", + "output_cost_per_token": 5e-07 + }, + "fireworks-ai-up-to-4b": { + "input_cost_per_token": 2e-07, + "litellm_provider": "fireworks_ai", + "output_cost_per_token": 2e-07 + }, + "fireworks_ai/WhereIsAI/UAE-Large-V1": { + "input_cost_per_token": 1.6e-08, + "litellm_provider": "fireworks_ai-embedding-models", + "max_input_tokens": 512, + "max_tokens": 512, + "mode": "embedding", + "output_cost_per_token": 0.0, + "source": "https://fireworks.ai/pricing" + }, + "fireworks_ai/accounts/fireworks/models/deepseek-coder-v2-instruct": { + "input_cost_per_token": 1.2e-06, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 65536, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://fireworks.ai/pricing", + "supports_function_calling": false, + "supports_response_schema": true, + "supports_tool_choice": false + }, + "fireworks_ai/accounts/fireworks/models/deepseek-r1": { + "input_cost_per_token": 3e-06, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 128000, + "max_output_tokens": 20480, + "max_tokens": 20480, + "mode": "chat", + "output_cost_per_token": 8e-06, + "source": "https://fireworks.ai/pricing", + "supports_response_schema": true, + "supports_tool_choice": false + }, + "fireworks_ai/accounts/fireworks/models/deepseek-r1-0528": { + "input_cost_per_token": 3e-06, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 160000, + "max_output_tokens": 160000, + "max_tokens": 160000, + "mode": "chat", + "output_cost_per_token": 8e-06, + "source": "https://fireworks.ai/pricing", + "supports_response_schema": true, + "supports_tool_choice": false + }, + "fireworks_ai/accounts/fireworks/models/deepseek-r1-basic": { + "input_cost_per_token": 5.5e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 128000, + "max_output_tokens": 20480, + "max_tokens": 20480, + "mode": "chat", + "output_cost_per_token": 2.19e-06, + "source": "https://fireworks.ai/pricing", + "supports_response_schema": true, + "supports_tool_choice": false + }, + "fireworks_ai/accounts/fireworks/models/deepseek-v3": { + "input_cost_per_token": 9e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 9e-07, + "source": "https://fireworks.ai/pricing", + "supports_response_schema": true, + "supports_tool_choice": false + }, + "fireworks_ai/accounts/fireworks/models/deepseek-v3-0324": { + "input_cost_per_token": 9e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 163840, + "max_output_tokens": 163840, + "max_tokens": 163840, + "mode": "chat", + "output_cost_per_token": 9e-07, + "source": "https://fireworks.ai/models/fireworks/deepseek-v3-0324", + "supports_response_schema": true, + "supports_tool_choice": false + }, + "fireworks_ai/accounts/fireworks/models/deepseek-v3p1": { + "input_cost_per_token": 5.6e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.68e-06, + "source": "https://fireworks.ai/pricing", + "supports_response_schema": true, + "supports_tool_choice": true + }, + "fireworks_ai/accounts/fireworks/models/firefunction-v2": { + "input_cost_per_token": 9e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 9e-07, + "source": "https://fireworks.ai/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "fireworks_ai/accounts/fireworks/models/glm-4p5": { + "input_cost_per_token": 5.5e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 128000, + "max_output_tokens": 96000, + "max_tokens": 96000, + "mode": "chat", + "output_cost_per_token": 2.19e-06, + "source": "https://fireworks.ai/models/fireworks/glm-4p5", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "fireworks_ai/accounts/fireworks/models/glm-4p5-air": { + "input_cost_per_token": 2.2e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 128000, + "max_output_tokens": 96000, + "max_tokens": 96000, + "mode": "chat", + "output_cost_per_token": 8.8e-07, + "source": "https://artificialanalysis.ai/models/glm-4-5-air", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "fireworks_ai/accounts/fireworks/models/gpt-oss-120b": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 6e-07, + "source": "https://fireworks.ai/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "fireworks_ai/accounts/fireworks/models/gpt-oss-20b": { + "input_cost_per_token": 5e-08, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2e-07, + "source": "https://fireworks.ai/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "fireworks_ai/accounts/fireworks/models/kimi-k2-instruct": { + "input_cost_per_token": 6e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 131072, + "max_output_tokens": 16384, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2.5e-06, + "source": "https://fireworks.ai/models/fireworks/kimi-k2-instruct", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "fireworks_ai/accounts/fireworks/models/llama-v3p1-405b-instruct": { + "input_cost_per_token": 3e-06, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 3e-06, + "source": "https://fireworks.ai/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "fireworks_ai/accounts/fireworks/models/llama-v3p1-8b-instruct": { + "input_cost_per_token": 1e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1e-07, + "source": "https://fireworks.ai/pricing", + "supports_function_calling": false, + "supports_response_schema": true, + "supports_tool_choice": false + }, + "fireworks_ai/accounts/fireworks/models/llama-v3p2-11b-vision-instruct": { + "input_cost_per_token": 2e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 2e-07, + "source": "https://fireworks.ai/pricing", + "supports_function_calling": false, + "supports_response_schema": true, + "supports_tool_choice": false, + "supports_vision": true + }, + "fireworks_ai/accounts/fireworks/models/llama-v3p2-1b-instruct": { + "input_cost_per_token": 1e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1e-07, + "source": "https://fireworks.ai/pricing", + "supports_function_calling": false, + "supports_response_schema": true, + "supports_tool_choice": false + }, + "fireworks_ai/accounts/fireworks/models/llama-v3p2-3b-instruct": { + "input_cost_per_token": 1e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1e-07, + "source": "https://fireworks.ai/pricing", + "supports_function_calling": false, + "supports_response_schema": true, + "supports_tool_choice": false + }, + "fireworks_ai/accounts/fireworks/models/llama-v3p2-90b-vision-instruct": { + "input_cost_per_token": 9e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 9e-07, + "source": "https://fireworks.ai/pricing", + "supports_response_schema": true, + "supports_tool_choice": false, + "supports_vision": true + }, + "fireworks_ai/accounts/fireworks/models/llama4-maverick-instruct-basic": { + "input_cost_per_token": 2.2e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 8.8e-07, + "source": "https://fireworks.ai/pricing", + "supports_response_schema": true, + "supports_tool_choice": false + }, + "fireworks_ai/accounts/fireworks/models/llama4-scout-instruct-basic": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 6e-07, + "source": "https://fireworks.ai/pricing", + "supports_response_schema": true, + "supports_tool_choice": false + }, + "fireworks_ai/accounts/fireworks/models/mixtral-8x22b-instruct-hf": { + "input_cost_per_token": 1.2e-06, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 65536, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://fireworks.ai/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "fireworks_ai/accounts/fireworks/models/qwen2-72b-instruct": { + "input_cost_per_token": 9e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 9e-07, + "source": "https://fireworks.ai/pricing", + "supports_function_calling": false, + "supports_response_schema": true, + "supports_tool_choice": false + }, + "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-32b-instruct": { + "input_cost_per_token": 9e-07, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 9e-07, + "source": "https://fireworks.ai/pricing", + "supports_function_calling": false, + "supports_response_schema": true, + "supports_tool_choice": false + }, + "fireworks_ai/accounts/fireworks/models/yi-large": { + "input_cost_per_token": 3e-06, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 3e-06, + "source": "https://fireworks.ai/pricing", + "supports_function_calling": false, + "supports_response_schema": true, + "supports_tool_choice": false + }, + "fireworks_ai/nomic-ai/nomic-embed-text-v1": { + "input_cost_per_token": 8e-09, + "litellm_provider": "fireworks_ai-embedding-models", + "max_input_tokens": 8192, + "max_tokens": 8192, + "mode": "embedding", + "output_cost_per_token": 0.0, + "source": "https://fireworks.ai/pricing" + }, + "fireworks_ai/nomic-ai/nomic-embed-text-v1.5": { + "input_cost_per_token": 8e-09, + "litellm_provider": "fireworks_ai-embedding-models", + "max_input_tokens": 8192, + "max_tokens": 8192, + "mode": "embedding", + "output_cost_per_token": 0.0, + "source": "https://fireworks.ai/pricing" + }, + "fireworks_ai/thenlper/gte-base": { + "input_cost_per_token": 8e-09, + "litellm_provider": "fireworks_ai-embedding-models", + "max_input_tokens": 512, + "max_tokens": 512, + "mode": "embedding", + "output_cost_per_token": 0.0, + "source": "https://fireworks.ai/pricing" + }, + "fireworks_ai/thenlper/gte-large": { + "input_cost_per_token": 1.6e-08, + "litellm_provider": "fireworks_ai-embedding-models", + "max_input_tokens": 512, + "max_tokens": 512, + "mode": "embedding", + "output_cost_per_token": 0.0, + "source": "https://fireworks.ai/pricing" + }, + "friendliai/meta-llama-3.1-70b-instruct": { + "input_cost_per_token": 6e-07, + "litellm_provider": "friendliai", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 6e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "friendliai/meta-llama-3.1-8b-instruct": { + "input_cost_per_token": 1e-07, + "litellm_provider": "friendliai", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "ft:babbage-002": { + "input_cost_per_token": 4e-07, + "input_cost_per_token_batches": 2e-07, + "litellm_provider": "text-completion-openai", + "max_input_tokens": 16384, + "max_output_tokens": 4096, + "max_tokens": 16384, + "mode": "completion", + "output_cost_per_token": 4e-07, + "output_cost_per_token_batches": 2e-07 + }, + "ft:davinci-002": { + "input_cost_per_token": 2e-06, + "input_cost_per_token_batches": 1e-06, + "litellm_provider": "text-completion-openai", + "max_input_tokens": 16384, + "max_output_tokens": 4096, + "max_tokens": 16384, + "mode": "completion", + "output_cost_per_token": 2e-06, + "output_cost_per_token_batches": 1e-06 + }, + "ft:gpt-3.5-turbo": { + "input_cost_per_token": 3e-06, + "input_cost_per_token_batches": 1.5e-06, + "litellm_provider": "openai", + "max_input_tokens": 16385, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 6e-06, + "output_cost_per_token_batches": 3e-06, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "ft:gpt-3.5-turbo-0125": { + "input_cost_per_token": 3e-06, + "litellm_provider": "openai", + "max_input_tokens": 16385, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 6e-06, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "ft:gpt-3.5-turbo-0613": { + "input_cost_per_token": 3e-06, + "litellm_provider": "openai", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 6e-06, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "ft:gpt-3.5-turbo-1106": { + "input_cost_per_token": 3e-06, + "litellm_provider": "openai", + "max_input_tokens": 16385, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 6e-06, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "ft:gpt-4-0613": { + "input_cost_per_token": 3e-05, + "litellm_provider": "openai", + "max_input_tokens": 8192, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 6e-05, + "source": "OpenAI needs to add pricing for this ft model, will be updated when added by OpenAI. Defaulting to base model pricing", + "supports_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "ft:gpt-4o-2024-08-06": { + "input_cost_per_token": 3.75e-06, + "input_cost_per_token_batches": 1.875e-06, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "output_cost_per_token_batches": 7.5e-06, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "ft:gpt-4o-2024-11-20": { + "cache_creation_input_token_cost": 1.875e-06, + "input_cost_per_token": 3.75e-06, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "ft:gpt-4o-mini-2024-07-18": { + "cache_read_input_token_cost": 1.5e-07, + "input_cost_per_token": 3e-07, + "input_cost_per_token_batches": 1.5e-07, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "output_cost_per_token_batches": 6e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "gemini-1.0-pro": { + "input_cost_per_character": 1.25e-07, + "input_cost_per_image": 0.0025, + "input_cost_per_token": 5e-07, + "input_cost_per_video_per_second": 0.002, + "litellm_provider": "vertex_ai-language-models", + "max_input_tokens": 32760, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_character": 3.75e-07, + "output_cost_per_token": 1.5e-06, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#google_models", + "supports_function_calling": true, + "supports_parallel_function_calling": true, "supports_tool_choice": true }, "gemini-1.0-pro-001": { - "max_tokens": 8192, + "deprecation_date": "2025-04-09", + "input_cost_per_character": 1.25e-07, + "input_cost_per_image": 0.0025, + "input_cost_per_token": 5e-07, + "input_cost_per_video_per_second": 0.002, + "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 32760, "max_output_tokens": 8192, - "input_cost_per_image": 0.0025, - "input_cost_per_video_per_second": 0.002, - "input_cost_per_token": 5e-07, - "input_cost_per_character": 1.25e-07, - "output_cost_per_token": 1.5e-06, - "output_cost_per_character": 3.75e-07, - "litellm_provider": "vertex_ai-language-models", + "max_tokens": 8192, "mode": "chat", - "supports_function_calling": true, + "output_cost_per_character": 3.75e-07, + "output_cost_per_token": 1.5e-06, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", - "deprecation_date": "2025-04-09", - "supports_tool_choice": true, - "supports_parallel_function_calling": true - }, - "gemini-1.0-ultra": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 2048, - "input_cost_per_image": 0.0025, - "input_cost_per_video_per_second": 0.002, - "input_cost_per_token": 5e-07, - "input_cost_per_character": 1.25e-07, - "output_cost_per_token": 1.5e-06, - "output_cost_per_character": 3.75e-07, - "litellm_provider": "vertex_ai-language-models", - "mode": "chat", "supports_function_calling": true, - "source": "As of Jun, 2024. There is no available doc on vertex ai pricing gemini-1.0-ultra-001. Using gemini-1.0-pro pricing. Got max_tokens info here: https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", - "supports_tool_choice": true, - "supports_parallel_function_calling": true - }, - "gemini-1.0-ultra-001": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 2048, - "input_cost_per_image": 0.0025, - "input_cost_per_video_per_second": 0.002, - "input_cost_per_token": 5e-07, - "input_cost_per_character": 1.25e-07, - "output_cost_per_token": 1.5e-06, - "output_cost_per_character": 3.75e-07, - "litellm_provider": "vertex_ai-language-models", - "mode": "chat", - "supports_function_calling": true, - "source": "As of Jun, 2024. There is no available doc on vertex ai pricing gemini-1.0-ultra-001. Using gemini-1.0-pro pricing. Got max_tokens info here: https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", - "supports_tool_choice": true, - "supports_parallel_function_calling": true + "supports_parallel_function_calling": true, + "supports_tool_choice": true }, "gemini-1.0-pro-002": { - "max_tokens": 8192, + "deprecation_date": "2025-04-09", + "input_cost_per_character": 1.25e-07, + "input_cost_per_image": 0.0025, + "input_cost_per_token": 5e-07, + "input_cost_per_video_per_second": 0.002, + "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 32760, "max_output_tokens": 8192, - "input_cost_per_image": 0.0025, - "input_cost_per_video_per_second": 0.002, - "input_cost_per_token": 5e-07, - "input_cost_per_character": 1.25e-07, - "output_cost_per_token": 1.5e-06, + "max_tokens": 8192, + "mode": "chat", "output_cost_per_character": 3.75e-07, - "litellm_provider": "vertex_ai-language-models", - "mode": "chat", - "supports_function_calling": true, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", - "deprecation_date": "2025-04-09", - "supports_tool_choice": true, - "supports_parallel_function_calling": true - }, - "gemini-1.5-pro": { - "max_tokens": 8192, - "max_input_tokens": 2097152, - "max_output_tokens": 8192, - "input_cost_per_image": 0.00032875, - "input_cost_per_audio_per_second": 3.125e-05, - "input_cost_per_video_per_second": 0.00032875, - "input_cost_per_token": 1.25e-06, - "input_cost_per_character": 3.125e-07, - "input_cost_per_image_above_128k_tokens": 0.0006575, - "input_cost_per_video_per_second_above_128k_tokens": 0.0006575, - "input_cost_per_audio_per_second_above_128k_tokens": 6.25e-05, - "input_cost_per_token_above_128k_tokens": 2.5e-06, - "input_cost_per_character_above_128k_tokens": 6.25e-07, - "output_cost_per_token": 5e-06, - "output_cost_per_character": 1.25e-06, - "output_cost_per_token_above_128k_tokens": 1e-05, - "output_cost_per_character_above_128k_tokens": 2.5e-06, - "litellm_provider": "vertex_ai-language-models", - "mode": "chat", - "supports_vision": true, - "supports_pdf_input": true, - "supports_system_messages": true, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": true, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", - "supports_parallel_function_calling": true - }, - "gemini-1.5-pro-002": { - "max_tokens": 8192, - "max_input_tokens": 2097152, - "max_output_tokens": 8192, - "input_cost_per_image": 0.00032875, - "input_cost_per_audio_per_second": 3.125e-05, - "input_cost_per_video_per_second": 0.00032875, - "input_cost_per_token": 1.25e-06, - "input_cost_per_character": 3.125e-07, - "input_cost_per_image_above_128k_tokens": 0.0006575, - "input_cost_per_video_per_second_above_128k_tokens": 0.0006575, - "input_cost_per_audio_per_second_above_128k_tokens": 6.25e-05, - "input_cost_per_token_above_128k_tokens": 2.5e-06, - "input_cost_per_character_above_128k_tokens": 6.25e-07, - "output_cost_per_token": 5e-06, - "output_cost_per_character": 1.25e-06, - "output_cost_per_token_above_128k_tokens": 1e-05, - "output_cost_per_character_above_128k_tokens": 2.5e-06, - "litellm_provider": "vertex_ai-language-models", - "mode": "chat", - "supports_vision": true, - "supports_system_messages": true, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": true, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-1.5-pro", - "deprecation_date": "2025-09-24", - "supports_parallel_function_calling": true - }, - "gemini-1.5-pro-001": { - "max_tokens": 8192, - "max_input_tokens": 1000000, - "max_output_tokens": 8192, - "input_cost_per_image": 0.00032875, - "input_cost_per_audio_per_second": 3.125e-05, - "input_cost_per_video_per_second": 0.00032875, - "input_cost_per_token": 1.25e-06, - "input_cost_per_character": 3.125e-07, - "input_cost_per_image_above_128k_tokens": 0.0006575, - "input_cost_per_video_per_second_above_128k_tokens": 0.0006575, - "input_cost_per_audio_per_second_above_128k_tokens": 6.25e-05, - "input_cost_per_token_above_128k_tokens": 2.5e-06, - "input_cost_per_character_above_128k_tokens": 6.25e-07, - "output_cost_per_token": 5e-06, - "output_cost_per_character": 1.25e-06, - "output_cost_per_token_above_128k_tokens": 1e-05, - "output_cost_per_character_above_128k_tokens": 2.5e-06, - "litellm_provider": "vertex_ai-language-models", - "mode": "chat", - "supports_vision": true, - "supports_system_messages": true, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": true, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", - "deprecation_date": "2025-05-24", - "supports_parallel_function_calling": true - }, - "gemini-1.5-pro-preview-0514": { - "max_tokens": 8192, - "max_input_tokens": 1000000, - "max_output_tokens": 8192, - "input_cost_per_image": 0.00032875, - "input_cost_per_audio_per_second": 3.125e-05, - "input_cost_per_video_per_second": 0.00032875, - "input_cost_per_token": 7.8125e-08, - "input_cost_per_character": 3.125e-07, - "input_cost_per_image_above_128k_tokens": 0.0006575, - "input_cost_per_video_per_second_above_128k_tokens": 0.0006575, - "input_cost_per_audio_per_second_above_128k_tokens": 6.25e-05, - "input_cost_per_token_above_128k_tokens": 1.5625e-07, - "input_cost_per_character_above_128k_tokens": 6.25e-07, - "output_cost_per_token": 3.125e-07, - "output_cost_per_character": 1.25e-06, - "output_cost_per_token_above_128k_tokens": 6.25e-07, - "output_cost_per_character_above_128k_tokens": 2.5e-06, - "litellm_provider": "vertex_ai-language-models", - "mode": "chat", - "supports_system_messages": true, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": true, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", - "supports_parallel_function_calling": true - }, - "gemini-1.5-pro-preview-0215": { - "max_tokens": 8192, - "max_input_tokens": 1000000, - "max_output_tokens": 8192, - "input_cost_per_image": 0.00032875, - "input_cost_per_audio_per_second": 3.125e-05, - "input_cost_per_video_per_second": 0.00032875, - "input_cost_per_token": 7.8125e-08, - "input_cost_per_character": 3.125e-07, - "input_cost_per_image_above_128k_tokens": 0.0006575, - "input_cost_per_video_per_second_above_128k_tokens": 0.0006575, - "input_cost_per_audio_per_second_above_128k_tokens": 6.25e-05, - "input_cost_per_token_above_128k_tokens": 1.5625e-07, - "input_cost_per_character_above_128k_tokens": 6.25e-07, - "output_cost_per_token": 3.125e-07, - "output_cost_per_character": 1.25e-06, - "output_cost_per_token_above_128k_tokens": 6.25e-07, - "output_cost_per_character_above_128k_tokens": 2.5e-06, - "litellm_provider": "vertex_ai-language-models", - "mode": "chat", - "supports_system_messages": true, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": true, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", - "supports_parallel_function_calling": true - }, - "gemini-1.5-pro-preview-0409": { - "max_tokens": 8192, - "max_input_tokens": 1000000, - "max_output_tokens": 8192, - "input_cost_per_image": 0.00032875, - "input_cost_per_audio_per_second": 3.125e-05, - "input_cost_per_video_per_second": 0.00032875, - "input_cost_per_token": 7.8125e-08, - "input_cost_per_character": 3.125e-07, - "input_cost_per_image_above_128k_tokens": 0.0006575, - "input_cost_per_video_per_second_above_128k_tokens": 0.0006575, - "input_cost_per_audio_per_second_above_128k_tokens": 6.25e-05, - "input_cost_per_token_above_128k_tokens": 1.5625e-07, - "input_cost_per_character_above_128k_tokens": 6.25e-07, - "output_cost_per_token": 3.125e-07, - "output_cost_per_character": 1.25e-06, - "output_cost_per_token_above_128k_tokens": 6.25e-07, - "output_cost_per_character_above_128k_tokens": 2.5e-06, - "litellm_provider": "vertex_ai-language-models", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": true, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", - "supports_parallel_function_calling": true - }, - "gemini-1.5-flash": { - "max_tokens": 8192, - "max_input_tokens": 1000000, - "max_output_tokens": 8192, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_pdf_size_mb": 30, - "input_cost_per_image": 2e-05, - "input_cost_per_video_per_second": 2e-05, - "input_cost_per_audio_per_second": 2e-06, - "input_cost_per_token": 7.5e-08, - "input_cost_per_character": 1.875e-08, - "input_cost_per_token_above_128k_tokens": 1e-06, - "input_cost_per_character_above_128k_tokens": 2.5e-07, - "input_cost_per_image_above_128k_tokens": 4e-05, - "input_cost_per_video_per_second_above_128k_tokens": 4e-05, - "input_cost_per_audio_per_second_above_128k_tokens": 4e-06, - "output_cost_per_token": 3e-07, - "output_cost_per_character": 7.5e-08, - "output_cost_per_token_above_128k_tokens": 6e-07, - "output_cost_per_character_above_128k_tokens": 1.5e-07, - "litellm_provider": "vertex_ai-language-models", - "mode": "chat", - "supports_system_messages": true, - "supports_function_calling": true, - "supports_vision": true, - "supports_response_schema": true, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", - "supports_tool_choice": true, - "supports_parallel_function_calling": true - }, - "gemini-1.5-flash-exp-0827": { - "max_tokens": 8192, - "max_input_tokens": 1000000, - "max_output_tokens": 8192, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_pdf_size_mb": 30, - "input_cost_per_image": 2e-05, - "input_cost_per_video_per_second": 2e-05, - "input_cost_per_audio_per_second": 2e-06, - "input_cost_per_token": 4.688e-09, - "input_cost_per_character": 1.875e-08, - "input_cost_per_token_above_128k_tokens": 1e-06, - "input_cost_per_character_above_128k_tokens": 2.5e-07, - "input_cost_per_image_above_128k_tokens": 4e-05, - "input_cost_per_video_per_second_above_128k_tokens": 4e-05, - "input_cost_per_audio_per_second_above_128k_tokens": 4e-06, - "output_cost_per_token": 4.6875e-09, - "output_cost_per_character": 1.875e-08, - "output_cost_per_token_above_128k_tokens": 9.375e-09, - "output_cost_per_character_above_128k_tokens": 3.75e-08, - "litellm_provider": "vertex_ai-language-models", - "mode": "chat", - "supports_system_messages": true, - "supports_function_calling": true, - "supports_vision": true, - "supports_response_schema": true, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", - "supports_tool_choice": true, - "supports_parallel_function_calling": true - }, - "gemini-1.5-flash-002": { - "max_tokens": 8192, - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_pdf_size_mb": 30, - "input_cost_per_image": 2e-05, - "input_cost_per_video_per_second": 2e-05, - "input_cost_per_audio_per_second": 2e-06, - "input_cost_per_token": 7.5e-08, - "input_cost_per_character": 1.875e-08, - "input_cost_per_token_above_128k_tokens": 1e-06, - "input_cost_per_character_above_128k_tokens": 2.5e-07, - "input_cost_per_image_above_128k_tokens": 4e-05, - "input_cost_per_video_per_second_above_128k_tokens": 4e-05, - "input_cost_per_audio_per_second_above_128k_tokens": 4e-06, - "output_cost_per_token": 3e-07, - "output_cost_per_character": 7.5e-08, - "output_cost_per_token_above_128k_tokens": 6e-07, - "output_cost_per_character_above_128k_tokens": 1.5e-07, - "litellm_provider": "vertex_ai-language-models", - "mode": "chat", - "supports_system_messages": true, - "supports_function_calling": true, - "supports_vision": true, - "supports_response_schema": true, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-1.5-flash", - "deprecation_date": "2025-09-24", - "supports_tool_choice": true, - "supports_parallel_function_calling": true - }, - "gemini-1.5-flash-001": { - "max_tokens": 8192, - "max_input_tokens": 1000000, - "max_output_tokens": 8192, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_pdf_size_mb": 30, - "input_cost_per_image": 2e-05, - "input_cost_per_video_per_second": 2e-05, - "input_cost_per_audio_per_second": 2e-06, - "input_cost_per_token": 7.5e-08, - "input_cost_per_character": 1.875e-08, - "input_cost_per_token_above_128k_tokens": 1e-06, - "input_cost_per_character_above_128k_tokens": 2.5e-07, - "input_cost_per_image_above_128k_tokens": 4e-05, - "input_cost_per_video_per_second_above_128k_tokens": 4e-05, - "input_cost_per_audio_per_second_above_128k_tokens": 4e-06, - "output_cost_per_token": 3e-07, - "output_cost_per_character": 7.5e-08, - "output_cost_per_token_above_128k_tokens": 6e-07, - "output_cost_per_character_above_128k_tokens": 1.5e-07, - "litellm_provider": "vertex_ai-language-models", - "mode": "chat", - "supports_system_messages": true, - "supports_function_calling": true, - "supports_vision": true, - "supports_response_schema": true, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", - "deprecation_date": "2025-05-24", - "supports_tool_choice": true, - "supports_parallel_function_calling": true - }, - "gemini-1.5-flash-preview-0514": { - "max_tokens": 8192, - "max_input_tokens": 1000000, - "max_output_tokens": 8192, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_pdf_size_mb": 30, - "input_cost_per_image": 2e-05, - "input_cost_per_video_per_second": 2e-05, - "input_cost_per_audio_per_second": 2e-06, - "input_cost_per_token": 7.5e-08, - "input_cost_per_character": 1.875e-08, - "input_cost_per_token_above_128k_tokens": 1e-06, - "input_cost_per_character_above_128k_tokens": 2.5e-07, - "input_cost_per_image_above_128k_tokens": 4e-05, - "input_cost_per_video_per_second_above_128k_tokens": 4e-05, - "input_cost_per_audio_per_second_above_128k_tokens": 4e-06, - "output_cost_per_token": 4.6875e-09, - "output_cost_per_character": 1.875e-08, - "output_cost_per_token_above_128k_tokens": 9.375e-09, - "output_cost_per_character_above_128k_tokens": 3.75e-08, - "litellm_provider": "vertex_ai-language-models", - "mode": "chat", - "supports_system_messages": true, - "supports_function_calling": true, - "supports_vision": true, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", - "supports_tool_choice": true, - "supports_parallel_function_calling": true - }, - "gemini-pro-experimental": { - "max_tokens": 8192, - "max_input_tokens": 1000000, - "max_output_tokens": 8192, - "input_cost_per_token": 0, - "output_cost_per_token": 0, - "input_cost_per_character": 0, - "output_cost_per_character": 0, - "litellm_provider": "vertex_ai-language-models", - "mode": "chat", - "supports_function_calling": false, - "supports_tool_choice": true, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/multimodal/gemini-experimental", - "supports_parallel_function_calling": true - }, - "gemini-flash-experimental": { - "max_tokens": 8192, - "max_input_tokens": 1000000, - "max_output_tokens": 8192, - "input_cost_per_token": 0, - "output_cost_per_token": 0, - "input_cost_per_character": 0, - "output_cost_per_character": 0, - "litellm_provider": "vertex_ai-language-models", - "mode": "chat", - "supports_function_calling": false, - "supports_tool_choice": true, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/multimodal/gemini-experimental", - "supports_parallel_function_calling": true - }, - "gemini-pro-vision": { - "max_tokens": 2048, - "max_input_tokens": 16384, - "max_output_tokens": 2048, - "max_images_per_prompt": 16, - "max_videos_per_prompt": 1, - "max_video_length": 2, - "input_cost_per_token": 5e-07, "output_cost_per_token": 1.5e-06, - "input_cost_per_image": 0.0025, - "litellm_provider": "vertex_ai-vision-models", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", - "supports_tool_choice": true, - "supports_parallel_function_calling": true + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true }, "gemini-1.0-pro-vision": { - "max_tokens": 2048, + "input_cost_per_image": 0.0025, + "input_cost_per_token": 5e-07, + "litellm_provider": "vertex_ai-vision-models", + "max_images_per_prompt": 16, "max_input_tokens": 16384, "max_output_tokens": 2048, - "max_images_per_prompt": 16, - "max_videos_per_prompt": 1, + "max_tokens": 2048, "max_video_length": 2, - "input_cost_per_token": 5e-07, - "output_cost_per_token": 1.5e-06, - "input_cost_per_image": 0.0025, - "litellm_provider": "vertex_ai-vision-models", + "max_videos_per_prompt": 1, "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, + "output_cost_per_token": 1.5e-06, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "supports_function_calling": true, + "supports_parallel_function_calling": true, "supports_tool_choice": true, - "supports_parallel_function_calling": true + "supports_vision": true }, "gemini-1.0-pro-vision-001": { - "max_tokens": 2048, + "deprecation_date": "2025-04-09", + "input_cost_per_image": 0.0025, + "input_cost_per_token": 5e-07, + "litellm_provider": "vertex_ai-vision-models", + "max_images_per_prompt": 16, "max_input_tokens": 16384, "max_output_tokens": 2048, - "max_images_per_prompt": 16, - "max_videos_per_prompt": 1, + "max_tokens": 2048, "max_video_length": 2, - "input_cost_per_token": 5e-07, + "max_videos_per_prompt": 1, + "mode": "chat", "output_cost_per_token": 1.5e-06, - "input_cost_per_image": 0.0025, - "litellm_provider": "vertex_ai-vision-models", - "mode": "chat", + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", "supports_function_calling": true, - "supports_vision": true, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", - "deprecation_date": "2025-04-09", + "supports_parallel_function_calling": true, "supports_tool_choice": true, - "supports_parallel_function_calling": true + "supports_vision": true }, - "medlm-medium": { - "max_tokens": 8192, - "max_input_tokens": 32768, - "max_output_tokens": 8192, - "input_cost_per_character": 5e-07, - "output_cost_per_character": 1e-06, + "gemini-1.0-ultra": { + "input_cost_per_character": 1.25e-07, + "input_cost_per_image": 0.0025, + "input_cost_per_token": 5e-07, + "input_cost_per_video_per_second": 0.002, "litellm_provider": "vertex_ai-language-models", - "mode": "chat", - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", - "supports_tool_choice": true - }, - "medlm-large": { - "max_tokens": 1024, "max_input_tokens": 8192, - "max_output_tokens": 1024, - "input_cost_per_character": 5e-06, - "output_cost_per_character": 1.5e-05, - "litellm_provider": "vertex_ai-language-models", + "max_output_tokens": 2048, + "max_tokens": 8192, "mode": "chat", - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "output_cost_per_character": 3.75e-07, + "output_cost_per_token": 1.5e-06, + "source": "As of Jun, 2024. There is no available doc on vertex ai pricing gemini-1.0-ultra-001. Using gemini-1.0-pro pricing. Got max_tokens info here: https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "supports_function_calling": true, + "supports_parallel_function_calling": true, "supports_tool_choice": true }, - "gemini-2.5-pro-exp-03-25": { - "max_tokens": 65535, - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, + "gemini-1.0-ultra-001": { + "input_cost_per_character": 1.25e-07, + "input_cost_per_image": 0.0025, + "input_cost_per_token": 5e-07, + "input_cost_per_video_per_second": 0.002, + "litellm_provider": "vertex_ai-language-models", + "max_input_tokens": 8192, + "max_output_tokens": 2048, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_character": 3.75e-07, + "output_cost_per_token": 1.5e-06, + "source": "As of Jun, 2024. There is no available doc on vertex ai pricing gemini-1.0-ultra-001. Using gemini-1.0-pro pricing. Got max_tokens info here: https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true + }, + "gemini-1.5-flash": { + "input_cost_per_audio_per_second": 2e-06, + "input_cost_per_audio_per_second_above_128k_tokens": 4e-06, + "input_cost_per_character": 1.875e-08, + "input_cost_per_character_above_128k_tokens": 2.5e-07, + "input_cost_per_image": 2e-05, + "input_cost_per_image_above_128k_tokens": 4e-05, + "input_cost_per_token": 7.5e-08, + "input_cost_per_token_above_128k_tokens": 1e-06, + "input_cost_per_video_per_second": 2e-05, + "input_cost_per_video_per_second_above_128k_tokens": 4e-05, + "litellm_provider": "vertex_ai-language-models", "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1000000, + "max_output_tokens": 8192, "max_pdf_size_mb": 30, - "input_cost_per_token": 1.25e-06, - "input_cost_per_token_above_200k_tokens": 2.5e-06, - "output_cost_per_token": 1e-05, - "output_cost_per_token_above_200k_tokens": 1.5e-05, - "litellm_provider": "vertex_ai-language-models", - "mode": "chat", - "supports_system_messages": true, - "supports_function_calling": true, - "supports_vision": true, - "supports_audio_input": true, - "supports_video_input": true, - "supports_pdf_input": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", - "supports_parallel_function_calling": true, - "supports_web_search": true, - "cache_read_input_token_cost": 3.125e-07, - "supports_prompt_caching": true - }, - "gemini-2.0-pro-exp-02-05": { "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_character": 7.5e-08, + "output_cost_per_character_above_128k_tokens": 1.5e-07, + "output_cost_per_token": 3e-07, + "output_cost_per_token_above_128k_tokens": 6e-07, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "gemini-1.5-flash-001": { + "deprecation_date": "2025-05-24", + "input_cost_per_audio_per_second": 2e-06, + "input_cost_per_audio_per_second_above_128k_tokens": 4e-06, + "input_cost_per_character": 1.875e-08, + "input_cost_per_character_above_128k_tokens": 2.5e-07, + "input_cost_per_image": 2e-05, + "input_cost_per_image_above_128k_tokens": 4e-05, + "input_cost_per_token": 7.5e-08, + "input_cost_per_token_above_128k_tokens": 1e-06, + "input_cost_per_video_per_second": 2e-05, + "input_cost_per_video_per_second_above_128k_tokens": 4e-05, + "litellm_provider": "vertex_ai-language-models", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1000000, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_character": 7.5e-08, + "output_cost_per_character_above_128k_tokens": 1.5e-07, + "output_cost_per_token": 3e-07, + "output_cost_per_token_above_128k_tokens": 6e-07, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "gemini-1.5-flash-002": { + "deprecation_date": "2025-09-24", + "input_cost_per_audio_per_second": 2e-06, + "input_cost_per_audio_per_second_above_128k_tokens": 4e-06, + "input_cost_per_character": 1.875e-08, + "input_cost_per_character_above_128k_tokens": 2.5e-07, + "input_cost_per_image": 2e-05, + "input_cost_per_image_above_128k_tokens": 4e-05, + "input_cost_per_token": 7.5e-08, + "input_cost_per_token_above_128k_tokens": 1e-06, + "input_cost_per_video_per_second": 2e-05, + "input_cost_per_video_per_second_above_128k_tokens": 4e-05, + "litellm_provider": "vertex_ai-language-models", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_character": 7.5e-08, + "output_cost_per_character_above_128k_tokens": 1.5e-07, + "output_cost_per_token": 3e-07, + "output_cost_per_token_above_128k_tokens": 6e-07, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-1.5-flash", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "gemini-1.5-flash-exp-0827": { + "input_cost_per_audio_per_second": 2e-06, + "input_cost_per_audio_per_second_above_128k_tokens": 4e-06, + "input_cost_per_character": 1.875e-08, + "input_cost_per_character_above_128k_tokens": 2.5e-07, + "input_cost_per_image": 2e-05, + "input_cost_per_image_above_128k_tokens": 4e-05, + "input_cost_per_token": 4.688e-09, + "input_cost_per_token_above_128k_tokens": 1e-06, + "input_cost_per_video_per_second": 2e-05, + "input_cost_per_video_per_second_above_128k_tokens": 4e-05, + "litellm_provider": "vertex_ai-language-models", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1000000, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_character": 1.875e-08, + "output_cost_per_character_above_128k_tokens": 3.75e-08, + "output_cost_per_token": 4.6875e-09, + "output_cost_per_token_above_128k_tokens": 9.375e-09, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "gemini-1.5-flash-preview-0514": { + "input_cost_per_audio_per_second": 2e-06, + "input_cost_per_audio_per_second_above_128k_tokens": 4e-06, + "input_cost_per_character": 1.875e-08, + "input_cost_per_character_above_128k_tokens": 2.5e-07, + "input_cost_per_image": 2e-05, + "input_cost_per_image_above_128k_tokens": 4e-05, + "input_cost_per_token": 7.5e-08, + "input_cost_per_token_above_128k_tokens": 1e-06, + "input_cost_per_video_per_second": 2e-05, + "input_cost_per_video_per_second_above_128k_tokens": 4e-05, + "litellm_provider": "vertex_ai-language-models", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1000000, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_character": 1.875e-08, + "output_cost_per_character_above_128k_tokens": 3.75e-08, + "output_cost_per_token": 4.6875e-09, + "output_cost_per_token_above_128k_tokens": 9.375e-09, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "gemini-1.5-pro": { + "input_cost_per_audio_per_second": 3.125e-05, + "input_cost_per_audio_per_second_above_128k_tokens": 6.25e-05, + "input_cost_per_character": 3.125e-07, + "input_cost_per_character_above_128k_tokens": 6.25e-07, + "input_cost_per_image": 0.00032875, + "input_cost_per_image_above_128k_tokens": 0.0006575, + "input_cost_per_token": 1.25e-06, + "input_cost_per_token_above_128k_tokens": 2.5e-06, + "input_cost_per_video_per_second": 0.00032875, + "input_cost_per_video_per_second_above_128k_tokens": 0.0006575, + "litellm_provider": "vertex_ai-language-models", "max_input_tokens": 2097152, "max_output_tokens": 8192, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_pdf_size_mb": 30, - "input_cost_per_token": 1.25e-06, - "input_cost_per_token_above_200k_tokens": 2.5e-06, - "output_cost_per_token": 1e-05, - "output_cost_per_token_above_200k_tokens": 1.5e-05, - "litellm_provider": "vertex_ai-language-models", - "mode": "chat", - "supports_system_messages": true, - "supports_function_calling": true, - "supports_vision": true, - "supports_audio_input": true, - "supports_video_input": true, - "supports_pdf_input": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", - "supports_parallel_function_calling": true, - "supports_web_search": true, - "cache_read_input_token_cost": 3.125e-07, - "supports_prompt_caching": true - }, - "gemini-2.0-flash-exp": { "max_tokens": 8192, - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_pdf_size_mb": 30, - "input_cost_per_image": 0, - "input_cost_per_video_per_second": 0, - "input_cost_per_audio_per_second": 0, - "input_cost_per_token": 1.5e-07, - "input_cost_per_character": 0, - "input_cost_per_token_above_128k_tokens": 0, - "input_cost_per_character_above_128k_tokens": 0, - "input_cost_per_image_above_128k_tokens": 0, - "input_cost_per_video_per_second_above_128k_tokens": 0, - "input_cost_per_audio_per_second_above_128k_tokens": 0, - "output_cost_per_token": 6e-07, - "output_cost_per_character": 0, - "output_cost_per_token_above_128k_tokens": 0, - "output_cost_per_character_above_128k_tokens": 0, - "litellm_provider": "vertex_ai-language-models", "mode": "chat", - "supports_system_messages": true, + "output_cost_per_character": 1.25e-06, + "output_cost_per_character_above_128k_tokens": 2.5e-06, + "output_cost_per_token": 5e-06, + "output_cost_per_token_above_128k_tokens": 1e-05, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", "supports_function_calling": true, - "supports_vision": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, "supports_response_schema": true, - "supports_audio_output": true, - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text", - "image" - ], - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", - "supports_tool_choice": true, - "supports_parallel_function_calling": true, - "supports_web_search": true, - "cache_read_input_token_cost": 3.75e-08, - "supports_prompt_caching": true - }, - "gemini-2.0-flash-001": { - "max_tokens": 8192, - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_pdf_size_mb": 30, - "input_cost_per_audio_token": 1e-06, - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 6e-07, - "litellm_provider": "vertex_ai-language-models", - "mode": "chat", "supports_system_messages": true, - "supports_function_calling": true, - "supports_vision": true, - "supports_response_schema": true, - "supports_audio_output": true, "supports_tool_choice": true, - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text", - "image" - ], - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", - "deprecation_date": "2026-02-05", - "supports_parallel_function_calling": true, - "supports_web_search": true, - "cache_read_input_token_cost": 3.75e-08, - "supports_prompt_caching": true + "supports_vision": true }, - "gemini-2.0-flash-thinking-exp": { - "max_tokens": 8192, - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_pdf_size_mb": 30, - "input_cost_per_image": 0, - "input_cost_per_video_per_second": 0, - "input_cost_per_audio_per_second": 0, - "input_cost_per_token": 0, - "input_cost_per_character": 0, - "input_cost_per_token_above_128k_tokens": 0, - "input_cost_per_character_above_128k_tokens": 0, - "input_cost_per_image_above_128k_tokens": 0, - "input_cost_per_video_per_second_above_128k_tokens": 0, - "input_cost_per_audio_per_second_above_128k_tokens": 0, - "output_cost_per_token": 0, - "output_cost_per_character": 0, - "output_cost_per_token_above_128k_tokens": 0, - "output_cost_per_character_above_128k_tokens": 0, - "litellm_provider": "vertex_ai-language-models", - "mode": "chat", - "supports_system_messages": true, - "supports_function_calling": true, - "supports_vision": true, - "supports_response_schema": true, - "supports_audio_output": true, - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text", - "image" - ], - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-2.0-flash", - "supports_tool_choice": true, - "supports_parallel_function_calling": true, - "supports_web_search": true, - "cache_read_input_token_cost": 0.0, - "supports_prompt_caching": true - }, - "gemini-2.0-flash-thinking-exp-01-21": { - "max_tokens": 65536, - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_pdf_size_mb": 30, - "input_cost_per_image": 0, - "input_cost_per_video_per_second": 0, - "input_cost_per_audio_per_second": 0, - "input_cost_per_token": 0, - "input_cost_per_character": 0, - "input_cost_per_token_above_128k_tokens": 0, - "input_cost_per_character_above_128k_tokens": 0, - "input_cost_per_image_above_128k_tokens": 0, - "input_cost_per_video_per_second_above_128k_tokens": 0, - "input_cost_per_audio_per_second_above_128k_tokens": 0, - "output_cost_per_token": 0, - "output_cost_per_character": 0, - "output_cost_per_token_above_128k_tokens": 0, - "output_cost_per_character_above_128k_tokens": 0, - "litellm_provider": "vertex_ai-language-models", - "mode": "chat", - "supports_system_messages": true, - "supports_function_calling": false, - "supports_vision": true, - "supports_response_schema": false, - "supports_audio_output": false, - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text", - "image" - ], - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-2.0-flash", - "supports_tool_choice": true, - "supports_parallel_function_calling": true, - "supports_web_search": true, - "cache_read_input_token_cost": 0.0, - "supports_prompt_caching": true - }, - "gemini-2.5-pro": { - "max_tokens": 65535, - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_pdf_size_mb": 30, + "gemini-1.5-pro-001": { + "deprecation_date": "2025-05-24", + "input_cost_per_audio_per_second": 3.125e-05, + "input_cost_per_audio_per_second_above_128k_tokens": 6.25e-05, + "input_cost_per_character": 3.125e-07, + "input_cost_per_character_above_128k_tokens": 6.25e-07, + "input_cost_per_image": 0.00032875, + "input_cost_per_image_above_128k_tokens": 0.0006575, "input_cost_per_token": 1.25e-06, - "input_cost_per_token_above_200k_tokens": 2.5e-06, - "output_cost_per_token": 1e-05, - "output_cost_per_token_above_200k_tokens": 1.5e-05, + "input_cost_per_token_above_128k_tokens": 2.5e-06, + "input_cost_per_video_per_second": 0.00032875, + "input_cost_per_video_per_second_above_128k_tokens": 0.0006575, "litellm_provider": "vertex_ai-language-models", + "max_input_tokens": 1000000, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", - "supports_system_messages": true, + "output_cost_per_character": 1.25e-06, + "output_cost_per_character_above_128k_tokens": 2.5e-06, + "output_cost_per_token": 5e-06, + "output_cost_per_token_above_128k_tokens": 1e-05, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", "supports_function_calling": true, - "supports_vision": true, - "supports_audio_input": true, - "supports_video_input": true, - "supports_pdf_input": true, + "supports_parallel_function_calling": true, "supports_response_schema": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", - "supports_web_search": true, - "cache_read_input_token_cost": 3.125e-07, - "supports_prompt_caching": true - }, - "gemini/gemini-2.5-pro-exp-03-25": { - "max_tokens": 65535, - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_pdf_size_mb": 30, - "input_cost_per_token": 0.0, - "input_cost_per_token_above_200k_tokens": 0.0, - "output_cost_per_token": 0.0, - "output_cost_per_token_above_200k_tokens": 0.0, - "litellm_provider": "gemini", - "mode": "chat", - "rpm": 5, - "tpm": 250000, "supports_system_messages": true, - "supports_function_calling": true, - "supports_vision": true, - "supports_audio_input": true, - "supports_video_input": true, - "supports_pdf_input": true, - "supports_response_schema": true, "supports_tool_choice": true, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", - "supports_web_search": true, - "cache_read_input_token_cost": 0.0, - "supports_prompt_caching": true + "supports_vision": true }, - "gemini/gemini-2.5-pro": { - "max_tokens": 65535, - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_pdf_size_mb": 30, + "gemini-1.5-pro-002": { + "deprecation_date": "2025-09-24", + "input_cost_per_audio_per_second": 3.125e-05, + "input_cost_per_audio_per_second_above_128k_tokens": 6.25e-05, + "input_cost_per_character": 3.125e-07, + "input_cost_per_character_above_128k_tokens": 6.25e-07, + "input_cost_per_image": 0.00032875, + "input_cost_per_image_above_128k_tokens": 0.0006575, "input_cost_per_token": 1.25e-06, - "input_cost_per_token_above_200k_tokens": 2.5e-06, - "output_cost_per_token": 1e-05, - "output_cost_per_token_above_200k_tokens": 1.5e-05, - "litellm_provider": "gemini", - "mode": "chat", - "rpm": 2000, - "tpm": 800000, - "supports_system_messages": true, - "supports_function_calling": true, - "supports_vision": true, - "supports_audio_input": true, - "supports_video_input": true, - "supports_pdf_input": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", - "supports_web_search": true, - "cache_read_input_token_cost": 3.125e-07, - "supports_prompt_caching": true - }, - "gemini/gemini-2.5-flash": { - "max_tokens": 65535, - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_pdf_size_mb": 30, - "input_cost_per_audio_token": 1e-06, - "input_cost_per_token": 3e-07, - "output_cost_per_token": 2.5e-06, - "output_cost_per_reasoning_token": 2.5e-06, - "litellm_provider": "gemini", - "mode": "chat", - "supports_reasoning": true, - "supports_system_messages": true, - "supports_function_calling": true, - "supports_vision": true, - "supports_response_schema": true, - "supports_audio_output": false, - "supports_tool_choice": true, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", - "supports_parallel_function_calling": true, - "supports_web_search": true, - "supports_url_context": true, - "tpm": 8000000, - "rpm": 100000, - "supports_pdf_input": true, - "cache_read_input_token_cost": 7.5e-08, - "supports_prompt_caching": true - }, - "gemini/gemini-2.5-flash-image-preview": { - "max_tokens": 65535, - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_pdf_size_mb": 30, - "input_cost_per_audio_token": 1e-06, - "input_cost_per_token": 3e-07, - "output_cost_per_token": 3e-05, - "output_cost_per_reasoning_token": 3e-05, - "output_cost_per_image": 0.039, - "litellm_provider": "gemini", - "mode": "chat", - "supports_system_messages": true, - "supports_function_calling": true, - "supports_vision": true, - "supports_response_schema": true, - "supports_audio_output": false, - "supports_tool_choice": true, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text", - "image" - ], - "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", - "supports_parallel_function_calling": true, - "supports_web_search": true, - "supports_url_context": true, - "tpm": 8000000, - "rpm": 100000, - "supports_pdf_input": true, - "cache_read_input_token_cost": 7.5e-08, - "supports_prompt_caching": true - }, - "gemini-2.5-flash": { - "max_tokens": 65535, - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_pdf_size_mb": 30, - "input_cost_per_audio_token": 1e-06, - "input_cost_per_token": 3e-07, - "output_cost_per_token": 2.5e-06, - "output_cost_per_reasoning_token": 2.5e-06, + "input_cost_per_token_above_128k_tokens": 2.5e-06, + "input_cost_per_video_per_second": 0.00032875, + "input_cost_per_video_per_second_above_128k_tokens": 0.0006575, "litellm_provider": "vertex_ai-language-models", + "max_input_tokens": 2097152, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", - "supports_reasoning": true, - "supports_system_messages": true, + "output_cost_per_character": 1.25e-06, + "output_cost_per_character_above_128k_tokens": 2.5e-06, + "output_cost_per_token": 5e-06, + "output_cost_per_token_above_128k_tokens": 1e-05, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-1.5-pro", "supports_function_calling": true, - "supports_vision": true, - "supports_response_schema": true, - "supports_audio_output": false, - "supports_tool_choice": true, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", "supports_parallel_function_calling": true, - "supports_web_search": true, - "supports_url_context": true, - "supports_pdf_input": true, - "cache_read_input_token_cost": 7.5e-08, - "supports_prompt_caching": true - }, - "gemini/gemini-2.0-flash-live-001": { - "max_tokens": 65535, - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_pdf_size_mb": 30, - "input_cost_per_token": 3.5e-07, - "input_cost_per_audio_token": 2.1e-06, - "input_cost_per_image": 2.1e-06, - "input_cost_per_video_per_second": 2.1e-06, - "output_cost_per_token": 1.5e-06, - "output_cost_per_audio_token": 8.5e-06, - "litellm_provider": "gemini", - "mode": "chat", - "rpm": 10, - "tpm": 250000, - "supports_system_messages": true, - "supports_function_calling": true, - "supports_vision": true, - "supports_reasoning": true, "supports_response_schema": true, - "supports_audio_output": true, - "supports_tool_choice": true, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text", - "audio" - ], - "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2-0-flash-live-001", - "supports_web_search": true, - "supports_url_context": true, - "supports_pdf_input": true, - "cache_read_input_token_cost": 7.5e-08, - "supports_prompt_caching": true - }, - "gemini/gemini-2.5-flash-preview-tts": { - "max_tokens": 65535, - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_pdf_size_mb": 30, - "input_cost_per_audio_token": 1e-06, - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 6e-07, - "output_cost_per_reasoning_token": 3.5e-06, - "litellm_provider": "gemini", - "mode": "chat", - "rpm": 10, - "tpm": 250000, "supports_system_messages": true, - "supports_function_calling": true, - "supports_vision": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_audio_output": false, "supports_tool_choice": true, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions" - ], - "supported_modalities": [ - "text" - ], - "supported_output_modalities": [ - "audio" - ], - "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", - "supports_web_search": true, - "cache_read_input_token_cost": 3.75e-08, - "supports_prompt_caching": true + "supports_vision": true }, - "gemini/gemini-2.5-flash-preview-05-20": { - "max_tokens": 65535, - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_pdf_size_mb": 30, - "input_cost_per_audio_token": 1e-06, - "input_cost_per_token": 3e-07, - "output_cost_per_token": 2.5e-06, - "output_cost_per_reasoning_token": 2.5e-06, - "litellm_provider": "gemini", - "mode": "chat", - "rpm": 10, - "tpm": 250000, - "supports_system_messages": true, - "supports_function_calling": true, - "supports_vision": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_audio_output": false, - "supports_tool_choice": true, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", - "supports_web_search": true, - "supports_url_context": true, - "supports_pdf_input": true, - "cache_read_input_token_cost": 7.5e-08, - "supports_prompt_caching": true - }, - "gemini/gemini-2.5-flash-preview-04-17": { - "max_tokens": 65535, - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_pdf_size_mb": 30, - "input_cost_per_audio_token": 1e-06, - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 6e-07, - "output_cost_per_reasoning_token": 3.5e-06, - "litellm_provider": "gemini", - "mode": "chat", - "rpm": 10, - "tpm": 250000, - "supports_system_messages": true, - "supports_function_calling": true, - "supports_vision": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_audio_output": false, - "supports_tool_choice": true, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", - "supports_web_search": true, - "supports_pdf_input": true, - "cache_read_input_token_cost": 3.75e-08, - "supports_prompt_caching": true - }, - "gemini/gemini-2.5-flash-lite-preview-06-17": { - "max_tokens": 65535, - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_pdf_size_mb": 30, - "input_cost_per_audio_token": 5e-07, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 4e-07, - "output_cost_per_reasoning_token": 4e-07, - "litellm_provider": "gemini", - "mode": "chat", - "rpm": 15, - "tpm": 250000, - "supports_reasoning": true, - "supports_system_messages": true, - "supports_function_calling": true, - "supports_vision": true, - "supports_response_schema": true, - "supports_audio_output": false, - "supports_tool_choice": true, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-lite", - "supports_parallel_function_calling": true, - "supports_web_search": true, - "supports_url_context": true, - "supports_pdf_input": true, - "cache_read_input_token_cost": 2.5e-08, - "supports_prompt_caching": true - }, - "gemini/gemini-2.5-flash-lite": { - "max_tokens": 65535, - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_pdf_size_mb": 30, - "input_cost_per_audio_token": 5e-07, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 4e-07, - "output_cost_per_reasoning_token": 4e-07, - "litellm_provider": "gemini", - "mode": "chat", - "rpm": 15, - "tpm": 250000, - "supports_reasoning": true, - "supports_system_messages": true, - "supports_function_calling": true, - "supports_vision": true, - "supports_response_schema": true, - "supports_audio_output": false, - "supports_tool_choice": true, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-lite", - "supports_parallel_function_calling": true, - "supports_web_search": true, - "supports_url_context": true, - "supports_pdf_input": true, - "cache_read_input_token_cost": 2.5e-08, - "supports_prompt_caching": true - }, - "gemini-2.5-flash-image-preview": { - "max_tokens": 65535, - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_pdf_size_mb": 30, - "input_cost_per_audio_token": 1e-06, - "input_cost_per_token": 3e-07, - "output_cost_per_token": 3e-05, - "output_cost_per_reasoning_token": 3e-05, - "output_cost_per_image": 0.039, + "gemini-1.5-pro-preview-0215": { + "input_cost_per_audio_per_second": 3.125e-05, + "input_cost_per_audio_per_second_above_128k_tokens": 6.25e-05, + "input_cost_per_character": 3.125e-07, + "input_cost_per_character_above_128k_tokens": 6.25e-07, + "input_cost_per_image": 0.00032875, + "input_cost_per_image_above_128k_tokens": 0.0006575, + "input_cost_per_token": 7.8125e-08, + "input_cost_per_token_above_128k_tokens": 1.5625e-07, + "input_cost_per_video_per_second": 0.00032875, + "input_cost_per_video_per_second_above_128k_tokens": 0.0006575, "litellm_provider": "vertex_ai-language-models", + "max_input_tokens": 1000000, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", - "supports_system_messages": true, + "output_cost_per_character": 1.25e-06, + "output_cost_per_character_above_128k_tokens": 2.5e-06, + "output_cost_per_token": 3.125e-07, + "output_cost_per_token_above_128k_tokens": 6.25e-07, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", "supports_function_calling": true, - "supports_vision": true, - "supports_response_schema": true, - "supports_audio_output": false, - "supports_tool_choice": true, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text", - "image" - ], - "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", "supports_parallel_function_calling": true, - "supports_web_search": true, - "supports_url_context": true, - "tpm": 8000000, - "rpm": 100000, - "supports_pdf_input": true, - "cache_read_input_token_cost": 7.5e-08, - "supports_prompt_caching": true + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true }, - "gemini-2.5-flash-preview-05-20": { - "max_tokens": 65535, - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_pdf_size_mb": 30, - "input_cost_per_audio_token": 1e-06, - "input_cost_per_token": 3e-07, - "output_cost_per_token": 2.5e-06, - "output_cost_per_reasoning_token": 2.5e-06, + "gemini-1.5-pro-preview-0409": { + "input_cost_per_audio_per_second": 3.125e-05, + "input_cost_per_audio_per_second_above_128k_tokens": 6.25e-05, + "input_cost_per_character": 3.125e-07, + "input_cost_per_character_above_128k_tokens": 6.25e-07, + "input_cost_per_image": 0.00032875, + "input_cost_per_image_above_128k_tokens": 0.0006575, + "input_cost_per_token": 7.8125e-08, + "input_cost_per_token_above_128k_tokens": 1.5625e-07, + "input_cost_per_video_per_second": 0.00032875, + "input_cost_per_video_per_second_above_128k_tokens": 0.0006575, "litellm_provider": "vertex_ai-language-models", + "max_input_tokens": 1000000, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", - "supports_reasoning": true, - "supports_system_messages": true, + "output_cost_per_character": 1.25e-06, + "output_cost_per_character_above_128k_tokens": 2.5e-06, + "output_cost_per_token": 3.125e-07, + "output_cost_per_token_above_128k_tokens": 6.25e-07, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", "supports_function_calling": true, - "supports_vision": true, - "supports_response_schema": true, - "supports_audio_output": false, - "supports_tool_choice": true, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", "supports_parallel_function_calling": true, - "supports_web_search": true, - "supports_url_context": true, - "supports_pdf_input": true, - "cache_read_input_token_cost": 7.5e-08, - "supports_prompt_caching": true + "supports_response_schema": true, + "supports_tool_choice": true }, - "gemini-2.5-flash-preview-04-17": { - "max_tokens": 65535, - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_pdf_size_mb": 30, - "input_cost_per_audio_token": 1e-06, - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 6e-07, - "output_cost_per_reasoning_token": 3.5e-06, + "gemini-1.5-pro-preview-0514": { + "input_cost_per_audio_per_second": 3.125e-05, + "input_cost_per_audio_per_second_above_128k_tokens": 6.25e-05, + "input_cost_per_character": 3.125e-07, + "input_cost_per_character_above_128k_tokens": 6.25e-07, + "input_cost_per_image": 0.00032875, + "input_cost_per_image_above_128k_tokens": 0.0006575, + "input_cost_per_token": 7.8125e-08, + "input_cost_per_token_above_128k_tokens": 1.5625e-07, + "input_cost_per_video_per_second": 0.00032875, + "input_cost_per_video_per_second_above_128k_tokens": 0.0006575, "litellm_provider": "vertex_ai-language-models", + "max_input_tokens": 1000000, + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", - "supports_reasoning": true, - "supports_system_messages": true, + "output_cost_per_character": 1.25e-06, + "output_cost_per_character_above_128k_tokens": 2.5e-06, + "output_cost_per_token": 3.125e-07, + "output_cost_per_token_above_128k_tokens": 6.25e-07, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", "supports_function_calling": true, - "supports_vision": true, - "supports_response_schema": true, - "supports_audio_output": false, - "supports_tool_choice": true, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", "supports_parallel_function_calling": true, - "supports_web_search": true, - "supports_pdf_input": true, - "cache_read_input_token_cost": 3.75e-08, - "supports_prompt_caching": true - }, - "gemini-2.5-flash-lite-preview-06-17": { - "max_tokens": 65535, - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_pdf_size_mb": 30, - "input_cost_per_audio_token": 5e-07, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 4e-07, - "output_cost_per_reasoning_token": 4e-07, - "litellm_provider": "vertex_ai-language-models", - "mode": "chat", - "supports_reasoning": true, + "supports_response_schema": true, "supports_system_messages": true, - "supports_function_calling": true, - "supports_vision": true, - "supports_response_schema": true, - "supports_audio_output": false, - "supports_tool_choice": true, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", - "supports_parallel_function_calling": true, - "supports_web_search": true, - "supports_url_context": true, - "supports_pdf_input": true, - "cache_read_input_token_cost": 2.5e-08, - "supports_prompt_caching": true - }, - "gemini-2.5-flash-lite": { - "max_tokens": 65535, - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_pdf_size_mb": 30, - "input_cost_per_audio_token": 5e-07, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 4e-07, - "output_cost_per_reasoning_token": 4e-07, - "litellm_provider": "vertex_ai-language-models", - "mode": "chat", - "supports_reasoning": true, - "supports_system_messages": true, - "supports_function_calling": true, - "supports_vision": true, - "supports_response_schema": true, - "supports_audio_output": false, - "supports_tool_choice": true, - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", - "supports_parallel_function_calling": true, - "supports_web_search": true, - "supports_url_context": true, - "supports_pdf_input": true, - "cache_read_input_token_cost": 2.5e-08, - "supports_prompt_caching": true + "supports_tool_choice": true }, "gemini-2.0-flash": { - "max_tokens": 8192, - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_pdf_size_mb": 30, + "cache_read_input_token_cost": 2.5e-08, "input_cost_per_audio_token": 7e-07, "input_cost_per_token": 1e-07, - "output_cost_per_token": 4e-07, "litellm_provider": "vertex_ai-language-models", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, "mode": "chat", - "supports_system_messages": true, - "supports_function_calling": true, - "supports_vision": true, - "supports_response_schema": true, - "supports_audio_output": true, - "supports_audio_input": true, + "output_cost_per_token": 4e-07, + "source": "https://ai.google.dev/pricing#2_0flash", "supported_modalities": [ "text", "image", @@ -8604,33 +8603,120 @@ "text", "image" ], - "supports_tool_choice": true, - "source": "https://ai.google.dev/pricing#2_0flash", + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, "supports_parallel_function_calling": true, - "supports_web_search": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, "supports_url_context": true, - "cache_read_input_token_cost": 2.5e-08, - "supports_prompt_caching": true + "supports_vision": true, + "supports_web_search": true + }, + "gemini-2.0-flash-001": { + "cache_read_input_token_cost": 3.75e-08, + "deprecation_date": "2026-02-05", + "input_cost_per_audio_token": 1e-06, + "input_cost_per_token": 1.5e-07, + "litellm_provider": "vertex_ai-language-models", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_token": 6e-07, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text", + "image" + ], + "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "gemini-2.0-flash-exp": { + "cache_read_input_token_cost": 3.75e-08, + "input_cost_per_audio_per_second": 0, + "input_cost_per_audio_per_second_above_128k_tokens": 0, + "input_cost_per_character": 0, + "input_cost_per_character_above_128k_tokens": 0, + "input_cost_per_image": 0, + "input_cost_per_image_above_128k_tokens": 0, + "input_cost_per_token": 1.5e-07, + "input_cost_per_token_above_128k_tokens": 0, + "input_cost_per_video_per_second": 0, + "input_cost_per_video_per_second_above_128k_tokens": 0, + "litellm_provider": "vertex_ai-language-models", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_character": 0, + "output_cost_per_character_above_128k_tokens": 0, + "output_cost_per_token": 6e-07, + "output_cost_per_token_above_128k_tokens": 0, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text", + "image" + ], + "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true }, "gemini-2.0-flash-lite": { - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_pdf_size_mb": 50, + "cache_read_input_token_cost": 1.875e-08, "input_cost_per_audio_token": 7.5e-08, "input_cost_per_token": 7.5e-08, - "output_cost_per_token": 3e-07, "litellm_provider": "vertex_ai-language-models", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_pdf_size_mb": 50, + "max_video_length": 1, + "max_videos_per_prompt": 10, "mode": "chat", - "supports_system_messages": true, - "supports_function_calling": true, - "supports_vision": true, - "supports_response_schema": true, - "supports_audio_output": true, + "output_cost_per_token": 3e-07, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-2.0-flash", "supported_modalities": [ "text", "image", @@ -8640,32 +8726,33 @@ "supported_output_modalities": [ "text" ], - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-2.0-flash", - "supports_tool_choice": true, + "supports_audio_output": true, + "supports_function_calling": true, "supports_parallel_function_calling": true, - "supports_web_search": true, - "cache_read_input_token_cost": 1.875e-08, - "supports_prompt_caching": true + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true }, "gemini-2.0-flash-lite-001": { - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_pdf_size_mb": 50, + "cache_read_input_token_cost": 1.875e-08, + "deprecation_date": "2026-02-25", "input_cost_per_audio_token": 7.5e-08, "input_cost_per_token": 7.5e-08, - "output_cost_per_token": 3e-07, "litellm_provider": "vertex_ai-language-models", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_pdf_size_mb": 50, + "max_video_length": 1, + "max_videos_per_prompt": 10, "mode": "chat", - "supports_system_messages": true, - "supports_function_calling": true, - "supports_vision": true, - "supports_response_schema": true, - "supports_audio_output": true, + "output_cost_per_token": 3e-07, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-2.0-flash", "supported_modalities": [ "text", "image", @@ -8675,38 +8762,259 @@ "supported_output_modalities": [ "text" ], - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-2.0-flash", - "supports_tool_choice": true, - "deprecation_date": "2026-02-25", + "supports_audio_output": true, + "supports_function_calling": true, "supports_parallel_function_calling": true, - "supports_web_search": true, - "cache_read_input_token_cost": 1.875e-08, - "supports_prompt_caching": true + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true }, - "gemini-2.5-pro-preview-06-05": { - "max_tokens": 65535, - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, + "gemini-2.0-flash-live-preview-04-09": { + "cache_read_input_token_cost": 7.5e-08, + "input_cost_per_audio_token": 3e-06, + "input_cost_per_image": 3e-06, + "input_cost_per_token": 5e-07, + "input_cost_per_video_per_second": 3e-06, + "litellm_provider": "vertex_ai-language-models", "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, "max_pdf_size_mb": 30, - "input_cost_per_audio_token": 1.25e-06, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_audio_token": 1.2e-05, + "output_cost_per_token": 2e-06, + "rpm": 10, + "source": "https://cloud.google.com/vertex-ai/docs/generative-ai/model-reference/gemini#gemini-2-0-flash-live-preview-04-09", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text", + "audio" + ], + "supports_audio_output": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 250000 + }, + "gemini-2.0-flash-preview-image-generation": { + "cache_read_input_token_cost": 2.5e-08, + "input_cost_per_audio_token": 7e-07, + "input_cost_per_token": 1e-07, + "litellm_provider": "vertex_ai-language-models", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_token": 4e-07, + "source": "https://ai.google.dev/pricing#2_0flash", + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text", + "image" + ], + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "gemini-2.0-flash-thinking-exp": { + "cache_read_input_token_cost": 0.0, + "input_cost_per_audio_per_second": 0, + "input_cost_per_audio_per_second_above_128k_tokens": 0, + "input_cost_per_character": 0, + "input_cost_per_character_above_128k_tokens": 0, + "input_cost_per_image": 0, + "input_cost_per_image_above_128k_tokens": 0, + "input_cost_per_token": 0, + "input_cost_per_token_above_128k_tokens": 0, + "input_cost_per_video_per_second": 0, + "input_cost_per_video_per_second_above_128k_tokens": 0, + "litellm_provider": "vertex_ai-language-models", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_character": 0, + "output_cost_per_character_above_128k_tokens": 0, + "output_cost_per_token": 0, + "output_cost_per_token_above_128k_tokens": 0, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-2.0-flash", + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text", + "image" + ], + "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "gemini-2.0-flash-thinking-exp-01-21": { + "cache_read_input_token_cost": 0.0, + "input_cost_per_audio_per_second": 0, + "input_cost_per_audio_per_second_above_128k_tokens": 0, + "input_cost_per_character": 0, + "input_cost_per_character_above_128k_tokens": 0, + "input_cost_per_image": 0, + "input_cost_per_image_above_128k_tokens": 0, + "input_cost_per_token": 0, + "input_cost_per_token_above_128k_tokens": 0, + "input_cost_per_video_per_second": 0, + "input_cost_per_video_per_second_above_128k_tokens": 0, + "litellm_provider": "vertex_ai-language-models", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_pdf_size_mb": 30, + "max_tokens": 65536, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_character": 0, + "output_cost_per_character_above_128k_tokens": 0, + "output_cost_per_token": 0, + "output_cost_per_token_above_128k_tokens": 0, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-2.0-flash", + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text", + "image" + ], + "supports_audio_output": false, + "supports_function_calling": false, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": false, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "gemini-2.0-pro-exp-02-05": { + "cache_read_input_token_cost": 3.125e-07, "input_cost_per_token": 1.25e-06, "input_cost_per_token_above_200k_tokens": 2.5e-06, + "litellm_provider": "vertex_ai-language-models", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 2097152, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_above_200k_tokens": 1.5e-05, - "litellm_provider": "vertex_ai-language-models", - "mode": "chat", - "supports_reasoning": true, - "supports_system_messages": true, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true, "supports_function_calling": true, - "supports_vision": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, "supports_response_schema": true, - "supports_audio_output": false, + "supports_system_messages": true, "supports_tool_choice": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true + }, + "gemini-2.5-flash": { + "cache_read_input_token_cost": 7.5e-08, + "input_cost_per_audio_token": 1e-06, + "input_cost_per_token": 3e-07, + "litellm_provider": "vertex_ai-language-models", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_reasoning_token": 2.5e-06, + "output_cost_per_token": 2.5e-06, + "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -8721,37 +9029,396 @@ "supported_output_modalities": [ "text" ], - "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", + "supports_audio_output": false, + "supports_function_calling": true, "supports_parallel_function_calling": true, - "supports_web_search": true, "supports_pdf_input": true, - "cache_read_input_token_cost": 3.125e-07, - "supports_prompt_caching": true + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_vision": true, + "supports_web_search": true }, - "gemini-2.5-pro-preview-05-06": { - "max_tokens": 65535, - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, + "gemini-2.5-flash-image-preview": { + "cache_read_input_token_cost": 7.5e-08, + "input_cost_per_audio_token": 1e-06, + "input_cost_per_token": 3e-07, + "litellm_provider": "vertex_ai-language-models", "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_image": 0.039, + "output_cost_per_reasoning_token": 3e-05, + "output_cost_per_token": 3e-05, + "rpm": 100000, + "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text", + "image" + ], + "supports_audio_output": false, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 8000000 + }, + "gemini-2.5-flash-lite": { + "cache_read_input_token_cost": 2.5e-08, + "input_cost_per_audio_token": 5e-07, + "input_cost_per_token": 1e-07, + "litellm_provider": "vertex_ai-language-models", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_reasoning_token": 4e-07, + "output_cost_per_token": 4e-07, + "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_output": false, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_vision": true, + "supports_web_search": true + }, + "gemini-2.5-flash-lite-preview-06-17": { + "cache_read_input_token_cost": 2.5e-08, + "input_cost_per_audio_token": 5e-07, + "input_cost_per_token": 1e-07, + "litellm_provider": "vertex_ai-language-models", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_reasoning_token": 4e-07, + "output_cost_per_token": 4e-07, + "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_output": false, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_vision": true, + "supports_web_search": true + }, + "gemini-2.5-flash-preview-04-17": { + "cache_read_input_token_cost": 3.75e-08, + "input_cost_per_audio_token": 1e-06, + "input_cost_per_token": 1.5e-07, + "litellm_provider": "vertex_ai-language-models", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_reasoning_token": 3.5e-06, + "output_cost_per_token": 6e-07, + "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_output": false, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "gemini-2.5-flash-preview-05-20": { + "cache_read_input_token_cost": 7.5e-08, + "input_cost_per_audio_token": 1e-06, + "input_cost_per_token": 3e-07, + "litellm_provider": "vertex_ai-language-models", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_reasoning_token": 2.5e-06, + "output_cost_per_token": 2.5e-06, + "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_output": false, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_vision": true, + "supports_web_search": true + }, + "gemini-2.5-pro": { + "cache_read_input_token_cost": 3.125e-07, + "input_cost_per_token": 1.25e-06, + "input_cost_per_token_above_200k_tokens": 2.5e-06, + "litellm_provider": "vertex_ai-language-models", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_token": 1e-05, + "output_cost_per_token_above_200k_tokens": 1.5e-05, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true + }, + "gemini-2.5-pro-exp-03-25": { + "cache_read_input_token_cost": 3.125e-07, + "input_cost_per_token": 1.25e-06, + "input_cost_per_token_above_200k_tokens": 2.5e-06, + "litellm_provider": "vertex_ai-language-models", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_token": 1e-05, + "output_cost_per_token_above_200k_tokens": 1.5e-05, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true + }, + "gemini-2.5-pro-preview-03-25": { + "cache_read_input_token_cost": 3.125e-07, "input_cost_per_audio_token": 1.25e-06, "input_cost_per_token": 1.25e-06, "input_cost_per_token_above_200k_tokens": 2.5e-06, + "litellm_provider": "vertex_ai-language-models", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_above_200k_tokens": 1.5e-05, - "litellm_provider": "vertex_ai-language-models", - "mode": "chat", - "supports_reasoning": true, - "supports_system_messages": true, - "supports_function_calling": true, - "supports_vision": true, - "supports_response_schema": true, + "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], "supports_audio_output": false, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "gemini-2.5-pro-preview-05-06": { + "cache_read_input_token_cost": 3.125e-07, + "input_cost_per_audio_token": 1.25e-06, + "input_cost_per_token": 1.25e-06, + "input_cost_per_token_above_200k_tokens": 2.5e-06, + "litellm_provider": "vertex_ai-language-models", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_token": 1e-05, + "output_cost_per_token_above_200k_tokens": 1.5e-05, + "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -8769,37 +9436,37 @@ "supported_regions": [ "global" ], - "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", + "supports_audio_output": false, + "supports_function_calling": true, "supports_parallel_function_calling": true, - "supports_web_search": true, "supports_pdf_input": true, - "cache_read_input_token_cost": 3.125e-07, - "supports_prompt_caching": true + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true }, - "gemini-2.5-pro-preview-03-25": { - "max_tokens": 65535, - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_pdf_size_mb": 30, + "gemini-2.5-pro-preview-06-05": { + "cache_read_input_token_cost": 3.125e-07, "input_cost_per_audio_token": 1.25e-06, "input_cost_per_token": 1.25e-06, "input_cost_per_token_above_200k_tokens": 2.5e-06, + "litellm_provider": "vertex_ai-language-models", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_above_200k_tokens": 1.5e-05, - "litellm_provider": "vertex_ai-language-models", - "mode": "chat", - "supports_reasoning": true, - "supports_system_messages": true, - "supports_function_calling": true, - "supports_vision": true, - "supports_response_schema": true, - "supports_audio_output": false, - "supports_tool_choice": true, + "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -8814,794 +9481,678 @@ "supported_output_modalities": [ "text" ], - "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", + "supports_audio_output": false, + "supports_function_calling": true, "supports_parallel_function_calling": true, - "supports_web_search": true, "supports_pdf_input": true, - "cache_read_input_token_cost": 3.125e-07, - "supports_prompt_caching": true - }, - "gemini-2.0-flash-preview-image-generation": { - "max_tokens": 8192, - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_pdf_size_mb": 30, - "input_cost_per_audio_token": 7e-07, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 4e-07, - "litellm_provider": "vertex_ai-language-models", - "mode": "chat", - "supports_system_messages": true, - "supports_function_calling": true, - "supports_vision": true, - "supports_response_schema": true, - "supports_audio_output": true, - "supports_audio_input": true, - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text", - "image" - ], - "supports_tool_choice": true, - "source": "https://ai.google.dev/pricing#2_0flash", - "supports_parallel_function_calling": true, - "supports_web_search": true, - "cache_read_input_token_cost": 2.5e-08, - "supports_prompt_caching": true - }, - "gemini-2.5-pro-preview-tts": { - "max_tokens": 65535, - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_pdf_size_mb": 30, - "input_cost_per_audio_token": 7e-07, - "input_cost_per_token": 1.25e-06, - "input_cost_per_token_above_200k_tokens": 2.5e-06, - "output_cost_per_token": 1e-05, - "output_cost_per_token_above_200k_tokens": 1.5e-05, - "litellm_provider": "vertex_ai-language-models", - "mode": "chat", - "supports_system_messages": true, - "supports_function_calling": true, - "supports_vision": true, - "supports_response_schema": true, - "supports_audio_output": false, - "supports_tool_choice": true, - "supported_modalities": [ - "text" - ], - "supported_output_modalities": [ - "audio" - ], - "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-pro-preview", - "supports_parallel_function_calling": true, - "supports_web_search": true, - "cache_read_input_token_cost": 3.125e-07, - "supports_prompt_caching": true - }, - "gemini/gemini-2.0-pro-exp-02-05": { - "max_tokens": 8192, - "max_input_tokens": 2097152, - "max_output_tokens": 8192, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_pdf_size_mb": 30, - "input_cost_per_image": 0, - "input_cost_per_video_per_second": 0, - "input_cost_per_audio_per_second": 0, - "input_cost_per_token": 0, - "input_cost_per_character": 0, - "input_cost_per_token_above_128k_tokens": 0, - "input_cost_per_character_above_128k_tokens": 0, - "input_cost_per_image_above_128k_tokens": 0, - "input_cost_per_video_per_second_above_128k_tokens": 0, - "input_cost_per_audio_per_second_above_128k_tokens": 0, - "output_cost_per_token": 0, - "output_cost_per_character": 0, - "output_cost_per_token_above_128k_tokens": 0, - "output_cost_per_character_above_128k_tokens": 0, - "litellm_provider": "gemini", - "mode": "chat", - "rpm": 2, - "tpm": 1000000, - "supports_system_messages": true, - "supports_function_calling": true, - "supports_vision": true, - "supports_audio_input": true, - "supports_video_input": true, - "supports_pdf_input": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", - "supports_web_search": true, - "cache_read_input_token_cost": 0.0, - "supports_prompt_caching": true - }, - "gemini/gemini-2.0-flash-preview-image-generation": { - "max_tokens": 8192, - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_pdf_size_mb": 30, - "input_cost_per_audio_token": 7e-07, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 4e-07, - "litellm_provider": "gemini", - "mode": "chat", - "rpm": 10000, - "tpm": 10000000, - "supports_system_messages": true, - "supports_function_calling": true, - "supports_vision": true, - "supports_response_schema": true, - "supports_audio_output": true, - "supports_audio_input": true, - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text", - "image" - ], - "supports_tool_choice": true, - "source": "https://ai.google.dev/pricing#2_0flash", - "supports_web_search": true, - "cache_read_input_token_cost": 2.5e-08, - "supports_prompt_caching": true - }, - "gemini/gemini-2.0-flash": { - "max_tokens": 8192, - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_pdf_size_mb": 30, - "input_cost_per_audio_token": 7e-07, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 4e-07, - "litellm_provider": "gemini", - "mode": "chat", - "rpm": 10000, - "tpm": 10000000, - "supports_system_messages": true, - "supports_function_calling": true, - "supports_vision": true, - "supports_response_schema": true, - "supports_audio_output": true, - "supports_audio_input": true, - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text", - "image" - ], - "supports_tool_choice": true, - "source": "https://ai.google.dev/pricing#2_0flash", - "supports_web_search": true, - "supports_url_context": true, - "cache_read_input_token_cost": 2.5e-08, - "supports_prompt_caching": true - }, - "gemini/gemini-2.0-flash-lite": { - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_pdf_size_mb": 50, - "input_cost_per_audio_token": 7.5e-08, - "input_cost_per_token": 7.5e-08, - "output_cost_per_token": 3e-07, - "litellm_provider": "gemini", - "mode": "chat", - "tpm": 4000000, - "rpm": 4000, - "supports_system_messages": true, - "supports_function_calling": true, - "supports_vision": true, - "supports_response_schema": true, - "supports_audio_output": true, - "supports_tool_choice": true, - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.0-flash-lite", - "supports_web_search": true, - "cache_read_input_token_cost": 1.875e-08, - "supports_prompt_caching": true - }, - "gemini/gemini-2.0-flash-001": { - "max_tokens": 8192, - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_pdf_size_mb": 30, - "input_cost_per_audio_token": 7e-07, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 4e-07, - "litellm_provider": "gemini", - "mode": "chat", - "rpm": 10000, - "tpm": 10000000, - "supports_system_messages": true, - "supports_function_calling": true, - "supports_vision": true, - "supports_response_schema": true, - "supports_audio_output": false, - "supports_tool_choice": true, - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text", - "image" - ], - "source": "https://ai.google.dev/pricing#2_0flash", - "supports_web_search": true, - "cache_read_input_token_cost": 2.5e-08, - "supports_prompt_caching": true - }, - "gemini/gemini-2.5-pro-preview-tts": { - "max_tokens": 65535, - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_pdf_size_mb": 30, - "input_cost_per_audio_token": 7e-07, - "input_cost_per_token": 1.25e-06, - "input_cost_per_token_above_200k_tokens": 2.5e-06, - "output_cost_per_token": 1e-05, - "output_cost_per_token_above_200k_tokens": 1.5e-05, - "litellm_provider": "gemini", - "mode": "chat", - "rpm": 10000, - "tpm": 10000000, - "supports_system_messages": true, - "supports_function_calling": true, - "supports_vision": true, - "supports_response_schema": true, - "supports_audio_output": false, - "supports_tool_choice": true, - "supported_modalities": [ - "text" - ], - "supported_output_modalities": [ - "audio" - ], - "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-pro-preview", - "supports_web_search": true, - "cache_read_input_token_cost": 3.125e-07, - "supports_prompt_caching": true - }, - "gemini/gemini-2.5-pro-preview-06-05": { - "max_tokens": 65535, - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_pdf_size_mb": 30, - "input_cost_per_audio_token": 7e-07, - "input_cost_per_token": 1.25e-06, - "input_cost_per_token_above_200k_tokens": 2.5e-06, - "output_cost_per_token": 1e-05, - "output_cost_per_token_above_200k_tokens": 1.5e-05, - "litellm_provider": "gemini", - "mode": "chat", - "rpm": 10000, - "tpm": 10000000, - "supports_system_messages": true, - "supports_function_calling": true, - "supports_vision": true, - "supports_response_schema": true, - "supports_audio_output": false, - "supports_tool_choice": true, - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-pro-preview", - "supports_web_search": true, - "supports_url_context": true, - "supports_pdf_input": true, - "cache_read_input_token_cost": 3.125e-07, - "supports_prompt_caching": true - }, - "gemini/gemini-2.5-pro-preview-05-06": { - "max_tokens": 65535, - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_pdf_size_mb": 30, - "input_cost_per_audio_token": 7e-07, - "input_cost_per_token": 1.25e-06, - "input_cost_per_token_above_200k_tokens": 2.5e-06, - "output_cost_per_token": 1e-05, - "output_cost_per_token_above_200k_tokens": 1.5e-05, - "litellm_provider": "gemini", - "mode": "chat", - "rpm": 10000, - "tpm": 10000000, - "supports_system_messages": true, - "supports_function_calling": true, - "supports_vision": true, - "supports_response_schema": true, - "supports_audio_output": false, - "supports_tool_choice": true, - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-pro-preview", - "supports_web_search": true, - "supports_url_context": true, - "supports_pdf_input": true, - "cache_read_input_token_cost": 3.125e-07, - "supports_prompt_caching": true - }, - "gemini/gemini-2.5-pro-preview-03-25": { - "max_tokens": 65535, - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_pdf_size_mb": 30, - "input_cost_per_audio_token": 7e-07, - "input_cost_per_token": 1.25e-06, - "input_cost_per_token_above_200k_tokens": 2.5e-06, - "output_cost_per_token": 1e-05, - "output_cost_per_token_above_200k_tokens": 1.5e-05, - "litellm_provider": "gemini", - "mode": "chat", - "rpm": 10000, - "tpm": 10000000, - "supports_system_messages": true, - "supports_function_calling": true, - "supports_vision": true, - "supports_response_schema": true, - "supports_audio_output": false, - "supports_tool_choice": true, - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-pro-preview", - "supports_web_search": true, - "supports_pdf_input": true, - "cache_read_input_token_cost": 3.125e-07, - "supports_prompt_caching": true - }, - "gemini/gemini-2.0-flash-exp": { - "max_tokens": 8192, - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_pdf_size_mb": 30, - "input_cost_per_image": 0, - "input_cost_per_video_per_second": 0, - "input_cost_per_audio_per_second": 0, - "input_cost_per_token": 0, - "input_cost_per_character": 0, - "input_cost_per_token_above_128k_tokens": 0, - "input_cost_per_character_above_128k_tokens": 0, - "input_cost_per_image_above_128k_tokens": 0, - "input_cost_per_video_per_second_above_128k_tokens": 0, - "input_cost_per_audio_per_second_above_128k_tokens": 0, - "output_cost_per_token": 0, - "output_cost_per_character": 0, - "output_cost_per_token_above_128k_tokens": 0, - "output_cost_per_character_above_128k_tokens": 0, - "litellm_provider": "gemini", - "mode": "chat", - "supports_system_messages": true, - "supports_function_calling": true, - "supports_vision": true, - "supports_response_schema": true, - "supports_audio_output": true, - "tpm": 4000000, - "rpm": 10, - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text", - "image" - ], - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-2.0-flash", - "supports_tool_choice": true, - "supports_web_search": true, - "cache_read_input_token_cost": 0.0, - "supports_prompt_caching": true - }, - "gemini/gemini-2.0-flash-lite-preview-02-05": { - "max_tokens": 8192, - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_pdf_size_mb": 30, - "input_cost_per_audio_token": 7.5e-08, - "input_cost_per_token": 7.5e-08, - "output_cost_per_token": 3e-07, - "litellm_provider": "gemini", - "mode": "chat", - "rpm": 60000, - "tpm": 10000000, - "supports_system_messages": true, - "supports_function_calling": true, - "supports_vision": true, - "supports_response_schema": true, - "supports_audio_output": false, - "supports_tool_choice": true, - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-2.0-flash-lite", - "supports_web_search": true, - "cache_read_input_token_cost": 1.875e-08, - "supports_prompt_caching": true - }, - "gemini/gemini-2.0-flash-thinking-exp": { - "max_tokens": 8192, - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_pdf_size_mb": 30, - "input_cost_per_image": 0, - "input_cost_per_video_per_second": 0, - "input_cost_per_audio_per_second": 0, - "input_cost_per_token": 0, - "input_cost_per_character": 0, - "input_cost_per_token_above_128k_tokens": 0, - "input_cost_per_character_above_128k_tokens": 0, - "input_cost_per_image_above_128k_tokens": 0, - "input_cost_per_video_per_second_above_128k_tokens": 0, - "input_cost_per_audio_per_second_above_128k_tokens": 0, - "output_cost_per_token": 0, - "output_cost_per_character": 0, - "output_cost_per_token_above_128k_tokens": 0, - "output_cost_per_character_above_128k_tokens": 0, - "litellm_provider": "gemini", - "mode": "chat", - "supports_system_messages": true, - "supports_function_calling": true, - "supports_vision": true, - "supports_response_schema": true, - "supports_audio_output": true, - "tpm": 4000000, - "rpm": 10, - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text", - "image" - ], - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-2.0-flash", - "supports_tool_choice": true, - "supports_web_search": true, - "cache_read_input_token_cost": 0.0, - "supports_prompt_caching": true - }, - "gemini/gemini-2.0-flash-thinking-exp-01-21": { - "max_tokens": 8192, - "max_input_tokens": 1048576, - "max_output_tokens": 65536, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_pdf_size_mb": 30, - "input_cost_per_image": 0, - "input_cost_per_video_per_second": 0, - "input_cost_per_audio_per_second": 0, - "input_cost_per_token": 0, - "input_cost_per_character": 0, - "input_cost_per_token_above_128k_tokens": 0, - "input_cost_per_character_above_128k_tokens": 0, - "input_cost_per_image_above_128k_tokens": 0, - "input_cost_per_video_per_second_above_128k_tokens": 0, - "input_cost_per_audio_per_second_above_128k_tokens": 0, - "output_cost_per_token": 0, - "output_cost_per_character": 0, - "output_cost_per_token_above_128k_tokens": 0, - "output_cost_per_character_above_128k_tokens": 0, - "litellm_provider": "gemini", - "mode": "chat", - "supports_system_messages": true, - "supports_function_calling": true, - "supports_vision": true, - "supports_response_schema": true, - "supports_audio_output": true, - "tpm": 4000000, - "rpm": 10, - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text", - "image" - ], - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-2.0-flash", - "supports_tool_choice": true, - "supports_web_search": true, - "cache_read_input_token_cost": 0.0, - "supports_prompt_caching": true - }, - "gemini/gemma-3-27b-it": { - "max_tokens": 8192, - "max_input_tokens": 131072, - "max_output_tokens": 8192, - "input_cost_per_image": 0, - "input_cost_per_video_per_second": 0, - "input_cost_per_audio_per_second": 0, - "input_cost_per_token": 0, - "input_cost_per_character": 0, - "input_cost_per_token_above_128k_tokens": 0, - "input_cost_per_character_above_128k_tokens": 0, - "input_cost_per_image_above_128k_tokens": 0, - "input_cost_per_video_per_second_above_128k_tokens": 0, - "input_cost_per_audio_per_second_above_128k_tokens": 0, - "output_cost_per_token": 0, - "output_cost_per_character": 0, - "output_cost_per_token_above_128k_tokens": 0, - "output_cost_per_character_above_128k_tokens": 0, - "litellm_provider": "gemini", - "mode": "chat", - "supports_system_messages": true, - "supports_function_calling": true, - "supports_vision": true, - "supports_response_schema": true, - "supports_audio_output": false, - "source": "https://aistudio.google.com", - "supports_tool_choice": true - }, - "gemini/learnlm-1.5-pro-experimental": { - "max_tokens": 8192, - "max_input_tokens": 32767, - "max_output_tokens": 8192, - "input_cost_per_image": 0, - "input_cost_per_video_per_second": 0, - "input_cost_per_audio_per_second": 0, - "input_cost_per_token": 0, - "input_cost_per_character": 0, - "input_cost_per_token_above_128k_tokens": 0, - "input_cost_per_character_above_128k_tokens": 0, - "input_cost_per_image_above_128k_tokens": 0, - "input_cost_per_video_per_second_above_128k_tokens": 0, - "input_cost_per_audio_per_second_above_128k_tokens": 0, - "output_cost_per_token": 0, - "output_cost_per_character": 0, - "output_cost_per_token_above_128k_tokens": 0, - "output_cost_per_character_above_128k_tokens": 0, - "litellm_provider": "gemini", - "mode": "chat", - "supports_system_messages": true, - "supports_function_calling": true, - "supports_vision": true, - "supports_response_schema": true, - "supports_audio_output": false, - "source": "https://aistudio.google.com", - "supports_tool_choice": true - }, - "gemini/veo-3.0-generate-preview": { - "max_tokens": 1024, - "max_input_tokens": 1024, - "output_cost_per_second": 0.75, - "litellm_provider": "gemini", - "mode": "video_generation", - "supported_modalities": [ - "text" - ], - "supported_output_modalities": [ - "video" - ], - "source": "https://ai.google.dev/gemini-api/docs/video" - }, - "gemini/veo-3.0-fast-generate-preview": { - "max_tokens": 1024, - "max_input_tokens": 1024, - "output_cost_per_second": 0.40, - "litellm_provider": "gemini", - "mode": "video_generation", - "supported_modalities": [ - "text" - ], - "supported_output_modalities": [ - "video" - ], - "source": "https://ai.google.dev/gemini-api/docs/video" - }, - "gemini/veo-2.0-generate-001": { - "max_tokens": 1024, - "max_input_tokens": 1024, - "output_cost_per_second": 0.35, - "litellm_provider": "gemini", - "mode": "video_generation", - "supported_modalities": [ - "text" - ], - "supported_output_modalities": [ - "video" - ], - "source": "https://ai.google.dev/gemini-api/docs/video" - }, - "vertex_ai/claude-opus-4-1": { - "max_tokens": 4096, - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "input_cost_per_token": 15e-06, - "output_cost_per_token": 75e-06, - "input_cost_per_token_batches": 7.5e-06, - "output_cost_per_token_batches": 37.5e-06, - "cache_creation_input_token_cost": 1.875e-05, - "cache_read_input_token_cost": 1.5e-06, - "litellm_provider": "vertex_ai-anthropic_models", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "supports_assistant_prefill": true, - "supports_tool_choice": true - }, - "vertex_ai/claude-opus-4-1@20250805": { - "max_tokens": 4096, - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "input_cost_per_token": 15e-06, - "output_cost_per_token": 75e-06, - "input_cost_per_token_batches": 7.5e-06, - "output_cost_per_token_batches": 37.5e-06, - "cache_creation_input_token_cost": 1.875e-05, - "cache_read_input_token_cost": 1.5e-06, - "litellm_provider": "vertex_ai-anthropic_models", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "supports_assistant_prefill": true, - "supports_tool_choice": true - }, - "vertex_ai/claude-3-sonnet": { - "max_tokens": 4096, - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "litellm_provider": "vertex_ai-anthropic_models", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "supports_assistant_prefill": true, - "supports_tool_choice": true - }, - "gemini-2.0-flash-live-preview-04-09": { - "max_tokens": 65535, - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_pdf_size_mb": 30, - "input_cost_per_token": 5e-07, - "input_cost_per_audio_token": 3e-06, - "input_cost_per_image": 3e-06, - "input_cost_per_video_per_second": 3e-06, - "output_cost_per_token": 2e-06, - "output_cost_per_audio_token": 1.2e-05, - "litellm_provider": "vertex_ai-language-models", - "mode": "chat", - "rpm": 10, - "tpm": 250000, - "supports_system_messages": true, - "supports_function_calling": true, - "supports_vision": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, - "supports_audio_output": true, + "supports_system_messages": true, "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "gemini-2.5-pro-preview-tts": { + "cache_read_input_token_cost": 3.125e-07, + "input_cost_per_audio_token": 7e-07, + "input_cost_per_token": 1.25e-06, + "input_cost_per_token_above_200k_tokens": 2.5e-06, + "litellm_provider": "vertex_ai-language-models", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_token": 1e-05, + "output_cost_per_token_above_200k_tokens": 1.5e-05, + "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-pro-preview", + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "audio" + ], + "supports_audio_output": false, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "gemini-embedding-001": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "vertex_ai-embedding-models", + "max_input_tokens": 2048, + "max_tokens": 2048, + "mode": "embedding", + "output_cost_per_token": 0, + "output_vector_size": 3072, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models" + }, + "gemini-flash-experimental": { + "input_cost_per_character": 0, + "input_cost_per_token": 0, + "litellm_provider": "vertex_ai-language-models", + "max_input_tokens": 1000000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_character": 0, + "output_cost_per_token": 0, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/multimodal/gemini-experimental", + "supports_function_calling": false, + "supports_parallel_function_calling": true, + "supports_tool_choice": true + }, + "gemini-pro": { + "input_cost_per_character": 1.25e-07, + "input_cost_per_image": 0.0025, + "input_cost_per_token": 5e-07, + "input_cost_per_video_per_second": 0.002, + "litellm_provider": "vertex_ai-language-models", + "max_input_tokens": 32760, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_character": 3.75e-07, + "output_cost_per_token": 1.5e-06, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true + }, + "gemini-pro-experimental": { + "input_cost_per_character": 0, + "input_cost_per_token": 0, + "litellm_provider": "vertex_ai-language-models", + "max_input_tokens": 1000000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_character": 0, + "output_cost_per_token": 0, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/multimodal/gemini-experimental", + "supports_function_calling": false, + "supports_parallel_function_calling": true, + "supports_tool_choice": true + }, + "gemini-pro-vision": { + "input_cost_per_image": 0.0025, + "input_cost_per_token": 5e-07, + "litellm_provider": "vertex_ai-vision-models", + "max_images_per_prompt": 16, + "max_input_tokens": 16384, + "max_output_tokens": 2048, + "max_tokens": 2048, + "max_video_length": 2, + "max_videos_per_prompt": 1, + "mode": "chat", + "output_cost_per_token": 1.5e-06, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "gemini/gemini-1.5-flash": { + "input_cost_per_token": 7.5e-08, + "input_cost_per_token_above_128k_tokens": 1.5e-07, + "litellm_provider": "gemini", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_token": 3e-07, + "output_cost_per_token_above_128k_tokens": 6e-07, + "rpm": 2000, + "source": "https://ai.google.dev/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "tpm": 4000000 + }, + "gemini/gemini-1.5-flash-001": { + "cache_creation_input_token_cost": 1e-06, + "cache_read_input_token_cost": 1.875e-08, + "deprecation_date": "2025-05-24", + "input_cost_per_token": 7.5e-08, + "input_cost_per_token_above_128k_tokens": 1.5e-07, + "litellm_provider": "gemini", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_token": 3e-07, + "output_cost_per_token_above_128k_tokens": 6e-07, + "rpm": 2000, + "source": "https://ai.google.dev/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "tpm": 4000000 + }, + "gemini/gemini-1.5-flash-002": { + "cache_creation_input_token_cost": 1e-06, + "cache_read_input_token_cost": 1.875e-08, + "deprecation_date": "2025-09-24", + "input_cost_per_token": 7.5e-08, + "input_cost_per_token_above_128k_tokens": 1.5e-07, + "litellm_provider": "gemini", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_token": 3e-07, + "output_cost_per_token_above_128k_tokens": 6e-07, + "rpm": 2000, + "source": "https://ai.google.dev/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "tpm": 4000000 + }, + "gemini/gemini-1.5-flash-8b": { + "input_cost_per_token": 0, + "input_cost_per_token_above_128k_tokens": 0, + "litellm_provider": "gemini", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_token": 0, + "output_cost_per_token_above_128k_tokens": 0, + "rpm": 4000, + "source": "https://ai.google.dev/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "tpm": 4000000 + }, + "gemini/gemini-1.5-flash-8b-exp-0827": { + "input_cost_per_token": 0, + "input_cost_per_token_above_128k_tokens": 0, + "litellm_provider": "gemini", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1000000, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_token": 0, + "output_cost_per_token_above_128k_tokens": 0, + "rpm": 4000, + "source": "https://ai.google.dev/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "tpm": 4000000 + }, + "gemini/gemini-1.5-flash-8b-exp-0924": { + "input_cost_per_token": 0, + "input_cost_per_token_above_128k_tokens": 0, + "litellm_provider": "gemini", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_token": 0, + "output_cost_per_token_above_128k_tokens": 0, + "rpm": 4000, + "source": "https://ai.google.dev/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "tpm": 4000000 + }, + "gemini/gemini-1.5-flash-exp-0827": { + "input_cost_per_token": 0, + "input_cost_per_token_above_128k_tokens": 0, + "litellm_provider": "gemini", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_token": 0, + "output_cost_per_token_above_128k_tokens": 0, + "rpm": 2000, + "source": "https://ai.google.dev/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "tpm": 4000000 + }, + "gemini/gemini-1.5-flash-latest": { + "input_cost_per_token": 7.5e-08, + "input_cost_per_token_above_128k_tokens": 1.5e-07, + "litellm_provider": "gemini", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_token": 3e-07, + "output_cost_per_token_above_128k_tokens": 6e-07, + "rpm": 2000, + "source": "https://ai.google.dev/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "tpm": 4000000 + }, + "gemini/gemini-1.5-pro": { + "input_cost_per_token": 3.5e-06, + "input_cost_per_token_above_128k_tokens": 7e-06, + "litellm_provider": "gemini", + "max_input_tokens": 2097152, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.05e-05, + "output_cost_per_token_above_128k_tokens": 2.1e-05, + "rpm": 1000, + "source": "https://ai.google.dev/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "tpm": 4000000 + }, + "gemini/gemini-1.5-pro-001": { + "deprecation_date": "2025-05-24", + "input_cost_per_token": 3.5e-06, + "input_cost_per_token_above_128k_tokens": 7e-06, + "litellm_provider": "gemini", + "max_input_tokens": 2097152, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.05e-05, + "output_cost_per_token_above_128k_tokens": 2.1e-05, + "rpm": 1000, + "source": "https://ai.google.dev/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "tpm": 4000000 + }, + "gemini/gemini-1.5-pro-002": { + "deprecation_date": "2025-09-24", + "input_cost_per_token": 3.5e-06, + "input_cost_per_token_above_128k_tokens": 7e-06, + "litellm_provider": "gemini", + "max_input_tokens": 2097152, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.05e-05, + "output_cost_per_token_above_128k_tokens": 2.1e-05, + "rpm": 1000, + "source": "https://ai.google.dev/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "tpm": 4000000 + }, + "gemini/gemini-1.5-pro-exp-0801": { + "input_cost_per_token": 3.5e-06, + "input_cost_per_token_above_128k_tokens": 7e-06, + "litellm_provider": "gemini", + "max_input_tokens": 2097152, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.05e-05, + "output_cost_per_token_above_128k_tokens": 2.1e-05, + "rpm": 1000, + "source": "https://ai.google.dev/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "tpm": 4000000 + }, + "gemini/gemini-1.5-pro-exp-0827": { + "input_cost_per_token": 0, + "input_cost_per_token_above_128k_tokens": 0, + "litellm_provider": "gemini", + "max_input_tokens": 2097152, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0, + "output_cost_per_token_above_128k_tokens": 0, + "rpm": 1000, + "source": "https://ai.google.dev/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "tpm": 4000000 + }, + "gemini/gemini-1.5-pro-latest": { + "input_cost_per_token": 3.5e-06, + "input_cost_per_token_above_128k_tokens": 7e-06, + "litellm_provider": "gemini", + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.05e-06, + "output_cost_per_token_above_128k_tokens": 2.1e-05, + "rpm": 1000, + "source": "https://ai.google.dev/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "tpm": 4000000 + }, + "gemini/gemini-2.0-flash": { + "cache_read_input_token_cost": 2.5e-08, + "input_cost_per_audio_token": 7e-07, + "input_cost_per_token": 1e-07, + "litellm_provider": "gemini", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_token": 4e-07, + "rpm": 10000, + "source": "https://ai.google.dev/pricing#2_0flash", + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text", + "image" + ], + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 10000000 + }, + "gemini/gemini-2.0-flash-001": { + "cache_read_input_token_cost": 2.5e-08, + "input_cost_per_audio_token": 7e-07, + "input_cost_per_token": 1e-07, + "litellm_provider": "gemini", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_token": 4e-07, + "rpm": 10000, + "source": "https://ai.google.dev/pricing#2_0flash", + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text", + "image" + ], + "supports_audio_output": false, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 10000000 + }, + "gemini/gemini-2.0-flash-exp": { + "cache_read_input_token_cost": 0.0, + "input_cost_per_audio_per_second": 0, + "input_cost_per_audio_per_second_above_128k_tokens": 0, + "input_cost_per_character": 0, + "input_cost_per_character_above_128k_tokens": 0, + "input_cost_per_image": 0, + "input_cost_per_image_above_128k_tokens": 0, + "input_cost_per_token": 0, + "input_cost_per_token_above_128k_tokens": 0, + "input_cost_per_video_per_second": 0, + "input_cost_per_video_per_second_above_128k_tokens": 0, + "litellm_provider": "gemini", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_character": 0, + "output_cost_per_character_above_128k_tokens": 0, + "output_cost_per_token": 0, + "output_cost_per_token_above_128k_tokens": 0, + "rpm": 10, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-2.0-flash", + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text", + "image" + ], + "supports_audio_output": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 4000000 + }, + "gemini/gemini-2.0-flash-lite": { + "cache_read_input_token_cost": 1.875e-08, + "input_cost_per_audio_token": 7.5e-08, + "input_cost_per_token": 7.5e-08, + "litellm_provider": "gemini", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_pdf_size_mb": 50, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_token": 3e-07, + "rpm": 4000, + "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.0-flash-lite", + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_output": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 4000000 + }, + "gemini/gemini-2.0-flash-lite-preview-02-05": { + "cache_read_input_token_cost": 1.875e-08, + "input_cost_per_audio_token": 7.5e-08, + "input_cost_per_token": 7.5e-08, + "litellm_provider": "gemini", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_token": 3e-07, + "rpm": 60000, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-2.0-flash-lite", + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_output": false, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 10000000 + }, + "gemini/gemini-2.0-flash-live-001": { + "cache_read_input_token_cost": 7.5e-08, + "input_cost_per_audio_token": 2.1e-06, + "input_cost_per_image": 2.1e-06, + "input_cost_per_token": 3.5e-07, + "input_cost_per_video_per_second": 2.1e-06, + "litellm_provider": "gemini", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_audio_token": 8.5e-06, + "output_cost_per_token": 1.5e-06, + "rpm": 10, + "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2-0-flash-live-001", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions" @@ -9616,11386 +10167,11104 @@ "text", "audio" ], - "source": "https://cloud.google.com/vertex-ai/docs/generative-ai/model-reference/gemini#gemini-2-0-flash-live-preview-04-09", - "supports_web_search": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, "supports_url_context": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 250000 + }, + "gemini/gemini-2.0-flash-preview-image-generation": { + "cache_read_input_token_cost": 2.5e-08, + "input_cost_per_audio_token": 7e-07, + "input_cost_per_token": 1e-07, + "litellm_provider": "gemini", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_token": 4e-07, + "rpm": 10000, + "source": "https://ai.google.dev/pricing#2_0flash", + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text", + "image" + ], + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 10000000 + }, + "gemini/gemini-2.0-flash-thinking-exp": { + "cache_read_input_token_cost": 0.0, + "input_cost_per_audio_per_second": 0, + "input_cost_per_audio_per_second_above_128k_tokens": 0, + "input_cost_per_character": 0, + "input_cost_per_character_above_128k_tokens": 0, + "input_cost_per_image": 0, + "input_cost_per_image_above_128k_tokens": 0, + "input_cost_per_token": 0, + "input_cost_per_token_above_128k_tokens": 0, + "input_cost_per_video_per_second": 0, + "input_cost_per_video_per_second_above_128k_tokens": 0, + "litellm_provider": "gemini", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_character": 0, + "output_cost_per_character_above_128k_tokens": 0, + "output_cost_per_token": 0, + "output_cost_per_token_above_128k_tokens": 0, + "rpm": 10, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-2.0-flash", + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text", + "image" + ], + "supports_audio_output": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 4000000 + }, + "gemini/gemini-2.0-flash-thinking-exp-01-21": { + "cache_read_input_token_cost": 0.0, + "input_cost_per_audio_per_second": 0, + "input_cost_per_audio_per_second_above_128k_tokens": 0, + "input_cost_per_character": 0, + "input_cost_per_character_above_128k_tokens": 0, + "input_cost_per_image": 0, + "input_cost_per_image_above_128k_tokens": 0, + "input_cost_per_token": 0, + "input_cost_per_token_above_128k_tokens": 0, + "input_cost_per_video_per_second": 0, + "input_cost_per_video_per_second_above_128k_tokens": 0, + "litellm_provider": "gemini", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_character": 0, + "output_cost_per_character_above_128k_tokens": 0, + "output_cost_per_token": 0, + "output_cost_per_token_above_128k_tokens": 0, + "rpm": 10, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-2.0-flash", + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text", + "image" + ], + "supports_audio_output": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 4000000 + }, + "gemini/gemini-2.0-pro-exp-02-05": { + "cache_read_input_token_cost": 0.0, + "input_cost_per_audio_per_second": 0, + "input_cost_per_audio_per_second_above_128k_tokens": 0, + "input_cost_per_character": 0, + "input_cost_per_character_above_128k_tokens": 0, + "input_cost_per_image": 0, + "input_cost_per_image_above_128k_tokens": 0, + "input_cost_per_token": 0, + "input_cost_per_token_above_128k_tokens": 0, + "input_cost_per_video_per_second": 0, + "input_cost_per_video_per_second_above_128k_tokens": 0, + "litellm_provider": "gemini", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 2097152, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_character": 0, + "output_cost_per_character_above_128k_tokens": 0, + "output_cost_per_token": 0, + "output_cost_per_token_above_128k_tokens": 0, + "rpm": 2, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "supports_audio_input": true, + "supports_function_calling": true, "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 1000000 + }, + "gemini/gemini-2.5-flash": { "cache_read_input_token_cost": 7.5e-08, - "supports_prompt_caching": true - }, - "vertex_ai/claude-3-sonnet@20240229": { - "max_tokens": 4096, - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "litellm_provider": "vertex_ai-anthropic_models", + "input_cost_per_audio_token": 1e-06, + "input_cost_per_token": 3e-07, + "litellm_provider": "gemini", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "supports_assistant_prefill": true, - "supports_tool_choice": true - }, - "vertex_ai/claude-3-5-sonnet": { - "supports_computer_use": true, - "max_tokens": 8192, - "max_input_tokens": 200000, - "max_output_tokens": 8192, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "litellm_provider": "vertex_ai-anthropic_models", - "mode": "chat", - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_vision": true, - "supports_assistant_prefill": true, - "supports_tool_choice": true - }, - "vertex_ai/claude-3-5-sonnet@20240620": { - "max_tokens": 8192, - "max_input_tokens": 200000, - "max_output_tokens": 8192, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "litellm_provider": "vertex_ai-anthropic_models", - "mode": "chat", - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_vision": true, - "supports_assistant_prefill": true, - "supports_tool_choice": true - }, - "vertex_ai/claude-3-5-sonnet-v2": { - "supports_computer_use": true, - "max_tokens": 8192, - "max_input_tokens": 200000, - "max_output_tokens": 8192, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "litellm_provider": "vertex_ai-anthropic_models", - "mode": "chat", - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_vision": true, - "supports_assistant_prefill": true, - "supports_tool_choice": true - }, - "vertex_ai/claude-3-5-sonnet-v2@20241022": { - "supports_computer_use": true, - "max_tokens": 8192, - "max_input_tokens": 200000, - "max_output_tokens": 8192, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "litellm_provider": "vertex_ai-anthropic_models", - "mode": "chat", - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_vision": true, - "supports_assistant_prefill": true, - "supports_tool_choice": true - }, - "vertex_ai/claude-3-7-sonnet@20250219": { - "supports_computer_use": true, - "max_tokens": 8192, - "max_input_tokens": 200000, - "max_output_tokens": 8192, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "cache_creation_input_token_cost": 3.75e-06, - "cache_read_input_token_cost": 3e-07, - "litellm_provider": "vertex_ai-anthropic_models", - "mode": "chat", - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 159, - "supports_assistant_prefill": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "deprecation_date": "2025-06-01", - "supports_reasoning": true, - "supports_tool_choice": true - }, - "vertex_ai/claude-opus-4": { - "max_tokens": 32000, - "max_input_tokens": 200000, - "max_output_tokens": 32000, - "input_cost_per_token": 1.5e-05, - "output_cost_per_token": 7.5e-05, - "search_context_cost_per_query": { - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01, - "search_context_size_high": 0.01 - }, - "cache_creation_input_token_cost": 1.875e-05, - "cache_read_input_token_cost": 1.5e-06, - "litellm_provider": "vertex_ai-anthropic_models", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 159, - "supports_assistant_prefill": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_computer_use": true - }, - "vertex_ai/claude-opus-4@20250514": { - "max_tokens": 32000, - "max_input_tokens": 200000, - "max_output_tokens": 32000, - "input_cost_per_token": 1.5e-05, - "output_cost_per_token": 7.5e-05, - "search_context_cost_per_query": { - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01, - "search_context_size_high": 0.01 - }, - "cache_creation_input_token_cost": 1.875e-05, - "cache_read_input_token_cost": 1.5e-06, - "litellm_provider": "vertex_ai-anthropic_models", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 159, - "supports_assistant_prefill": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_computer_use": true - }, - "vertex_ai/claude-sonnet-4": { - "max_tokens": 64000, - "max_input_tokens": 200000, - "max_output_tokens": 64000, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "search_context_cost_per_query": { - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01, - "search_context_size_high": 0.01 - }, - "cache_creation_input_token_cost": 3.75e-06, - "cache_read_input_token_cost": 3e-07, - "litellm_provider": "vertex_ai-anthropic_models", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 159, - "supports_assistant_prefill": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_computer_use": true - }, - "vertex_ai/claude-sonnet-4@20250514": { - "max_tokens": 64000, - "max_input_tokens": 200000, - "max_output_tokens": 64000, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "search_context_cost_per_query": { - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01, - "search_context_size_high": 0.01 - }, - "cache_creation_input_token_cost": 3.75e-06, - "cache_read_input_token_cost": 3e-07, - "litellm_provider": "vertex_ai-anthropic_models", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 159, - "supports_assistant_prefill": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_computer_use": true - }, - "vertex_ai/claude-3-haiku": { - "max_tokens": 4096, - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "input_cost_per_token": 2.5e-07, - "output_cost_per_token": 1.25e-06, - "litellm_provider": "vertex_ai-anthropic_models", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "supports_assistant_prefill": true, - "supports_tool_choice": true - }, - "vertex_ai/claude-3-haiku@20240307": { - "max_tokens": 4096, - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "input_cost_per_token": 2.5e-07, - "output_cost_per_token": 1.25e-06, - "litellm_provider": "vertex_ai-anthropic_models", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "supports_assistant_prefill": true, - "supports_tool_choice": true - }, - "vertex_ai/claude-3-5-haiku": { - "max_tokens": 8192, - "max_input_tokens": 200000, - "max_output_tokens": 8192, - "input_cost_per_token": 1e-06, - "output_cost_per_token": 5e-06, - "litellm_provider": "vertex_ai-anthropic_models", - "mode": "chat", - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_assistant_prefill": true, - "supports_tool_choice": true - }, - "vertex_ai/claude-3-5-haiku@20241022": { - "max_tokens": 8192, - "max_input_tokens": 200000, - "max_output_tokens": 8192, - "input_cost_per_token": 1e-06, - "output_cost_per_token": 5e-06, - "litellm_provider": "vertex_ai-anthropic_models", - "mode": "chat", - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_assistant_prefill": true, - "supports_tool_choice": true - }, - "vertex_ai/claude-3-opus": { - "max_tokens": 4096, - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "input_cost_per_token": 1.5e-05, - "output_cost_per_token": 7.5e-05, - "litellm_provider": "vertex_ai-anthropic_models", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "supports_assistant_prefill": true, - "supports_tool_choice": true - }, - "vertex_ai/claude-3-opus@20240229": { - "max_tokens": 4096, - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "input_cost_per_token": 1.5e-05, - "output_cost_per_token": 7.5e-05, - "litellm_provider": "vertex_ai-anthropic_models", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "supports_assistant_prefill": true, - "supports_tool_choice": true - }, - "vertex_ai/deepseek-ai/deepseek-r1-0528-maas": { - "max_tokens": 8192, - "max_input_tokens": 65336, - "max_output_tokens": 8192, - "input_cost_per_token": 1.35e-06, - "output_cost_per_token": 5.4e-06, - "litellm_provider": "vertex_ai-deepseek_models", - "mode": "chat", - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", - "supports_function_calling": true, - "supports_assistant_prefill": true, - "supports_reasoning": true, - "supports_tool_choice": true, - "supports_prompt_caching": true - }, - "vertex_ai/openai/gpt-oss-20b-maas": { - "max_tokens": 32768, - "max_input_tokens": 131072, - "max_output_tokens": 32768, - "input_cost_per_token": 0.075e-06, - "output_cost_per_token": 0.30e-06, - "litellm_provider": "vertex_ai-openai_models", - "mode": "chat", - "supports_reasoning": true, - "source": "https://console.cloud.google.com/vertex-ai/publishers/openai/model-garden/gpt-oss-120b-maas" - }, - "vertex_ai/openai/gpt-oss-120b-maas": { - "max_tokens": 32768, - "max_input_tokens": 131072, - "max_output_tokens": 32768, - "input_cost_per_token": 0.15e-06, - "output_cost_per_token": 0.60e-06, - "litellm_provider": "vertex_ai-openai_models", - "mode": "chat", - "supports_reasoning": true, - "source": "https://console.cloud.google.com/vertex-ai/publishers/openai/model-garden/gpt-oss-120b-maas" - }, - "vertex_ai/qwen/qwen3-coder-480b-a35b-instruct-maas": { - "max_tokens": 32768, - "max_input_tokens": 262144, - "max_output_tokens": 32768, - "input_cost_per_token": 1e-06, - "output_cost_per_token": 4e-06, - "litellm_provider": "vertex_ai-qwen_models", - "mode": "chat", - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", - "supports_function_calling": true, - "supports_tool_choice": true - }, - "vertex_ai/qwen/qwen3-235b-a22b-instruct-2507-maas": { - "max_tokens": 16384, - "max_input_tokens": 262144, - "max_output_tokens": 16384, - "input_cost_per_token": 0.25e-06, - "output_cost_per_token": 1e-06, - "litellm_provider": "vertex_ai-qwen_models", - "mode": "chat", - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", - "supports_function_calling": true, - "supports_tool_choice": true - }, - "vertex_ai/meta/llama3-405b-instruct-maas": { - "max_tokens": 32000, - "max_input_tokens": 32000, - "max_output_tokens": 32000, - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "vertex_ai-llama_models", - "mode": "chat", - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", - "supports_tool_choice": true - }, - "vertex_ai/meta/llama-4-scout-17b-16e-instruct-maas": { - "max_tokens": 10000000, - "max_input_tokens": 10000000, - "max_output_tokens": 10000000, - "input_cost_per_token": 2.5e-07, - "output_cost_per_token": 7e-07, - "litellm_provider": "vertex_ai-llama_models", - "mode": "chat", - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", - "supports_tool_choice": true, - "supports_function_calling": true, - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text", - "code" - ] - }, - "vertex_ai/meta/llama-4-scout-17b-128e-instruct-maas": { - "max_tokens": 10000000, - "max_input_tokens": 10000000, - "max_output_tokens": 10000000, - "input_cost_per_token": 2.5e-07, - "output_cost_per_token": 7e-07, - "litellm_provider": "vertex_ai-llama_models", - "mode": "chat", - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", - "supports_tool_choice": true, - "supports_function_calling": true, - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text", - "code" - ] - }, - "vertex_ai/meta/llama-4-maverick-17b-128e-instruct-maas": { - "max_tokens": 1000000, - "max_input_tokens": 1000000, - "max_output_tokens": 1000000, - "input_cost_per_token": 3.5e-07, - "output_cost_per_token": 1.15e-06, - "litellm_provider": "vertex_ai-llama_models", - "mode": "chat", - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", - "supports_tool_choice": true, - "supports_function_calling": true, - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text", - "code" - ] - }, - "vertex_ai/meta/llama-4-maverick-17b-16e-instruct-maas": { - "max_tokens": 1000000, - "max_input_tokens": 1000000, - "max_output_tokens": 1000000, - "input_cost_per_token": 3.5e-07, - "output_cost_per_token": 1.15e-06, - "litellm_provider": "vertex_ai-llama_models", - "mode": "chat", - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", - "supports_tool_choice": true, - "supports_function_calling": true, - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text", - "code" - ] - }, - "vertex_ai/meta/llama3-70b-instruct-maas": { - "max_tokens": 32000, - "max_input_tokens": 32000, - "max_output_tokens": 32000, - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "vertex_ai-llama_models", - "mode": "chat", - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", - "supports_tool_choice": true - }, - "vertex_ai/meta/llama3-8b-instruct-maas": { - "max_tokens": 32000, - "max_input_tokens": 32000, - "max_output_tokens": 32000, - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "vertex_ai-llama_models", - "mode": "chat", - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", - "supports_tool_choice": true - }, - "vertex_ai/meta/llama-3.1-8b-instruct-maas": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 2048, - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "vertex_ai-llama_models", - "mode": "chat", - "supports_system_messages": true, - "supports_vision": true, - "source": "https://console.cloud.google.com/vertex-ai/publishers/meta/model-garden/llama-3.2-90b-vision-instruct-maas", - "supports_tool_choice": true, - "metadata": { - "notes": "VertexAI states that The Llama 3.1 API service for llama-3.1-70b-instruct-maas and llama-3.1-8b-instruct-maas are in public preview and at no cost." - } - }, - "vertex_ai/meta/llama-3.1-70b-instruct-maas": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 2048, - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "vertex_ai-llama_models", - "mode": "chat", - "supports_system_messages": true, - "supports_vision": true, - "source": "https://console.cloud.google.com/vertex-ai/publishers/meta/model-garden/llama-3.2-90b-vision-instruct-maas", - "supports_tool_choice": true - }, - "vertex_ai/meta/llama-3.1-405b-instruct-maas": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 2048, - "input_cost_per_token": 5e-06, - "output_cost_per_token": 1.6e-05, - "litellm_provider": "vertex_ai-llama_models", - "mode": "chat", - "supports_system_messages": true, - "supports_vision": true, - "source": "https://console.cloud.google.com/vertex-ai/publishers/meta/model-garden/llama-3.2-90b-vision-instruct-maas", - "supports_tool_choice": true - }, - "vertex_ai/meta/llama-3.2-90b-vision-instruct-maas": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 2048, - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "vertex_ai-llama_models", - "mode": "chat", - "supports_system_messages": true, - "supports_vision": true, - "source": "https://console.cloud.google.com/vertex-ai/publishers/meta/model-garden/llama-3.2-90b-vision-instruct-maas", - "supports_tool_choice": true, - "metadata": { - "notes": "VertexAI states that The Llama 3.2 API service is at no cost during public preview, and will be priced as per dollar-per-1M-tokens at GA." - } - }, - "vertex_ai/mistral-large@latest": { - "max_tokens": 8191, - "max_input_tokens": 128000, - "max_output_tokens": 8191, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 6e-06, - "litellm_provider": "vertex_ai-mistral_models", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true - }, - "vertex_ai/mistral-large@2411-001": { - "max_tokens": 8191, - "max_input_tokens": 128000, - "max_output_tokens": 8191, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 6e-06, - "litellm_provider": "vertex_ai-mistral_models", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true - }, - "vertex_ai/mistral-large-2411": { - "max_tokens": 8191, - "max_input_tokens": 128000, - "max_output_tokens": 8191, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 6e-06, - "litellm_provider": "vertex_ai-mistral_models", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true - }, - "vertex_ai/mistral-large@2407": { - "max_tokens": 8191, - "max_input_tokens": 128000, - "max_output_tokens": 8191, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 6e-06, - "litellm_provider": "vertex_ai-mistral_models", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true - }, - "vertex_ai/mistral-nemo@latest": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 1.5e-07, - "litellm_provider": "vertex_ai-mistral_models", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true - }, - "vertex_ai/mistral-small-2503@001": { - "max_tokens": 8191, - "max_input_tokens": 32000, - "max_output_tokens": 8191, - "input_cost_per_token": 1e-06, - "output_cost_per_token": 3e-06, - "litellm_provider": "vertex_ai-mistral_models", - "supports_function_calling": true, - "mode": "chat", - "supports_tool_choice": true - }, - "vertex_ai/mistral-small-2503": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "input_cost_per_token": 1e-06, - "output_cost_per_token": 3e-06, - "litellm_provider": "vertex_ai-mistral_models", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "supports_tool_choice": true - }, - "vertex_ai/jamba-1.5-mini@001": { - "max_tokens": 256000, - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "input_cost_per_token": 2e-07, - "output_cost_per_token": 4e-07, - "litellm_provider": "vertex_ai-ai21_models", - "mode": "chat", - "supports_tool_choice": true - }, - "vertex_ai/jamba-1.5-large@001": { - "max_tokens": 256000, - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 8e-06, - "litellm_provider": "vertex_ai-ai21_models", - "mode": "chat", - "supports_tool_choice": true - }, - "vertex_ai/jamba-1.5": { - "max_tokens": 256000, - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "input_cost_per_token": 2e-07, - "output_cost_per_token": 4e-07, - "litellm_provider": "vertex_ai-ai21_models", - "mode": "chat", - "supports_tool_choice": true - }, - "vertex_ai/jamba-1.5-mini": { - "max_tokens": 256000, - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "input_cost_per_token": 2e-07, - "output_cost_per_token": 4e-07, - "litellm_provider": "vertex_ai-ai21_models", - "mode": "chat", - "supports_tool_choice": true - }, - "vertex_ai/jamba-1.5-large": { - "max_tokens": 256000, - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 8e-06, - "litellm_provider": "vertex_ai-ai21_models", - "mode": "chat", - "supports_tool_choice": true - }, - "vertex_ai/mistral-nemo@2407": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 3e-06, - "litellm_provider": "vertex_ai-mistral_models", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true - }, - "vertex_ai/codestral@latest": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "input_cost_per_token": 2e-07, - "output_cost_per_token": 6e-07, - "litellm_provider": "vertex_ai-mistral_models", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true - }, - "vertex_ai/codestral@2405": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "input_cost_per_token": 2e-07, - "output_cost_per_token": 6e-07, - "litellm_provider": "vertex_ai-mistral_models", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true - }, - "vertex_ai/codestral-2501": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "input_cost_per_token": 2e-07, - "output_cost_per_token": 6e-07, - "litellm_provider": "vertex_ai-mistral_models", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true - }, - "vertex_ai/imagegeneration@006": { - "output_cost_per_image": 0.02, - "litellm_provider": "vertex_ai-image-models", - "mode": "image_generation", - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" - }, - "vertex_ai/imagen-4.0-generate-001": { - "output_cost_per_image": 0.04, - "litellm_provider": "vertex_ai-image-models", - "mode": "image_generation", - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" - }, - "vertex_ai/imagen-4.0-ultra-generate-001": { - "output_cost_per_image": 0.06, - "litellm_provider": "vertex_ai-image-models", - "mode": "image_generation", - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" - }, - "vertex_ai/imagen-4.0-fast-generate-001": { - "output_cost_per_image": 0.02, - "litellm_provider": "vertex_ai-image-models", - "mode": "image_generation", - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" - }, - "vertex_ai/imagen-3.0-generate-002": { - "output_cost_per_image": 0.04, - "litellm_provider": "vertex_ai-image-models", - "mode": "image_generation", - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" - }, - "vertex_ai/imagen-3.0-generate-001": { - "output_cost_per_image": 0.04, - "litellm_provider": "vertex_ai-image-models", - "mode": "image_generation", - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" - }, - "vertex_ai/imagen-3.0-fast-generate-001": { - "output_cost_per_image": 0.02, - "litellm_provider": "vertex_ai-image-models", - "mode": "image_generation", - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" - }, - "vertex_ai/veo-3.0-generate-preview": { - "max_tokens": 1024, - "max_input_tokens": 1024, - "output_cost_per_second": 0.75, - "litellm_provider": "vertex_ai-video-models", - "mode": "video_generation", - "supported_modalities": [ - "text" - ], - "supported_output_modalities": [ - "video" - ], - "source": "https://ai.google.dev/gemini-api/docs/video" - }, - "vertex_ai/veo-3.0-fast-generate-preview": { - "max_tokens": 1024, - "max_input_tokens": 1024, - "output_cost_per_second": 0.40, - "litellm_provider": "vertex_ai-video-models", - "mode": "video_generation", - "supported_modalities": [ - "text" - ], - "supported_output_modalities": [ - "video" - ], - "source": "https://ai.google.dev/gemini-api/docs/video" - }, - "vertex_ai/veo-2.0-generate-001": { - "max_tokens": 1024, - "max_input_tokens": 1024, - "output_cost_per_second": 0.35, - "litellm_provider": "vertex_ai-video-models", - "mode": "video_generation", - "supported_modalities": [ - "text" - ], - "supported_output_modalities": [ - "video" - ], - "source": "https://ai.google.dev/gemini-api/docs/video" - }, - "text-embedding-004": { - "max_tokens": 2048, - "max_input_tokens": 2048, - "output_vector_size": 768, - "input_cost_per_character": 2.5e-08, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 0, - "litellm_provider": "vertex_ai-embedding-models", - "mode": "embedding", - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models" - }, - "gemini-embedding-001": { - "max_tokens": 2048, - "max_input_tokens": 2048, - "output_vector_size": 3072, - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 0, - "litellm_provider": "vertex_ai-embedding-models", - "mode": "embedding", - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models" - }, - "text-embedding-005": { - "max_tokens": 2048, - "max_input_tokens": 2048, - "output_vector_size": 768, - "input_cost_per_character": 2.5e-08, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 0, - "litellm_provider": "vertex_ai-embedding-models", - "mode": "embedding", - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models" - }, - "text-multilingual-embedding-002": { - "max_tokens": 2048, - "max_input_tokens": 2048, - "output_vector_size": 768, - "input_cost_per_character": 2.5e-08, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 0, - "litellm_provider": "vertex_ai-embedding-models", - "mode": "embedding", - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models" - }, - "multimodalembedding": { - "max_tokens": 2048, - "max_input_tokens": 2048, - "output_vector_size": 768, - "input_cost_per_character": 2e-07, - "input_cost_per_image": 0.0001, - "input_cost_per_video_per_second": 0.0005, - "input_cost_per_video_per_second_above_8s_interval": 0.001, - "input_cost_per_video_per_second_above_15s_interval": 0.002, - "input_cost_per_token": 8e-07, - "output_cost_per_token": 0, - "litellm_provider": "vertex_ai-embedding-models", - "mode": "embedding", + "output_cost_per_reasoning_token": 2.5e-06, + "output_cost_per_token": 2.5e-06, + "rpm": 100000, + "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", "supported_endpoints": [ - "/v1/embeddings" + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" ], "supported_modalities": [ "text", "image", + "audio", "video" ], - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models" + "supported_output_modalities": [ + "text" + ], + "supports_audio_output": false, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 8000000 }, - "multimodalembedding@001": { - "max_tokens": 2048, - "max_input_tokens": 2048, - "output_vector_size": 768, - "input_cost_per_character": 2e-07, - "input_cost_per_image": 0.0001, - "input_cost_per_video_per_second": 0.0005, - "input_cost_per_video_per_second_above_8s_interval": 0.001, - "input_cost_per_video_per_second_above_15s_interval": 0.002, - "input_cost_per_token": 8e-07, - "output_cost_per_token": 0, - "litellm_provider": "vertex_ai-embedding-models", - "mode": "embedding", + "gemini/gemini-2.5-flash-image-preview": { + "cache_read_input_token_cost": 7.5e-08, + "input_cost_per_audio_token": 1e-06, + "input_cost_per_token": 3e-07, + "litellm_provider": "gemini", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_image": 0.039, + "output_cost_per_reasoning_token": 3e-05, + "output_cost_per_token": 3e-05, + "rpm": 100000, + "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", "supported_endpoints": [ - "/v1/embeddings" + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" ], "supported_modalities": [ "text", "image", + "audio", "video" ], - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models" + "supported_output_modalities": [ + "text", + "image" + ], + "supports_audio_output": false, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 8000000 }, - "text-embedding-large-exp-03-07": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "output_vector_size": 3072, - "input_cost_per_character": 2.5e-08, + "gemini/gemini-2.5-flash-lite": { + "cache_read_input_token_cost": 2.5e-08, + "input_cost_per_audio_token": 5e-07, "input_cost_per_token": 1e-07, - "output_cost_per_token": 0, - "litellm_provider": "vertex_ai-embedding-models", - "mode": "embedding", - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models" - }, - "textembedding-gecko": { - "max_tokens": 3072, - "max_input_tokens": 3072, - "output_vector_size": 768, - "input_cost_per_character": 2.5e-08, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 0, - "litellm_provider": "vertex_ai-embedding-models", - "mode": "embedding", - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" - }, - "textembedding-gecko-multilingual": { - "max_tokens": 3072, - "max_input_tokens": 3072, - "output_vector_size": 768, - "input_cost_per_character": 2.5e-08, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 0, - "litellm_provider": "vertex_ai-embedding-models", - "mode": "embedding", - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" - }, - "textembedding-gecko-multilingual@001": { - "max_tokens": 3072, - "max_input_tokens": 3072, - "output_vector_size": 768, - "input_cost_per_character": 2.5e-08, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 0, - "litellm_provider": "vertex_ai-embedding-models", - "mode": "embedding", - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" - }, - "textembedding-gecko@001": { - "max_tokens": 3072, - "max_input_tokens": 3072, - "output_vector_size": 768, - "input_cost_per_character": 2.5e-08, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 0, - "litellm_provider": "vertex_ai-embedding-models", - "mode": "embedding", - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" - }, - "textembedding-gecko@003": { - "max_tokens": 3072, - "max_input_tokens": 3072, - "output_vector_size": 768, - "input_cost_per_character": 2.5e-08, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 0, - "litellm_provider": "vertex_ai-embedding-models", - "mode": "embedding", - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" - }, - "text-embedding-preview-0409": { - "max_tokens": 3072, - "max_input_tokens": 3072, - "output_vector_size": 768, - "input_cost_per_token": 6.25e-09, - "input_cost_per_token_batch_requests": 5e-09, - "output_cost_per_token": 0, - "litellm_provider": "vertex_ai-embedding-models", - "mode": "embedding", - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" - }, - "text-multilingual-embedding-preview-0409": { - "max_tokens": 3072, - "max_input_tokens": 3072, - "output_vector_size": 768, - "input_cost_per_token": 6.25e-09, - "output_cost_per_token": 0, - "litellm_provider": "vertex_ai-embedding-models", - "mode": "embedding", - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" - }, - "palm/chat-bison": { - "max_tokens": 4096, - "max_input_tokens": 8192, - "max_output_tokens": 4096, - "input_cost_per_token": 1.25e-07, - "output_cost_per_token": 1.25e-07, - "litellm_provider": "palm", - "mode": "chat", - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" - }, - "palm/chat-bison-001": { - "max_tokens": 4096, - "max_input_tokens": 8192, - "max_output_tokens": 4096, - "input_cost_per_token": 1.25e-07, - "output_cost_per_token": 1.25e-07, - "litellm_provider": "palm", - "mode": "chat", - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" - }, - "palm/text-bison": { - "max_tokens": 1024, - "max_input_tokens": 8192, - "max_output_tokens": 1024, - "input_cost_per_token": 1.25e-07, - "output_cost_per_token": 1.25e-07, - "litellm_provider": "palm", - "mode": "completion", - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" - }, - "palm/text-bison-001": { - "max_tokens": 1024, - "max_input_tokens": 8192, - "max_output_tokens": 1024, - "input_cost_per_token": 1.25e-07, - "output_cost_per_token": 1.25e-07, - "litellm_provider": "palm", - "mode": "completion", - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" - }, - "palm/text-bison-safety-off": { - "max_tokens": 1024, - "max_input_tokens": 8192, - "max_output_tokens": 1024, - "input_cost_per_token": 1.25e-07, - "output_cost_per_token": 1.25e-07, - "litellm_provider": "palm", - "mode": "completion", - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" - }, - "palm/text-bison-safety-recitation-off": { - "max_tokens": 1024, - "max_input_tokens": 8192, - "max_output_tokens": 1024, - "input_cost_per_token": 1.25e-07, - "output_cost_per_token": 1.25e-07, - "litellm_provider": "palm", - "mode": "completion", - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" - }, - "gemini/gemini-1.5-flash-002": { - "max_tokens": 8192, - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, + "litellm_provider": "gemini", "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, "max_pdf_size_mb": 30, - "cache_read_input_token_cost": 1.875e-08, - "cache_creation_input_token_cost": 1e-06, - "input_cost_per_token": 7.5e-08, - "input_cost_per_token_above_128k_tokens": 1.5e-07, - "output_cost_per_token": 3e-07, - "output_cost_per_token_above_128k_tokens": 6e-07, - "litellm_provider": "gemini", + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, "mode": "chat", - "supports_system_messages": true, + "output_cost_per_reasoning_token": 4e-07, + "output_cost_per_token": 4e-07, + "rpm": 15, + "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-lite", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_output": false, "supports_function_calling": true, - "supports_vision": true, - "supports_response_schema": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, "supports_prompt_caching": true, - "tpm": 4000000, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 250000 + }, + "gemini/gemini-2.5-flash-lite-preview-06-17": { + "cache_read_input_token_cost": 2.5e-08, + "input_cost_per_audio_token": 5e-07, + "input_cost_per_token": 1e-07, + "litellm_provider": "gemini", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_reasoning_token": 4e-07, + "output_cost_per_token": 4e-07, + "rpm": 15, + "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-lite", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_output": false, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 250000 + }, + "gemini/gemini-2.5-flash-preview-04-17": { + "cache_read_input_token_cost": 3.75e-08, + "input_cost_per_audio_token": 1e-06, + "input_cost_per_token": 1.5e-07, + "litellm_provider": "gemini", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_reasoning_token": 3.5e-06, + "output_cost_per_token": 6e-07, + "rpm": 10, + "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_output": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 250000 + }, + "gemini/gemini-2.5-flash-preview-05-20": { + "cache_read_input_token_cost": 7.5e-08, + "input_cost_per_audio_token": 1e-06, + "input_cost_per_token": 3e-07, + "litellm_provider": "gemini", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_reasoning_token": 2.5e-06, + "output_cost_per_token": 2.5e-06, + "rpm": 10, + "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_output": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 250000 + }, + "gemini/gemini-2.5-flash-preview-tts": { + "cache_read_input_token_cost": 3.75e-08, + "input_cost_per_audio_token": 1e-06, + "input_cost_per_token": 1.5e-07, + "litellm_provider": "gemini", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_reasoning_token": 3.5e-06, + "output_cost_per_token": 6e-07, + "rpm": 10, + "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "audio" + ], + "supports_audio_output": false, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 250000 + }, + "gemini/gemini-2.5-pro": { + "cache_read_input_token_cost": 3.125e-07, + "input_cost_per_token": 1.25e-06, + "input_cost_per_token_above_200k_tokens": 2.5e-06, + "litellm_provider": "gemini", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_token": 1e-05, + "output_cost_per_token_above_200k_tokens": 1.5e-05, "rpm": 2000, - "source": "https://ai.google.dev/pricing", - "deprecation_date": "2025-09-24", - "supports_tool_choice": true - }, - "gemini/gemini-1.5-flash-001": { - "max_tokens": 8192, - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_pdf_size_mb": 30, - "cache_read_input_token_cost": 1.875e-08, - "cache_creation_input_token_cost": 1e-06, - "input_cost_per_token": 7.5e-08, - "input_cost_per_token_above_128k_tokens": 1.5e-07, - "output_cost_per_token": 3e-07, - "output_cost_per_token_above_128k_tokens": 6e-07, - "litellm_provider": "gemini", - "mode": "chat", - "supports_system_messages": true, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true, "supports_function_calling": true, - "supports_vision": true, - "supports_response_schema": true, + "supports_pdf_input": true, "supports_prompt_caching": true, - "tpm": 4000000, - "rpm": 2000, - "source": "https://ai.google.dev/pricing", - "deprecation_date": "2025-05-24", - "supports_tool_choice": true + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 800000 }, - "gemini/gemini-1.5-flash": { - "max_tokens": 8192, - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, + "gemini/gemini-2.5-pro-exp-03-25": { + "cache_read_input_token_cost": 0.0, + "input_cost_per_token": 0.0, + "input_cost_per_token_above_200k_tokens": 0.0, + "litellm_provider": "gemini", "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, - "max_pdf_size_mb": 30, - "input_cost_per_token": 7.5e-08, - "input_cost_per_token_above_128k_tokens": 1.5e-07, - "output_cost_per_token": 3e-07, - "output_cost_per_token_above_128k_tokens": 6e-07, - "litellm_provider": "gemini", - "mode": "chat", - "supports_system_messages": true, - "supports_function_calling": true, - "supports_vision": true, - "supports_response_schema": true, - "tpm": 4000000, - "rpm": 2000, - "source": "https://ai.google.dev/pricing", - "supports_tool_choice": true - }, - "gemini/gemini-1.5-flash-latest": { - "max_tokens": 8192, - "max_input_tokens": 1048576, - "max_output_tokens": 8192, "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, "max_pdf_size_mb": 30, - "input_cost_per_token": 7.5e-08, - "input_cost_per_token_above_128k_tokens": 1.5e-07, - "output_cost_per_token": 3e-07, - "output_cost_per_token_above_128k_tokens": 6e-07, - "litellm_provider": "gemini", + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, "mode": "chat", - "supports_system_messages": true, + "output_cost_per_token": 0.0, + "output_cost_per_token_above_200k_tokens": 0.0, + "rpm": 5, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true, "supports_function_calling": true, - "supports_vision": true, - "supports_response_schema": true, + "supports_pdf_input": true, "supports_prompt_caching": true, - "tpm": 4000000, - "rpm": 2000, - "source": "https://ai.google.dev/pricing", - "supports_tool_choice": true + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 250000 }, - "gemini/gemini-1.5-flash-8b": { - "max_tokens": 8192, - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, + "gemini/gemini-2.5-pro-preview-03-25": { + "cache_read_input_token_cost": 3.125e-07, + "input_cost_per_audio_token": 7e-07, + "input_cost_per_token": 1.25e-06, + "input_cost_per_token_above_200k_tokens": 2.5e-06, + "litellm_provider": "gemini", "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, - "max_pdf_size_mb": 30, - "input_cost_per_token": 0, - "input_cost_per_token_above_128k_tokens": 0, - "output_cost_per_token": 0, - "output_cost_per_token_above_128k_tokens": 0, - "litellm_provider": "gemini", - "mode": "chat", - "supports_system_messages": true, - "supports_function_calling": true, - "supports_vision": true, - "supports_response_schema": true, - "supports_prompt_caching": true, - "tpm": 4000000, - "rpm": 4000, - "source": "https://ai.google.dev/pricing", - "supports_tool_choice": true - }, - "gemini/gemini-1.5-flash-8b-exp-0924": { - "max_tokens": 8192, - "max_input_tokens": 1048576, - "max_output_tokens": 8192, "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_token": 1e-05, + "output_cost_per_token_above_200k_tokens": 1.5e-05, + "rpm": 10000, + "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-pro-preview", + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_output": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 10000000 + }, + "gemini/gemini-2.5-pro-preview-05-06": { + "cache_read_input_token_cost": 3.125e-07, + "input_cost_per_audio_token": 7e-07, + "input_cost_per_token": 1.25e-06, + "input_cost_per_token_above_200k_tokens": 2.5e-06, + "litellm_provider": "gemini", "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, "max_pdf_size_mb": 30, - "input_cost_per_token": 0, - "input_cost_per_token_above_128k_tokens": 0, - "output_cost_per_token": 0, - "output_cost_per_token_above_128k_tokens": 0, - "litellm_provider": "gemini", + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, "mode": "chat", - "supports_system_messages": true, + "output_cost_per_token": 1e-05, + "output_cost_per_token_above_200k_tokens": 1.5e-05, + "rpm": 10000, + "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-pro-preview", + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_output": false, "supports_function_calling": true, - "supports_vision": true, - "supports_response_schema": true, + "supports_pdf_input": true, "supports_prompt_caching": true, - "tpm": 4000000, - "rpm": 4000, - "source": "https://ai.google.dev/pricing", - "supports_tool_choice": true + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 10000000 + }, + "gemini/gemini-2.5-pro-preview-06-05": { + "cache_read_input_token_cost": 3.125e-07, + "input_cost_per_audio_token": 7e-07, + "input_cost_per_token": 1.25e-06, + "input_cost_per_token_above_200k_tokens": 2.5e-06, + "litellm_provider": "gemini", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_token": 1e-05, + "output_cost_per_token_above_200k_tokens": 1.5e-05, + "rpm": 10000, + "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-pro-preview", + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_output": false, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 10000000 + }, + "gemini/gemini-2.5-pro-preview-tts": { + "cache_read_input_token_cost": 3.125e-07, + "input_cost_per_audio_token": 7e-07, + "input_cost_per_token": 1.25e-06, + "input_cost_per_token_above_200k_tokens": 2.5e-06, + "litellm_provider": "gemini", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65535, + "max_pdf_size_mb": 30, + "max_tokens": 65535, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_token": 1e-05, + "output_cost_per_token_above_200k_tokens": 1.5e-05, + "rpm": 10000, + "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-pro-preview", + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "audio" + ], + "supports_audio_output": false, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 10000000 }, "gemini/gemini-exp-1114": { - "max_tokens": 8192, - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_pdf_size_mb": 30, "input_cost_per_token": 0, "input_cost_per_token_above_128k_tokens": 0, - "output_cost_per_token": 0, - "output_cost_per_token_above_128k_tokens": 0, "litellm_provider": "gemini", - "mode": "chat", - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_function_calling": true, - "supports_vision": true, - "supports_response_schema": true, - "tpm": 4000000, - "rpm": 1000, - "source": "https://ai.google.dev/pricing", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, "metadata": { "notes": "Rate limits not documented for gemini-exp-1114. Assuming same as gemini-1.5-pro.", "supports_tool_choice": true - } - }, - "gemini/gemini-exp-1206": { - "max_tokens": 8192, - "max_input_tokens": 2097152, - "max_output_tokens": 8192, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_pdf_size_mb": 30, - "input_cost_per_token": 0, - "input_cost_per_token_above_128k_tokens": 0, + }, + "mode": "chat", "output_cost_per_token": 0, "output_cost_per_token_above_128k_tokens": 0, - "litellm_provider": "gemini", - "mode": "chat", - "supports_system_messages": true, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_vision": true, - "supports_response_schema": true, - "tpm": 4000000, "rpm": 1000, "source": "https://ai.google.dev/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "tpm": 4000000 + }, + "gemini/gemini-exp-1206": { + "input_cost_per_token": 0, + "input_cost_per_token_above_128k_tokens": 0, + "litellm_provider": "gemini", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 2097152, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, "metadata": { "notes": "Rate limits not documented for gemini-exp-1206. Assuming same as gemini-1.5-pro.", "supports_tool_choice": true - } - }, - "gemini/gemini-1.5-flash-exp-0827": { - "max_tokens": 8192, - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_pdf_size_mb": 30, - "input_cost_per_token": 0, - "input_cost_per_token_above_128k_tokens": 0, + }, + "mode": "chat", "output_cost_per_token": 0, "output_cost_per_token_above_128k_tokens": 0, - "litellm_provider": "gemini", - "mode": "chat", - "supports_system_messages": true, - "supports_function_calling": true, - "supports_vision": true, - "supports_response_schema": true, - "tpm": 4000000, - "rpm": 2000, - "source": "https://ai.google.dev/pricing", - "supports_tool_choice": true - }, - "gemini/gemini-1.5-flash-8b-exp-0827": { - "max_tokens": 8192, - "max_input_tokens": 1000000, - "max_output_tokens": 8192, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_pdf_size_mb": 30, - "input_cost_per_token": 0, - "input_cost_per_token_above_128k_tokens": 0, - "output_cost_per_token": 0, - "output_cost_per_token_above_128k_tokens": 0, - "litellm_provider": "gemini", - "mode": "chat", - "supports_system_messages": true, - "supports_function_calling": true, - "supports_vision": true, - "supports_response_schema": true, - "tpm": 4000000, - "rpm": 4000, - "source": "https://ai.google.dev/pricing", - "supports_tool_choice": true - }, - "gemini/gemini-pro": { - "max_tokens": 8192, - "max_input_tokens": 32760, - "max_output_tokens": 8192, - "input_cost_per_token": 3.5e-07, - "input_cost_per_token_above_128k_tokens": 7e-07, - "output_cost_per_token": 1.05e-06, - "output_cost_per_token_above_128k_tokens": 2.1e-06, - "litellm_provider": "gemini", - "mode": "chat", - "supports_function_calling": true, - "rpd": 30000, - "tpm": 120000, - "rpm": 360, - "source": "https://ai.google.dev/gemini-api/docs/models/gemini", - "supports_tool_choice": true - }, - "gemini/gemini-1.5-pro": { - "max_tokens": 8192, - "max_input_tokens": 2097152, - "max_output_tokens": 8192, - "input_cost_per_token": 3.5e-06, - "input_cost_per_token_above_128k_tokens": 7e-06, - "output_cost_per_token": 1.05e-05, - "output_cost_per_token_above_128k_tokens": 2.1e-05, - "litellm_provider": "gemini", - "mode": "chat", - "supports_system_messages": true, - "supports_function_calling": true, - "supports_vision": true, - "supports_tool_choice": true, - "supports_response_schema": true, - "tpm": 4000000, - "rpm": 1000, - "source": "https://ai.google.dev/pricing" - }, - "gemini/gemini-1.5-pro-002": { - "max_tokens": 8192, - "max_input_tokens": 2097152, - "max_output_tokens": 8192, - "input_cost_per_token": 3.5e-06, - "input_cost_per_token_above_128k_tokens": 7e-06, - "output_cost_per_token": 1.05e-05, - "output_cost_per_token_above_128k_tokens": 2.1e-05, - "litellm_provider": "gemini", - "mode": "chat", - "supports_system_messages": true, - "supports_function_calling": true, - "supports_vision": true, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_prompt_caching": true, - "tpm": 4000000, "rpm": 1000, "source": "https://ai.google.dev/pricing", - "deprecation_date": "2025-09-24" - }, - "gemini/gemini-1.5-pro-001": { - "max_tokens": 8192, - "max_input_tokens": 2097152, - "max_output_tokens": 8192, - "input_cost_per_token": 3.5e-06, - "input_cost_per_token_above_128k_tokens": 7e-06, - "output_cost_per_token": 1.05e-05, - "output_cost_per_token_above_128k_tokens": 2.1e-05, - "litellm_provider": "gemini", - "mode": "chat", - "supports_system_messages": true, "supports_function_calling": true, - "supports_vision": true, - "supports_tool_choice": true, "supports_response_schema": true, - "supports_prompt_caching": true, - "tpm": 4000000, - "rpm": 1000, - "source": "https://ai.google.dev/pricing", - "deprecation_date": "2025-05-24" - }, - "gemini/gemini-1.5-pro-exp-0801": { - "max_tokens": 8192, - "max_input_tokens": 2097152, - "max_output_tokens": 8192, - "input_cost_per_token": 3.5e-06, - "input_cost_per_token_above_128k_tokens": 7e-06, - "output_cost_per_token": 1.05e-05, - "output_cost_per_token_above_128k_tokens": 2.1e-05, - "litellm_provider": "gemini", - "mode": "chat", "supports_system_messages": true, - "supports_function_calling": true, - "supports_vision": true, "supports_tool_choice": true, - "supports_response_schema": true, - "tpm": 4000000, - "rpm": 1000, - "source": "https://ai.google.dev/pricing" - }, - "gemini/gemini-1.5-pro-exp-0827": { - "max_tokens": 8192, - "max_input_tokens": 2097152, - "max_output_tokens": 8192, - "input_cost_per_token": 0, - "input_cost_per_token_above_128k_tokens": 0, - "output_cost_per_token": 0, - "output_cost_per_token_above_128k_tokens": 0, - "litellm_provider": "gemini", - "mode": "chat", - "supports_system_messages": true, - "supports_function_calling": true, "supports_vision": true, - "supports_tool_choice": true, - "supports_response_schema": true, - "tpm": 4000000, - "rpm": 1000, - "source": "https://ai.google.dev/pricing" - }, - "gemini/gemini-1.5-pro-latest": { - "max_tokens": 8192, - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "input_cost_per_token": 3.5e-06, - "input_cost_per_token_above_128k_tokens": 7e-06, - "output_cost_per_token": 1.05e-06, - "output_cost_per_token_above_128k_tokens": 2.1e-05, - "litellm_provider": "gemini", - "mode": "chat", - "supports_system_messages": true, - "supports_function_calling": true, - "supports_vision": true, - "supports_tool_choice": true, - "supports_response_schema": true, - "tpm": 4000000, - "rpm": 1000, - "source": "https://ai.google.dev/pricing" - }, - "gemini/gemini-pro-vision": { - "max_tokens": 2048, - "max_input_tokens": 30720, - "max_output_tokens": 2048, - "input_cost_per_token": 3.5e-07, - "input_cost_per_token_above_128k_tokens": 7e-07, - "output_cost_per_token": 1.05e-06, - "output_cost_per_token_above_128k_tokens": 2.1e-06, - "litellm_provider": "gemini", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "rpd": 30000, - "tpm": 120000, - "rpm": 360, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", - "supports_tool_choice": true + "tpm": 4000000 }, "gemini/gemini-gemma-2-27b-it": { - "max_tokens": 8192, - "max_output_tokens": 8192, "input_cost_per_token": 3.5e-07, - "output_cost_per_token": 1.05e-06, "litellm_provider": "gemini", + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, + "output_cost_per_token": 1.05e-06, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", - "supports_tool_choice": true + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true }, "gemini/gemini-gemma-2-9b-it": { - "max_tokens": 8192, - "max_output_tokens": 8192, "input_cost_per_token": 3.5e-07, - "output_cost_per_token": 1.05e-06, "litellm_provider": "gemini", + "max_output_tokens": 8192, + "max_tokens": 8192, "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, + "output_cost_per_token": 1.05e-06, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", - "supports_tool_choice": true + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true }, - "gemini/imagen-4.0-generate-001": { - "output_cost_per_image": 0.04, + "gemini/gemini-pro": { + "input_cost_per_token": 3.5e-07, + "input_cost_per_token_above_128k_tokens": 7e-07, + "litellm_provider": "gemini", + "max_input_tokens": 32760, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.05e-06, + "output_cost_per_token_above_128k_tokens": 2.1e-06, + "rpd": 30000, + "rpm": 360, + "source": "https://ai.google.dev/gemini-api/docs/models/gemini", + "supports_function_calling": true, + "supports_tool_choice": true, + "tpm": 120000 + }, + "gemini/gemini-pro-vision": { + "input_cost_per_token": 3.5e-07, + "input_cost_per_token_above_128k_tokens": 7e-07, + "litellm_provider": "gemini", + "max_input_tokens": 30720, + "max_output_tokens": 2048, + "max_tokens": 2048, + "mode": "chat", + "output_cost_per_token": 1.05e-06, + "output_cost_per_token_above_128k_tokens": 2.1e-06, + "rpd": 30000, + "rpm": 360, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true, + "tpm": 120000 + }, + "gemini/gemma-3-27b-it": { + "input_cost_per_audio_per_second": 0, + "input_cost_per_audio_per_second_above_128k_tokens": 0, + "input_cost_per_character": 0, + "input_cost_per_character_above_128k_tokens": 0, + "input_cost_per_image": 0, + "input_cost_per_image_above_128k_tokens": 0, + "input_cost_per_token": 0, + "input_cost_per_token_above_128k_tokens": 0, + "input_cost_per_video_per_second": 0, + "input_cost_per_video_per_second_above_128k_tokens": 0, + "litellm_provider": "gemini", + "max_input_tokens": 131072, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_character": 0, + "output_cost_per_character_above_128k_tokens": 0, + "output_cost_per_token": 0, + "output_cost_per_token_above_128k_tokens": 0, + "source": "https://aistudio.google.com", + "supports_audio_output": false, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "gemini/imagen-3.0-fast-generate-001": { "litellm_provider": "gemini", "mode": "image_generation", - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" - }, - "gemini/imagen-4.0-ultra-generate-001": { - "output_cost_per_image": 0.06, - "litellm_provider": "gemini", - "mode": "image_generation", - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" - }, - "gemini/imagen-4.0-fast-generate-001": { "output_cost_per_image": 0.02, - "litellm_provider": "gemini", - "mode": "image_generation", - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" - }, - "gemini/imagen-3.0-generate-002": { - "output_cost_per_image": 0.04, - "litellm_provider": "gemini", - "mode": "image_generation", "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" }, "gemini/imagen-3.0-generate-001": { - "output_cost_per_image": 0.04, "litellm_provider": "gemini", "mode": "image_generation", + "output_cost_per_image": 0.04, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" }, - "gemini/imagen-3.0-fast-generate-001": { + "gemini/imagen-3.0-generate-002": { + "litellm_provider": "gemini", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" + }, + "gemini/imagen-4.0-fast-generate-001": { + "litellm_provider": "gemini", + "mode": "image_generation", "output_cost_per_image": 0.02, - "litellm_provider": "gemini", - "mode": "image_generation", "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" }, - "command-a-03-2025": { - "max_tokens": 8000, - "max_input_tokens": 256000, - "max_output_tokens": 8000, - "input_cost_per_token": 2.5e-06, - "output_cost_per_token": 1e-05, - "litellm_provider": "cohere_chat", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true - }, - "command-r": { - "max_tokens": 4096, - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 6e-07, - "litellm_provider": "cohere_chat", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true - }, - "command-r-08-2024": { - "max_tokens": 4096, - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 6e-07, - "litellm_provider": "cohere_chat", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true - }, - "command-r7b-12-2024": { - "max_tokens": 4096, - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 3.75e-08, - "litellm_provider": "cohere_chat", - "mode": "chat", - "supports_function_calling": true, - "source": "https://docs.cohere.com/v2/docs/command-r7b", - "supports_tool_choice": true - }, - "command-light": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 3e-07, - "output_cost_per_token": 6e-07, - "litellm_provider": "cohere_chat", - "mode": "chat", - "supports_tool_choice": true - }, - "command-r-plus": { - "max_tokens": 4096, - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 2.5e-06, - "output_cost_per_token": 1e-05, - "litellm_provider": "cohere_chat", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true - }, - "command-r-plus-08-2024": { - "max_tokens": 4096, - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 2.5e-06, - "output_cost_per_token": 1e-05, - "litellm_provider": "cohere_chat", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true - }, - "command-nightly": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 1e-06, - "output_cost_per_token": 2e-06, - "litellm_provider": "cohere", - "mode": "completion" - }, - "command": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 1e-06, - "output_cost_per_token": 2e-06, - "litellm_provider": "cohere", - "mode": "completion" - }, - "rerank-v3.5": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "max_query_tokens": 2048, - "input_cost_per_token": 0.0, - "input_cost_per_query": 0.002, - "output_cost_per_token": 0.0, - "litellm_provider": "cohere", - "mode": "rerank" - }, - "rerank-english-v3.0": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "max_query_tokens": 2048, - "input_cost_per_token": 0.0, - "input_cost_per_query": 0.002, - "output_cost_per_token": 0.0, - "litellm_provider": "cohere", - "mode": "rerank" - }, - "rerank-multilingual-v3.0": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "max_query_tokens": 2048, - "input_cost_per_token": 0.0, - "input_cost_per_query": 0.002, - "output_cost_per_token": 0.0, - "litellm_provider": "cohere", - "mode": "rerank" - }, - "rerank-english-v2.0": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "max_query_tokens": 2048, - "input_cost_per_token": 0.0, - "input_cost_per_query": 0.002, - "output_cost_per_token": 0.0, - "litellm_provider": "cohere", - "mode": "rerank" - }, - "rerank-multilingual-v2.0": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "max_query_tokens": 2048, - "input_cost_per_token": 0.0, - "input_cost_per_query": 0.002, - "output_cost_per_token": 0.0, - "litellm_provider": "cohere", - "mode": "rerank" - }, - "embed-english-light-v3.0": { - "max_tokens": 1024, - "max_input_tokens": 1024, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 0.0, - "litellm_provider": "cohere", - "mode": "embedding" - }, - "embed-multilingual-v3.0": { - "max_tokens": 1024, - "max_input_tokens": 1024, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 0.0, - "litellm_provider": "cohere", - "supports_embedding_image_input": true, - "mode": "embedding" - }, - "embed-english-v2.0": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 0.0, - "litellm_provider": "cohere", - "mode": "embedding" - }, - "embed-english-light-v2.0": { - "max_tokens": 1024, - "max_input_tokens": 1024, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 0.0, - "litellm_provider": "cohere", - "mode": "embedding" - }, - "embed-multilingual-v2.0": { - "max_tokens": 768, - "max_input_tokens": 768, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 0.0, - "litellm_provider": "cohere", - "mode": "embedding" - }, - "embed-english-v3.0": { - "max_tokens": 1024, - "max_input_tokens": 1024, - "input_cost_per_token": 1e-07, - "input_cost_per_image": 0.0001, - "output_cost_per_token": 0.0, - "litellm_provider": "cohere", - "mode": "embedding", - "supports_image_input": true, - "supports_embedding_image_input": true, - "metadata": { - "notes": "'supports_image_input' is a deprecated field. Use 'supports_embedding_image_input' instead." - } - }, - "replicate/meta/llama-2-13b": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 5e-07, - "litellm_provider": "replicate", - "mode": "chat", - "supports_tool_choice": true - }, - "replicate/meta/llama-2-13b-chat": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 5e-07, - "litellm_provider": "replicate", - "mode": "chat", - "supports_tool_choice": true - }, - "replicate/meta/llama-2-70b": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 6.5e-07, - "output_cost_per_token": 2.75e-06, - "litellm_provider": "replicate", - "mode": "chat", - "supports_tool_choice": true - }, - "replicate/meta/llama-2-70b-chat": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 6.5e-07, - "output_cost_per_token": 2.75e-06, - "litellm_provider": "replicate", - "mode": "chat", - "supports_tool_choice": true - }, - "replicate/meta/llama-2-7b": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 5e-08, - "output_cost_per_token": 2.5e-07, - "litellm_provider": "replicate", - "mode": "chat", - "supports_tool_choice": true - }, - "replicate/meta/llama-2-7b-chat": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 5e-08, - "output_cost_per_token": 2.5e-07, - "litellm_provider": "replicate", - "mode": "chat", - "supports_tool_choice": true - }, - "replicate/meta/llama-3-70b": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 6.5e-07, - "output_cost_per_token": 2.75e-06, - "litellm_provider": "replicate", - "mode": "chat", - "supports_tool_choice": true - }, - "replicate/meta/llama-3-70b-instruct": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 6.5e-07, - "output_cost_per_token": 2.75e-06, - "litellm_provider": "replicate", - "mode": "chat", - "supports_tool_choice": true - }, - "replicate/meta/llama-3-8b": { - "max_tokens": 8086, - "max_input_tokens": 8086, - "max_output_tokens": 8086, - "input_cost_per_token": 5e-08, - "output_cost_per_token": 2.5e-07, - "litellm_provider": "replicate", - "mode": "chat", - "supports_tool_choice": true - }, - "replicate/meta/llama-3-8b-instruct": { - "max_tokens": 8086, - "max_input_tokens": 8086, - "max_output_tokens": 8086, - "input_cost_per_token": 5e-08, - "output_cost_per_token": 2.5e-07, - "litellm_provider": "replicate", - "mode": "chat", - "supports_tool_choice": true - }, - "replicate/mistralai/mistral-7b-v0.1": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 5e-08, - "output_cost_per_token": 2.5e-07, - "litellm_provider": "replicate", - "mode": "chat", - "supports_tool_choice": true - }, - "replicate/mistralai/mistral-7b-instruct-v0.2": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 5e-08, - "output_cost_per_token": 2.5e-07, - "litellm_provider": "replicate", - "mode": "chat", - "supports_tool_choice": true - }, - "replicate/mistralai/mixtral-8x7b-instruct-v0.1": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 3e-07, - "output_cost_per_token": 1e-06, - "litellm_provider": "replicate", - "mode": "chat", - "supports_tool_choice": true - }, - "openrouter/deepseek/deepseek-r1-0528": { - "max_tokens": 8192, - "max_input_tokens": 65336, - "max_output_tokens": 8192, - "input_cost_per_token": 5e-07, - "input_cost_per_token_cache_hit": 1.4e-07, - "output_cost_per_token": 2.15e-06, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_function_calling": true, - "supports_assistant_prefill": true, - "supports_reasoning": true, - "supports_tool_choice": true, - "supports_prompt_caching": true - }, - "openrouter/deepseek/deepseek-chat-v3.1": { - "max_tokens": 8192, - "max_input_tokens": 163840, - "max_output_tokens": 163840, - "input_cost_per_token": 2e-07, - "input_cost_per_token_cache_hit": 2e-08, - "output_cost_per_token": 8e-07, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_function_calling": true, - "supports_assistant_prefill": true, - "supports_reasoning": true, - "supports_tool_choice": true, - "supports_prompt_caching": true - }, - "openrouter/x-ai/grok-4": { - "max_tokens": 256000, - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "source": "https://openrouter.ai/x-ai/grok-4", - "supports_web_search": true - }, - "openrouter/bytedance/ui-tars-1.5-7b": { - "max_tokens": 2048, - "max_input_tokens": 131072, - "max_output_tokens": 2048, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 2e-07, - "litellm_provider": "openrouter", - "mode": "chat", - "source": "https://openrouter.ai/api/v1/models/bytedance/ui-tars-1.5-7b", - "supports_tool_choice": true - }, - "openrouter/deepseek/deepseek-r1": { - "max_tokens": 8192, - "max_input_tokens": 65336, - "max_output_tokens": 8192, - "input_cost_per_token": 5.5e-07, - "input_cost_per_token_cache_hit": 1.4e-07, - "output_cost_per_token": 2.19e-06, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_function_calling": true, - "supports_assistant_prefill": true, - "supports_reasoning": true, - "supports_tool_choice": true, - "supports_prompt_caching": true - }, - "openrouter/deepseek/deepseek-chat": { - "max_tokens": 8192, - "max_input_tokens": 65536, - "max_output_tokens": 8192, - "input_cost_per_token": 1.4e-07, - "output_cost_per_token": 2.8e-07, - "litellm_provider": "openrouter", - "supports_prompt_caching": true, - "mode": "chat", - "supports_tool_choice": true - }, - "openrouter/deepseek/deepseek-chat-v3-0324": { - "max_tokens": 8192, - "max_input_tokens": 65536, - "max_output_tokens": 8192, - "input_cost_per_token": 1.4e-07, - "output_cost_per_token": 2.8e-07, - "litellm_provider": "openrouter", - "supports_prompt_caching": true, - "mode": "chat", - "supports_tool_choice": true - }, - "openrouter/deepseek/deepseek-coder": { - "max_tokens": 8192, - "max_input_tokens": 66000, - "max_output_tokens": 4096, - "input_cost_per_token": 1.4e-07, - "output_cost_per_token": 2.8e-07, - "litellm_provider": "openrouter", - "supports_prompt_caching": true, - "mode": "chat", - "supports_tool_choice": true - }, - "openrouter/microsoft/wizardlm-2-8x22b:nitro": { - "max_tokens": 65536, - "input_cost_per_token": 1e-06, - "output_cost_per_token": 1e-06, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_tool_choice": true - }, - "openrouter/google/gemini-2.5-pro": { - "max_tokens": 8192, - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_pdf_size_mb": 30, - "input_cost_per_audio_token": 7e-07, - "input_cost_per_token": 1.25e-06, - "output_cost_per_token": 1e-05, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_system_messages": true, - "supports_function_calling": true, - "supports_vision": true, - "supports_response_schema": true, - "supports_audio_output": true, - "supports_tool_choice": true - }, - "openrouter/google/gemini-pro-1.5": { - "max_tokens": 8192, - "max_input_tokens": 1000000, - "max_output_tokens": 8192, - "input_cost_per_token": 2.5e-06, - "output_cost_per_token": 7.5e-06, - "input_cost_per_image": 0.00265, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "supports_tool_choice": true - }, - "openrouter/google/gemini-2.0-flash-001": { - "max_tokens": 8192, - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_pdf_size_mb": 30, - "input_cost_per_audio_token": 7e-07, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 4e-07, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_system_messages": true, - "supports_function_calling": true, - "supports_vision": true, - "supports_response_schema": true, - "supports_audio_output": true, - "supports_tool_choice": true - }, - "openrouter/google/gemini-2.5-flash": { - "max_tokens": 8192, - "max_input_tokens": 1048576, - "max_output_tokens": 8192, - "max_images_per_prompt": 3000, - "max_videos_per_prompt": 10, - "max_video_length": 1, - "max_audio_length_hours": 8.4, - "max_audio_per_prompt": 1, - "max_pdf_size_mb": 30, - "input_cost_per_audio_token": 7e-07, - "input_cost_per_token": 3e-07, - "output_cost_per_token": 2.5e-06, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_system_messages": true, - "supports_function_calling": true, - "supports_vision": true, - "supports_response_schema": true, - "supports_audio_output": true, - "supports_tool_choice": true - }, - "openrouter/mistralai/mixtral-8x22b-instruct": { - "max_tokens": 65536, - "input_cost_per_token": 6.5e-07, - "output_cost_per_token": 6.5e-07, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_tool_choice": true - }, - "openrouter/cohere/command-r-plus": { - "max_tokens": 128000, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_tool_choice": true - }, - "openrouter/databricks/dbrx-instruct": { - "max_tokens": 32768, - "input_cost_per_token": 6e-07, - "output_cost_per_token": 6e-07, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_tool_choice": true - }, - "openrouter/anthropic/claude-3-haiku": { - "max_tokens": 200000, - "input_cost_per_token": 2.5e-07, - "output_cost_per_token": 1.25e-06, - "input_cost_per_image": 0.0004, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "supports_tool_choice": true - }, - "openrouter/anthropic/claude-3-5-haiku": { - "max_tokens": 200000, - "input_cost_per_token": 1e-06, - "output_cost_per_token": 5e-06, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true - }, - "openrouter/anthropic/claude-3-haiku-20240307": { - "max_tokens": 4096, - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "input_cost_per_token": 2.5e-07, - "output_cost_per_token": 1.25e-06, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 264, - "supports_tool_choice": true - }, - "openrouter/anthropic/claude-3-5-haiku-20241022": { - "max_tokens": 8192, - "max_input_tokens": 200000, - "max_output_tokens": 8192, - "input_cost_per_token": 1e-06, - "output_cost_per_token": 5e-06, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_function_calling": true, - "tool_use_system_prompt_tokens": 264, - "supports_tool_choice": true - }, - "openrouter/anthropic/claude-3.5-sonnet": { - "supports_computer_use": true, - "max_tokens": 8192, - "max_input_tokens": 200000, - "max_output_tokens": 8192, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 159, - "supports_assistant_prefill": true, - "supports_tool_choice": true - }, - "openrouter/anthropic/claude-3.5-sonnet:beta": { - "supports_computer_use": true, - "max_tokens": 8192, - "max_input_tokens": 200000, - "max_output_tokens": 8192, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 159, - "supports_tool_choice": true - }, - "openrouter/anthropic/claude-3.7-sonnet": { - "supports_computer_use": true, - "max_tokens": 128000, - "max_input_tokens": 200000, - "max_output_tokens": 128000, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "input_cost_per_image": 0.0048, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "supports_reasoning": true, - "tool_use_system_prompt_tokens": 159, - "supports_assistant_prefill": true, - "supports_tool_choice": true - }, - "openrouter/anthropic/claude-3.7-sonnet:beta": { - "supports_computer_use": true, - "max_tokens": 128000, - "max_input_tokens": 200000, - "max_output_tokens": 128000, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "input_cost_per_image": 0.0048, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "supports_reasoning": true, - "tool_use_system_prompt_tokens": 159, - "supports_tool_choice": true - }, - "openrouter/anthropic/claude-3-sonnet": { - "max_tokens": 200000, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "input_cost_per_image": 0.0048, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "supports_tool_choice": true - }, - "openrouter/anthropic/claude-sonnet-4": { - "supports_computer_use": true, - "max_tokens": 64000, - "max_input_tokens": 200000, - "max_output_tokens": 64000, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "input_cost_per_image": 0.0048, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "supports_reasoning": true, - "tool_use_system_prompt_tokens": 159, - "supports_assistant_prefill": true, - "supports_tool_choice": true - }, - "openrouter/anthropic/claude-opus-4": { - "max_tokens": 32000, - "max_input_tokens": 200000, - "max_output_tokens": 32000, - "input_cost_per_token": 1.5e-05, - "output_cost_per_token": 7.5e-05, - "input_cost_per_image": 0.0048, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 159, - "supports_assistant_prefill": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_computer_use": true - }, - "openrouter/anthropic/claude-opus-4.1": { - "max_tokens": 32000, - "max_input_tokens": 200000, - "max_output_tokens": 32000, - "input_cost_per_token": 1.5e-05, - "output_cost_per_token": 7.5e-05, - "input_cost_per_image": 0.0048, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 159, - "supports_assistant_prefill": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_computer_use": true - }, - "openrouter/mistralai/mistral-large": { - "max_tokens": 32000, - "input_cost_per_token": 8e-06, - "output_cost_per_token": 2.4e-05, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_tool_choice": true - }, - "openrouter/mistralai/mistral-small-3.1-24b-instruct": { - "max_tokens": 32000, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 3e-07, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_tool_choice": true - }, - "openrouter/mistralai/mistral-small-3.2-24b-instruct": { - "max_tokens": 32000, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 3e-07, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_tool_choice": true - }, - "openrouter/cognitivecomputations/dolphin-mixtral-8x7b": { - "max_tokens": 32769, - "input_cost_per_token": 5e-07, - "output_cost_per_token": 5e-07, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_tool_choice": true - }, - "openrouter/google/gemini-pro-vision": { - "max_tokens": 45875, - "input_cost_per_token": 1.25e-07, - "output_cost_per_token": 3.75e-07, - "input_cost_per_image": 0.0025, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "supports_tool_choice": true - }, - "openrouter/fireworks/firellava-13b": { - "max_tokens": 4096, - "input_cost_per_token": 2e-07, - "output_cost_per_token": 2e-07, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_tool_choice": true - }, - "openrouter/meta-llama/llama-3-8b-instruct:free": { - "max_tokens": 8192, - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_tool_choice": true - }, - "openrouter/meta-llama/llama-3-8b-instruct:extended": { - "max_tokens": 16384, - "input_cost_per_token": 2.25e-07, - "output_cost_per_token": 2.25e-06, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_tool_choice": true - }, - "openrouter/meta-llama/llama-3-70b-instruct:nitro": { - "max_tokens": 8192, - "input_cost_per_token": 9e-07, - "output_cost_per_token": 9e-07, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_tool_choice": true - }, - "openrouter/meta-llama/llama-3-70b-instruct": { - "max_tokens": 8192, - "input_cost_per_token": 5.9e-07, - "output_cost_per_token": 7.9e-07, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_tool_choice": true - }, - "openrouter/openai/o1": { - "max_tokens": 100000, - "max_input_tokens": 200000, - "max_output_tokens": 100000, - "input_cost_per_token": 1.5e-05, - "output_cost_per_token": 6e-05, - "cache_read_input_token_cost": 7.5e-06, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "openrouter/openai/o1-mini": { - "max_tokens": 65536, - "max_input_tokens": 128000, - "max_output_tokens": 65536, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.2e-05, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_vision": false, - "supports_tool_choice": true - }, - "openrouter/openai/o1-mini-2024-09-12": { - "max_tokens": 65536, - "max_input_tokens": 128000, - "max_output_tokens": 65536, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.2e-05, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_vision": false, - "supports_tool_choice": true - }, - "openrouter/openai/o1-preview": { - "max_tokens": 32768, - "max_input_tokens": 128000, - "max_output_tokens": 32768, - "input_cost_per_token": 1.5e-05, - "output_cost_per_token": 6e-05, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_vision": false, - "supports_tool_choice": true - }, - "openrouter/openai/o1-preview-2024-09-12": { - "max_tokens": 32768, - "max_input_tokens": 128000, - "max_output_tokens": 32768, - "input_cost_per_token": 1.5e-05, - "output_cost_per_token": 6e-05, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_vision": false, - "supports_tool_choice": true - }, - "openrouter/openai/o3-mini": { - "max_tokens": 65536, - "max_input_tokens": 128000, - "max_output_tokens": 65536, - "input_cost_per_token": 1.1e-06, - "output_cost_per_token": 4.4e-06, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_function_calling": true, - "supports_reasoning": true, - "supports_parallel_function_calling": true, - "supports_vision": false, - "supports_tool_choice": true - }, - "openrouter/openai/o3-mini-high": { - "max_tokens": 65536, - "max_input_tokens": 128000, - "max_output_tokens": 65536, - "input_cost_per_token": 1.1e-06, - "output_cost_per_token": 4.4e-06, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_function_calling": true, - "supports_reasoning": true, - "supports_parallel_function_calling": true, - "supports_vision": false, - "supports_tool_choice": true - }, - "openrouter/openai/gpt-4o": { - "max_tokens": 4096, - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 2.5e-06, - "output_cost_per_token": 1e-05, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_vision": true, - "supports_tool_choice": true - }, - "openrouter/openai/gpt-4o-2024-05-13": { - "max_tokens": 4096, - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 5e-06, - "output_cost_per_token": 1.5e-05, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_vision": true, - "supports_tool_choice": true - }, - "openrouter/openai/gpt-4-vision-preview": { - "max_tokens": 130000, - "input_cost_per_token": 1e-05, - "output_cost_per_token": 3e-05, - "input_cost_per_image": 0.01445, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "supports_tool_choice": true - }, - "openrouter/openai/gpt-3.5-turbo": { - "max_tokens": 4095, - "input_cost_per_token": 1.5e-06, - "output_cost_per_token": 2e-06, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_tool_choice": true - }, - "openrouter/openai/gpt-3.5-turbo-16k": { - "max_tokens": 16383, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 4e-06, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_tool_choice": true - }, - "openrouter/openai/gpt-4": { - "max_tokens": 8192, - "input_cost_per_token": 3e-05, - "output_cost_per_token": 6e-05, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_tool_choice": true - }, - "openrouter/openai/gpt-4.1": { - "max_tokens": 32768, - "max_input_tokens": 1047576, - "max_output_tokens": 32768, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 8e-06, - "cache_read_input_token_cost": 5e-07, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "openrouter/openai/gpt-4.1-2025-04-14": { - "max_tokens": 32768, - "max_input_tokens": 1047576, - "max_output_tokens": 32768, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 8e-06, - "cache_read_input_token_cost": 5e-07, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "openrouter/openai/gpt-4.1-mini": { - "max_tokens": 32768, - "max_input_tokens": 1047576, - "max_output_tokens": 32768, - "input_cost_per_token": 4e-07, - "output_cost_per_token": 1.6e-06, - "cache_read_input_token_cost": 1e-07, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "openrouter/openai/gpt-4.1-mini-2025-04-14": { - "max_tokens": 32768, - "max_input_tokens": 1047576, - "max_output_tokens": 32768, - "input_cost_per_token": 4e-07, - "output_cost_per_token": 1.6e-06, - "cache_read_input_token_cost": 1e-07, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "openrouter/openai/gpt-4.1-nano": { - "max_tokens": 32768, - "max_input_tokens": 1047576, - "max_output_tokens": 32768, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 4e-07, - "cache_read_input_token_cost": 2.5e-08, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "openrouter/openai/gpt-4.1-nano-2025-04-14": { - "max_tokens": 32768, - "max_input_tokens": 1047576, - "max_output_tokens": 32768, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 4e-07, - "cache_read_input_token_cost": 2.5e-08, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "openrouter/openai/gpt-5-mini": { - "max_tokens": 128000, - "max_input_tokens": 400000, - "max_output_tokens": 128000, - "input_cost_per_token": 2.5e-07, - "output_cost_per_token": 2e-06, - "cache_read_input_token_cost": 2.5e-08, - "litellm_provider": "openrouter", - "mode": "chat", - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_tool_choice": true, - "supports_reasoning": true - }, - "openrouter/openai/gpt-5-nano": { - "max_tokens": 128000, - "max_input_tokens": 400000, - "max_output_tokens": 128000, - "input_cost_per_token": 5e-08, - "output_cost_per_token": 4e-07, - "cache_read_input_token_cost": 5e-09, - "litellm_provider": "openrouter", - "mode": "chat", - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_tool_choice": true, - "supports_reasoning": true - }, - "openrouter/openai/gpt-5-chat": { - "max_tokens": 128000, - "max_input_tokens": 400000, - "max_output_tokens": 128000, - "input_cost_per_token": 1.25e-06, - "output_cost_per_token": 1e-05, - "cache_read_input_token_cost": 1.25e-07, - "litellm_provider": "openrouter", - "mode": "chat", - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text" - ], - "supports_tool_choice": true, - "supports_reasoning": true - }, - "openrouter/openai/gpt-oss-20b": { - "max_tokens": 32768, - "max_input_tokens": 131072, - "max_output_tokens": 32768, - "input_cost_per_token": 1.8e-07, - "output_cost_per_token": 8e-07, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_reasoning": true, - "supports_tool_choice": true, - "source": "https://openrouter.ai/openai/gpt-oss-20b" - }, - "openrouter/openai/gpt-oss-120b": { - "max_tokens": 32768, - "max_input_tokens": 131072, - "max_output_tokens": 32768, - "input_cost_per_token": 1.8e-07, - "output_cost_per_token": 8e-07, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "supports_reasoning": true, - "supports_tool_choice": true, - "source": "https://openrouter.ai/openai/gpt-oss-120b" - }, - "openrouter/anthropic/claude-instant-v1": { - "max_tokens": 100000, - "max_output_tokens": 8191, - "input_cost_per_token": 1.63e-06, - "output_cost_per_token": 5.51e-06, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_tool_choice": true - }, - "openrouter/anthropic/claude-2": { - "max_tokens": 100000, - "max_output_tokens": 8191, - "input_cost_per_token": 1.102e-05, - "output_cost_per_token": 3.268e-05, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_tool_choice": true - }, - "openrouter/anthropic/claude-3-opus": { - "max_tokens": 4096, - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "input_cost_per_token": 1.5e-05, - "output_cost_per_token": 7.5e-05, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 395, - "supports_tool_choice": true - }, - "openrouter/google/palm-2-chat-bison": { - "max_tokens": 25804, - "input_cost_per_token": 5e-07, - "output_cost_per_token": 5e-07, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_tool_choice": true - }, - "openrouter/google/palm-2-codechat-bison": { - "max_tokens": 20070, - "input_cost_per_token": 5e-07, - "output_cost_per_token": 5e-07, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_tool_choice": true - }, - "openrouter/meta-llama/llama-2-13b-chat": { - "max_tokens": 4096, - "input_cost_per_token": 2e-07, - "output_cost_per_token": 2e-07, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_tool_choice": true - }, - "openrouter/meta-llama/llama-2-70b-chat": { - "max_tokens": 4096, - "input_cost_per_token": 1.5e-06, - "output_cost_per_token": 1.5e-06, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_tool_choice": true - }, - "openrouter/meta-llama/codellama-34b-instruct": { - "max_tokens": 8192, - "input_cost_per_token": 5e-07, - "output_cost_per_token": 5e-07, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_tool_choice": true - }, - "openrouter/nousresearch/nous-hermes-llama2-13b": { - "max_tokens": 4096, - "input_cost_per_token": 2e-07, - "output_cost_per_token": 2e-07, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_tool_choice": true - }, - "openrouter/mancer/weaver": { - "max_tokens": 8000, - "input_cost_per_token": 5.625e-06, - "output_cost_per_token": 5.625e-06, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_tool_choice": true - }, - "openrouter/gryphe/mythomax-l2-13b": { - "max_tokens": 8192, - "input_cost_per_token": 1.875e-06, - "output_cost_per_token": 1.875e-06, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_tool_choice": true - }, - "openrouter/jondurbin/airoboros-l2-70b-2.1": { - "max_tokens": 4096, - "input_cost_per_token": 1.3875e-05, - "output_cost_per_token": 1.3875e-05, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_tool_choice": true - }, - "openrouter/undi95/remm-slerp-l2-13b": { - "max_tokens": 6144, - "input_cost_per_token": 1.875e-06, - "output_cost_per_token": 1.875e-06, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_tool_choice": true - }, - "openrouter/pygmalionai/mythalion-13b": { - "max_tokens": 4096, - "input_cost_per_token": 1.875e-06, - "output_cost_per_token": 1.875e-06, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_tool_choice": true - }, - "openrouter/mistralai/mistral-7b-instruct": { - "max_tokens": 8192, - "input_cost_per_token": 1.3e-07, - "output_cost_per_token": 1.3e-07, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_tool_choice": true - }, - "openrouter/mistralai/mistral-7b-instruct:free": { - "max_tokens": 8192, - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_tool_choice": true - }, - "openrouter/qwen/qwen-2.5-coder-32b-instruct": { - "max_tokens": 33792, - "max_input_tokens": 33792, - "max_output_tokens": 33792, - "input_cost_per_token": 1.8e-07, - "output_cost_per_token": 1.8e-07, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_tool_choice": true - }, - "openrouter/qwen/qwen-vl-plus": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 2048, - "input_cost_per_token": 2.1e-07, - "output_cost_per_token": 6.3e-07, - "litellm_provider": "openrouter", - "mode": "chat", - "supports_tool_choice": true - }, - "openrouter/qwen/qwen3-coder": { - "max_tokens": 1000000, - "max_input_tokens": 1000000, - "max_output_tokens": 1000000, - "input_cost_per_token": 1e-06, - "output_cost_per_token": 5e-06, - "litellm_provider": "openrouter", - "source": "https://openrouter.ai/qwen/qwen3-coder", - "mode": "chat", - "supports_tool_choice": true - }, - "openrouter/switchpoint/router": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 8.5e-07, - "output_cost_per_token": 3.4e-06, - "litellm_provider": "openrouter", - "source": "https://openrouter.ai/switchpoint/router", - "mode": "chat", - "supports_tool_choice": true - }, - "j2-ultra": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 1.5e-05, - "output_cost_per_token": 1.5e-05, - "litellm_provider": "ai21", - "mode": "completion" - }, - "jamba-1.5-mini@001": { - "max_tokens": 256000, - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "input_cost_per_token": 2e-07, - "output_cost_per_token": 4e-07, - "litellm_provider": "ai21", - "mode": "chat", - "supports_tool_choice": true - }, - "jamba-1.5-large@001": { - "max_tokens": 256000, - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 8e-06, - "litellm_provider": "ai21", - "mode": "chat", - "supports_tool_choice": true - }, - "jamba-1.5": { - "max_tokens": 256000, - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "input_cost_per_token": 2e-07, - "output_cost_per_token": 4e-07, - "litellm_provider": "ai21", - "mode": "chat", - "supports_tool_choice": true - }, - "jamba-1.5-mini": { - "max_tokens": 256000, - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "input_cost_per_token": 2e-07, - "output_cost_per_token": 4e-07, - "litellm_provider": "ai21", - "mode": "chat", - "supports_tool_choice": true - }, - "jamba-1.5-large": { - "max_tokens": 256000, - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 8e-06, - "litellm_provider": "ai21", - "mode": "chat", - "supports_tool_choice": true - }, - "jamba-large-1.6": { - "max_tokens": 256000, - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 8e-06, - "litellm_provider": "ai21", - "mode": "chat", - "supports_tool_choice": true - }, - "jamba-large-1.7": { - "max_tokens": 256000, - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 8e-06, - "litellm_provider": "ai21", - "mode": "chat", - "supports_tool_choice": true - }, - "jamba-mini-1.6": { - "max_tokens": 256000, - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "input_cost_per_token": 2e-07, - "output_cost_per_token": 4e-07, - "litellm_provider": "ai21", - "mode": "chat", - "supports_tool_choice": true - }, - "jamba-mini-1.7": { - "max_tokens": 256000, - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "input_cost_per_token": 2e-07, - "output_cost_per_token": 4e-07, - "litellm_provider": "ai21", - "mode": "chat", - "supports_tool_choice": true - }, - "j2-mid": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 1e-05, - "output_cost_per_token": 1e-05, - "litellm_provider": "ai21", - "mode": "completion" - }, - "j2-light": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 3e-06, - "litellm_provider": "ai21", - "mode": "completion" - }, - "dolphin": { - "max_tokens": 16384, - "max_input_tokens": 16384, - "max_output_tokens": 16384, - "input_cost_per_token": 5e-07, - "output_cost_per_token": 5e-07, - "litellm_provider": "nlp_cloud", - "mode": "completion" - }, - "chatdolphin": { - "max_tokens": 16384, - "max_input_tokens": 16384, - "max_output_tokens": 16384, - "input_cost_per_token": 5e-07, - "output_cost_per_token": 5e-07, - "litellm_provider": "nlp_cloud", - "mode": "chat" - }, - "luminous-base": { - "max_tokens": 2048, - "input_cost_per_token": 3e-05, - "output_cost_per_token": 3.3e-05, - "litellm_provider": "aleph_alpha", - "mode": "completion" - }, - "luminous-base-control": { - "max_tokens": 2048, - "input_cost_per_token": 3.75e-05, - "output_cost_per_token": 4.125e-05, - "litellm_provider": "aleph_alpha", - "mode": "chat" - }, - "luminous-extended": { - "max_tokens": 2048, - "input_cost_per_token": 4.5e-05, - "output_cost_per_token": 4.95e-05, - "litellm_provider": "aleph_alpha", - "mode": "completion" - }, - "luminous-extended-control": { - "max_tokens": 2048, - "input_cost_per_token": 5.625e-05, - "output_cost_per_token": 6.1875e-05, - "litellm_provider": "aleph_alpha", - "mode": "chat" - }, - "luminous-supreme": { - "max_tokens": 2048, - "input_cost_per_token": 0.000175, - "output_cost_per_token": 0.0001925, - "litellm_provider": "aleph_alpha", - "mode": "completion" - }, - "luminous-supreme-control": { - "max_tokens": 2048, - "input_cost_per_token": 0.00021875, - "output_cost_per_token": 0.000240625, - "litellm_provider": "aleph_alpha", - "mode": "chat" - }, - "ai21.j2-mid-v1": { - "max_tokens": 8191, - "max_input_tokens": 8191, - "max_output_tokens": 8191, - "input_cost_per_token": 1.25e-05, - "output_cost_per_token": 1.25e-05, - "litellm_provider": "bedrock", - "mode": "chat" - }, - "ai21.j2-ultra-v1": { - "max_tokens": 8191, - "max_input_tokens": 8191, - "max_output_tokens": 8191, - "input_cost_per_token": 1.88e-05, - "output_cost_per_token": 1.88e-05, - "litellm_provider": "bedrock", - "mode": "chat" - }, - "ai21.jamba-instruct-v1:0": { - "max_tokens": 4096, - "max_input_tokens": 70000, - "max_output_tokens": 4096, - "input_cost_per_token": 5e-07, - "output_cost_per_token": 7e-07, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_system_messages": true - }, - "ai21.jamba-1-5-large-v1:0": { - "max_tokens": 256000, - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 8e-06, - "litellm_provider": "bedrock", - "mode": "chat" - }, - "ai21.jamba-1-5-mini-v1:0": { - "max_tokens": 256000, - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "input_cost_per_token": 2e-07, - "output_cost_per_token": 4e-07, - "litellm_provider": "bedrock", - "mode": "chat" - }, - "amazon.rerank-v1:0": { - "max_tokens": 32000, - "max_input_tokens": 32000, - "max_output_tokens": 32000, - "max_query_tokens": 32000, - "max_document_chunks_per_query": 100, - "max_tokens_per_document_chunk": 512, - "input_cost_per_token": 0.0, - "input_cost_per_query": 0.001, - "output_cost_per_token": 0.0, - "litellm_provider": "bedrock", - "mode": "rerank" - }, - "amazon.titan-text-lite-v1": { - "max_tokens": 4000, - "max_input_tokens": 42000, - "max_output_tokens": 4000, - "input_cost_per_token": 3e-07, - "output_cost_per_token": 4e-07, - "litellm_provider": "bedrock", - "mode": "chat" - }, - "amazon.titan-text-express-v1": { - "max_tokens": 8000, - "max_input_tokens": 42000, - "max_output_tokens": 8000, - "input_cost_per_token": 1.3e-06, - "output_cost_per_token": 1.7e-06, - "litellm_provider": "bedrock", - "mode": "chat" - }, - "amazon.titan-text-premier-v1:0": { - "max_tokens": 32000, - "max_input_tokens": 42000, - "max_output_tokens": 32000, - "input_cost_per_token": 5e-07, - "output_cost_per_token": 1.5e-06, - "litellm_provider": "bedrock", - "mode": "chat" - }, - "amazon.titan-embed-text-v1": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "output_vector_size": 1536, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 0.0, - "litellm_provider": "bedrock", - "mode": "embedding" - }, - "amazon.titan-embed-text-v2:0": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "output_vector_size": 1024, - "input_cost_per_token": 2e-07, - "output_cost_per_token": 0.0, - "litellm_provider": "bedrock", - "mode": "embedding" - }, - "amazon.titan-embed-image-v1": { - "max_tokens": 128, - "max_input_tokens": 128, - "output_vector_size": 1024, - "input_cost_per_token": 8e-07, - "input_cost_per_image": 6e-05, - "output_cost_per_token": 0.0, - "litellm_provider": "bedrock", - "supports_image_input": true, - "supports_embedding_image_input": true, - "mode": "embedding", - "source": "https://us-east-1.console.aws.amazon.com/bedrock/home?region=us-east-1#/providers?model=amazon.titan-image-generator-v1", - "metadata": { - "notes": "'supports_image_input' is a deprecated field. Use 'supports_embedding_image_input' instead." - } - }, - "mistral.mistral-7b-instruct-v0:2": { - "max_tokens": 8191, - "max_input_tokens": 32000, - "max_output_tokens": 8191, - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 2e-07, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_tool_choice": true - }, - "mistral.mixtral-8x7b-instruct-v0:1": { - "max_tokens": 8191, - "max_input_tokens": 32000, - "max_output_tokens": 8191, - "input_cost_per_token": 4.5e-07, - "output_cost_per_token": 7e-07, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_tool_choice": true - }, - "mistral.mistral-large-2402-v1:0": { - "max_tokens": 8191, - "max_input_tokens": 32000, - "max_output_tokens": 8191, - "input_cost_per_token": 8e-06, - "output_cost_per_token": 2.4e-05, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_function_calling": true - }, - "mistral.mistral-large-2407-v1:0": { - "max_tokens": 8191, - "max_input_tokens": 128000, - "max_output_tokens": 8191, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 9e-06, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true - }, - "mistral.mistral-small-2402-v1:0": { - "max_tokens": 8191, - "max_input_tokens": 32000, - "max_output_tokens": 8191, - "input_cost_per_token": 1e-06, - "output_cost_per_token": 3e-06, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_function_calling": true - }, - "eu.mistral.pixtral-large-2502-v1:0": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 6e-06, - "litellm_provider": "bedrock_converse", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": false - }, - "us.mistral.pixtral-large-2502-v1:0": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 6e-06, - "litellm_provider": "bedrock_converse", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": false - }, - "bedrock/us-west-2/mistral.mixtral-8x7b-instruct-v0:1": { - "max_tokens": 8191, - "max_input_tokens": 32000, - "max_output_tokens": 8191, - "input_cost_per_token": 4.5e-07, - "output_cost_per_token": 7e-07, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_tool_choice": true - }, - "bedrock/us-east-1/mistral.mixtral-8x7b-instruct-v0:1": { - "max_tokens": 8191, - "max_input_tokens": 32000, - "max_output_tokens": 8191, - "input_cost_per_token": 4.5e-07, - "output_cost_per_token": 7e-07, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_tool_choice": true - }, - "bedrock/eu-west-3/mistral.mixtral-8x7b-instruct-v0:1": { - "max_tokens": 8191, - "max_input_tokens": 32000, - "max_output_tokens": 8191, - "input_cost_per_token": 5.9e-07, - "output_cost_per_token": 9.1e-07, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_tool_choice": true - }, - "bedrock/us-west-2/mistral.mistral-7b-instruct-v0:2": { - "max_tokens": 8191, - "max_input_tokens": 32000, - "max_output_tokens": 8191, - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 2e-07, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_tool_choice": true - }, - "bedrock/us-east-1/mistral.mistral-7b-instruct-v0:2": { - "max_tokens": 8191, - "max_input_tokens": 32000, - "max_output_tokens": 8191, - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 2e-07, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_tool_choice": true - }, - "bedrock/eu-west-3/mistral.mistral-7b-instruct-v0:2": { - "max_tokens": 8191, - "max_input_tokens": 32000, - "max_output_tokens": 8191, - "input_cost_per_token": 2e-07, - "output_cost_per_token": 2.6e-07, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_tool_choice": true - }, - "bedrock/us-east-1/mistral.mistral-large-2402-v1:0": { - "max_tokens": 8191, - "max_input_tokens": 32000, - "max_output_tokens": 8191, - "input_cost_per_token": 8e-06, - "output_cost_per_token": 2.4e-05, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_function_calling": true - }, - "bedrock/us-west-2/mistral.mistral-large-2402-v1:0": { - "max_tokens": 8191, - "max_input_tokens": 32000, - "max_output_tokens": 8191, - "input_cost_per_token": 8e-06, - "output_cost_per_token": 2.4e-05, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_function_calling": true - }, - "bedrock/eu-west-3/mistral.mistral-large-2402-v1:0": { - "max_tokens": 8191, - "max_input_tokens": 32000, - "max_output_tokens": 8191, - "input_cost_per_token": 1.04e-05, - "output_cost_per_token": 3.12e-05, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_function_calling": true - }, - "amazon.nova-micro-v1:0": { - "max_tokens": 10000, - "max_input_tokens": 128000, - "max_output_tokens": 10000, - "input_cost_per_token": 3.5e-08, - "output_cost_per_token": 1.4e-07, - "litellm_provider": "bedrock_converse", - "mode": "chat", - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_response_schema": true - }, - "us.amazon.nova-micro-v1:0": { - "max_tokens": 10000, - "max_input_tokens": 128000, - "max_output_tokens": 10000, - "input_cost_per_token": 3.5e-08, - "output_cost_per_token": 1.4e-07, - "litellm_provider": "bedrock_converse", - "mode": "chat", - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_response_schema": true - }, - "eu.amazon.nova-micro-v1:0": { - "max_tokens": 10000, - "max_input_tokens": 128000, - "max_output_tokens": 10000, - "input_cost_per_token": 4.6e-08, - "output_cost_per_token": 1.84e-07, - "litellm_provider": "bedrock_converse", - "mode": "chat", - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_response_schema": true - }, - "amazon.nova-lite-v1:0": { - "max_tokens": 10000, - "max_input_tokens": 300000, - "max_output_tokens": 10000, - "input_cost_per_token": 6e-08, - "output_cost_per_token": 2.4e-07, - "litellm_provider": "bedrock_converse", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_response_schema": true - }, - "us.amazon.nova-lite-v1:0": { - "max_tokens": 10000, - "max_input_tokens": 300000, - "max_output_tokens": 10000, - "input_cost_per_token": 6e-08, - "output_cost_per_token": 2.4e-07, - "litellm_provider": "bedrock_converse", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_response_schema": true - }, - "eu.amazon.nova-lite-v1:0": { - "max_tokens": 10000, - "max_input_tokens": 300000, - "max_output_tokens": 10000, - "input_cost_per_token": 7.8e-08, - "output_cost_per_token": 3.12e-07, - "litellm_provider": "bedrock_converse", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_response_schema": true - }, - "amazon.nova-pro-v1:0": { - "max_tokens": 10000, - "max_input_tokens": 300000, - "max_output_tokens": 10000, - "input_cost_per_token": 8e-07, - "output_cost_per_token": 3.2e-06, - "litellm_provider": "bedrock_converse", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_response_schema": true - }, - "us.amazon.nova-pro-v1:0": { - "max_tokens": 10000, - "max_input_tokens": 300000, - "max_output_tokens": 10000, - "input_cost_per_token": 8e-07, - "output_cost_per_token": 3.2e-06, - "litellm_provider": "bedrock_converse", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_response_schema": true - }, - "1024-x-1024/50-steps/bedrock/amazon.nova-canvas-v1:0": { - "max_input_tokens": 2600, + "gemini/imagen-4.0-generate-001": { + "litellm_provider": "gemini", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" + }, + "gemini/imagen-4.0-ultra-generate-001": { + "litellm_provider": "gemini", + "mode": "image_generation", "output_cost_per_image": 0.06, - "litellm_provider": "bedrock", - "mode": "image_generation" - }, - "eu.amazon.nova-pro-v1:0": { - "max_tokens": 10000, - "max_input_tokens": 300000, - "max_output_tokens": 10000, - "input_cost_per_token": 1.05e-06, - "output_cost_per_token": 4.2e-06, - "litellm_provider": "bedrock_converse", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "source": "https://aws.amazon.com/bedrock/pricing/" - }, - "apac.amazon.nova-micro-v1:0": { - "max_tokens": 10000, - "max_input_tokens": 128000, - "max_output_tokens": 10000, - "input_cost_per_token": 3.7e-08, - "output_cost_per_token": 1.48e-07, - "litellm_provider": "bedrock_converse", - "mode": "chat", - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_response_schema": true - }, - "apac.amazon.nova-lite-v1:0": { - "max_tokens": 10000, - "max_input_tokens": 300000, - "max_output_tokens": 10000, - "input_cost_per_token": 6.3e-08, - "output_cost_per_token": 2.52e-07, - "litellm_provider": "bedrock_converse", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_response_schema": true - }, - "apac.amazon.nova-pro-v1:0": { - "max_tokens": 10000, - "max_input_tokens": 300000, - "max_output_tokens": 10000, - "input_cost_per_token": 8.4e-07, - "output_cost_per_token": 3.36e-06, - "litellm_provider": "bedrock_converse", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_response_schema": true - }, - "us.amazon.nova-premier-v1:0": { - "max_tokens": 10000, - "max_input_tokens": 1000000, - "max_output_tokens": 10000, - "input_cost_per_token": 2.5e-06, - "output_cost_per_token": 1.25e-05, - "litellm_provider": "bedrock_converse", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_prompt_caching": false, - "supports_response_schema": true - }, - "anthropic.claude-3-sonnet-20240229-v1:0": { - "max_tokens": 4096, - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_tool_choice": true - }, - "bedrock/invoke/anthropic.claude-3-5-sonnet-20240620-v1:0": { - "max_tokens": 4096, - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_tool_choice": true, - "metadata": { - "notes": "Anthropic via Invoke route does not currently support pdf input." - } - }, - "anthropic.claude-3-5-sonnet-20240620-v1:0": { - "max_tokens": 4096, - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_tool_choice": true - }, - "openai.gpt-oss-20b-1:0": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "input_cost_per_token": 7e-08, - "output_cost_per_token": 3e-07, - "litellm_provider": "bedrock_converse", - "mode": "chat", - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_function_calling": true, - "supports_reasoning": true - }, - "openai.gpt-oss-120b-1:0": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 6e-07, - "litellm_provider": "bedrock_converse", - "mode": "chat", - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_function_calling": true, - "supports_reasoning": true - }, - "anthropic.claude-opus-4-1-20250805-v1:0": { - "max_tokens": 32000, - "max_input_tokens": 200000, - "max_output_tokens": 32000, - "input_cost_per_token": 1.5e-05, - "output_cost_per_token": 7.5e-05, - "search_context_cost_per_query": { - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01, - "search_context_size_high": 0.01 - }, - "cache_creation_input_token_cost": 1.875e-05, - "cache_read_input_token_cost": 1.5e-06, - "litellm_provider": "bedrock_converse", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 159, - "supports_assistant_prefill": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_computer_use": true - }, - "anthropic.claude-opus-4-20250514-v1:0": { - "max_tokens": 32000, - "max_input_tokens": 200000, - "max_output_tokens": 32000, - "input_cost_per_token": 1.5e-05, - "output_cost_per_token": 7.5e-05, - "search_context_cost_per_query": { - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01, - "search_context_size_high": 0.01 - }, - "cache_creation_input_token_cost": 1.875e-05, - "cache_read_input_token_cost": 1.5e-06, - "litellm_provider": "bedrock_converse", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 159, - "supports_assistant_prefill": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_computer_use": true - }, - "anthropic.claude-sonnet-4-20250514-v1:0": { - "max_tokens": 64000, - "max_input_tokens": 200000, - "max_output_tokens": 64000, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "search_context_cost_per_query": { - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01, - "search_context_size_high": 0.01 - }, - "cache_creation_input_token_cost": 3.75e-06, - "cache_read_input_token_cost": 3e-07, - "litellm_provider": "bedrock_converse", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 159, - "supports_assistant_prefill": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_computer_use": true - }, - "anthropic.claude-3-7-sonnet-20250219-v1:0": { - "supports_computer_use": true, - "max_tokens": 8192, - "max_input_tokens": 200000, - "max_output_tokens": 8192, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "cache_creation_input_token_cost": 3.75e-06, - "cache_read_input_token_cost": 3e-07, - "litellm_provider": "bedrock_converse", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "supports_assistant_prefill": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_pdf_input": true, - "supports_reasoning": true, - "supports_tool_choice": true - }, - "anthropic.claude-3-5-sonnet-20241022-v2:0": { - "supports_computer_use": true, - "max_tokens": 8192, - "max_input_tokens": 200000, - "max_output_tokens": 8192, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "cache_creation_input_token_cost": 3.75e-06, - "cache_read_input_token_cost": 3e-07, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_assistant_prefill": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "anthropic.claude-3-haiku-20240307-v1:0": { - "max_tokens": 4096, - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "input_cost_per_token": 2.5e-07, - "output_cost_per_token": 1.25e-06, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_tool_choice": true - }, - "anthropic.claude-3-5-haiku-20241022-v1:0": { - "max_tokens": 8192, - "max_input_tokens": 200000, - "max_output_tokens": 8192, - "input_cost_per_token": 8e-07, - "output_cost_per_token": 4e-06, - "cache_creation_input_token_cost": 1e-06, - "cache_read_input_token_cost": 8e-08, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_assistant_prefill": true, - "supports_pdf_input": true, - "supports_function_calling": true, - "supports_response_schema": true, - "supports_prompt_caching": true, - "supports_tool_choice": true - }, - "anthropic.claude-3-opus-20240229-v1:0": { - "max_tokens": 4096, - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "input_cost_per_token": 1.5e-05, - "output_cost_per_token": 7.5e-05, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_tool_choice": true - }, - "us.anthropic.claude-3-sonnet-20240229-v1:0": { - "max_tokens": 4096, - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_tool_choice": true - }, - "us.anthropic.claude-3-5-sonnet-20240620-v1:0": { - "max_tokens": 4096, - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_tool_choice": true - }, - "us.anthropic.claude-3-5-sonnet-20241022-v2:0": { - "supports_computer_use": true, - "max_tokens": 8192, - "max_input_tokens": 200000, - "max_output_tokens": 8192, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "cache_creation_input_token_cost": 3.75e-06, - "cache_read_input_token_cost": 3e-07, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_assistant_prefill": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "us.anthropic.claude-3-7-sonnet-20250219-v1:0": { - "supports_computer_use": true, - "max_tokens": 8192, - "max_input_tokens": 200000, - "max_output_tokens": 8192, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "cache_creation_input_token_cost": 3.75e-06, - "cache_read_input_token_cost": 3e-07, - "litellm_provider": "bedrock_converse", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "supports_assistant_prefill": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_pdf_input": true, - "supports_tool_choice": true, - "supports_reasoning": true - }, - "us.anthropic.claude-opus-4-1-20250805-v1:0": { - "max_tokens": 32000, - "max_input_tokens": 200000, - "max_output_tokens": 32000, - "input_cost_per_token": 1.5e-05, - "output_cost_per_token": 7.5e-05, - "search_context_cost_per_query": { - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01, - "search_context_size_high": 0.01 - }, - "cache_creation_input_token_cost": 1.875e-05, - "cache_read_input_token_cost": 1.5e-06, - "litellm_provider": "bedrock_converse", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 159, - "supports_assistant_prefill": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_computer_use": true - }, - "us.anthropic.claude-opus-4-20250514-v1:0": { - "max_tokens": 32000, - "max_input_tokens": 200000, - "max_output_tokens": 32000, - "input_cost_per_token": 1.5e-05, - "output_cost_per_token": 7.5e-05, - "search_context_cost_per_query": { - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01, - "search_context_size_high": 0.01 - }, - "cache_creation_input_token_cost": 1.875e-05, - "cache_read_input_token_cost": 1.5e-06, - "litellm_provider": "bedrock_converse", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 159, - "supports_assistant_prefill": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_computer_use": true - }, - "us.anthropic.claude-sonnet-4-20250514-v1:0": { - "max_tokens": 64000, - "max_input_tokens": 200000, - "max_output_tokens": 64000, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "search_context_cost_per_query": { - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01, - "search_context_size_high": 0.01 - }, - "cache_creation_input_token_cost": 3.75e-06, - "cache_read_input_token_cost": 3e-07, - "litellm_provider": "bedrock_converse", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 159, - "supports_assistant_prefill": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_computer_use": true - }, - "us.anthropic.claude-3-haiku-20240307-v1:0": { - "max_tokens": 4096, - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "input_cost_per_token": 2.5e-07, - "output_cost_per_token": 1.25e-06, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_tool_choice": true - }, - "us.anthropic.claude-3-5-haiku-20241022-v1:0": { - "max_tokens": 8192, - "max_input_tokens": 200000, - "max_output_tokens": 8192, - "input_cost_per_token": 8e-07, - "output_cost_per_token": 4e-06, - "cache_creation_input_token_cost": 1e-06, - "cache_read_input_token_cost": 8e-08, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_assistant_prefill": true, - "supports_pdf_input": true, - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "bedrock/us.anthropic.claude-3-5-haiku-20241022-v1:0": { - "max_tokens": 8192, - "max_input_tokens": 200000, - "max_output_tokens": 8192, - "input_cost_per_token": 8e-07, - "output_cost_per_token": 4e-06, - "cache_creation_input_token_cost": 1e-06, - "cache_read_input_token_cost": 8e-08, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_assistant_prefill": true, - "supports_pdf_input": true, - "supports_function_calling": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "us.anthropic.claude-3-opus-20240229-v1:0": { - "max_tokens": 4096, - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "input_cost_per_token": 1.5e-05, - "output_cost_per_token": 7.5e-05, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_tool_choice": true - }, - "eu.anthropic.claude-3-sonnet-20240229-v1:0": { - "max_tokens": 4096, - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_tool_choice": true - }, - "eu.anthropic.claude-3-5-sonnet-20240620-v1:0": { - "max_tokens": 4096, - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_tool_choice": true - }, - "eu.anthropic.claude-3-5-sonnet-20241022-v2:0": { - "supports_computer_use": true, - "max_tokens": 8192, - "max_input_tokens": 200000, - "max_output_tokens": 8192, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_assistant_prefill": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "eu.anthropic.claude-3-7-sonnet-20250219-v1:0": { - "supports_computer_use": true, - "max_tokens": 8192, - "max_input_tokens": 200000, - "max_output_tokens": 8192, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "supports_assistant_prefill": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_pdf_input": true, - "supports_tool_choice": true, - "supports_reasoning": true - }, - "eu.anthropic.claude-3-haiku-20240307-v1:0": { - "max_tokens": 4096, - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "input_cost_per_token": 2.5e-07, - "output_cost_per_token": 1.25e-06, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_tool_choice": true - }, - "eu.anthropic.claude-opus-4-1-20250805-v1:0": { - "max_tokens": 32000, - "max_input_tokens": 200000, - "max_output_tokens": 32000, - "input_cost_per_token": 1.5e-05, - "output_cost_per_token": 7.5e-05, - "search_context_cost_per_query": { - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01, - "search_context_size_high": 0.01 - }, - "cache_creation_input_token_cost": 1.875e-05, - "cache_read_input_token_cost": 1.5e-06, - "litellm_provider": "bedrock_converse", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 159, - "supports_assistant_prefill": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_computer_use": true - }, - "eu.anthropic.claude-opus-4-20250514-v1:0": { - "max_tokens": 32000, - "max_input_tokens": 200000, - "max_output_tokens": 32000, - "input_cost_per_token": 1.5e-05, - "output_cost_per_token": 7.5e-05, - "search_context_cost_per_query": { - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01, - "search_context_size_high": 0.01 - }, - "cache_creation_input_token_cost": 1.875e-05, - "cache_read_input_token_cost": 1.5e-06, - "litellm_provider": "bedrock_converse", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 159, - "supports_assistant_prefill": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_computer_use": true - }, - "eu.anthropic.claude-sonnet-4-20250514-v1:0": { - "max_tokens": 64000, - "max_input_tokens": 200000, - "max_output_tokens": 64000, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "search_context_cost_per_query": { - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01, - "search_context_size_high": 0.01 - }, - "cache_creation_input_token_cost": 3.75e-06, - "cache_read_input_token_cost": 3e-07, - "litellm_provider": "bedrock_converse", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 159, - "supports_assistant_prefill": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_computer_use": true - }, - "apac.anthropic.claude-3-haiku-20240307-v1:0": { - "max_tokens": 4096, - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "input_cost_per_token": 2.5e-07, - "output_cost_per_token": 1.25e-06, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_tool_choice": true - }, - "apac.anthropic.claude-3-sonnet-20240229-v1:0": { - "max_tokens": 4096, - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_tool_choice": true - }, - "apac.anthropic.claude-3-5-sonnet-20240620-v1:0": { - "max_tokens": 4096, - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_tool_choice": true - }, - "apac.anthropic.claude-3-5-sonnet-20241022-v2:0": { - "max_tokens": 8192, - "max_input_tokens": 200000, - "max_output_tokens": 8192, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "cache_creation_input_token_cost": 3.75e-06, - "cache_read_input_token_cost": 3e-07, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "supports_assistant_prefill": true, - "supports_computer_use": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "apac.anthropic.claude-sonnet-4-20250514-v1:0": { - "max_tokens": 64000, - "max_input_tokens": 200000, - "max_output_tokens": 64000, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "search_context_cost_per_query": { - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01, - "search_context_size_high": 0.01 - }, - "cache_creation_input_token_cost": 3.75e-06, - "cache_read_input_token_cost": 3e-07, - "litellm_provider": "bedrock_converse", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 159, - "supports_assistant_prefill": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "supports_computer_use": true - }, - "eu.anthropic.claude-3-5-haiku-20241022-v1:0": { - "max_tokens": 8192, - "max_input_tokens": 200000, - "max_output_tokens": 8192, - "input_cost_per_token": 2.5e-07, - "output_cost_per_token": 1.25e-06, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_function_calling": true, - "supports_assistant_prefill": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_response_schema": true, - "supports_tool_choice": true - }, - "eu.anthropic.claude-3-opus-20240229-v1:0": { - "max_tokens": 4096, - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "input_cost_per_token": 1.5e-05, - "output_cost_per_token": 7.5e-05, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_tool_choice": true - }, - "anthropic.claude-v1": { - "max_tokens": 8191, - "max_input_tokens": 100000, - "max_output_tokens": 8191, - "input_cost_per_token": 8e-06, - "output_cost_per_token": 2.4e-05, - "litellm_provider": "bedrock", - "mode": "chat" - }, - "bedrock/us-east-1/anthropic.claude-v1": { - "max_tokens": 8191, - "max_input_tokens": 100000, - "max_output_tokens": 8191, - "input_cost_per_token": 8e-06, - "output_cost_per_token": 2.4e-05, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_tool_choice": true - }, - "bedrock/us-west-2/anthropic.claude-v1": { - "max_tokens": 8191, - "max_input_tokens": 100000, - "max_output_tokens": 8191, - "input_cost_per_token": 8e-06, - "output_cost_per_token": 2.4e-05, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_tool_choice": true - }, - "bedrock/ap-northeast-1/anthropic.claude-v1": { - "max_tokens": 8191, - "max_input_tokens": 100000, - "max_output_tokens": 8191, - "input_cost_per_token": 8e-06, - "output_cost_per_token": 2.4e-05, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_tool_choice": true - }, - "bedrock/ap-northeast-1/1-month-commitment/anthropic.claude-v1": { - "max_tokens": 8191, - "max_input_tokens": 100000, - "max_output_tokens": 8191, - "input_cost_per_second": 0.0455, - "output_cost_per_second": 0.0455, - "litellm_provider": "bedrock", - "mode": "chat" - }, - "bedrock/ap-northeast-1/6-month-commitment/anthropic.claude-v1": { - "max_tokens": 8191, - "max_input_tokens": 100000, - "max_output_tokens": 8191, - "input_cost_per_second": 0.02527, - "output_cost_per_second": 0.02527, - "litellm_provider": "bedrock", - "mode": "chat" - }, - "bedrock/eu-central-1/anthropic.claude-v1": { - "max_tokens": 8191, - "max_input_tokens": 100000, - "max_output_tokens": 8191, - "input_cost_per_token": 8e-06, - "output_cost_per_token": 2.4e-05, - "litellm_provider": "bedrock", - "mode": "chat" - }, - "bedrock/eu-central-1/1-month-commitment/anthropic.claude-v1": { - "max_tokens": 8191, - "max_input_tokens": 100000, - "max_output_tokens": 8191, - "input_cost_per_second": 0.0415, - "output_cost_per_second": 0.0415, - "litellm_provider": "bedrock", - "mode": "chat" - }, - "bedrock/eu-central-1/6-month-commitment/anthropic.claude-v1": { - "max_tokens": 8191, - "max_input_tokens": 100000, - "max_output_tokens": 8191, - "input_cost_per_second": 0.02305, - "output_cost_per_second": 0.02305, - "litellm_provider": "bedrock", - "mode": "chat" - }, - "bedrock/us-east-1/1-month-commitment/anthropic.claude-v1": { - "max_tokens": 8191, - "max_input_tokens": 100000, - "max_output_tokens": 8191, - "input_cost_per_second": 0.0175, - "output_cost_per_second": 0.0175, - "litellm_provider": "bedrock", - "mode": "chat" - }, - "bedrock/us-east-1/6-month-commitment/anthropic.claude-v1": { - "max_tokens": 8191, - "max_input_tokens": 100000, - "max_output_tokens": 8191, - "input_cost_per_second": 0.00972, - "output_cost_per_second": 0.00972, - "litellm_provider": "bedrock", - "mode": "chat" - }, - "bedrock/us-west-2/1-month-commitment/anthropic.claude-v1": { - "max_tokens": 8191, - "max_input_tokens": 100000, - "max_output_tokens": 8191, - "input_cost_per_second": 0.0175, - "output_cost_per_second": 0.0175, - "litellm_provider": "bedrock", - "mode": "chat" - }, - "bedrock/us-west-2/6-month-commitment/anthropic.claude-v1": { - "max_tokens": 8191, - "max_input_tokens": 100000, - "max_output_tokens": 8191, - "input_cost_per_second": 0.00972, - "output_cost_per_second": 0.00972, - "litellm_provider": "bedrock", - "mode": "chat" - }, - "anthropic.claude-v2:1": { - "max_tokens": 8191, - "max_input_tokens": 100000, - "max_output_tokens": 8191, - "input_cost_per_token": 8e-06, - "output_cost_per_token": 2.4e-05, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_tool_choice": true - }, - "bedrock/us-east-1/anthropic.claude-v2:1": { - "max_tokens": 8191, - "max_input_tokens": 100000, - "max_output_tokens": 8191, - "input_cost_per_token": 8e-06, - "output_cost_per_token": 2.4e-05, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_tool_choice": true - }, - "bedrock/us-west-2/anthropic.claude-v2:1": { - "max_tokens": 8191, - "max_input_tokens": 100000, - "max_output_tokens": 8191, - "input_cost_per_token": 8e-06, - "output_cost_per_token": 2.4e-05, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_tool_choice": true - }, - "bedrock/ap-northeast-1/anthropic.claude-v2:1": { - "max_tokens": 8191, - "max_input_tokens": 100000, - "max_output_tokens": 8191, - "input_cost_per_token": 8e-06, - "output_cost_per_token": 2.4e-05, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_tool_choice": true - }, - "bedrock/ap-northeast-1/1-month-commitment/anthropic.claude-v2:1": { - "max_tokens": 8191, - "max_input_tokens": 100000, - "max_output_tokens": 8191, - "input_cost_per_second": 0.0455, - "output_cost_per_second": 0.0455, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_tool_choice": true - }, - "bedrock/ap-northeast-1/6-month-commitment/anthropic.claude-v2:1": { - "max_tokens": 8191, - "max_input_tokens": 100000, - "max_output_tokens": 8191, - "input_cost_per_second": 0.02527, - "output_cost_per_second": 0.02527, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_tool_choice": true - }, - "bedrock/eu-central-1/anthropic.claude-v2:1": { - "max_tokens": 8191, - "max_input_tokens": 100000, - "max_output_tokens": 8191, - "input_cost_per_token": 8e-06, - "output_cost_per_token": 2.4e-05, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_tool_choice": true - }, - "bedrock/eu-central-1/1-month-commitment/anthropic.claude-v2:1": { - "max_tokens": 8191, - "max_input_tokens": 100000, - "max_output_tokens": 8191, - "input_cost_per_second": 0.0415, - "output_cost_per_second": 0.0415, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_tool_choice": true - }, - "bedrock/eu-central-1/6-month-commitment/anthropic.claude-v2:1": { - "max_tokens": 8191, - "max_input_tokens": 100000, - "max_output_tokens": 8191, - "input_cost_per_second": 0.02305, - "output_cost_per_second": 0.02305, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_tool_choice": true - }, - "bedrock/us-east-1/1-month-commitment/anthropic.claude-v2:1": { - "max_tokens": 8191, - "max_input_tokens": 100000, - "max_output_tokens": 8191, - "input_cost_per_second": 0.0175, - "output_cost_per_second": 0.0175, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_tool_choice": true - }, - "bedrock/us-east-1/6-month-commitment/anthropic.claude-v2:1": { - "max_tokens": 8191, - "max_input_tokens": 100000, - "max_output_tokens": 8191, - "input_cost_per_second": 0.00972, - "output_cost_per_second": 0.00972, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_tool_choice": true - }, - "bedrock/us-west-2/1-month-commitment/anthropic.claude-v2:1": { - "max_tokens": 8191, - "max_input_tokens": 100000, - "max_output_tokens": 8191, - "input_cost_per_second": 0.0175, - "output_cost_per_second": 0.0175, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_tool_choice": true - }, - "bedrock/us-west-2/6-month-commitment/anthropic.claude-v2:1": { - "max_tokens": 8191, - "max_input_tokens": 100000, - "max_output_tokens": 8191, - "input_cost_per_second": 0.00972, - "output_cost_per_second": 0.00972, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_tool_choice": true - }, - "anthropic.claude-instant-v1": { - "max_tokens": 8191, - "max_input_tokens": 100000, - "max_output_tokens": 8191, - "input_cost_per_token": 8e-07, - "output_cost_per_token": 2.4e-06, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_tool_choice": true - }, - "bedrock/us-east-1/anthropic.claude-instant-v1": { - "max_tokens": 8191, - "max_input_tokens": 100000, - "max_output_tokens": 8191, - "input_cost_per_token": 8e-07, - "output_cost_per_token": 2.4e-06, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_tool_choice": true - }, - "bedrock/us-east-1/1-month-commitment/anthropic.claude-instant-v1": { - "max_tokens": 8191, - "max_input_tokens": 100000, - "max_output_tokens": 8191, - "input_cost_per_second": 0.011, - "output_cost_per_second": 0.011, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_tool_choice": true - }, - "bedrock/us-east-1/6-month-commitment/anthropic.claude-instant-v1": { - "max_tokens": 8191, - "max_input_tokens": 100000, - "max_output_tokens": 8191, - "input_cost_per_second": 0.00611, - "output_cost_per_second": 0.00611, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_tool_choice": true - }, - "bedrock/us-west-2/1-month-commitment/anthropic.claude-instant-v1": { - "max_tokens": 8191, - "max_input_tokens": 100000, - "max_output_tokens": 8191, - "input_cost_per_second": 0.011, - "output_cost_per_second": 0.011, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_tool_choice": true - }, - "bedrock/us-west-2/6-month-commitment/anthropic.claude-instant-v1": { - "max_tokens": 8191, - "max_input_tokens": 100000, - "max_output_tokens": 8191, - "input_cost_per_second": 0.00611, - "output_cost_per_second": 0.00611, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_tool_choice": true - }, - "bedrock/us-west-2/anthropic.claude-instant-v1": { - "max_tokens": 8191, - "max_input_tokens": 100000, - "max_output_tokens": 8191, - "input_cost_per_token": 8e-07, - "output_cost_per_token": 2.4e-06, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_tool_choice": true - }, - "bedrock/ap-northeast-1/anthropic.claude-instant-v1": { - "max_tokens": 8191, - "max_input_tokens": 100000, - "max_output_tokens": 8191, - "input_cost_per_token": 2.23e-06, - "output_cost_per_token": 7.55e-06, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_tool_choice": true - }, - "bedrock/ap-northeast-1/1-month-commitment/anthropic.claude-instant-v1": { - "max_tokens": 8191, - "max_input_tokens": 100000, - "max_output_tokens": 8191, - "input_cost_per_second": 0.01475, - "output_cost_per_second": 0.01475, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_tool_choice": true - }, - "bedrock/ap-northeast-1/6-month-commitment/anthropic.claude-instant-v1": { - "max_tokens": 8191, - "max_input_tokens": 100000, - "max_output_tokens": 8191, - "input_cost_per_second": 0.008194, - "output_cost_per_second": 0.008194, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_tool_choice": true - }, - "bedrock/eu-central-1/anthropic.claude-instant-v1": { - "max_tokens": 8191, - "max_input_tokens": 100000, - "max_output_tokens": 8191, - "input_cost_per_token": 2.48e-06, - "output_cost_per_token": 8.38e-06, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_tool_choice": true - }, - "bedrock/eu-central-1/1-month-commitment/anthropic.claude-instant-v1": { - "max_tokens": 8191, - "max_input_tokens": 100000, - "max_output_tokens": 8191, - "input_cost_per_second": 0.01635, - "output_cost_per_second": 0.01635, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_tool_choice": true - }, - "bedrock/eu-central-1/6-month-commitment/anthropic.claude-instant-v1": { - "max_tokens": 8191, - "max_input_tokens": 100000, - "max_output_tokens": 8191, - "input_cost_per_second": 0.009083, - "output_cost_per_second": 0.009083, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_tool_choice": true - }, - "cohere.rerank-v3-5:0": { - "max_tokens": 32000, - "max_input_tokens": 32000, - "max_output_tokens": 32000, - "max_query_tokens": 32000, - "max_document_chunks_per_query": 100, - "max_tokens_per_document_chunk": 512, - "input_cost_per_token": 0.0, - "input_cost_per_query": 0.002, - "output_cost_per_token": 0.0, - "litellm_provider": "bedrock", - "mode": "rerank" - }, - "cohere.command-text-v14": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 1.5e-06, - "output_cost_per_token": 2e-06, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_tool_choice": true - }, - "bedrock/*/1-month-commitment/cohere.command-text-v14": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_second": 0.011, - "output_cost_per_second": 0.011, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_tool_choice": true - }, - "bedrock/*/6-month-commitment/cohere.command-text-v14": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_second": 0.0066027, - "output_cost_per_second": 0.0066027, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_tool_choice": true - }, - "cohere.command-light-text-v14": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 3e-07, - "output_cost_per_token": 6e-07, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_tool_choice": true - }, - "bedrock/*/1-month-commitment/cohere.command-light-text-v14": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_second": 0.001902, - "output_cost_per_second": 0.001902, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_tool_choice": true - }, - "bedrock/*/6-month-commitment/cohere.command-light-text-v14": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_second": 0.0011416, - "output_cost_per_second": 0.0011416, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_tool_choice": true - }, - "cohere.command-r-plus-v1:0": { - "max_tokens": 4096, - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_tool_choice": true - }, - "cohere.command-r-v1:0": { - "max_tokens": 4096, - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 5e-07, - "output_cost_per_token": 1.5e-06, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_tool_choice": true - }, - "cohere.embed-english-v3": { - "max_tokens": 512, - "max_input_tokens": 512, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 0.0, - "litellm_provider": "bedrock", - "mode": "embedding", - "supports_embedding_image_input": true - }, - "cohere.embed-multilingual-v3": { - "max_tokens": 512, - "max_input_tokens": 512, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 0.0, - "litellm_provider": "bedrock", - "mode": "embedding", - "supports_embedding_image_input": true - }, - "us.deepseek.r1-v1:0": { - "max_tokens": 4096, - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 1.35e-06, - "output_cost_per_token": 5.4e-06, - "litellm_provider": "bedrock_converse", - "mode": "chat", - "supports_reasoning": true, - "supports_function_calling": false, - "supports_tool_choice": false - }, - "meta.llama3-3-70b-instruct-v1:0": { - "max_tokens": 4096, - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 7.2e-07, - "output_cost_per_token": 7.2e-07, - "litellm_provider": "bedrock_converse", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": false - }, - "meta.llama2-13b-chat-v1": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 7.5e-07, - "output_cost_per_token": 1e-06, - "litellm_provider": "bedrock", - "mode": "chat" - }, - "meta.llama2-70b-chat-v1": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 1.95e-06, - "output_cost_per_token": 2.56e-06, - "litellm_provider": "bedrock", - "mode": "chat" - }, - "meta.llama3-8b-instruct-v1:0": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 3e-07, - "output_cost_per_token": 6e-07, - "litellm_provider": "bedrock", - "mode": "chat" - }, - "bedrock/us-east-1/meta.llama3-8b-instruct-v1:0": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 3e-07, - "output_cost_per_token": 6e-07, - "litellm_provider": "bedrock", - "mode": "chat" - }, - "bedrock/us-west-1/meta.llama3-8b-instruct-v1:0": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 3e-07, - "output_cost_per_token": 6e-07, - "litellm_provider": "bedrock", - "mode": "chat" - }, - "bedrock/ap-south-1/meta.llama3-8b-instruct-v1:0": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 3.6e-07, - "output_cost_per_token": 7.2e-07, - "litellm_provider": "bedrock", - "mode": "chat" - }, - "bedrock/ca-central-1/meta.llama3-8b-instruct-v1:0": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 3.5e-07, - "output_cost_per_token": 6.9e-07, - "litellm_provider": "bedrock", - "mode": "chat" - }, - "bedrock/eu-west-1/meta.llama3-8b-instruct-v1:0": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 3.2e-07, - "output_cost_per_token": 6.5e-07, - "litellm_provider": "bedrock", - "mode": "chat" - }, - "bedrock/eu-west-2/meta.llama3-8b-instruct-v1:0": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 3.9e-07, - "output_cost_per_token": 7.8e-07, - "litellm_provider": "bedrock", - "mode": "chat" - }, - "bedrock/sa-east-1/meta.llama3-8b-instruct-v1:0": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 5e-07, - "output_cost_per_token": 1.01e-06, - "litellm_provider": "bedrock", - "mode": "chat" - }, - "meta.llama3-70b-instruct-v1:0": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 2.65e-06, - "output_cost_per_token": 3.5e-06, - "litellm_provider": "bedrock", - "mode": "chat" - }, - "bedrock/us-east-1/meta.llama3-70b-instruct-v1:0": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 2.65e-06, - "output_cost_per_token": 3.5e-06, - "litellm_provider": "bedrock", - "mode": "chat" - }, - "bedrock/us-west-1/meta.llama3-70b-instruct-v1:0": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 2.65e-06, - "output_cost_per_token": 3.5e-06, - "litellm_provider": "bedrock", - "mode": "chat" - }, - "bedrock/ap-south-1/meta.llama3-70b-instruct-v1:0": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 3.18e-06, - "output_cost_per_token": 4.2e-06, - "litellm_provider": "bedrock", - "mode": "chat" - }, - "bedrock/ca-central-1/meta.llama3-70b-instruct-v1:0": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 3.05e-06, - "output_cost_per_token": 4.03e-06, - "litellm_provider": "bedrock", - "mode": "chat" - }, - "bedrock/eu-west-1/meta.llama3-70b-instruct-v1:0": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 2.86e-06, - "output_cost_per_token": 3.78e-06, - "litellm_provider": "bedrock", - "mode": "chat" - }, - "bedrock/eu-west-2/meta.llama3-70b-instruct-v1:0": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 3.45e-06, - "output_cost_per_token": 4.55e-06, - "litellm_provider": "bedrock", - "mode": "chat" - }, - "bedrock/sa-east-1/meta.llama3-70b-instruct-v1:0": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 4.45e-06, - "output_cost_per_token": 5.88e-06, - "litellm_provider": "bedrock", - "mode": "chat" - }, - "meta.llama3-1-8b-instruct-v1:0": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 2048, - "input_cost_per_token": 2.2e-07, - "output_cost_per_token": 2.2e-07, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": false - }, - "us.meta.llama3-1-8b-instruct-v1:0": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 2048, - "input_cost_per_token": 2.2e-07, - "output_cost_per_token": 2.2e-07, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": false - }, - "meta.llama3-1-70b-instruct-v1:0": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 2048, - "input_cost_per_token": 9.9e-07, - "output_cost_per_token": 9.9e-07, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": false - }, - "us.meta.llama3-1-70b-instruct-v1:0": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 2048, - "input_cost_per_token": 9.9e-07, - "output_cost_per_token": 9.9e-07, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": false - }, - "meta.llama3-1-405b-instruct-v1:0": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 5.32e-06, - "output_cost_per_token": 1.6e-05, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": false - }, - "us.meta.llama3-1-405b-instruct-v1:0": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 5.32e-06, - "output_cost_per_token": 1.6e-05, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": false - }, - "meta.llama3-2-1b-instruct-v1:0": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 1e-07, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": false - }, - "us.meta.llama3-2-1b-instruct-v1:0": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 1e-07, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": false - }, - "eu.meta.llama3-2-1b-instruct-v1:0": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 1.3e-07, - "output_cost_per_token": 1.3e-07, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": false - }, - "meta.llama3-2-3b-instruct-v1:0": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 1.5e-07, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": false - }, - "us.meta.llama3-2-3b-instruct-v1:0": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 1.5e-07, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": false - }, - "eu.meta.llama3-2-3b-instruct-v1:0": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 1.9e-07, - "output_cost_per_token": 1.9e-07, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": false - }, - "meta.llama3-2-11b-instruct-v1:0": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 3.5e-07, - "output_cost_per_token": 3.5e-07, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": false, - "supports_vision": true - }, - "us.meta.llama3-2-11b-instruct-v1:0": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 3.5e-07, - "output_cost_per_token": 3.5e-07, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": false, - "supports_vision": true - }, - "meta.llama3-2-90b-instruct-v1:0": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 2e-06, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": false, - "supports_vision": true - }, - "us.meta.llama3-2-90b-instruct-v1:0": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 2e-06, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": false, - "supports_vision": true - }, - "us.meta.llama3-3-70b-instruct-v1:0": { - "max_tokens": 4096, - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 7.2e-07, - "output_cost_per_token": 7.2e-07, - "litellm_provider": "bedrock_converse", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": false - }, - "meta.llama4-maverick-17b-instruct-v1:0": { - "max_tokens": 4096, - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 2.4e-07, - "input_cost_per_token_batches": 1.2e-07, - "output_cost_per_token": 9.7e-07, - "output_cost_per_token_batches": 4.85e-07, - "litellm_provider": "bedrock_converse", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": false, - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text", - "code" - ] - }, - "us.meta.llama4-maverick-17b-instruct-v1:0": { - "max_tokens": 4096, - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 2.4e-07, - "input_cost_per_token_batches": 1.2e-07, - "output_cost_per_token": 9.7e-07, - "output_cost_per_token_batches": 4.85e-07, - "litellm_provider": "bedrock_converse", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": false, - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text", - "code" - ] - }, - "meta.llama4-scout-17b-instruct-v1:0": { - "max_tokens": 4096, - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 1.7e-07, - "input_cost_per_token_batches": 8.5e-08, - "output_cost_per_token": 6.6e-07, - "output_cost_per_token_batches": 3.3e-07, - "litellm_provider": "bedrock_converse", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": false, - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text", - "code" - ] - }, - "us.meta.llama4-scout-17b-instruct-v1:0": { - "max_tokens": 4096, - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "input_cost_per_token": 1.7e-07, - "input_cost_per_token_batches": 8.5e-08, - "output_cost_per_token": 6.6e-07, - "output_cost_per_token_batches": 3.3e-07, - "litellm_provider": "bedrock_converse", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": false, - "supported_modalities": [ - "text", - "image" - ], - "supported_output_modalities": [ - "text", - "code" - ] - }, - "512-x-512/50-steps/stability.stable-diffusion-xl-v0": { - "max_tokens": 77, - "max_input_tokens": 77, - "output_cost_per_image": 0.018, - "litellm_provider": "bedrock", - "mode": "image_generation" - }, - "512-x-512/max-steps/stability.stable-diffusion-xl-v0": { - "max_tokens": 77, - "max_input_tokens": 77, - "output_cost_per_image": 0.036, - "litellm_provider": "bedrock", - "mode": "image_generation" - }, - "max-x-max/50-steps/stability.stable-diffusion-xl-v0": { - "max_tokens": 77, - "max_input_tokens": 77, - "output_cost_per_image": 0.036, - "litellm_provider": "bedrock", - "mode": "image_generation" - }, - "max-x-max/max-steps/stability.stable-diffusion-xl-v0": { - "max_tokens": 77, - "max_input_tokens": 77, - "output_cost_per_image": 0.072, - "litellm_provider": "bedrock", - "mode": "image_generation" - }, - "1024-x-1024/50-steps/stability.stable-diffusion-xl-v1": { - "max_tokens": 77, - "max_input_tokens": 77, - "output_cost_per_image": 0.04, - "litellm_provider": "bedrock", - "mode": "image_generation" - }, - "1024-x-1024/max-steps/stability.stable-diffusion-xl-v1": { - "max_tokens": 77, - "max_input_tokens": 77, - "output_cost_per_image": 0.08, - "litellm_provider": "bedrock", - "mode": "image_generation" - }, - "stability.sd3-large-v1:0": { - "max_tokens": 77, - "max_input_tokens": 77, - "output_cost_per_image": 0.08, - "litellm_provider": "bedrock", - "mode": "image_generation" - }, - "stability.sd3-5-large-v1:0": { - "max_tokens": 77, - "max_input_tokens": 77, - "output_cost_per_image": 0.08, - "litellm_provider": "bedrock", - "mode": "image_generation" - }, - "stability.stable-image-core-v1:0": { - "max_tokens": 77, - "max_input_tokens": 77, - "output_cost_per_image": 0.04, - "litellm_provider": "bedrock", - "mode": "image_generation" - }, - "stability.stable-image-core-v1:1": { - "max_tokens": 77, - "max_input_tokens": 77, - "output_cost_per_image": 0.04, - "litellm_provider": "bedrock", - "mode": "image_generation" - }, - "stability.stable-image-ultra-v1:0": { - "max_tokens": 77, - "max_input_tokens": 77, - "output_cost_per_image": 0.14, - "litellm_provider": "bedrock", - "mode": "image_generation" - }, - "stability.stable-image-ultra-v1:1": { - "max_tokens": 77, - "max_input_tokens": 77, - "output_cost_per_image": 0.14, - "litellm_provider": "bedrock", - "mode": "image_generation" - }, - "sagemaker/meta-textgeneration-llama-2-7b": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "sagemaker", - "mode": "completion" - }, - "sagemaker/meta-textgeneration-llama-2-7b-f": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "sagemaker", - "mode": "chat" - }, - "sagemaker/meta-textgeneration-llama-2-13b": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "sagemaker", - "mode": "completion" - }, - "sagemaker/meta-textgeneration-llama-2-13b-f": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "sagemaker", - "mode": "chat" - }, - "sagemaker/meta-textgeneration-llama-2-70b": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "sagemaker", - "mode": "completion" - }, - "sagemaker/meta-textgeneration-llama-2-70b-b-f": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "sagemaker", - "mode": "chat" - }, - "together-ai-up-to-4b": { - "input_cost_per_token": 1e-07, - "output_cost_per_token": 1e-07, - "litellm_provider": "together_ai", - "mode": "chat" - }, - "together-ai-4.1b-8b": { - "input_cost_per_token": 2e-07, - "output_cost_per_token": 2e-07, - "litellm_provider": "together_ai", - "mode": "chat" - }, - "together-ai-8.1b-21b": { - "max_tokens": 1000, - "input_cost_per_token": 3e-07, - "output_cost_per_token": 3e-07, - "litellm_provider": "together_ai", - "mode": "chat" - }, - "together-ai-21.1b-41b": { - "input_cost_per_token": 8e-07, - "output_cost_per_token": 8e-07, - "litellm_provider": "together_ai", - "mode": "chat" - }, - "together-ai-41.1b-80b": { - "input_cost_per_token": 9e-07, - "output_cost_per_token": 9e-07, - "litellm_provider": "together_ai", - "mode": "chat" - }, - "together-ai-81.1b-110b": { - "input_cost_per_token": 1.8e-06, - "output_cost_per_token": 1.8e-06, - "litellm_provider": "together_ai", - "mode": "chat" - }, - "together-ai-embedding-up-to-150m": { - "input_cost_per_token": 8e-09, - "output_cost_per_token": 0.0, - "litellm_provider": "together_ai", - "mode": "embedding" - }, - "together-ai-embedding-151m-to-350m": { - "input_cost_per_token": 1.6e-08, - "output_cost_per_token": 0.0, - "litellm_provider": "together_ai", - "mode": "embedding" - }, - "together_ai/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo": { - "input_cost_per_token": 1.8e-07, - "output_cost_per_token": 1.8e-07, - "litellm_provider": "together_ai", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "mode": "chat", - "supports_tool_choice": true - }, - "together_ai/meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo": { - "input_cost_per_token": 8.8e-07, - "output_cost_per_token": 8.8e-07, - "litellm_provider": "together_ai", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "mode": "chat", - "supports_tool_choice": true - }, - "together_ai/meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo": { - "input_cost_per_token": 3.5e-06, - "output_cost_per_token": 3.5e-06, - "litellm_provider": "together_ai", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "mode": "chat", - "supports_tool_choice": true - }, - "together_ai/meta-llama/Llama-3.3-70B-Instruct-Turbo": { - "input_cost_per_token": 8.8e-07, - "output_cost_per_token": 8.8e-07, - "litellm_provider": "together_ai", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "mode": "chat", - "supports_tool_choice": true - }, - "together_ai/meta-llama/Llama-3.3-70B-Instruct-Turbo-Free": { + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" + }, + "gemini/learnlm-1.5-pro-experimental": { + "input_cost_per_audio_per_second": 0, + "input_cost_per_audio_per_second_above_128k_tokens": 0, + "input_cost_per_character": 0, + "input_cost_per_character_above_128k_tokens": 0, + "input_cost_per_image": 0, + "input_cost_per_image_above_128k_tokens": 0, "input_cost_per_token": 0, + "input_cost_per_token_above_128k_tokens": 0, + "input_cost_per_video_per_second": 0, + "input_cost_per_video_per_second_above_128k_tokens": 0, + "litellm_provider": "gemini", + "max_input_tokens": 32767, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_character": 0, + "output_cost_per_character_above_128k_tokens": 0, "output_cost_per_token": 0, - "litellm_provider": "together_ai", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "mode": "chat", - "supports_tool_choice": true - }, - "together_ai/mistralai/Mixtral-8x7B-Instruct-v0.1": { - "input_cost_per_token": 6e-07, - "output_cost_per_token": 6e-07, - "litellm_provider": "together_ai", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "mode": "chat", - "supports_tool_choice": true - }, - "together_ai/mistralai/Mistral-7B-Instruct-v0.1": { - "litellm_provider": "together_ai", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_response_schema": true, - "mode": "chat", - "supports_tool_choice": true - }, - "together_ai/togethercomputer/CodeLlama-34b-Instruct": { - "litellm_provider": "together_ai", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "mode": "chat", - "supports_tool_choice": true - }, - "together_ai/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8": { - "input_cost_per_token": 2.7e-07, - "output_cost_per_token": 8.5e-07, - "litellm_provider": "together_ai", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "mode": "chat", - "supports_tool_choice": true - }, - "together_ai/meta-llama/Llama-4-Scout-17B-16E-Instruct": { - "input_cost_per_token": 1.8e-07, - "output_cost_per_token": 5.9e-07, - "litellm_provider": "together_ai", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "mode": "chat", - "supports_tool_choice": true - }, - "together_ai/meta-llama/Llama-3.2-3B-Instruct-Turbo": { - "litellm_provider": "together_ai", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "mode": "chat", - "supports_tool_choice": true - }, - "together_ai/Qwen/Qwen2.5-7B-Instruct-Turbo": { - "litellm_provider": "together_ai", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "mode": "chat", - "supports_tool_choice": true - }, - "together_ai/Qwen/Qwen2.5-72B-Instruct-Turbo": { - "litellm_provider": "together_ai", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "mode": "chat", - "supports_tool_choice": true - }, - "together_ai/Qwen/Qwen3-235B-A22B-Instruct-2507-tput": { - "input_cost_per_token": 2e-07, - "output_cost_per_token": 6e-06, - "max_input_tokens": 262000, - "litellm_provider": "together_ai", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "mode": "chat", - "supports_tool_choice": true, - "source": "https://www.together.ai/models/qwen3-235b-a22b-instruct-2507-fp8" - }, - "together_ai/Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8": { - "input_cost_per_token": 2e-06, - "output_cost_per_token": 2e-06, - "max_input_tokens": 256000, - "litellm_provider": "together_ai", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "mode": "chat", - "supports_tool_choice": true, - "source": "https://www.together.ai/models/qwen3-coder-480b-a35b-instruct" - }, - "together_ai/Qwen/Qwen3-235B-A22B-Thinking-2507": { - "input_cost_per_token": 6.5e-07, - "output_cost_per_token": 3e-06, - "max_input_tokens": 256000, - "litellm_provider": "together_ai", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "mode": "chat", - "supports_tool_choice": true, - "source": "https://www.together.ai/models/qwen3-235b-a22b-thinking-2507" - }, - "together_ai/Qwen/Qwen3-235B-A22B-fp8-tput": { - "input_cost_per_token": 2e-07, - "output_cost_per_token": 6e-07, - "max_input_tokens": 40000, - "litellm_provider": "together_ai", - "supports_function_calling": false, - "supports_parallel_function_calling": false, - "mode": "chat", - "supports_tool_choice": false, - "source": "https://www.together.ai/models/qwen3-235b-a22b-fp8-tput" - }, - "together_ai/deepseek-ai/DeepSeek-V3": { - "input_cost_per_token": 1.25e-06, - "output_cost_per_token": 1.25e-06, - "max_tokens": 8192, - "max_input_tokens": 65536, - "max_output_tokens": 8192, - "litellm_provider": "together_ai", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "mode": "chat", - "supports_tool_choice": true - }, - "together_ai/deepseek-ai/DeepSeek-R1": { - "input_cost_per_token": 3e-06, - "output_cost_per_token": 7e-06, - "max_tokens": 20480, - "max_input_tokens": 128000, - "max_output_tokens": 20480, - "litellm_provider": "together_ai", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "mode": "chat", - "supports_tool_choice": true - }, - "together_ai/deepseek-ai/DeepSeek-R1-0528-tput": { - "input_cost_per_token": 5.5e-07, - "output_cost_per_token": 2.19e-06, - "max_input_tokens": 128000, - "litellm_provider": "together_ai", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "mode": "chat", - "supports_tool_choice": true, - "source": "https://www.together.ai/models/deepseek-r1-0528-throughput" - }, - "together_ai/mistralai/Mistral-Small-24B-Instruct-2501": { - "litellm_provider": "together_ai", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "mode": "chat", - "supports_tool_choice": true - }, - "together_ai/moonshotai/Kimi-K2-Instruct": { - "input_cost_per_token": 1e-06, - "output_cost_per_token": 3e-06, - "litellm_provider": "together_ai", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_parallel_function_calling": true, - "mode": "chat", - "source": "https://www.together.ai/models/kimi-k2-instruct" - }, - "together_ai/openai/gpt-oss-120b": { - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 6e-07, - "max_input_tokens": 128000, - "litellm_provider": "together_ai", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_parallel_function_calling": true, - "mode": "chat", - "source": "https://www.together.ai/models/gpt-oss-120b" - }, - "together_ai/openai/gpt-oss-20b": { - "input_cost_per_token": 5e-08, - "output_cost_per_token": 2e-07, - "max_input_tokens": 128000, - "litellm_provider": "together_ai", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_parallel_function_calling": true, - "mode": "chat", - "source": "https://www.together.ai/models/gpt-oss-20b" - }, - "together_ai/zai-org/GLM-4.5-Air-FP8": { - "input_cost_per_token": 2e-07, - "output_cost_per_token": 1.1e-06, - "max_input_tokens": 128000, - "litellm_provider": "together_ai", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_parallel_function_calling": true, - "mode": "chat", - "source": "https://www.together.ai/models/glm-4-5-air" - }, - "together_ai/deepseek-ai/DeepSeek-V3.1": { - "input_cost_per_token": 0.6e-06, - "output_cost_per_token": 1.7e-06, - "max_tokens": 128000, - "litellm_provider": "together_ai", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_reasoning": true, - "mode": "chat", - "supports_tool_choice": true, - "source": "https://www.together.ai/models/deepseek-v3-1" - }, - "ollama/codegemma": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "ollama", - "mode": "completion" - }, - "ollama/codegeex4": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 8192, - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "ollama", - "mode": "chat", - "supports_function_calling": false - }, - "ollama/deepseek-coder-v2-instruct": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 8192, - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "ollama", - "mode": "chat", - "supports_function_calling": true - }, - "ollama/deepseek-coder-v2-base": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "ollama", - "mode": "completion", - "supports_function_calling": true - }, - "ollama/deepseek-coder-v2-lite-instruct": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 8192, - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "ollama", - "mode": "chat", - "supports_function_calling": true - }, - "ollama/deepseek-coder-v2-lite-base": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "ollama", - "mode": "completion", - "supports_function_calling": true - }, - "ollama/internlm2_5-20b-chat": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 8192, - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "ollama", - "mode": "chat", - "supports_function_calling": true - }, - "ollama/llama2": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "ollama", - "mode": "chat" - }, - "ollama/llama2:7b": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "ollama", - "mode": "chat" - }, - "ollama/llama2:13b": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "ollama", - "mode": "chat" - }, - "ollama/llama2:70b": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "ollama", - "mode": "chat" - }, - "ollama/llama2-uncensored": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "ollama", - "mode": "completion" - }, - "ollama/llama3": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "ollama", - "mode": "chat" - }, - "ollama/llama3:8b": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "ollama", - "mode": "chat" - }, - "ollama/llama3:70b": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "ollama", - "mode": "chat" - }, - "ollama/llama3.1": { - "max_tokens": 32768, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "ollama", - "mode": "chat", - "supports_function_calling": true - }, - "ollama/mistral-large-instruct-2407": { - "max_tokens": 65536, - "max_input_tokens": 65536, - "max_output_tokens": 8192, - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "ollama", - "mode": "chat", - "supports_function_calling": true - }, - "ollama/mistral": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "ollama", - "mode": "completion", - "supports_function_calling": true - }, - "ollama/mistral-7B-Instruct-v0.1": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "ollama", - "mode": "chat", - "supports_function_calling": true - }, - "ollama/mistral-7B-Instruct-v0.2": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "ollama", - "mode": "chat", - "supports_function_calling": true - }, - "ollama/mixtral-8x7B-Instruct-v0.1": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "ollama", - "mode": "chat", - "supports_function_calling": true - }, - "ollama/mixtral-8x22B-Instruct-v0.1": { - "max_tokens": 65536, - "max_input_tokens": 65536, - "max_output_tokens": 65536, - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "ollama", - "mode": "chat", - "supports_function_calling": true - }, - "ollama/codellama": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "ollama", - "mode": "completion" - }, - "ollama/orca-mini": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "ollama", - "mode": "completion" - }, - "ollama/vicuna": { - "max_tokens": 2048, - "max_input_tokens": 2048, - "max_output_tokens": 2048, - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "ollama", - "mode": "completion" - }, - "deepinfra/Gryphe/MythoMax-L2-13b": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 7.2e-08, - "output_cost_per_token": 7.2e-08, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": true - }, - "deepinfra/NousResearch/Hermes-3-Llama-3.1-405B": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 7e-07, - "output_cost_per_token": 8e-07, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": true - }, - "deepinfra/NousResearch/Hermes-3-Llama-3.1-70B": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 2.8e-07, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": false - }, - "deepinfra/Qwen/QwQ-32B": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 4e-07, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": true - }, - "deepinfra/Qwen/Qwen2.5-72B-Instruct": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "input_cost_per_token": 1.2e-07, - "output_cost_per_token": 3.9e-07, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": true - }, - "deepinfra/Qwen/Qwen2.5-7B-Instruct": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "input_cost_per_token": 4e-08, - "output_cost_per_token": 1e-07, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": false - }, - "deepinfra/Qwen/Qwen2.5-VL-32B-Instruct": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "input_cost_per_token": 2e-07, - "output_cost_per_token": 6e-07, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": true - }, - "deepinfra/Qwen/Qwen3-14B": { - "max_tokens": 40960, - "max_input_tokens": 40960, - "max_output_tokens": 40960, - "input_cost_per_token": 6e-08, - "output_cost_per_token": 2.4e-07, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": true - }, - "deepinfra/Qwen/Qwen3-235B-A22B": { - "max_tokens": 40960, - "max_input_tokens": 40960, - "max_output_tokens": 40960, - "input_cost_per_token": 1.3e-07, - "output_cost_per_token": 6e-07, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": true - }, - "deepinfra/Qwen/Qwen3-235B-A22B-Instruct-2507": { - "max_tokens": 262144, - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "input_cost_per_token": 1.3e-07, - "output_cost_per_token": 6e-07, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": true - }, - "deepinfra/Qwen/Qwen3-235B-A22B-Thinking-2507": { - "max_tokens": 262144, - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "input_cost_per_token": 1.3e-07, - "output_cost_per_token": 6e-07, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": true - }, - "deepinfra/Qwen/Qwen3-30B-A3B": { - "max_tokens": 40960, - "max_input_tokens": 40960, - "max_output_tokens": 40960, - "input_cost_per_token": 8e-08, - "output_cost_per_token": 2.9e-07, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": true - }, - "deepinfra/Qwen/Qwen3-32B": { - "max_tokens": 40960, - "max_input_tokens": 40960, - "max_output_tokens": 40960, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 3e-07, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": true - }, - "deepinfra/Qwen/Qwen3-Coder-480B-A35B-Instruct": { - "max_tokens": 262144, - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "input_cost_per_token": 4e-07, - "output_cost_per_token": 1.6e-06, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": true - }, - "deepinfra/Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo": { - "max_tokens": 262144, - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "input_cost_per_token": 3e-07, - "output_cost_per_token": 1.2e-06, - "cache_read_input_token_cost": 2.4e-07, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": true - }, - "deepinfra/Sao10K/L3-8B-Lunaris-v1-Turbo": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 2e-08, - "output_cost_per_token": 5e-08, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": false - }, - "deepinfra/Sao10K/L3.1-70B-Euryale-v2.2": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 6.5e-07, - "output_cost_per_token": 7.5e-07, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": false - }, - "deepinfra/Sao10K/L3.3-70B-Euryale-v2.3": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 6.5e-07, - "output_cost_per_token": 7.5e-07, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": false - }, - "deepinfra/allenai/olmOCR-7B-0725-FP8": { - "max_tokens": 16384, - "max_input_tokens": 16384, - "max_output_tokens": 16384, - "input_cost_per_token": 2.7e-07, - "output_cost_per_token": 1.5e-06, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": false - }, - "deepinfra/anthropic/claude-3-7-sonnet-latest": { - "max_tokens": 200000, - "max_input_tokens": 200000, - "max_output_tokens": 200000, - "input_cost_per_token": 3.3e-06, - "output_cost_per_token": 1.65e-05, - "cache_read_input_token_cost": 3.3e-07, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": true - }, - "deepinfra/anthropic/claude-4-opus": { - "max_tokens": 200000, - "max_input_tokens": 200000, - "max_output_tokens": 200000, - "input_cost_per_token": 1.65e-05, - "output_cost_per_token": 8.25e-05, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": true - }, - "deepinfra/anthropic/claude-4-sonnet": { - "max_tokens": 200000, - "max_input_tokens": 200000, - "max_output_tokens": 200000, - "input_cost_per_token": 3.3e-06, - "output_cost_per_token": 1.65e-05, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": true - }, - "deepinfra/deepseek-ai/DeepSeek-R1": { - "max_tokens": 163840, - "max_input_tokens": 163840, - "max_output_tokens": 163840, - "input_cost_per_token": 7e-07, - "output_cost_per_token": 2.4e-06, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": true - }, - "deepinfra/deepseek-ai/DeepSeek-R1-0528": { - "max_tokens": 163840, - "max_input_tokens": 163840, - "max_output_tokens": 163840, - "input_cost_per_token": 5e-07, - "output_cost_per_token": 2.15e-06, - "cache_read_input_token_cost": 4e-07, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": true - }, - "deepinfra/deepseek-ai/DeepSeek-R1-0528-Turbo": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "input_cost_per_token": 1e-06, - "output_cost_per_token": 3e-06, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": true - }, - "deepinfra/deepseek-ai/DeepSeek-R1-Distill-Llama-70B": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 4e-07, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": false - }, - "deepinfra/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 7.5e-08, - "output_cost_per_token": 1.5e-07, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": true - }, - "deepinfra/deepseek-ai/DeepSeek-R1-Turbo": { - "max_tokens": 40960, - "max_input_tokens": 40960, - "max_output_tokens": 40960, - "input_cost_per_token": 1e-06, - "output_cost_per_token": 3e-06, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": true - }, - "deepinfra/deepseek-ai/DeepSeek-V3": { - "max_tokens": 163840, - "max_input_tokens": 163840, - "max_output_tokens": 163840, - "input_cost_per_token": 3.8e-07, - "output_cost_per_token": 8.9e-07, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": true - }, - "deepinfra/deepseek-ai/DeepSeek-V3-0324": { - "max_tokens": 163840, - "max_input_tokens": 163840, - "max_output_tokens": 163840, - "input_cost_per_token": 2.8e-07, - "output_cost_per_token": 8.8e-07, - "cache_read_input_token_cost": 2.24e-07, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": true - }, - "deepinfra/deepseek-ai/DeepSeek-V3.1": { - "max_tokens": 163840, - "max_input_tokens": 163840, - "max_output_tokens": 163840, - "input_cost_per_token": 2.7e-07, - "output_cost_per_token": 1e-06, - "cache_read_input_token_cost": 2.16e-07, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": true, - "supports_reasoning": true - }, - "deepinfra/google/gemini-2.0-flash-001": { - "max_tokens": 1000000, - "max_input_tokens": 1000000, - "max_output_tokens": 1000000, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 4e-07, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": true - }, - "deepinfra/google/gemini-2.5-flash": { - "max_tokens": 1000000, - "max_input_tokens": 1000000, - "max_output_tokens": 1000000, - "input_cost_per_token": 2.1e-07, - "output_cost_per_token": 1.75e-06, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": true - }, - "deepinfra/google/gemini-2.5-pro": { - "max_tokens": 1000000, - "max_input_tokens": 1000000, - "max_output_tokens": 1000000, - "input_cost_per_token": 8.75e-07, - "output_cost_per_token": 7e-06, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": true - }, - "deepinfra/google/gemma-3-12b-it": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 5e-08, - "output_cost_per_token": 1e-07, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": true - }, - "deepinfra/google/gemma-3-27b-it": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 9e-08, - "output_cost_per_token": 1.7e-07, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": true - }, - "deepinfra/google/gemma-3-4b-it": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 4e-08, - "output_cost_per_token": 8e-08, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": true - }, - "deepinfra/meta-llama/Llama-3.2-11B-Vision-Instruct": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 4.9e-08, - "output_cost_per_token": 4.9e-08, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": false - }, - "deepinfra/meta-llama/Llama-3.2-3B-Instruct": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 1.2e-08, - "output_cost_per_token": 2.4e-08, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": true - }, - "deepinfra/meta-llama/Llama-3.3-70B-Instruct": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 2.3e-07, - "output_cost_per_token": 4e-07, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": true - }, - "deepinfra/meta-llama/Llama-3.3-70B-Instruct-Turbo": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 3.8e-08, - "output_cost_per_token": 1.2e-07, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": true - }, - "deepinfra/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8": { - "max_tokens": 1048576, - "max_input_tokens": 1048576, - "max_output_tokens": 1048576, - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 6e-07, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": true - }, - "deepinfra/meta-llama/Llama-4-Scout-17B-16E-Instruct": { - "max_tokens": 327680, - "max_input_tokens": 327680, - "max_output_tokens": 327680, - "input_cost_per_token": 8e-08, - "output_cost_per_token": 3e-07, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": true - }, - "deepinfra/meta-llama/Llama-Guard-3-8B": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 5.5e-08, - "output_cost_per_token": 5.5e-08, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": false - }, - "deepinfra/meta-llama/Llama-Guard-4-12B": { - "max_tokens": 163840, - "max_input_tokens": 163840, - "max_output_tokens": 163840, - "input_cost_per_token": 1.8e-07, - "output_cost_per_token": 1.8e-07, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": false - }, - "deepinfra/meta-llama/Meta-Llama-3-8B-Instruct": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 3e-08, - "output_cost_per_token": 6e-08, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": true - }, - "deepinfra/meta-llama/Meta-Llama-3.1-70B-Instruct": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 2.3e-07, - "output_cost_per_token": 4e-07, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": true - }, - "deepinfra/meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 2.8e-07, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": true - }, - "deepinfra/meta-llama/Meta-Llama-3.1-8B-Instruct": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 3e-08, - "output_cost_per_token": 5e-08, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": true - }, - "deepinfra/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 1.5e-08, - "output_cost_per_token": 2e-08, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": true - }, - "deepinfra/microsoft/WizardLM-2-8x22B": { - "max_tokens": 65536, - "max_input_tokens": 65536, - "max_output_tokens": 65536, - "input_cost_per_token": 4.8e-07, - "output_cost_per_token": 4.8e-07, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": false - }, - "deepinfra/microsoft/phi-4": { - "max_tokens": 16384, - "max_input_tokens": 16384, - "max_output_tokens": 16384, - "input_cost_per_token": 7e-08, - "output_cost_per_token": 1.4e-07, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": true - }, - "deepinfra/mistralai/Mistral-Nemo-Instruct-2407": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 2e-08, - "output_cost_per_token": 4e-08, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": true - }, - "deepinfra/mistralai/Mistral-Small-24B-Instruct-2501": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "input_cost_per_token": 5e-08, - "output_cost_per_token": 8e-08, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": true - }, - "deepinfra/mistralai/Mistral-Small-3.2-24B-Instruct-2506": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "input_cost_per_token": 5e-08, - "output_cost_per_token": 1e-07, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": true - }, - "deepinfra/mistralai/Mixtral-8x7B-Instruct-v0.1": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "input_cost_per_token": 8e-08, - "output_cost_per_token": 2.4e-07, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": true - }, - "deepinfra/moonshotai/Kimi-K2-Instruct": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 5e-07, - "output_cost_per_token": 2e-06, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": true - }, - "deepinfra/nvidia/Llama-3.1-Nemotron-70B-Instruct": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 1.2e-07, - "output_cost_per_token": 3e-07, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": true - }, - "deepinfra/openai/gpt-oss-120b": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 9e-08, - "output_cost_per_token": 4.5e-07, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": true - }, - "deepinfra/openai/gpt-oss-20b": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 4e-08, - "output_cost_per_token": 1.6e-07, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": true - }, - "deepinfra/zai-org/GLM-4.5": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 5.5e-07, - "output_cost_per_token": 2e-06, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": true - }, - "deepinfra/zai-org/GLM-4.5-Air": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 2e-07, - "output_cost_per_token": 1.1e-06, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": true - }, - "perplexity/codellama-34b-instruct": { - "max_tokens": 16384, - "max_input_tokens": 16384, - "max_output_tokens": 16384, - "input_cost_per_token": 3.5e-07, - "output_cost_per_token": 1.4e-06, - "litellm_provider": "perplexity", - "mode": "chat" - }, - "perplexity/codellama-70b-instruct": { - "max_tokens": 16384, - "max_input_tokens": 16384, - "max_output_tokens": 16384, - "input_cost_per_token": 7e-07, - "output_cost_per_token": 2.8e-06, - "litellm_provider": "perplexity", - "mode": "chat" - }, - "perplexity/llama-3.1-70b-instruct": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 1e-06, - "output_cost_per_token": 1e-06, - "litellm_provider": "perplexity", - "mode": "chat" - }, - "perplexity/llama-3.1-8b-instruct": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 2e-07, - "output_cost_per_token": 2e-07, - "litellm_provider": "perplexity", - "mode": "chat" - }, - "perplexity/llama-3.1-sonar-huge-128k-online": { - "max_tokens": 127072, - "max_input_tokens": 127072, - "max_output_tokens": 127072, - "input_cost_per_token": 5e-06, - "output_cost_per_token": 5e-06, - "litellm_provider": "perplexity", - "mode": "chat", - "deprecation_date": "2025-02-22" - }, - "perplexity/llama-3.1-sonar-large-128k-online": { - "max_tokens": 127072, - "max_input_tokens": 127072, - "max_output_tokens": 127072, - "input_cost_per_token": 1e-06, - "output_cost_per_token": 1e-06, - "litellm_provider": "perplexity", - "mode": "chat", - "deprecation_date": "2025-02-22" - }, - "perplexity/llama-3.1-sonar-large-128k-chat": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 1e-06, - "output_cost_per_token": 1e-06, - "litellm_provider": "perplexity", - "mode": "chat", - "deprecation_date": "2025-02-22" - }, - "perplexity/llama-3.1-sonar-small-128k-chat": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 2e-07, - "output_cost_per_token": 2e-07, - "litellm_provider": "perplexity", - "mode": "chat", - "deprecation_date": "2025-02-22" - }, - "perplexity/llama-3.1-sonar-small-128k-online": { - "max_tokens": 127072, - "max_input_tokens": 127072, - "max_output_tokens": 127072, - "input_cost_per_token": 2e-07, - "output_cost_per_token": 2e-07, - "litellm_provider": "perplexity", - "mode": "chat", - "deprecation_date": "2025-02-22" - }, - "perplexity/pplx-7b-chat": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 7e-08, - "output_cost_per_token": 2.8e-07, - "litellm_provider": "perplexity", - "mode": "chat" - }, - "perplexity/pplx-70b-chat": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 7e-07, - "output_cost_per_token": 2.8e-06, - "litellm_provider": "perplexity", - "mode": "chat" - }, - "perplexity/pplx-7b-online": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 0.0, - "output_cost_per_token": 2.8e-07, - "input_cost_per_request": 0.005, - "litellm_provider": "perplexity", - "mode": "chat" - }, - "perplexity/pplx-70b-online": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 0.0, - "output_cost_per_token": 2.8e-06, - "input_cost_per_request": 0.005, - "litellm_provider": "perplexity", - "mode": "chat" - }, - "perplexity/llama-2-70b-chat": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 7e-07, - "output_cost_per_token": 2.8e-06, - "litellm_provider": "perplexity", - "mode": "chat" - }, - "perplexity/mistral-7b-instruct": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 7e-08, - "output_cost_per_token": 2.8e-07, - "litellm_provider": "perplexity", - "mode": "chat" - }, - "perplexity/mixtral-8x7b-instruct": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 7e-08, - "output_cost_per_token": 2.8e-07, - "litellm_provider": "perplexity", - "mode": "chat" - }, - "perplexity/sonar-small-chat": { - "max_tokens": 16384, - "max_input_tokens": 16384, - "max_output_tokens": 16384, - "input_cost_per_token": 7e-08, - "output_cost_per_token": 2.8e-07, - "litellm_provider": "perplexity", - "mode": "chat" - }, - "perplexity/sonar-small-online": { - "max_tokens": 12000, - "max_input_tokens": 12000, - "max_output_tokens": 12000, - "input_cost_per_token": 0, - "output_cost_per_token": 2.8e-07, - "input_cost_per_request": 0.005, - "litellm_provider": "perplexity", - "mode": "chat" - }, - "perplexity/sonar-medium-chat": { - "max_tokens": 16384, - "max_input_tokens": 16384, - "max_output_tokens": 16384, - "input_cost_per_token": 6e-07, - "output_cost_per_token": 1.8e-06, - "litellm_provider": "perplexity", - "mode": "chat" - }, - "perplexity/sonar-medium-online": { - "max_tokens": 12000, - "max_input_tokens": 12000, - "max_output_tokens": 12000, - "input_cost_per_token": 0, - "output_cost_per_token": 1.8e-06, - "input_cost_per_request": 0.005, - "litellm_provider": "perplexity", - "mode": "chat" - }, - "perplexity/sonar": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "input_cost_per_token": 1e-06, - "output_cost_per_token": 1e-06, - "litellm_provider": "perplexity", - "mode": "chat", - "search_context_cost_per_query": { - "search_context_size_low": 0.005, - "search_context_size_medium": 0.008, - "search_context_size_high": 0.012 - }, - "supports_web_search": true - }, - "perplexity/sonar-pro": { - "max_tokens": 8000, - "max_input_tokens": 200000, - "max_output_tokens": 8000, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "litellm_provider": "perplexity", - "mode": "chat", - "search_context_cost_per_query": { - "search_context_size_low": 0.006, - "search_context_size_medium": 0.01, - "search_context_size_high": 0.014 - }, - "supports_web_search": true - }, - "perplexity/sonar-reasoning": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "input_cost_per_token": 1e-06, - "output_cost_per_token": 5e-06, - "litellm_provider": "perplexity", - "mode": "chat", - "search_context_cost_per_query": { - "search_context_size_low": 0.005, - "search_context_size_medium": 0.008, - "search_context_size_high": 0.014 - }, - "supports_web_search": true, - "supports_reasoning": true - }, - "perplexity/sonar-reasoning-pro": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 8e-06, - "litellm_provider": "perplexity", - "mode": "chat", - "search_context_cost_per_query": { - "search_context_size_low": 0.006, - "search_context_size_medium": 0.01, - "search_context_size_high": 0.014 - }, - "supports_web_search": true, - "supports_reasoning": true - }, - "perplexity/sonar-deep-research": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 8e-06, - "output_cost_per_reasoning_token": 3e-06, - "citation_cost_per_token": 2e-06, - "search_context_cost_per_query": { - "search_context_size_low": 0.005, - "search_context_size_medium": 0.005, - "search_context_size_high": 0.005 - }, - "litellm_provider": "perplexity", - "mode": "chat", - "supports_reasoning": true, - "supports_web_search": true - }, - "fireworks_ai/accounts/fireworks/models/llama-v3p2-1b-instruct": { - "max_tokens": 16384, - "max_input_tokens": 16384, - "max_output_tokens": 16384, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 1e-07, - "litellm_provider": "fireworks_ai", - "mode": "chat", - "supports_function_calling": false, - "supports_response_schema": true, - "source": "https://fireworks.ai/pricing", - "supports_tool_choice": false - }, - "fireworks_ai/accounts/fireworks/models/llama-v3p2-3b-instruct": { - "max_tokens": 16384, - "max_input_tokens": 16384, - "max_output_tokens": 16384, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 1e-07, - "litellm_provider": "fireworks_ai", - "mode": "chat", - "supports_function_calling": false, - "supports_response_schema": true, - "source": "https://fireworks.ai/pricing", - "supports_tool_choice": false - }, - "fireworks_ai/accounts/fireworks/models/llama-v3p1-8b-instruct": { - "max_tokens": 16384, - "max_input_tokens": 16384, - "max_output_tokens": 16384, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 1e-07, - "litellm_provider": "fireworks_ai", - "mode": "chat", - "supports_function_calling": false, - "supports_response_schema": true, - "source": "https://fireworks.ai/pricing", - "supports_tool_choice": false - }, - "fireworks_ai/accounts/fireworks/models/llama-v3p2-11b-vision-instruct": { - "max_tokens": 16384, - "max_input_tokens": 16384, - "max_output_tokens": 16384, - "input_cost_per_token": 2e-07, - "output_cost_per_token": 2e-07, - "litellm_provider": "fireworks_ai", - "mode": "chat", - "supports_function_calling": false, - "supports_vision": true, - "supports_response_schema": true, - "source": "https://fireworks.ai/pricing", - "supports_tool_choice": false - }, - "fireworks_ai/accounts/fireworks/models/llama-v3p2-90b-vision-instruct": { - "max_tokens": 16384, - "max_input_tokens": 16384, - "max_output_tokens": 16384, - "input_cost_per_token": 9e-07, - "output_cost_per_token": 9e-07, - "litellm_provider": "fireworks_ai", - "mode": "chat", - "supports_tool_choice": false, - "supports_vision": true, - "supports_response_schema": true, - "source": "https://fireworks.ai/pricing" - }, - "fireworks_ai/accounts/fireworks/models/firefunction-v2": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 9e-07, - "output_cost_per_token": 9e-07, - "litellm_provider": "fireworks_ai", - "mode": "chat", + "output_cost_per_token_above_128k_tokens": 0, + "source": "https://aistudio.google.com", + "supports_audio_output": false, "supports_function_calling": true, "supports_response_schema": true, - "source": "https://fireworks.ai/pricing", - "supports_tool_choice": true - }, - "fireworks_ai/accounts/fireworks/models/mixtral-8x22b-instruct-hf": { - "max_tokens": 65536, - "max_input_tokens": 65536, - "max_output_tokens": 65536, - "input_cost_per_token": 1.2e-06, - "output_cost_per_token": 1.2e-06, - "litellm_provider": "fireworks_ai", - "mode": "chat", - "supports_function_calling": true, - "supports_response_schema": true, - "source": "https://fireworks.ai/pricing", - "supports_tool_choice": true - }, - "fireworks_ai/accounts/fireworks/models/qwen2-72b-instruct": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "input_cost_per_token": 9e-07, - "output_cost_per_token": 9e-07, - "litellm_provider": "fireworks_ai", - "mode": "chat", - "supports_function_calling": false, - "supports_response_schema": true, - "source": "https://fireworks.ai/pricing", - "supports_tool_choice": false - }, - "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-32b-instruct": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 9e-07, - "output_cost_per_token": 9e-07, - "litellm_provider": "fireworks_ai", - "mode": "chat", - "supports_function_calling": false, - "supports_response_schema": true, - "source": "https://fireworks.ai/pricing", - "supports_tool_choice": false - }, - "fireworks_ai/accounts/fireworks/models/yi-large": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 3e-06, - "litellm_provider": "fireworks_ai", - "mode": "chat", - "supports_function_calling": false, - "supports_response_schema": true, - "source": "https://fireworks.ai/pricing", - "supports_tool_choice": false - }, - "fireworks_ai/accounts/fireworks/models/deepseek-coder-v2-instruct": { - "max_tokens": 65536, - "max_input_tokens": 65536, - "max_output_tokens": 65536, - "input_cost_per_token": 1.2e-06, - "output_cost_per_token": 1.2e-06, - "litellm_provider": "fireworks_ai", - "mode": "chat", - "supports_function_calling": false, - "supports_response_schema": true, - "source": "https://fireworks.ai/pricing", - "supports_tool_choice": false - }, - "fireworks_ai/accounts/fireworks/models/deepseek-v3": { - "max_tokens": 8192, - "max_input_tokens": 128000, - "max_output_tokens": 8192, - "input_cost_per_token": 9e-07, - "output_cost_per_token": 9e-07, - "litellm_provider": "fireworks_ai", - "mode": "chat", - "supports_response_schema": true, - "source": "https://fireworks.ai/pricing", - "supports_tool_choice": false - }, - "fireworks_ai/accounts/fireworks/models/deepseek-v3-0324": { - "max_tokens": 163840, - "max_input_tokens": 163840, - "max_output_tokens": 163840, - "input_cost_per_token": 9e-07, - "output_cost_per_token": 9e-07, - "litellm_provider": "fireworks_ai", - "mode": "chat", - "supports_response_schema": true, - "source": "https://fireworks.ai/models/fireworks/deepseek-v3-0324", - "supports_tool_choice": false - }, - "fireworks_ai/accounts/fireworks/models/deepseek-r1": { - "max_tokens": 20480, - "max_input_tokens": 128000, - "max_output_tokens": 20480, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 8e-06, - "litellm_provider": "fireworks_ai", - "mode": "chat", - "supports_response_schema": true, - "source": "https://fireworks.ai/pricing", - "supports_tool_choice": false - }, - "fireworks_ai/accounts/fireworks/models/deepseek-r1-basic": { - "max_tokens": 20480, - "max_input_tokens": 128000, - "max_output_tokens": 20480, - "input_cost_per_token": 5.5e-07, - "output_cost_per_token": 2.19e-06, - "litellm_provider": "fireworks_ai", - "mode": "chat", - "supports_response_schema": true, - "source": "https://fireworks.ai/pricing", - "supports_tool_choice": false - }, - "fireworks_ai/accounts/fireworks/models/deepseek-r1-0528": { - "max_tokens": 160000, - "max_input_tokens": 160000, - "max_output_tokens": 160000, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 8e-06, - "litellm_provider": "fireworks_ai", - "mode": "chat", - "source": "https://fireworks.ai/pricing", - "supports_tool_choice": false, - "supports_response_schema": true - }, - "fireworks_ai/accounts/fireworks/models/deepseek-v3p1": { - "max_tokens": 8192, - "max_input_tokens": 128000, - "max_output_tokens": 8192, - "input_cost_per_token": 5.6e-07, - "output_cost_per_token": 1.68e-06, - "litellm_provider": "fireworks_ai", - "mode": "chat", - "supports_response_schema": true, - "source": "https://fireworks.ai/pricing", - "supports_tool_choice": true - }, - "fireworks_ai/accounts/fireworks/models/kimi-k2-instruct": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 16384, - "input_cost_per_token": 6e-07, - "output_cost_per_token": 2.5e-06, - "litellm_provider": "fireworks_ai", - "mode": "chat", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "source": "https://fireworks.ai/models/fireworks/kimi-k2-instruct" - }, - "fireworks_ai/accounts/fireworks/models/llama-v3p1-405b-instruct": { - "max_tokens": 16384, - "max_input_tokens": 128000, - "max_output_tokens": 16384, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 3e-06, - "litellm_provider": "fireworks_ai", - "mode": "chat", - "supports_response_schema": true, - "source": "https://fireworks.ai/pricing", - "supports_tool_choice": true, - "supports_function_calling": true - }, - "fireworks_ai/accounts/fireworks/models/llama4-maverick-instruct-basic": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 2.2e-07, - "output_cost_per_token": 8.8e-07, - "litellm_provider": "fireworks_ai", - "mode": "chat", - "supports_response_schema": true, - "source": "https://fireworks.ai/pricing", - "supports_tool_choice": false - }, - "fireworks_ai/accounts/fireworks/models/llama4-scout-instruct-basic": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 6e-07, - "litellm_provider": "fireworks_ai", - "mode": "chat", - "supports_response_schema": true, - "source": "https://fireworks.ai/pricing", - "supports_tool_choice": false - }, - "fireworks_ai/accounts/fireworks/models/glm-4p5": { - "max_tokens": 96000, - "max_input_tokens": 128000, - "max_output_tokens": 96000, - "input_cost_per_token": 5.5e-07, - "output_cost_per_token": 2.19e-06, - "litellm_provider": "fireworks_ai", - "mode": "chat", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "source": "https://fireworks.ai/models/fireworks/glm-4p5" - }, - "fireworks_ai/accounts/fireworks/models/glm-4p5-air": { - "max_tokens": 96000, - "max_input_tokens": 128000, - "max_output_tokens": 96000, - "input_cost_per_token": 2.2e-07, - "output_cost_per_token": 8.8e-07, - "litellm_provider": "fireworks_ai", - "mode": "chat", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "source": "https://artificialanalysis.ai/models/glm-4-5-air" - }, - "fireworks_ai/accounts/fireworks/models/gpt-oss-120b": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 6e-07, - "litellm_provider": "fireworks_ai", - "mode": "chat", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "source": "https://fireworks.ai/pricing" - }, - "fireworks_ai/accounts/fireworks/models/gpt-oss-20b": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 5e-08, - "output_cost_per_token": 2e-07, - "litellm_provider": "fireworks_ai", - "mode": "chat", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "source": "https://fireworks.ai/pricing" - }, - "fireworks_ai/nomic-ai/nomic-embed-text-v1.5": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "input_cost_per_token": 8e-09, - "output_cost_per_token": 0.0, - "litellm_provider": "fireworks_ai-embedding-models", - "mode": "embedding", - "source": "https://fireworks.ai/pricing" - }, - "fireworks_ai/nomic-ai/nomic-embed-text-v1": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "input_cost_per_token": 8e-09, - "output_cost_per_token": 0.0, - "litellm_provider": "fireworks_ai-embedding-models", - "mode": "embedding", - "source": "https://fireworks.ai/pricing" - }, - "fireworks_ai/WhereIsAI/UAE-Large-V1": { - "max_tokens": 512, - "max_input_tokens": 512, - "input_cost_per_token": 1.6e-08, - "output_cost_per_token": 0.0, - "litellm_provider": "fireworks_ai-embedding-models", - "mode": "embedding", - "source": "https://fireworks.ai/pricing" - }, - "fireworks_ai/thenlper/gte-large": { - "max_tokens": 512, - "max_input_tokens": 512, - "input_cost_per_token": 1.6e-08, - "output_cost_per_token": 0.0, - "litellm_provider": "fireworks_ai-embedding-models", - "mode": "embedding", - "source": "https://fireworks.ai/pricing" - }, - "fireworks_ai/thenlper/gte-base": { - "max_tokens": 512, - "max_input_tokens": 512, - "input_cost_per_token": 8e-09, - "output_cost_per_token": 0.0, - "litellm_provider": "fireworks_ai-embedding-models", - "mode": "embedding", - "source": "https://fireworks.ai/pricing" - }, - "fireworks-ai-up-to-4b": { - "input_cost_per_token": 2e-07, - "output_cost_per_token": 2e-07, - "litellm_provider": "fireworks_ai" - }, - "fireworks-ai-4.1b-to-16b": { - "input_cost_per_token": 2e-07, - "output_cost_per_token": 2e-07, - "litellm_provider": "fireworks_ai" - }, - "fireworks-ai-above-16b": { - "input_cost_per_token": 9e-07, - "output_cost_per_token": 9e-07, - "litellm_provider": "fireworks_ai" - }, - "fireworks-ai-moe-up-to-56b": { - "input_cost_per_token": 5e-07, - "output_cost_per_token": 5e-07, - "litellm_provider": "fireworks_ai" - }, - "fireworks-ai-56b-to-176b": { - "input_cost_per_token": 1.2e-06, - "output_cost_per_token": 1.2e-06, - "litellm_provider": "fireworks_ai" - }, - "fireworks-ai-default": { - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "fireworks_ai" - }, - "fireworks-ai-embedding-up-to-150m": { - "input_cost_per_token": 8e-09, - "output_cost_per_token": 0.0, - "litellm_provider": "fireworks_ai-embedding-models" - }, - "fireworks-ai-embedding-150m-to-350m": { - "input_cost_per_token": 1.6e-08, - "output_cost_per_token": 0.0, - "litellm_provider": "fireworks_ai-embedding-models" - }, - "anyscale/mistralai/Mistral-7B-Instruct-v0.1": { - "max_tokens": 16384, - "max_input_tokens": 16384, - "max_output_tokens": 16384, - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 1.5e-07, - "litellm_provider": "anyscale", - "mode": "chat", - "supports_function_calling": true, - "source": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/mistralai-Mistral-7B-Instruct-v0.1" - }, - "anyscale/mistralai/Mixtral-8x7B-Instruct-v0.1": { - "max_tokens": 16384, - "max_input_tokens": 16384, - "max_output_tokens": 16384, - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 1.5e-07, - "litellm_provider": "anyscale", - "mode": "chat", - "supports_function_calling": true, - "source": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/mistralai-Mixtral-8x7B-Instruct-v0.1" - }, - "anyscale/mistralai/Mixtral-8x22B-Instruct-v0.1": { - "max_tokens": 65536, - "max_input_tokens": 65536, - "max_output_tokens": 65536, - "input_cost_per_token": 9e-07, - "output_cost_per_token": 9e-07, - "litellm_provider": "anyscale", - "mode": "chat", - "supports_function_calling": true, - "source": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/mistralai-Mixtral-8x22B-Instruct-v0.1" - }, - "anyscale/HuggingFaceH4/zephyr-7b-beta": { - "max_tokens": 16384, - "max_input_tokens": 16384, - "max_output_tokens": 16384, - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 1.5e-07, - "litellm_provider": "anyscale", - "mode": "chat" - }, - "anyscale/google/gemma-7b-it": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 1.5e-07, - "litellm_provider": "anyscale", - "mode": "chat", - "source": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/google-gemma-7b-it" - }, - "anyscale/meta-llama/Llama-2-7b-chat-hf": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 1.5e-07, - "litellm_provider": "anyscale", - "mode": "chat" - }, - "anyscale/meta-llama/Llama-2-13b-chat-hf": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 2.5e-07, - "output_cost_per_token": 2.5e-07, - "litellm_provider": "anyscale", - "mode": "chat" - }, - "anyscale/meta-llama/Llama-2-70b-chat-hf": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 1e-06, - "output_cost_per_token": 1e-06, - "litellm_provider": "anyscale", - "mode": "chat" - }, - "anyscale/codellama/CodeLlama-34b-Instruct-hf": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 1e-06, - "output_cost_per_token": 1e-06, - "litellm_provider": "anyscale", - "mode": "chat" - }, - "anyscale/codellama/CodeLlama-70b-Instruct-hf": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 1e-06, - "output_cost_per_token": 1e-06, - "litellm_provider": "anyscale", - "mode": "chat", - "source": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/codellama-CodeLlama-70b-Instruct-hf" - }, - "anyscale/meta-llama/Meta-Llama-3-8B-Instruct": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 1.5e-07, - "litellm_provider": "anyscale", - "mode": "chat", - "source": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/meta-llama-Meta-Llama-3-8B-Instruct" - }, - "anyscale/meta-llama/Meta-Llama-3-70B-Instruct": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 1e-06, - "output_cost_per_token": 1e-06, - "litellm_provider": "anyscale", - "mode": "chat", - "source": "https://docs.anyscale.com/preview/endpoints/text-generation/supported-models/meta-llama-Meta-Llama-3-70B-Instruct" - }, - "cloudflare/@cf/meta/llama-2-7b-chat-fp16": { - "max_tokens": 3072, - "max_input_tokens": 3072, - "max_output_tokens": 3072, - "input_cost_per_token": 1.923e-06, - "output_cost_per_token": 1.923e-06, - "litellm_provider": "cloudflare", - "mode": "chat" - }, - "cloudflare/@cf/meta/llama-2-7b-chat-int8": { - "max_tokens": 2048, - "max_input_tokens": 2048, - "max_output_tokens": 2048, - "input_cost_per_token": 1.923e-06, - "output_cost_per_token": 1.923e-06, - "litellm_provider": "cloudflare", - "mode": "chat" - }, - "cloudflare/@cf/mistral/mistral-7b-instruct-v0.1": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 1.923e-06, - "output_cost_per_token": 1.923e-06, - "litellm_provider": "cloudflare", - "mode": "chat" - }, - "cloudflare/@hf/thebloke/codellama-7b-instruct-awq": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 1.923e-06, - "output_cost_per_token": 1.923e-06, - "litellm_provider": "cloudflare", - "mode": "chat" - }, - "v0/v0-1.0-md": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "litellm_provider": "v0", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_vision": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "v0/v0-1.5-md": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "litellm_provider": "v0", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_vision": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "v0/v0-1.5-lg": { - "max_tokens": 512000, - "max_input_tokens": 512000, - "max_output_tokens": 512000, - "input_cost_per_token": 1.5e-05, - "output_cost_per_token": 7.5e-05, - "litellm_provider": "v0", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_vision": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "lambda_ai/deepseek-llama3.3-70b": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 2e-07, - "output_cost_per_token": 6e-07, - "litellm_provider": "lambda_ai", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_reasoning": true + "supports_vision": true }, - "lambda_ai/deepseek-r1-0528": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 2e-07, - "output_cost_per_token": 6e-07, - "litellm_provider": "lambda_ai", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_reasoning": true - }, - "lambda_ai/deepseek-r1-671b": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 8e-07, - "output_cost_per_token": 8e-07, - "litellm_provider": "lambda_ai", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_reasoning": true - }, - "lambda_ai/deepseek-v3-0324": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 2e-07, - "output_cost_per_token": 6e-07, - "litellm_provider": "lambda_ai", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "lambda_ai/hermes3-405b": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 8e-07, - "output_cost_per_token": 8e-07, - "litellm_provider": "lambda_ai", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "lambda_ai/hermes3-70b": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 1.2e-07, - "output_cost_per_token": 3e-07, - "litellm_provider": "lambda_ai", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "lambda_ai/hermes3-8b": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 2.5e-08, - "output_cost_per_token": 4e-08, - "litellm_provider": "lambda_ai", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "lambda_ai/lfm-40b": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 2e-07, - "litellm_provider": "lambda_ai", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "lambda_ai/lfm-7b": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 2.5e-08, - "output_cost_per_token": 4e-08, - "litellm_provider": "lambda_ai", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "lambda_ai/llama-4-maverick-17b-128e-instruct-fp8": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 8192, - "input_cost_per_token": 5e-08, - "output_cost_per_token": 1e-07, - "litellm_provider": "lambda_ai", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "lambda_ai/llama-4-scout-17b-16e-instruct": { - "max_tokens": 16384, - "max_input_tokens": 16384, - "max_output_tokens": 8192, - "input_cost_per_token": 5e-08, - "output_cost_per_token": 1e-07, - "litellm_provider": "lambda_ai", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "lambda_ai/llama3.1-405b-instruct-fp8": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 8e-07, - "output_cost_per_token": 8e-07, - "litellm_provider": "lambda_ai", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "lambda_ai/llama3.1-70b-instruct-fp8": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 1.2e-07, - "output_cost_per_token": 3e-07, - "litellm_provider": "lambda_ai", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "lambda_ai/llama3.1-8b-instruct": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 2.5e-08, - "output_cost_per_token": 4e-08, - "litellm_provider": "lambda_ai", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "lambda_ai/llama3.1-nemotron-70b-instruct-fp8": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 1.2e-07, - "output_cost_per_token": 3e-07, - "litellm_provider": "lambda_ai", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "lambda_ai/llama3.2-11b-vision-instruct": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 1.5e-08, - "output_cost_per_token": 2.5e-08, - "litellm_provider": "lambda_ai", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_vision": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "lambda_ai/llama3.2-3b-instruct": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 1.5e-08, - "output_cost_per_token": 2.5e-08, - "litellm_provider": "lambda_ai", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "lambda_ai/llama3.3-70b-instruct-fp8": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 1.2e-07, - "output_cost_per_token": 3e-07, - "litellm_provider": "lambda_ai", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "lambda_ai/qwen25-coder-32b-instruct": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 5e-08, - "output_cost_per_token": 1e-07, - "litellm_provider": "lambda_ai", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "lambda_ai/qwen3-32b-fp8": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 5e-08, - "output_cost_per_token": 1e-07, - "litellm_provider": "lambda_ai", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_reasoning": true - }, - "hyperbolic/moonshotai/Kimi-K2-Instruct": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 2e-06, - "litellm_provider": "hyperbolic", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "hyperbolic/deepseek-ai/DeepSeek-R1-0528": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 2.5e-07, - "output_cost_per_token": 2.5e-07, - "litellm_provider": "hyperbolic", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "hyperbolic/Qwen/Qwen3-235B-A22B": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 2e-06, - "litellm_provider": "hyperbolic", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "hyperbolic/deepseek-ai/DeepSeek-V3-0324": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "input_cost_per_token": 4e-07, - "output_cost_per_token": 4e-07, - "litellm_provider": "hyperbolic", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "hyperbolic/Qwen/QwQ-32B": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 2e-07, - "output_cost_per_token": 2e-07, - "litellm_provider": "hyperbolic", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "hyperbolic/deepseek-ai/DeepSeek-R1": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "input_cost_per_token": 4e-07, - "output_cost_per_token": 4e-07, - "litellm_provider": "hyperbolic", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "hyperbolic/deepseek-ai/DeepSeek-V3": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "input_cost_per_token": 2e-07, - "output_cost_per_token": 2e-07, - "litellm_provider": "hyperbolic", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "hyperbolic/meta-llama/Llama-3.3-70B-Instruct": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 1.2e-07, - "output_cost_per_token": 3e-07, - "litellm_provider": "hyperbolic", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "hyperbolic/Qwen/Qwen2.5-Coder-32B-Instruct": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "input_cost_per_token": 1.2e-07, - "output_cost_per_token": 3e-07, - "litellm_provider": "hyperbolic", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "hyperbolic/meta-llama/Llama-3.2-3B-Instruct": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "input_cost_per_token": 1.2e-07, - "output_cost_per_token": 3e-07, - "litellm_provider": "hyperbolic", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "hyperbolic/Qwen/Qwen2.5-72B-Instruct": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 1.2e-07, - "output_cost_per_token": 3e-07, - "litellm_provider": "hyperbolic", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "hyperbolic/meta-llama/Meta-Llama-3-70B-Instruct": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 1.2e-07, - "output_cost_per_token": 3e-07, - "litellm_provider": "hyperbolic", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "hyperbolic/NousResearch/Hermes-3-Llama-3.1-70B": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "input_cost_per_token": 1.2e-07, - "output_cost_per_token": 3e-07, - "litellm_provider": "hyperbolic", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "hyperbolic/meta-llama/Meta-Llama-3.1-405B-Instruct": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "input_cost_per_token": 1.2e-07, - "output_cost_per_token": 3e-07, - "litellm_provider": "hyperbolic", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "hyperbolic/meta-llama/Meta-Llama-3.1-8B-Instruct": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "input_cost_per_token": 1.2e-07, - "output_cost_per_token": 3e-07, - "litellm_provider": "hyperbolic", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "hyperbolic/meta-llama/Meta-Llama-3.1-70B-Instruct": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "input_cost_per_token": 1.2e-07, - "output_cost_per_token": 3e-07, - "litellm_provider": "hyperbolic", - "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_system_messages": true, - "supports_tool_choice": true - }, - "voyage/voyage-lite-01": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 0.0, - "litellm_provider": "voyage", - "mode": "embedding" - }, - "voyage/voyage-large-2": { - "max_tokens": 16000, - "max_input_tokens": 16000, - "input_cost_per_token": 1.2e-07, - "output_cost_per_token": 0.0, - "litellm_provider": "voyage", - "mode": "embedding" - }, - "voyage/voyage-finance-2": { - "max_tokens": 32000, - "max_input_tokens": 32000, - "input_cost_per_token": 1.2e-07, - "output_cost_per_token": 0.0, - "litellm_provider": "voyage", - "mode": "embedding" - }, - "voyage/voyage-lite-02-instruct": { - "max_tokens": 4000, - "max_input_tokens": 4000, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 0.0, - "litellm_provider": "voyage", - "mode": "embedding" - }, - "voyage/voyage-law-2": { - "max_tokens": 16000, - "max_input_tokens": 16000, - "input_cost_per_token": 1.2e-07, - "output_cost_per_token": 0.0, - "litellm_provider": "voyage", - "mode": "embedding" - }, - "voyage/voyage-code-2": { - "max_tokens": 16000, - "max_input_tokens": 16000, - "input_cost_per_token": 1.2e-07, - "output_cost_per_token": 0.0, - "litellm_provider": "voyage", - "mode": "embedding" - }, - "voyage/voyage-2": { - "max_tokens": 4000, - "max_input_tokens": 4000, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 0.0, - "litellm_provider": "voyage", - "mode": "embedding" - }, - "voyage/voyage-3-large": { - "max_tokens": 32000, - "max_input_tokens": 32000, - "input_cost_per_token": 1.8e-07, - "output_cost_per_token": 0.0, - "litellm_provider": "voyage", - "mode": "embedding" - }, - "voyage/voyage-3": { - "max_tokens": 32000, - "max_input_tokens": 32000, - "input_cost_per_token": 6e-08, - "output_cost_per_token": 0.0, - "litellm_provider": "voyage", - "mode": "embedding" - }, - "voyage/voyage-3-lite": { - "max_tokens": 32000, - "max_input_tokens": 32000, - "input_cost_per_token": 2e-08, - "output_cost_per_token": 0.0, - "litellm_provider": "voyage", - "mode": "embedding" - }, - "voyage/voyage-code-3": { - "max_tokens": 32000, - "max_input_tokens": 32000, - "input_cost_per_token": 1.8e-07, - "output_cost_per_token": 0.0, - "litellm_provider": "voyage", - "mode": "embedding" - }, - "voyage/voyage-multimodal-3": { - "max_tokens": 32000, - "max_input_tokens": 32000, - "input_cost_per_token": 1.2e-07, - "output_cost_per_token": 0.0, - "litellm_provider": "voyage", - "mode": "embedding" - }, - "voyage/voyage-context-3": { - "max_tokens": 120000, - "max_input_tokens": 120000, - "input_cost_per_token": 1.8e-07, - "output_cost_per_token": 0.0, - "litellm_provider": "voyage", - "mode": "embedding" - }, - "voyage/rerank-2": { - "max_tokens": 16000, - "max_input_tokens": 16000, - "max_output_tokens": 16000, - "max_query_tokens": 16000, - "input_cost_per_token": 5e-08, - "input_cost_per_query": 5e-08, - "output_cost_per_token": 0.0, - "litellm_provider": "voyage", - "mode": "rerank" - }, - "voyage/rerank-2-lite": { - "max_tokens": 8000, - "max_input_tokens": 8000, - "max_output_tokens": 8000, - "max_query_tokens": 8000, - "input_cost_per_token": 2e-08, - "input_cost_per_query": 2e-08, - "output_cost_per_token": 0.0, - "litellm_provider": "voyage", - "mode": "rerank" - }, - "databricks/databricks-claude-3-7-sonnet": { - "max_tokens": 200000, - "max_input_tokens": 200000, - "max_output_tokens": 128000, - "input_cost_per_token": 2.5e-06, - "input_dbu_cost_per_token": 3.571e-05, - "output_cost_per_token": 1.7857e-05, - "output_db_cost_per_token": 0.000214286, - "litellm_provider": "databricks", - "mode": "chat", - "source": "https://www.databricks.com/product/pricing/foundation-model-serving", - "metadata": { - "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Claude 3.7 conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." - }, - "supports_assistant_prefill": true, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true - }, - "databricks/databricks-meta-llama-3-1-405b-instruct": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "input_cost_per_token": 5e-06, - "input_dbu_cost_per_token": 7.1429e-05, - "output_cost_per_token": 1.500002e-05, - "output_db_cost_per_token": 0.000214286, - "litellm_provider": "databricks", - "mode": "chat", - "source": "https://www.databricks.com/product/pricing/foundation-model-serving", - "metadata": { - "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." - }, - "supports_tool_choice": true - }, - "databricks/databricks-meta-llama-3-3-70b-instruct": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "input_cost_per_token": 1.00002e-06, - "input_dbu_cost_per_token": 1.4286e-05, - "output_cost_per_token": 2.99999e-06, - "output_dbu_cost_per_token": 4.2857e-05, - "litellm_provider": "databricks", - "mode": "chat", - "source": "https://www.databricks.com/product/pricing/foundation-model-serving", - "metadata": { - "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." - }, - "supports_tool_choice": true - }, - "databricks/databricks-llama-4-maverick": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "input_cost_per_token": 5e-06, - "input_dbu_cost_per_token": 7.143e-05, - "output_cost_per_token": 1.5e-05, - "output_dbu_cost_per_token": 0.00021429, - "litellm_provider": "databricks", - "mode": "chat", - "source": "https://www.databricks.com/product/pricing/foundation-model-serving", - "metadata": { - "notes": "Databricks documentation now provides both DBU costs (_dbu_cost_per_token) and dollar costs(_cost_per_token)." - }, - "supports_tool_choice": true - }, - "databricks/databricks-meta-llama-3-70b-instruct": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "input_cost_per_token": 1.00002e-06, - "input_dbu_cost_per_token": 1.4286e-05, - "output_cost_per_token": 2.99999e-06, - "output_dbu_cost_per_token": 4.2857e-05, - "litellm_provider": "databricks", - "mode": "chat", - "source": "https://www.databricks.com/product/pricing/foundation-model-serving", - "metadata": { - "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." - }, - "supports_tool_choice": true - }, - "databricks/databricks-llama-2-70b-chat": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 5.0001e-07, - "input_dbu_cost_per_token": 7.143e-06, - "output_cost_per_token": 1.5e-06, - "output_dbu_cost_per_token": 2.1429e-05, - "litellm_provider": "databricks", - "mode": "chat", - "source": "https://www.databricks.com/product/pricing/foundation-model-serving", - "metadata": { - "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." - }, - "supports_tool_choice": true - }, - "databricks/databricks-mixtral-8x7b-instruct": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 5.0001e-07, - "input_dbu_cost_per_token": 7.143e-06, - "output_cost_per_token": 9.9902e-07, - "output_dbu_cost_per_token": 1.4286e-05, - "litellm_provider": "databricks", - "mode": "chat", - "source": "https://www.databricks.com/product/pricing/foundation-model-serving", - "metadata": { - "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." - }, - "supports_tool_choice": true - }, - "databricks/databricks-mpt-30b-instruct": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 9.9902e-07, - "input_dbu_cost_per_token": 1.4286e-05, - "output_cost_per_token": 9.9902e-07, - "output_dbu_cost_per_token": 1.4286e-05, - "litellm_provider": "databricks", - "mode": "chat", - "source": "https://www.databricks.com/product/pricing/foundation-model-serving", - "metadata": { - "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." - }, - "supports_tool_choice": true - }, - "databricks/databricks-mpt-7b-instruct": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 5.0001e-07, - "input_dbu_cost_per_token": 7.143e-06, - "output_cost_per_token": 0.0, - "output_dbu_cost_per_token": 0.0, - "litellm_provider": "databricks", - "mode": "chat", - "source": "https://www.databricks.com/product/pricing/foundation-model-serving", - "metadata": { - "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." - }, - "supports_tool_choice": true - }, - "databricks/databricks-bge-large-en": { - "max_tokens": 512, - "max_input_tokens": 512, - "output_vector_size": 1024, - "input_cost_per_token": 1.0003e-07, - "input_dbu_cost_per_token": 1.429e-06, - "output_cost_per_token": 0.0, - "output_dbu_cost_per_token": 0.0, - "litellm_provider": "databricks", - "mode": "embedding", - "source": "https://www.databricks.com/product/pricing/foundation-model-serving", - "metadata": { - "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." - } - }, - "databricks/databricks-gte-large-en": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "output_vector_size": 1024, - "input_cost_per_token": 1.2999e-07, - "input_dbu_cost_per_token": 1.857e-06, - "output_cost_per_token": 0.0, - "output_dbu_cost_per_token": 0.0, - "litellm_provider": "databricks", - "mode": "embedding", - "source": "https://www.databricks.com/product/pricing/foundation-model-serving", - "metadata": { - "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation." - } - }, - "sambanova/Meta-Llama-3.1-8B-Instruct": { - "max_tokens": 16384, - "max_input_tokens": 16384, - "max_output_tokens": 16384, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 2e-07, - "litellm_provider": "sambanova", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": true, - "source": "https://cloud.sambanova.ai/plans/pricing" - }, - "sambanova/Meta-Llama-3.1-405B-Instruct": { - "max_tokens": 16384, - "max_input_tokens": 16384, - "max_output_tokens": 16384, - "input_cost_per_token": 5e-06, - "output_cost_per_token": 1e-05, - "litellm_provider": "sambanova", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": true, - "source": "https://cloud.sambanova.ai/plans/pricing" - }, - "sambanova/Meta-Llama-3.2-1B-Instruct": { - "max_tokens": 16384, - "max_input_tokens": 16384, - "max_output_tokens": 16384, - "input_cost_per_token": 4e-08, - "output_cost_per_token": 8e-08, - "litellm_provider": "sambanova", - "mode": "chat", - "source": "https://cloud.sambanova.ai/plans/pricing" - }, - "sambanova/Meta-Llama-3.2-3B-Instruct": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 8e-08, - "output_cost_per_token": 1.6e-07, - "litellm_provider": "sambanova", - "mode": "chat", - "source": "https://cloud.sambanova.ai/plans/pricing" - }, - "sambanova/Llama-4-Maverick-17B-128E-Instruct": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 6.3e-07, - "output_cost_per_token": 1.8e-06, - "litellm_provider": "sambanova", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_vision": true, - "source": "https://cloud.sambanova.ai/plans/pricing", - "metadata": { - "notes": "For vision models, images are converted to 6432 input tokens and are billed at that amount" - } - }, - "sambanova/Llama-4-Scout-17B-16E-Instruct": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 4e-07, - "output_cost_per_token": 7e-07, - "litellm_provider": "sambanova", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": true, - "source": "https://cloud.sambanova.ai/plans/pricing", - "metadata": { - "notes": "For vision models, images are converted to 6432 input tokens and are billed at that amount" - } - }, - "sambanova/Meta-Llama-3.3-70B-Instruct": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 6e-07, - "output_cost_per_token": 1.2e-06, - "litellm_provider": "sambanova", - "mode": "chat", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "source": "https://cloud.sambanova.ai/plans/pricing" - }, - "sambanova/Meta-Llama-Guard-3-8B": { - "max_tokens": 16384, - "max_input_tokens": 16384, - "max_output_tokens": 16384, - "input_cost_per_token": 3e-07, - "output_cost_per_token": 3e-07, - "litellm_provider": "sambanova", - "mode": "chat", - "source": "https://cloud.sambanova.ai/plans/pricing" - }, - "sambanova/Qwen3-32B": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 4e-07, - "output_cost_per_token": 8e-07, - "litellm_provider": "sambanova", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "mode": "chat", - "source": "https://cloud.sambanova.ai/plans/pricing" - }, - "sambanova/QwQ-32B": { - "max_tokens": 16384, - "max_input_tokens": 16384, - "max_output_tokens": 16384, - "input_cost_per_token": 5e-07, - "output_cost_per_token": 1e-06, - "litellm_provider": "sambanova", - "mode": "chat", - "source": "https://cloud.sambanova.ai/plans/pricing" - }, - "sambanova/Qwen2-Audio-7B-Instruct": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 5e-07, - "output_cost_per_token": 0.0001, - "litellm_provider": "sambanova", - "mode": "chat", - "supports_audio_input": true, - "source": "https://cloud.sambanova.ai/plans/pricing" - }, - "sambanova/DeepSeek-R1-Distill-Llama-70B": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 7e-07, - "output_cost_per_token": 1.4e-06, - "litellm_provider": "sambanova", - "mode": "chat", - "source": "https://cloud.sambanova.ai/plans/pricing" - }, - "sambanova/DeepSeek-R1": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "input_cost_per_token": 5e-06, - "output_cost_per_token": 7e-06, - "litellm_provider": "sambanova", - "mode": "chat", - "source": "https://cloud.sambanova.ai/plans/pricing" - }, - "sambanova/DeepSeek-V3-0324": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 4.5e-06, - "litellm_provider": "sambanova", - "mode": "chat", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "source": "https://cloud.sambanova.ai/plans/pricing" - }, - "assemblyai/nano": { - "mode": "audio_transcription", - "input_cost_per_second": 0.00010278, - "output_cost_per_second": 0.0, - "litellm_provider": "assemblyai" - }, - "assemblyai/best": { - "mode": "audio_transcription", - "input_cost_per_second": 3.333e-05, - "output_cost_per_second": 0.0, - "litellm_provider": "assemblyai" - }, - "jina-reranker-v2-base-multilingual": { - "max_tokens": 1024, + "gemini/veo-2.0-generate-001": { + "litellm_provider": "gemini", "max_input_tokens": 1024, - "max_output_tokens": 1024, - "max_document_chunks_per_query": 2048, - "input_cost_per_token": 1.8e-08, - "output_cost_per_token": 1.8e-08, - "litellm_provider": "jina_ai", - "mode": "rerank" - }, - "snowflake/deepseek-r1": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 8192, - "litellm_provider": "snowflake", - "supports_reasoning": true, - "mode": "chat" - }, - "snowflake/snowflake-arctic": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 8192, - "litellm_provider": "snowflake", - "mode": "chat" - }, - "snowflake/claude-3-5-sonnet": { - "supports_computer_use": true, - "max_tokens": 18000, - "max_input_tokens": 18000, - "max_output_tokens": 8192, - "litellm_provider": "snowflake", - "mode": "chat" - }, - "snowflake/mistral-large": { - "max_tokens": 32000, - "max_input_tokens": 32000, - "max_output_tokens": 8192, - "litellm_provider": "snowflake", - "mode": "chat" - }, - "snowflake/mistral-large2": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 8192, - "litellm_provider": "snowflake", - "mode": "chat" - }, - "snowflake/reka-flash": { - "max_tokens": 100000, - "max_input_tokens": 100000, - "max_output_tokens": 8192, - "litellm_provider": "snowflake", - "mode": "chat" - }, - "snowflake/reka-core": { - "max_tokens": 32000, - "max_input_tokens": 32000, - "max_output_tokens": 8192, - "litellm_provider": "snowflake", - "mode": "chat" - }, - "snowflake/jamba-instruct": { - "max_tokens": 256000, - "max_input_tokens": 256000, - "max_output_tokens": 8192, - "litellm_provider": "snowflake", - "mode": "chat" - }, - "snowflake/jamba-1.5-mini": { - "max_tokens": 256000, - "max_input_tokens": 256000, - "max_output_tokens": 8192, - "litellm_provider": "snowflake", - "mode": "chat" - }, - "snowflake/jamba-1.5-large": { - "max_tokens": 256000, - "max_input_tokens": 256000, - "max_output_tokens": 8192, - "litellm_provider": "snowflake", - "mode": "chat" - }, - "snowflake/mixtral-8x7b": { - "max_tokens": 32000, - "max_input_tokens": 32000, - "max_output_tokens": 8192, - "litellm_provider": "snowflake", - "mode": "chat" - }, - "snowflake/llama2-70b-chat": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 8192, - "litellm_provider": "snowflake", - "mode": "chat" - }, - "snowflake/llama3-8b": { - "max_tokens": 8000, - "max_input_tokens": 8000, - "max_output_tokens": 8192, - "litellm_provider": "snowflake", - "mode": "chat" - }, - "snowflake/llama3-70b": { - "max_tokens": 8000, - "max_input_tokens": 8000, - "max_output_tokens": 8192, - "litellm_provider": "snowflake", - "mode": "chat" - }, - "snowflake/llama3.1-8b": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 8192, - "litellm_provider": "snowflake", - "mode": "chat" - }, - "snowflake/llama3.1-70b": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 8192, - "litellm_provider": "snowflake", - "mode": "chat" - }, - "snowflake/llama3.3-70b": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 8192, - "litellm_provider": "snowflake", - "mode": "chat" - }, - "snowflake/snowflake-llama-3.3-70b": { - "max_tokens": 8000, - "max_input_tokens": 8000, - "max_output_tokens": 8192, - "litellm_provider": "snowflake", - "mode": "chat" - }, - "snowflake/llama3.1-405b": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 8192, - "litellm_provider": "snowflake", - "mode": "chat" - }, - "snowflake/snowflake-llama-3.1-405b": { - "max_tokens": 8000, - "max_input_tokens": 8000, - "max_output_tokens": 8192, - "litellm_provider": "snowflake", - "mode": "chat" - }, - "snowflake/llama3.2-1b": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 8192, - "litellm_provider": "snowflake", - "mode": "chat" - }, - "snowflake/llama3.2-3b": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 8192, - "litellm_provider": "snowflake", - "mode": "chat" - }, - "snowflake/mistral-7b": { - "max_tokens": 32000, - "max_input_tokens": 32000, - "max_output_tokens": 8192, - "litellm_provider": "snowflake", - "mode": "chat" - }, - "snowflake/gemma-7b": { - "max_tokens": 8000, - "max_input_tokens": 8000, - "max_output_tokens": 8192, - "litellm_provider": "snowflake", - "mode": "chat" - }, - "gradient_ai/anthropic-claude-3.7-sonnet": { - "input_cost_per_token": 3e-06, - "output_cost_per_token": 15e-06, - "litellm_provider": "gradient_ai", - "mode": "chat", "max_tokens": 1024, - "supported_endpoints": ["/v1/chat/completions"], - "supported_modalities": ["text"], + "mode": "video_generation", + "output_cost_per_second": 0.35, + "source": "https://ai.google.dev/gemini-api/docs/video", + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "gemini/veo-3.0-fast-generate-preview": { + "litellm_provider": "gemini", + "max_input_tokens": 1024, + "max_tokens": 1024, + "mode": "video_generation", + "output_cost_per_second": 0.4, + "source": "https://ai.google.dev/gemini-api/docs/video", + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "gemini/veo-3.0-generate-preview": { + "litellm_provider": "gemini", + "max_input_tokens": 1024, + "max_tokens": 1024, + "mode": "video_generation", + "output_cost_per_second": 0.75, + "source": "https://ai.google.dev/gemini-api/docs/video", + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "gpt-3.5-turbo": { + "input_cost_per_token": 1.5e-06, + "litellm_provider": "openai", + "max_input_tokens": 16385, + "max_output_tokens": 4096, + "max_tokens": 4097, + "mode": "chat", + "output_cost_per_token": 2e-06, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "gpt-3.5-turbo-0125": { + "input_cost_per_token": 5e-07, + "litellm_provider": "openai", + "max_input_tokens": 16385, + "max_output_tokens": 4096, + "max_tokens": 16385, + "mode": "chat", + "output_cost_per_token": 1.5e-06, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "gpt-3.5-turbo-0301": { + "input_cost_per_token": 1.5e-06, + "litellm_provider": "openai", + "max_input_tokens": 4097, + "max_output_tokens": 4096, + "max_tokens": 4097, + "mode": "chat", + "output_cost_per_token": 2e-06, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "gpt-3.5-turbo-0613": { + "input_cost_per_token": 1.5e-06, + "litellm_provider": "openai", + "max_input_tokens": 4097, + "max_output_tokens": 4096, + "max_tokens": 4097, + "mode": "chat", + "output_cost_per_token": 2e-06, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "gpt-3.5-turbo-1106": { + "input_cost_per_token": 1e-06, + "litellm_provider": "openai", + "max_input_tokens": 16385, + "max_output_tokens": 4096, + "max_tokens": 16385, + "mode": "chat", + "output_cost_per_token": 2e-06, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "gpt-3.5-turbo-16k": { + "input_cost_per_token": 3e-06, + "litellm_provider": "openai", + "max_input_tokens": 16385, + "max_output_tokens": 4096, + "max_tokens": 16385, + "mode": "chat", + "output_cost_per_token": 4e-06, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "gpt-3.5-turbo-16k-0613": { + "input_cost_per_token": 3e-06, + "litellm_provider": "openai", + "max_input_tokens": 16385, + "max_output_tokens": 4096, + "max_tokens": 16385, + "mode": "chat", + "output_cost_per_token": 4e-06, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "gpt-3.5-turbo-instruct": { + "input_cost_per_token": 1.5e-06, + "litellm_provider": "text-completion-openai", + "max_input_tokens": 8192, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "completion", + "output_cost_per_token": 2e-06 + }, + "gpt-3.5-turbo-instruct-0914": { + "input_cost_per_token": 1.5e-06, + "litellm_provider": "text-completion-openai", + "max_input_tokens": 8192, + "max_output_tokens": 4097, + "max_tokens": 4097, + "mode": "completion", + "output_cost_per_token": 2e-06 + }, + "gpt-4": { + "input_cost_per_token": 3e-05, + "litellm_provider": "openai", + "max_input_tokens": 8192, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 6e-05, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "gpt-4-0125-preview": { + "input_cost_per_token": 1e-05, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 3e-05, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "gpt-4-0314": { + "input_cost_per_token": 3e-05, + "litellm_provider": "openai", + "max_input_tokens": 8192, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 6e-05, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "gpt-4-0613": { + "deprecation_date": "2025-06-06", + "input_cost_per_token": 3e-05, + "litellm_provider": "openai", + "max_input_tokens": 8192, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 6e-05, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "gpt-4-1106-preview": { + "input_cost_per_token": 1e-05, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 3e-05, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "gpt-4-1106-vision-preview": { + "deprecation_date": "2024-12-06", + "input_cost_per_token": 1e-05, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 3e-05, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "gpt-4-32k": { + "input_cost_per_token": 6e-05, + "litellm_provider": "openai", + "max_input_tokens": 32768, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.00012, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "gpt-4-32k-0314": { + "input_cost_per_token": 6e-05, + "litellm_provider": "openai", + "max_input_tokens": 32768, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.00012, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "gpt-4-32k-0613": { + "input_cost_per_token": 6e-05, + "litellm_provider": "openai", + "max_input_tokens": 32768, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.00012, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "gpt-4-turbo": { + "input_cost_per_token": 1e-05, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 3e-05, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "gpt-4-turbo-2024-04-09": { + "input_cost_per_token": 1e-05, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 3e-05, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "gpt-4-turbo-preview": { + "input_cost_per_token": 1e-05, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 3e-05, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "gpt-4-vision-preview": { + "deprecation_date": "2024-12-06", + "input_cost_per_token": 1e-05, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 3e-05, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "gpt-4.1": { + "cache_read_input_token_cost": 5e-07, + "input_cost_per_token": 2e-06, + "input_cost_per_token_batches": 1e-06, + "litellm_provider": "openai", + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 8e-06, + "output_cost_per_token_batches": 4e-06, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "gpt-4.1-2025-04-14": { + "cache_read_input_token_cost": 5e-07, + "input_cost_per_token": 2e-06, + "input_cost_per_token_batches": 1e-06, + "litellm_provider": "openai", + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 8e-06, + "output_cost_per_token_batches": 4e-06, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "gpt-4.1-mini": { + "cache_read_input_token_cost": 1e-07, + "input_cost_per_token": 4e-07, + "input_cost_per_token_batches": 2e-07, + "litellm_provider": "openai", + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 1.6e-06, + "output_cost_per_token_batches": 8e-07, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "gpt-4.1-mini-2025-04-14": { + "cache_read_input_token_cost": 1e-07, + "input_cost_per_token": 4e-07, + "input_cost_per_token_batches": 2e-07, + "litellm_provider": "openai", + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 1.6e-06, + "output_cost_per_token_batches": 8e-07, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "gpt-4.1-nano": { + "cache_read_input_token_cost": 2.5e-08, + "input_cost_per_token": 1e-07, + "input_cost_per_token_batches": 5e-08, + "litellm_provider": "openai", + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 4e-07, + "output_cost_per_token_batches": 2e-07, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "gpt-4.1-nano-2025-04-14": { + "cache_read_input_token_cost": 2.5e-08, + "input_cost_per_token": 1e-07, + "input_cost_per_token_batches": 5e-08, + "litellm_provider": "openai", + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 4e-07, + "output_cost_per_token_batches": 2e-07, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "gpt-4.5-preview": { + "cache_read_input_token_cost": 3.75e-05, + "input_cost_per_token": 7.5e-05, + "input_cost_per_token_batches": 3.75e-05, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 0.00015, + "output_cost_per_token_batches": 7.5e-05, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "gpt-4.5-preview-2025-02-27": { + "cache_read_input_token_cost": 3.75e-05, + "deprecation_date": "2025-07-14", + "input_cost_per_token": 7.5e-05, + "input_cost_per_token_batches": 3.75e-05, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 0.00015, + "output_cost_per_token_batches": 7.5e-05, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "gpt-4o": { + "cache_read_input_token_cost": 1.25e-06, + "input_cost_per_token": 2.5e-06, + "input_cost_per_token_batches": 1.25e-06, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1e-05, + "output_cost_per_token_batches": 5e-06, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "gpt-4o-2024-05-13": { + "input_cost_per_token": 5e-06, + "input_cost_per_token_batches": 2.5e-06, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "output_cost_per_token_batches": 7.5e-06, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "gpt-4o-2024-08-06": { + "cache_read_input_token_cost": 1.25e-06, + "input_cost_per_token": 2.5e-06, + "input_cost_per_token_batches": 1.25e-06, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1e-05, + "output_cost_per_token_batches": 5e-06, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "gpt-4o-2024-11-20": { + "cache_read_input_token_cost": 1.25e-06, + "input_cost_per_token": 2.5e-06, + "input_cost_per_token_batches": 1.25e-06, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1e-05, + "output_cost_per_token_batches": 5e-06, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "gpt-4o-audio-preview": { + "input_cost_per_audio_token": 0.0001, + "input_cost_per_token": 2.5e-06, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_audio_token": 0.0002, + "output_cost_per_token": 1e-05, + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "gpt-4o-audio-preview-2024-10-01": { + "input_cost_per_audio_token": 0.0001, + "input_cost_per_token": 2.5e-06, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_audio_token": 0.0002, + "output_cost_per_token": 1e-05, + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "gpt-4o-audio-preview-2024-12-17": { + "input_cost_per_audio_token": 4e-05, + "input_cost_per_token": 2.5e-06, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_audio_token": 8e-05, + "output_cost_per_token": 1e-05, + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "gpt-4o-audio-preview-2025-06-03": { + "input_cost_per_audio_token": 4e-05, + "input_cost_per_token": 2.5e-06, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_audio_token": 8e-05, + "output_cost_per_token": 1e-05, + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "gpt-4o-mini": { + "cache_read_input_token_cost": 7.5e-08, + "input_cost_per_token": 1.5e-07, + "input_cost_per_token_batches": 7.5e-08, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 6e-07, + "output_cost_per_token_batches": 3e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "gpt-4o-mini-2024-07-18": { + "cache_read_input_token_cost": 7.5e-08, + "input_cost_per_token": 1.5e-07, + "input_cost_per_token_batches": 7.5e-08, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 6e-07, + "output_cost_per_token_batches": 3e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.03, + "search_context_size_low": 0.025, + "search_context_size_medium": 0.0275 + }, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "gpt-4o-mini-audio-preview": { + "input_cost_per_audio_token": 1e-05, + "input_cost_per_token": 1.5e-07, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_audio_token": 2e-05, + "output_cost_per_token": 6e-07, + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "gpt-4o-mini-audio-preview-2024-12-17": { + "input_cost_per_audio_token": 1e-05, + "input_cost_per_token": 1.5e-07, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_audio_token": 2e-05, + "output_cost_per_token": 6e-07, + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "gpt-4o-mini-realtime-preview": { + "cache_creation_input_audio_token_cost": 3e-07, + "cache_read_input_token_cost": 3e-07, + "input_cost_per_audio_token": 1e-05, + "input_cost_per_token": 6e-07, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_audio_token": 2e-05, + "output_cost_per_token": 2.4e-06, + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "gpt-4o-mini-realtime-preview-2024-12-17": { + "cache_creation_input_audio_token_cost": 3e-07, + "cache_read_input_token_cost": 3e-07, + "input_cost_per_audio_token": 1e-05, + "input_cost_per_token": 6e-07, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_audio_token": 2e-05, + "output_cost_per_token": 2.4e-06, + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "gpt-4o-mini-search-preview": { + "cache_read_input_token_cost": 7.5e-08, + "input_cost_per_token": 1.5e-07, + "input_cost_per_token_batches": 7.5e-08, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 6e-07, + "output_cost_per_token_batches": 3e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.03, + "search_context_size_low": 0.025, + "search_context_size_medium": 0.0275 + }, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "gpt-4o-mini-search-preview-2025-03-11": { + "cache_read_input_token_cost": 7.5e-08, + "input_cost_per_token": 1.5e-07, + "input_cost_per_token_batches": 7.5e-08, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 6e-07, + "output_cost_per_token_batches": 3e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "gpt-4o-mini-transcribe": { + "input_cost_per_audio_token": 3e-06, + "input_cost_per_token": 1.25e-06, + "litellm_provider": "openai", + "max_input_tokens": 16000, + "max_output_tokens": 2000, + "mode": "audio_transcription", + "output_cost_per_token": 5e-06, + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "gpt-4o-mini-tts": { + "input_cost_per_token": 2.5e-06, + "litellm_provider": "openai", + "mode": "audio_speech", + "output_cost_per_audio_token": 1.2e-05, + "output_cost_per_second": 0.00025, + "output_cost_per_token": 1e-05, + "supported_endpoints": [ + "/v1/audio/speech" + ], + "supported_modalities": [ + "text", + "audio" + ], + "supported_output_modalities": [ + "audio" + ] + }, + "gpt-4o-realtime-preview": { + "cache_read_input_token_cost": 2.5e-06, + "input_cost_per_audio_token": 4e-05, + "input_cost_per_token": 5e-06, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_audio_token": 8e-05, + "output_cost_per_token": 2e-05, + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "gpt-4o-realtime-preview-2024-10-01": { + "cache_creation_input_audio_token_cost": 2e-05, + "cache_read_input_token_cost": 2.5e-06, + "input_cost_per_audio_token": 0.0001, + "input_cost_per_token": 5e-06, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_audio_token": 0.0002, + "output_cost_per_token": 2e-05, + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "gpt-4o-realtime-preview-2024-12-17": { + "cache_read_input_token_cost": 2.5e-06, + "input_cost_per_audio_token": 4e-05, + "input_cost_per_token": 5e-06, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_audio_token": 8e-05, + "output_cost_per_token": 2e-05, + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "gpt-4o-realtime-preview-2025-06-03": { + "cache_read_input_token_cost": 2.5e-06, + "input_cost_per_audio_token": 4e-05, + "input_cost_per_token": 5e-06, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_audio_token": 8e-05, + "output_cost_per_token": 2e-05, + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "gpt-4o-search-preview": { + "cache_read_input_token_cost": 1.25e-06, + "input_cost_per_token": 2.5e-06, + "input_cost_per_token_batches": 1.25e-06, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1e-05, + "output_cost_per_token_batches": 5e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.05, + "search_context_size_low": 0.03, + "search_context_size_medium": 0.035 + }, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "gpt-4o-search-preview-2025-03-11": { + "cache_read_input_token_cost": 1.25e-06, + "input_cost_per_token": 2.5e-06, + "input_cost_per_token_batches": 1.25e-06, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1e-05, + "output_cost_per_token_batches": 5e-06, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "gpt-4o-transcribe": { + "input_cost_per_audio_token": 6e-06, + "input_cost_per_token": 2.5e-06, + "litellm_provider": "openai", + "max_input_tokens": 16000, + "max_output_tokens": 2000, + "mode": "audio_transcription", + "output_cost_per_token": 1e-05, + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "gpt-5": { + "cache_read_input_token_cost": 1.25e-07, + "input_cost_per_token": 1.25e-06, + "litellm_provider": "openai", + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "gpt-5-2025-08-07": { + "cache_read_input_token_cost": 1.25e-07, + "input_cost_per_token": 1.25e-06, + "litellm_provider": "openai", + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "gpt-5-chat": { + "cache_read_input_token_cost": 1.25e-07, + "input_cost_per_token": 1.25e-06, + "litellm_provider": "openai", + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": false, + "supports_native_streaming": true, + "supports_parallel_function_calling": false, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": false, + "supports_vision": true + }, + "gpt-5-chat-latest": { + "cache_read_input_token_cost": 1.25e-07, + "input_cost_per_token": 1.25e-06, + "litellm_provider": "openai", + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": false, + "supports_native_streaming": true, + "supports_parallel_function_calling": false, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": false, + "supports_vision": true + }, + "gpt-5-mini": { + "cache_read_input_token_cost": 2.5e-08, + "input_cost_per_token": 2.5e-07, + "litellm_provider": "openai", + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2e-06, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "gpt-5-mini-2025-08-07": { + "cache_read_input_token_cost": 2.5e-08, + "input_cost_per_token": 2.5e-07, + "litellm_provider": "openai", + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2e-06, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "gpt-5-nano": { + "cache_read_input_token_cost": 5e-09, + "input_cost_per_token": 5e-08, + "litellm_provider": "openai", + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4e-07, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "gpt-5-nano-2025-08-07": { + "cache_read_input_token_cost": 5e-09, + "input_cost_per_token": 5e-08, + "litellm_provider": "openai", + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4e-07, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "gpt-image-1": { + "input_cost_per_pixel": 4.0054321e-08, + "litellm_provider": "openai", + "mode": "image_generation", + "output_cost_per_pixel": 0.0, + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "gpt-realtime": { + "cache_creation_input_audio_token_cost": 4e-07, + "cache_read_input_token_cost": 4e-07, + "input_cost_per_audio_token": 3.2e-05, + "input_cost_per_image": 5e-06, + "input_cost_per_token": 4e-06, + "litellm_provider": "openai", + "max_input_tokens": 32000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_audio_token": 6.4e-05, + "output_cost_per_token": 1.6e-05, + "supported_endpoints": [ + "/v1/realtime" + ], + "supported_modalities": [ + "text", + "image", + "audio" + ], + "supported_output_modalities": [ + "text", + "audio" + ], + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "gpt-realtime-2025-08-28": { + "cache_creation_input_audio_token_cost": 4e-07, + "cache_read_input_token_cost": 4e-07, + "input_cost_per_audio_token": 3.2e-05, + "input_cost_per_image": 5e-06, + "input_cost_per_token": 4e-06, + "litellm_provider": "openai", + "max_input_tokens": 32000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_audio_token": 6.4e-05, + "output_cost_per_token": 1.6e-05, + "supported_endpoints": [ + "/v1/realtime" + ], + "supported_modalities": [ + "text", + "image", + "audio" + ], + "supported_output_modalities": [ + "text", + "audio" + ], + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "gradient_ai/alibaba-qwen3-32b": { + "litellm_provider": "gradient_ai", + "max_tokens": 2048, + "mode": "chat", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supported_modalities": [ + "text" + ], "supports_tool_choice": false }, - "gradient_ai/anthropic-claude-3.5-sonnet": { - "input_cost_per_token": 3e-06, - "output_cost_per_token": 15e-06, + "gradient_ai/anthropic-claude-3-opus": { + "input_cost_per_token": 1.5e-05, "litellm_provider": "gradient_ai", - "mode": "chat", "max_tokens": 1024, - "supported_endpoints": ["/v1/chat/completions"], - "supported_modalities": ["text"], + "mode": "chat", + "output_cost_per_token": 7.5e-05, + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supported_modalities": [ + "text" + ], "supports_tool_choice": false }, "gradient_ai/anthropic-claude-3.5-haiku": { "input_cost_per_token": 8e-07, - "output_cost_per_token": 4e-06, "litellm_provider": "gradient_ai", - "mode": "chat", "max_tokens": 1024, - "supported_endpoints": ["/v1/chat/completions"], - "supported_modalities": ["text"], + "mode": "chat", + "output_cost_per_token": 4e-06, + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supported_modalities": [ + "text" + ], "supports_tool_choice": false }, - "gradient_ai/anthropic-claude-3-opus": { - "input_cost_per_token": 15e-06, - "output_cost_per_token": 75e-06, + "gradient_ai/anthropic-claude-3.5-sonnet": { + "input_cost_per_token": 3e-06, "litellm_provider": "gradient_ai", - "mode": "chat", "max_tokens": 1024, - "supported_endpoints": ["/v1/chat/completions"], - "supported_modalities": ["text"], + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supported_modalities": [ + "text" + ], + "supports_tool_choice": false + }, + "gradient_ai/anthropic-claude-3.7-sonnet": { + "input_cost_per_token": 3e-06, + "litellm_provider": "gradient_ai", + "max_tokens": 1024, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supported_modalities": [ + "text" + ], "supports_tool_choice": false }, "gradient_ai/deepseek-r1-distill-llama-70b": { - "input_cost_per_token": 99e-08, - "output_cost_per_token": 99e-08, + "input_cost_per_token": 9.9e-07, "litellm_provider": "gradient_ai", - "mode": "chat", "max_tokens": 8000, - "supported_endpoints": ["/v1/chat/completions"], - "supported_modalities": ["text"], - "supports_tool_choice": false - }, - "gradient_ai/llama3.3-70b-instruct": { - "input_cost_per_token": 65e-08, - "output_cost_per_token": 65e-08, - "litellm_provider": "gradient_ai", "mode": "chat", - "max_tokens": 2048, - "supported_endpoints": ["/v1/chat/completions"], - "supported_modalities": ["text"], + "output_cost_per_token": 9.9e-07, + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supported_modalities": [ + "text" + ], "supports_tool_choice": false }, "gradient_ai/llama3-8b-instruct": { "input_cost_per_token": 2e-07, - "output_cost_per_token": 2e-07, "litellm_provider": "gradient_ai", - "mode": "chat", "max_tokens": 512, - "supported_endpoints": ["/v1/chat/completions"], - "supported_modalities": ["text"], + "mode": "chat", + "output_cost_per_token": 2e-07, + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supported_modalities": [ + "text" + ], + "supports_tool_choice": false + }, + "gradient_ai/llama3.3-70b-instruct": { + "input_cost_per_token": 6.5e-07, + "litellm_provider": "gradient_ai", + "max_tokens": 2048, + "mode": "chat", + "output_cost_per_token": 6.5e-07, + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supported_modalities": [ + "text" + ], "supports_tool_choice": false }, "gradient_ai/mistral-nemo-instruct-2407": { "input_cost_per_token": 3e-07, - "output_cost_per_token": 3e-07, "litellm_provider": "gradient_ai", - "mode": "chat", "max_tokens": 512, - "supported_endpoints": ["/v1/chat/completions"], - "supported_modalities": ["text"], - "supports_tool_choice": false - }, - "gradient_ai/openai-o3": { - "input_cost_per_token": 2e-06, - "output_cost_per_token": 8e-06, - "litellm_provider": "gradient_ai", "mode": "chat", - "max_tokens": 100000, - "supported_endpoints": ["/v1/chat/completions"], - "supported_modalities": ["text"], - "supports_tool_choice": false - }, - "gradient_ai/openai-o3-mini": { - "input_cost_per_token": 11e-07, - "output_cost_per_token": 44e-07, - "litellm_provider": "gradient_ai", - "mode": "chat", - "max_tokens": 100000, - "supported_endpoints": ["/v1/chat/completions"], - "supported_modalities": ["text"], + "output_cost_per_token": 3e-07, + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supported_modalities": [ + "text" + ], "supports_tool_choice": false }, "gradient_ai/openai-gpt-4o": { "litellm_provider": "gradient_ai", - "mode": "chat", "max_tokens": 16384, - "supported_endpoints": ["/v1/chat/completions"], - "supported_modalities": ["text"], + "mode": "chat", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supported_modalities": [ + "text" + ], "supports_tool_choice": false }, "gradient_ai/openai-gpt-4o-mini": { "litellm_provider": "gradient_ai", - "mode": "chat", "max_tokens": 16384, - "supported_endpoints": ["/v1/chat/completions"], - "supported_modalities": ["text"], + "mode": "chat", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supported_modalities": [ + "text" + ], "supports_tool_choice": false }, - "gradient_ai/alibaba-qwen3-32b": { + "gradient_ai/openai-o3": { + "input_cost_per_token": 2e-06, "litellm_provider": "gradient_ai", + "max_tokens": 100000, "mode": "chat", - "max_tokens": 2048, - "supported_endpoints": ["/v1/chat/completions"], - "supported_modalities": ["text"], + "output_cost_per_token": 8e-06, + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supported_modalities": [ + "text" + ], "supports_tool_choice": false }, - "nscale/meta-llama/Llama-4-Scout-17B-16E-Instruct": { - "input_cost_per_token": 9e-08, - "output_cost_per_token": 2.9e-07, - "litellm_provider": "nscale", + "gradient_ai/openai-o3-mini": { + "input_cost_per_token": 1.1e-06, + "litellm_provider": "gradient_ai", + "max_tokens": 100000, "mode": "chat", - "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" + "output_cost_per_token": 4.4e-06, + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supported_modalities": [ + "text" + ], + "supports_tool_choice": false }, - "nscale/Qwen/Qwen2.5-Coder-3B-Instruct": { - "input_cost_per_token": 1e-08, - "output_cost_per_token": 3e-08, - "litellm_provider": "nscale", + "groq/deepseek-r1-distill-llama-70b": { + "input_cost_per_token": 7.5e-07, + "litellm_provider": "groq", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, "mode": "chat", - "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" + "output_cost_per_token": 9.9e-07, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true }, - "nscale/Qwen/Qwen2.5-Coder-7B-Instruct": { - "input_cost_per_token": 1e-08, - "output_cost_per_token": 3e-08, - "litellm_provider": "nscale", - "mode": "chat", - "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" + "groq/distil-whisper-large-v3-en": { + "input_cost_per_second": 5.56e-06, + "litellm_provider": "groq", + "mode": "audio_transcription", + "output_cost_per_second": 0.0 }, - "nscale/Qwen/Qwen2.5-Coder-32B-Instruct": { - "input_cost_per_token": 6e-08, - "output_cost_per_token": 2e-07, - "litellm_provider": "nscale", - "mode": "chat", - "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" - }, - "nscale/Qwen/QwQ-32B": { - "input_cost_per_token": 1.8e-07, - "output_cost_per_token": 2e-07, - "litellm_provider": "nscale", - "mode": "chat", - "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" - }, - "nscale/deepseek-ai/DeepSeek-R1-Distill-Llama-70B": { - "input_cost_per_token": 3.75e-07, - "output_cost_per_token": 3.75e-07, - "litellm_provider": "nscale", - "mode": "chat", - "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models", - "metadata": { - "notes": "Pricing listed as $0.75/1M tokens total. Assumed 50/50 split for input/output." - } - }, - "nscale/deepseek-ai/DeepSeek-R1-Distill-Llama-8B": { - "input_cost_per_token": 2.5e-08, - "output_cost_per_token": 2.5e-08, - "litellm_provider": "nscale", - "mode": "chat", - "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models", - "metadata": { - "notes": "Pricing listed as $0.05/1M tokens total. Assumed 50/50 split for input/output." - } - }, - "nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B": { - "input_cost_per_token": 9e-08, - "output_cost_per_token": 9e-08, - "litellm_provider": "nscale", - "mode": "chat", - "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models", - "metadata": { - "notes": "Pricing listed as $0.18/1M tokens total. Assumed 50/50 split for input/output." - } - }, - "nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B": { - "input_cost_per_token": 2e-07, - "output_cost_per_token": 2e-07, - "litellm_provider": "nscale", - "mode": "chat", - "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models", - "metadata": { - "notes": "Pricing listed as $0.40/1M tokens total. Assumed 50/50 split for input/output." - } - }, - "nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B": { + "groq/gemma-7b-it": { + "deprecation_date": "2024-12-18", "input_cost_per_token": 7e-08, + "litellm_provider": "groq", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", "output_cost_per_token": 7e-08, - "litellm_provider": "nscale", - "mode": "chat", - "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models", - "metadata": { - "notes": "Pricing listed as $0.14/1M tokens total. Assumed 50/50 split for input/output." - } - }, - "nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B": { - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 1.5e-07, - "litellm_provider": "nscale", - "mode": "chat", - "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models", - "metadata": { - "notes": "Pricing listed as $0.30/1M tokens total. Assumed 50/50 split for input/output." - } - }, - "nscale/mistralai/mixtral-8x22b-instruct-v0.1": { - "input_cost_per_token": 6e-07, - "output_cost_per_token": 6e-07, - "litellm_provider": "nscale", - "mode": "chat", - "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models", - "metadata": { - "notes": "Pricing listed as $1.20/1M tokens total. Assumed 50/50 split for input/output." - } - }, - "nscale/meta-llama/Llama-3.1-8B-Instruct": { - "input_cost_per_token": 3e-08, - "output_cost_per_token": 3e-08, - "litellm_provider": "nscale", - "mode": "chat", - "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models", - "metadata": { - "notes": "Pricing listed as $0.06/1M tokens total. Assumed 50/50 split for input/output." - } - }, - "nscale/meta-llama/Llama-3.3-70B-Instruct": { - "input_cost_per_token": 2e-07, - "output_cost_per_token": 2e-07, - "litellm_provider": "nscale", - "mode": "chat", - "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models", - "metadata": { - "notes": "Pricing listed as $0.40/1M tokens total. Assumed 50/50 split for input/output." - } - }, - "nscale/black-forest-labs/FLUX.1-schnell": { - "mode": "image_generation", - "input_cost_per_pixel": 1.3e-09, - "output_cost_per_pixel": 0.0, - "litellm_provider": "nscale", - "supported_endpoints": [ - "/v1/images/generations" - ], - "source": "https://docs.nscale.com/docs/inference/serverless-models/current#image-models" - }, - "nscale/stabilityai/stable-diffusion-xl-base-1.0": { - "mode": "image_generation", - "input_cost_per_pixel": 3e-09, - "output_cost_per_pixel": 0.0, - "litellm_provider": "nscale", - "supported_endpoints": [ - "/v1/images/generations" - ], - "source": "https://docs.nscale.com/docs/inference/serverless-models/current#image-models" - }, - "featherless_ai/featherless-ai/Qwerky-72B": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 4096, - "litellm_provider": "featherless_ai", - "mode": "chat" - }, - "featherless_ai/featherless-ai/Qwerky-QwQ-32B": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 4096, - "litellm_provider": "featherless_ai", - "mode": "chat" - }, - "deepgram/nova-3": { - "mode": "audio_transcription", - "input_cost_per_second": 7.167e-05, - "output_cost_per_second": 0.0, - "litellm_provider": "deepgram", - "supported_endpoints": [ - "/v1/audio/transcriptions" - ], - "source": "https://deepgram.com/pricing", - "metadata": { - "original_pricing_per_minute": 0.0043, - "calculation": "$0.0043/60 seconds = $0.00007167 per second" - } - }, - "deepgram/nova-3-general": { - "mode": "audio_transcription", - "input_cost_per_second": 7.167e-05, - "output_cost_per_second": 0.0, - "litellm_provider": "deepgram", - "supported_endpoints": [ - "/v1/audio/transcriptions" - ], - "source": "https://deepgram.com/pricing", - "metadata": { - "original_pricing_per_minute": 0.0043, - "calculation": "$0.0043/60 seconds = $0.00007167 per second" - } - }, - "deepgram/nova-3-medical": { - "mode": "audio_transcription", - "input_cost_per_second": 8.667e-05, - "output_cost_per_second": 0.0, - "litellm_provider": "deepgram", - "supported_endpoints": [ - "/v1/audio/transcriptions" - ], - "source": "https://deepgram.com/pricing", - "metadata": { - "original_pricing_per_minute": 0.0052, - "calculation": "$0.0052/60 seconds = $0.00008667 per second (multilingual)" - } - }, - "deepgram/nova-2": { - "mode": "audio_transcription", - "input_cost_per_second": 7.167e-05, - "output_cost_per_second": 0.0, - "litellm_provider": "deepgram", - "supported_endpoints": [ - "/v1/audio/transcriptions" - ], - "source": "https://deepgram.com/pricing", - "metadata": { - "original_pricing_per_minute": 0.0043, - "calculation": "$0.0043/60 seconds = $0.00007167 per second" - } - }, - "deepgram/nova-2-general": { - "mode": "audio_transcription", - "input_cost_per_second": 7.167e-05, - "output_cost_per_second": 0.0, - "litellm_provider": "deepgram", - "supported_endpoints": [ - "/v1/audio/transcriptions" - ], - "source": "https://deepgram.com/pricing", - "metadata": { - "original_pricing_per_minute": 0.0043, - "calculation": "$0.0043/60 seconds = $0.00007167 per second" - } - }, - "deepgram/nova-2-meeting": { - "mode": "audio_transcription", - "input_cost_per_second": 7.167e-05, - "output_cost_per_second": 0.0, - "litellm_provider": "deepgram", - "supported_endpoints": [ - "/v1/audio/transcriptions" - ], - "source": "https://deepgram.com/pricing", - "metadata": { - "original_pricing_per_minute": 0.0043, - "calculation": "$0.0043/60 seconds = $0.00007167 per second" - } - }, - "deepgram/nova-2-phonecall": { - "mode": "audio_transcription", - "input_cost_per_second": 7.167e-05, - "output_cost_per_second": 0.0, - "litellm_provider": "deepgram", - "supported_endpoints": [ - "/v1/audio/transcriptions" - ], - "source": "https://deepgram.com/pricing", - "metadata": { - "original_pricing_per_minute": 0.0043, - "calculation": "$0.0043/60 seconds = $0.00007167 per second" - } - }, - "deepgram/nova-2-voicemail": { - "mode": "audio_transcription", - "input_cost_per_second": 7.167e-05, - "output_cost_per_second": 0.0, - "litellm_provider": "deepgram", - "supported_endpoints": [ - "/v1/audio/transcriptions" - ], - "source": "https://deepgram.com/pricing", - "metadata": { - "original_pricing_per_minute": 0.0043, - "calculation": "$0.0043/60 seconds = $0.00007167 per second" - } - }, - "deepgram/nova-2-finance": { - "mode": "audio_transcription", - "input_cost_per_second": 7.167e-05, - "output_cost_per_second": 0.0, - "litellm_provider": "deepgram", - "supported_endpoints": [ - "/v1/audio/transcriptions" - ], - "source": "https://deepgram.com/pricing", - "metadata": { - "original_pricing_per_minute": 0.0043, - "calculation": "$0.0043/60 seconds = $0.00007167 per second" - } - }, - "deepgram/nova-2-conversationalai": { - "mode": "audio_transcription", - "input_cost_per_second": 7.167e-05, - "output_cost_per_second": 0.0, - "litellm_provider": "deepgram", - "supported_endpoints": [ - "/v1/audio/transcriptions" - ], - "source": "https://deepgram.com/pricing", - "metadata": { - "original_pricing_per_minute": 0.0043, - "calculation": "$0.0043/60 seconds = $0.00007167 per second" - } - }, - "deepgram/nova-2-video": { - "mode": "audio_transcription", - "input_cost_per_second": 7.167e-05, - "output_cost_per_second": 0.0, - "litellm_provider": "deepgram", - "supported_endpoints": [ - "/v1/audio/transcriptions" - ], - "source": "https://deepgram.com/pricing", - "metadata": { - "original_pricing_per_minute": 0.0043, - "calculation": "$0.0043/60 seconds = $0.00007167 per second" - } - }, - "deepgram/nova-2-drivethru": { - "mode": "audio_transcription", - "input_cost_per_second": 7.167e-05, - "output_cost_per_second": 0.0, - "litellm_provider": "deepgram", - "supported_endpoints": [ - "/v1/audio/transcriptions" - ], - "source": "https://deepgram.com/pricing", - "metadata": { - "original_pricing_per_minute": 0.0043, - "calculation": "$0.0043/60 seconds = $0.00007167 per second" - } - }, - "deepgram/nova-2-automotive": { - "mode": "audio_transcription", - "input_cost_per_second": 7.167e-05, - "output_cost_per_second": 0.0, - "litellm_provider": "deepgram", - "supported_endpoints": [ - "/v1/audio/transcriptions" - ], - "source": "https://deepgram.com/pricing", - "metadata": { - "original_pricing_per_minute": 0.0043, - "calculation": "$0.0043/60 seconds = $0.00007167 per second" - } - }, - "deepgram/nova-2-atc": { - "mode": "audio_transcription", - "input_cost_per_second": 7.167e-05, - "output_cost_per_second": 0.0, - "litellm_provider": "deepgram", - "supported_endpoints": [ - "/v1/audio/transcriptions" - ], - "source": "https://deepgram.com/pricing", - "metadata": { - "original_pricing_per_minute": 0.0043, - "calculation": "$0.0043/60 seconds = $0.00007167 per second" - } - }, - "deepgram/nova": { - "mode": "audio_transcription", - "input_cost_per_second": 7.167e-05, - "output_cost_per_second": 0.0, - "litellm_provider": "deepgram", - "supported_endpoints": [ - "/v1/audio/transcriptions" - ], - "source": "https://deepgram.com/pricing", - "metadata": { - "original_pricing_per_minute": 0.0043, - "calculation": "$0.0043/60 seconds = $0.00007167 per second" - } - }, - "deepgram/nova-general": { - "mode": "audio_transcription", - "input_cost_per_second": 7.167e-05, - "output_cost_per_second": 0.0, - "litellm_provider": "deepgram", - "supported_endpoints": [ - "/v1/audio/transcriptions" - ], - "source": "https://deepgram.com/pricing", - "metadata": { - "original_pricing_per_minute": 0.0043, - "calculation": "$0.0043/60 seconds = $0.00007167 per second" - } - }, - "deepgram/nova-phonecall": { - "mode": "audio_transcription", - "input_cost_per_second": 7.167e-05, - "output_cost_per_second": 0.0, - "litellm_provider": "deepgram", - "supported_endpoints": [ - "/v1/audio/transcriptions" - ], - "source": "https://deepgram.com/pricing", - "metadata": { - "original_pricing_per_minute": 0.0043, - "calculation": "$0.0043/60 seconds = $0.00007167 per second" - } - }, - "deepgram/enhanced": { - "mode": "audio_transcription", - "input_cost_per_second": 0.00024167, - "output_cost_per_second": 0.0, - "litellm_provider": "deepgram", - "supported_endpoints": [ - "/v1/audio/transcriptions" - ], - "source": "https://deepgram.com/pricing", - "metadata": { - "original_pricing_per_minute": 0.0145, - "calculation": "$0.0145/60 seconds = $0.00024167 per second" - } - }, - "deepgram/enhanced-general": { - "mode": "audio_transcription", - "input_cost_per_second": 0.00024167, - "output_cost_per_second": 0.0, - "litellm_provider": "deepgram", - "supported_endpoints": [ - "/v1/audio/transcriptions" - ], - "source": "https://deepgram.com/pricing", - "metadata": { - "original_pricing_per_minute": 0.0145, - "calculation": "$0.0145/60 seconds = $0.00024167 per second" - } - }, - "deepgram/enhanced-meeting": { - "mode": "audio_transcription", - "input_cost_per_second": 0.00024167, - "output_cost_per_second": 0.0, - "litellm_provider": "deepgram", - "supported_endpoints": [ - "/v1/audio/transcriptions" - ], - "source": "https://deepgram.com/pricing", - "metadata": { - "original_pricing_per_minute": 0.0145, - "calculation": "$0.0145/60 seconds = $0.00024167 per second" - } - }, - "deepgram/enhanced-phonecall": { - "mode": "audio_transcription", - "input_cost_per_second": 0.00024167, - "output_cost_per_second": 0.0, - "litellm_provider": "deepgram", - "supported_endpoints": [ - "/v1/audio/transcriptions" - ], - "source": "https://deepgram.com/pricing", - "metadata": { - "original_pricing_per_minute": 0.0145, - "calculation": "$0.0145/60 seconds = $0.00024167 per second" - } - }, - "deepgram/enhanced-finance": { - "mode": "audio_transcription", - "input_cost_per_second": 0.00024167, - "output_cost_per_second": 0.0, - "litellm_provider": "deepgram", - "supported_endpoints": [ - "/v1/audio/transcriptions" - ], - "source": "https://deepgram.com/pricing", - "metadata": { - "original_pricing_per_minute": 0.0145, - "calculation": "$0.0145/60 seconds = $0.00024167 per second" - } - }, - "deepgram/base": { - "mode": "audio_transcription", - "input_cost_per_second": 0.00020833, - "output_cost_per_second": 0.0, - "litellm_provider": "deepgram", - "supported_endpoints": [ - "/v1/audio/transcriptions" - ], - "source": "https://deepgram.com/pricing", - "metadata": { - "original_pricing_per_minute": 0.0125, - "calculation": "$0.0125/60 seconds = $0.00020833 per second" - } - }, - "deepgram/base-general": { - "mode": "audio_transcription", - "input_cost_per_second": 0.00020833, - "output_cost_per_second": 0.0, - "litellm_provider": "deepgram", - "supported_endpoints": [ - "/v1/audio/transcriptions" - ], - "source": "https://deepgram.com/pricing", - "metadata": { - "original_pricing_per_minute": 0.0125, - "calculation": "$0.0125/60 seconds = $0.00020833 per second" - } - }, - "deepgram/base-meeting": { - "mode": "audio_transcription", - "input_cost_per_second": 0.00020833, - "output_cost_per_second": 0.0, - "litellm_provider": "deepgram", - "supported_endpoints": [ - "/v1/audio/transcriptions" - ], - "source": "https://deepgram.com/pricing", - "metadata": { - "original_pricing_per_minute": 0.0125, - "calculation": "$0.0125/60 seconds = $0.00020833 per second" - } - }, - "deepgram/base-phonecall": { - "mode": "audio_transcription", - "input_cost_per_second": 0.00020833, - "output_cost_per_second": 0.0, - "litellm_provider": "deepgram", - "supported_endpoints": [ - "/v1/audio/transcriptions" - ], - "source": "https://deepgram.com/pricing", - "metadata": { - "original_pricing_per_minute": 0.0125, - "calculation": "$0.0125/60 seconds = $0.00020833 per second" - } - }, - "deepgram/base-voicemail": { - "mode": "audio_transcription", - "input_cost_per_second": 0.00020833, - "output_cost_per_second": 0.0, - "litellm_provider": "deepgram", - "supported_endpoints": [ - "/v1/audio/transcriptions" - ], - "source": "https://deepgram.com/pricing", - "metadata": { - "original_pricing_per_minute": 0.0125, - "calculation": "$0.0125/60 seconds = $0.00020833 per second" - } - }, - "deepgram/base-finance": { - "mode": "audio_transcription", - "input_cost_per_second": 0.00020833, - "output_cost_per_second": 0.0, - "litellm_provider": "deepgram", - "supported_endpoints": [ - "/v1/audio/transcriptions" - ], - "source": "https://deepgram.com/pricing", - "metadata": { - "original_pricing_per_minute": 0.0125, - "calculation": "$0.0125/60 seconds = $0.00020833 per second" - } - }, - "deepgram/base-conversationalai": { - "mode": "audio_transcription", - "input_cost_per_second": 0.00020833, - "output_cost_per_second": 0.0, - "litellm_provider": "deepgram", - "supported_endpoints": [ - "/v1/audio/transcriptions" - ], - "source": "https://deepgram.com/pricing", - "metadata": { - "original_pricing_per_minute": 0.0125, - "calculation": "$0.0125/60 seconds = $0.00020833 per second" - } - }, - "deepgram/base-video": { - "mode": "audio_transcription", - "input_cost_per_second": 0.00020833, - "output_cost_per_second": 0.0, - "litellm_provider": "deepgram", - "supported_endpoints": [ - "/v1/audio/transcriptions" - ], - "source": "https://deepgram.com/pricing", - "metadata": { - "original_pricing_per_minute": 0.0125, - "calculation": "$0.0125/60 seconds = $0.00020833 per second" - } - }, - "deepgram/whisper": { - "mode": "audio_transcription", - "input_cost_per_second": 0.0001, - "output_cost_per_second": 0.0, - "litellm_provider": "deepgram", - "supported_endpoints": [ - "/v1/audio/transcriptions" - ], - "source": "https://deepgram.com/pricing", - "metadata": { - "notes": "Deepgram's hosted OpenAI Whisper models - pricing may differ from native Deepgram models" - } - }, - "deepgram/whisper-tiny": { - "mode": "audio_transcription", - "input_cost_per_second": 0.0001, - "output_cost_per_second": 0.0, - "litellm_provider": "deepgram", - "supported_endpoints": [ - "/v1/audio/transcriptions" - ], - "source": "https://deepgram.com/pricing", - "metadata": { - "notes": "Deepgram's hosted OpenAI Whisper models - pricing may differ from native Deepgram models" - } - }, - "deepgram/whisper-base": { - "mode": "audio_transcription", - "input_cost_per_second": 0.0001, - "output_cost_per_second": 0.0, - "litellm_provider": "deepgram", - "supported_endpoints": [ - "/v1/audio/transcriptions" - ], - "source": "https://deepgram.com/pricing", - "metadata": { - "notes": "Deepgram's hosted OpenAI Whisper models - pricing may differ from native Deepgram models" - } - }, - "deepgram/whisper-small": { - "mode": "audio_transcription", - "input_cost_per_second": 0.0001, - "output_cost_per_second": 0.0, - "litellm_provider": "deepgram", - "supported_endpoints": [ - "/v1/audio/transcriptions" - ], - "source": "https://deepgram.com/pricing", - "metadata": { - "notes": "Deepgram's hosted OpenAI Whisper models - pricing may differ from native Deepgram models" - } - }, - "deepgram/whisper-medium": { - "mode": "audio_transcription", - "input_cost_per_second": 0.0001, - "output_cost_per_second": 0.0, - "litellm_provider": "deepgram", - "supported_endpoints": [ - "/v1/audio/transcriptions" - ], - "source": "https://deepgram.com/pricing", - "metadata": { - "notes": "Deepgram's hosted OpenAI Whisper models - pricing may differ from native Deepgram models" - } - }, - "deepgram/whisper-large": { - "mode": "audio_transcription", - "input_cost_per_second": 0.0001, - "output_cost_per_second": 0.0, - "litellm_provider": "deepgram", - "supported_endpoints": [ - "/v1/audio/transcriptions" - ], - "source": "https://deepgram.com/pricing", - "metadata": { - "notes": "Deepgram's hosted OpenAI Whisper models - pricing may differ from native Deepgram models" - } - }, - "elevenlabs/scribe_v1": { - "mode": "audio_transcription", - "input_cost_per_second": 6.11e-05, - "output_cost_per_second": 0.0, - "litellm_provider": "elevenlabs", - "supported_endpoints": [ - "/v1/audio/transcriptions" - ], - "source": "https://elevenlabs.io/pricing", - "metadata": { - "original_pricing_per_hour": 0.22, - "calculation": "$0.22/hour = $0.00366/minute = $0.0000611 per second (enterprise pricing)", - "notes": "ElevenLabs Scribe v1 - state-of-the-art speech recognition model with 99 language support" - } - }, - "elevenlabs/scribe_v1_experimental": { - "mode": "audio_transcription", - "input_cost_per_second": 6.11e-05, - "output_cost_per_second": 0.0, - "litellm_provider": "elevenlabs", - "supported_endpoints": [ - "/v1/audio/transcriptions" - ], - "source": "https://elevenlabs.io/pricing", - "metadata": { - "original_pricing_per_hour": 0.22, - "calculation": "$0.22/hour = $0.00366/minute = $0.0000611 per second (enterprise pricing)", - "notes": "ElevenLabs Scribe v1 experimental - enhanced version of the main Scribe model" - } - }, - "bedrock/us-gov-east-1/amazon.titan-embed-text-v1": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "output_vector_size": 1536, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 0.0, - "litellm_provider": "bedrock", - "mode": "embedding" - }, - "bedrock/us-gov-east-1/amazon.titan-embed-text-v2:0": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "output_vector_size": 1024, - "input_cost_per_token": 2e-07, - "output_cost_per_token": 0.0, - "litellm_provider": "bedrock", - "mode": "embedding" - }, - "bedrock/us-gov-east-1/amazon.titan-text-express-v1": { - "max_tokens": 8000, - "max_input_tokens": 42000, - "max_output_tokens": 8000, - "input_cost_per_token": 1.3e-06, - "output_cost_per_token": 1.7e-06, - "litellm_provider": "bedrock", - "mode": "chat" - }, - "bedrock/us-gov-east-1/amazon.titan-text-lite-v1": { - "max_tokens": 4000, - "max_input_tokens": 42000, - "max_output_tokens": 4000, - "input_cost_per_token": 3e-07, - "output_cost_per_token": 4e-07, - "litellm_provider": "bedrock", - "mode": "chat" - }, - "bedrock/us-gov-east-1/amazon.titan-text-premier-v1:0": { - "max_tokens": 32000, - "max_input_tokens": 42000, - "max_output_tokens": 32000, - "input_cost_per_token": 5e-07, - "output_cost_per_token": 1.5e-06, - "litellm_provider": "bedrock", - "mode": "chat" - }, - "bedrock/us-gov-east-1/anthropic.claude-3-5-sonnet-20240620-v1:0": { - "max_tokens": 8192, - "max_input_tokens": 200000, - "max_output_tokens": 8192, - "input_cost_per_token": 3.6e-06, - "output_cost_per_token": 1.8e-05, - "litellm_provider": "bedrock", - "mode": "chat", "supports_function_calling": true, "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, "supports_tool_choice": true }, - "bedrock/us-gov-east-1/anthropic.claude-3-haiku-20240307-v1:0": { - "max_tokens": 4096, - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "input_cost_per_token": 3e-07, - "output_cost_per_token": 1.5e-06, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_tool_choice": true - }, - "bedrock/us-gov-east-1/meta.llama3-70b-instruct-v1:0": { - "max_tokens": 2048, - "max_input_tokens": 8000, - "max_output_tokens": 2048, - "input_cost_per_token": 2.65e-06, - "output_cost_per_token": 3.5e-06, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_pdf_input": true - }, - "bedrock/us-gov-east-1/meta.llama3-8b-instruct-v1:0": { - "max_tokens": 2048, - "max_input_tokens": 8000, - "max_output_tokens": 2048, - "input_cost_per_token": 3e-07, - "output_cost_per_token": 2.65e-06, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_pdf_input": true - }, - "bedrock/us-gov-west-1/amazon.titan-embed-text-v1": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "output_vector_size": 1536, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 0.0, - "litellm_provider": "bedrock", - "mode": "embedding" - }, - "bedrock/us-gov-west-1/amazon.titan-embed-text-v2:0": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "output_vector_size": 1024, + "groq/gemma2-9b-it": { "input_cost_per_token": 2e-07, - "output_cost_per_token": 0.0, - "litellm_provider": "bedrock", - "mode": "embedding" - }, - "bedrock/us-gov-west-1/amazon.titan-text-express-v1": { - "max_tokens": 8000, - "max_input_tokens": 42000, - "max_output_tokens": 8000, - "input_cost_per_token": 1.3e-06, - "output_cost_per_token": 1.7e-06, - "litellm_provider": "bedrock", - "mode": "chat" - }, - "bedrock/us-gov-west-1/amazon.titan-text-lite-v1": { - "max_tokens": 4000, - "max_input_tokens": 42000, - "max_output_tokens": 4000, - "input_cost_per_token": 3e-07, - "output_cost_per_token": 4e-07, - "litellm_provider": "bedrock", - "mode": "chat" - }, - "bedrock/us-gov-west-1/amazon.titan-text-premier-v1:0": { - "max_tokens": 32000, - "max_input_tokens": 42000, - "max_output_tokens": 32000, - "input_cost_per_token": 5e-07, - "output_cost_per_token": 1.5e-06, - "litellm_provider": "bedrock", - "mode": "chat" - }, - "bedrock/us-gov-west-1/anthropic.claude-3-5-sonnet-20240620-v1:0": { + "litellm_provider": "groq", + "max_input_tokens": 8192, + "max_output_tokens": 8192, "max_tokens": 8192, - "max_input_tokens": 200000, - "max_output_tokens": 8192, - "input_cost_per_token": 3.6e-06, - "output_cost_per_token": 1.8e-05, - "litellm_provider": "bedrock", "mode": "chat", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_tool_choice": true - }, - "bedrock/us-gov-west-1/anthropic.claude-3-haiku-20240307-v1:0": { - "max_tokens": 4096, - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "input_cost_per_token": 3e-07, - "output_cost_per_token": 1.5e-06, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_tool_choice": true - }, - "bedrock/us-gov-west-1/meta.llama3-70b-instruct-v1:0": { - "max_tokens": 2048, - "max_input_tokens": 8000, - "max_output_tokens": 2048, - "input_cost_per_token": 2.65e-06, - "output_cost_per_token": 3.5e-06, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_pdf_input": true - }, - "bedrock/us-gov-west-1/meta.llama3-8b-instruct-v1:0": { - "max_tokens": 2048, - "max_input_tokens": 8000, - "max_output_tokens": 2048, - "input_cost_per_token": 3e-07, - "output_cost_per_token": 2.65e-06, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_pdf_input": true - }, - "bedrock/us-gov-east-1/amazon.nova-pro-v1:0": { - "max_tokens": 10000, - "max_input_tokens": 300000, - "max_output_tokens": 10000, - "input_cost_per_token": 9.6e-07, - "output_cost_per_token": 3.84e-06, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_response_schema": true - }, - "bedrock/us-gov-west-1/amazon.nova-pro-v1:0": { - "max_tokens": 10000, - "max_input_tokens": 300000, - "max_output_tokens": 10000, - "input_cost_per_token": 9.6e-07, - "output_cost_per_token": 3.84e-06, - "litellm_provider": "bedrock", - "mode": "chat", - "supports_function_calling": true, - "supports_vision": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_response_schema": true - }, - "dashscope/qwen-max": { - "max_tokens": 32768, - "max_input_tokens": 30720, - "max_output_tokens": 8192, - "input_cost_per_token": 1.6e-06, - "output_cost_per_token": 6.4e-06, - "litellm_provider": "dashscope", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "mode": "chat", - "source": "https://www.alibabacloud.com/help/en/model-studio/models" - }, - "dashscope/qwen-plus-latest": { - "max_tokens": 1000000, - "max_input_tokens": 997952, - "max_output_tokens": 32768, - "litellm_provider": "dashscope", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "mode": "chat", - "tiered_pricing": [ - {"range": [0, 256e3], "input_cost_per_token": 4e-07, "output_cost_per_token": 1.2e-06, "output_cost_per_reasoning_token": 4e-06}, - {"range": [256e3, 1e6], "input_cost_per_token": 1.2e-06, "output_cost_per_token": 3.6e-06, "output_cost_per_reasoning_token": 1.2e-05} - ], - "source": "https://www.alibabacloud.com/help/en/model-studio/models" - }, - "dashscope/qwen-turbo-latest": { - "max_tokens": 1000000, - "max_input_tokens": 1000000, - "max_output_tokens": 16384, - "input_cost_per_token": 5e-08, "output_cost_per_token": 2e-07, - "output_cost_per_reasoning_token": 5e-07, - "litellm_provider": "dashscope", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "mode": "chat", - "source": "https://www.alibabacloud.com/help/en/model-studio/models" - }, - "dashscope/qwen3-30b-a3b": { - "max_tokens": 131072, - "max_input_tokens": 129024, - "max_output_tokens": 16384, - "litellm_provider": "dashscope", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "mode": "chat", - "source": "https://www.alibabacloud.com/help/en/model-studio/models" - }, - "dashscope/qwen3-max-preview": { - "max_tokens": 262144, - "max_input_tokens": 258048, - "max_output_tokens": 65536, - "litellm_provider": "dashscope", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "mode": "chat", - "tiered_pricing": [ - {"range": [0, 32e3], "input_cost_per_token": 1.2e-06, "output_cost_per_token": 6e-06}, - {"range": [32e3, 128e3], "input_cost_per_token": 2.4e-06, "output_cost_per_token": 1.2e-05}, - {"range": [128e3, 252e3], "input_cost_per_token": 3.0e-06, "output_cost_per_token": 1.5e-05} - ], - "source": "https://www.alibabacloud.com/help/en/model-studio/models" - }, - "dashscope/qwen-plus": { - "max_tokens": 131072, - "max_input_tokens": 129024, - "max_output_tokens": 16384, - "input_cost_per_token": 4e-07, - "output_cost_per_token": 1.2e-06, - "litellm_provider": "dashscope", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "mode": "chat", - "source": "https://www.alibabacloud.com/help/en/model-studio/models" - }, - "dashscope/qwen-flash": { - "max_tokens": 1000000, - "max_input_tokens": 997952, - "max_output_tokens": 32768, - "litellm_provider": "dashscope", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "mode": "chat", - "tiered_pricing": [ - {"range": [0, 256e3], "input_cost_per_token": 5e-08, "output_cost_per_token": 4e-07}, - {"range": [256e3, 1e6], "input_cost_per_token": 2.5e-07, "output_cost_per_token": 2e-06} - ], - "source": "https://www.alibabacloud.com/help/en/model-studio/models" - }, - "dashscope/qwen-coder": { - "max_tokens": 1000000, - "max_input_tokens": 1000000, - "max_output_tokens": 16384, - "input_cost_per_token": 3e-07, - "output_cost_per_token": 1.5e-06, - "litellm_provider": "dashscope", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "mode": "chat", - "source": "https://www.alibabacloud.com/help/en/model-studio/models" - }, - "dashscope/qwen3-coder-plus": { - "max_tokens": 1000000, - "max_input_tokens": 997952, - "max_output_tokens": 65536, - "litellm_provider": "dashscope", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "mode": "chat", - "tiered_pricing": [ - {"range": [0, 32e3], "input_cost_per_token": 1e-06, "output_cost_per_token": 5e-06, "cache_read_input_token_cost": 1e-07}, - {"range": [32e3, 128e3], "input_cost_per_token": 1.8e-06, "output_cost_per_token": 9e-06, "cache_read_input_token_cost": 1.8e-07}, - {"range": [128e3, 256e3], "input_cost_per_token": 3e-06, "output_cost_per_token": 1.5e-05, "cache_read_input_token_cost": 3e-07}, - {"range": [256e3, 1e6], "input_cost_per_token": 6e-06, "output_cost_per_token": 6e-05, "cache_read_input_token_cost": 6e-07} - ], - "source": "https://www.alibabacloud.com/help/en/model-studio/models" - }, - "dashscope/qwen3-coder-plus-2025-07-22": { - "max_tokens": 1000000, - "max_input_tokens": 997952, - "max_output_tokens": 65536, - "litellm_provider": "dashscope", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "mode": "chat", - "tiered_pricing": [ - {"range": [0, 32e3], "input_cost_per_token": 1e-06, "output_cost_per_token": 5e-06}, - {"range": [32e3, 128e3], "input_cost_per_token": 1.8e-06, "output_cost_per_token": 9e-06}, - {"range": [128e3, 256e3], "input_cost_per_token": 3e-06, "output_cost_per_token": 1.5e-05}, - {"range": [256e3, 1e6], "input_cost_per_token": 6e-06, "output_cost_per_token": 6e-05} - ], - "source": "https://www.alibabacloud.com/help/en/model-studio/models" - }, - "dashscope/qwen3-coder-flash": { - "max_tokens": 1000000, - "max_input_tokens": 997952, - "max_output_tokens": 65536, - "litellm_provider": "dashscope", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "mode": "chat", - "tiered_pricing": [ - {"range": [0, 32e3], "input_cost_per_token": 3e-07, "output_cost_per_token": 1.5e-06, "cache_read_input_token_cost": 8e-08}, - {"range": [32e3, 128e3], "input_cost_per_token": 5e-07, "output_cost_per_token": 2.5e-06, "cache_read_input_token_cost": 1.2e-07}, - {"range": [128e3, 256e3], "input_cost_per_token": 8e-07, "output_cost_per_token": 4e-06, "cache_read_input_token_cost": 2e-07}, - {"range": [256e3, 1e6], "input_cost_per_token": 1.6e-06, "output_cost_per_token": 9.6e-06, "cache_read_input_token_cost": 4e-07} - ], - "source": "https://www.alibabacloud.com/help/en/model-studio/models" - }, - "dashscope/qwen3-coder-flash-2025-07-28": { - "max_tokens": 1000000, - "max_input_tokens": 997952, - "max_output_tokens": 65536, - "litellm_provider": "dashscope", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "mode": "chat", - "tiered_pricing": [ - {"range": [0, 32e3], "input_cost_per_token": 3e-07, "output_cost_per_token": 1.5e-06}, - {"range": [32e3, 128e3], "input_cost_per_token": 5e-07, "output_cost_per_token": 2.5e-06}, - {"range": [128e3, 256e3], "input_cost_per_token": 8e-07, "output_cost_per_token": 4e-06}, - {"range": [256e3, 1e6], "input_cost_per_token": 1.6e-06, "output_cost_per_token": 9.6e-06} - ], - "source": "https://www.alibabacloud.com/help/en/model-studio/models" - }, - "dashscope/qwen-plus-2025-09-11": { - "max_tokens": 1000000, - "max_input_tokens": 997952, - "max_output_tokens": 32768, - "litellm_provider": "dashscope", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "mode": "chat", - "tiered_pricing": [ - {"range": [0, 256e3], "input_cost_per_token": 4e-07, "output_cost_per_token": 1.2e-06, "output_cost_per_reasoning_token": 4e-06}, - {"range": [256e3, 1e6], "input_cost_per_token": 1.2e-06, "output_cost_per_token": 3.6e-06, "output_cost_per_reasoning_token": 1.2e-05} - ], - "source": "https://www.alibabacloud.com/help/en/model-studio/models" - }, - "dashscope/qwen-plus-2025-07-28": { - "max_tokens": 1000000, - "max_input_tokens": 997952, - "max_output_tokens": 32768, - "litellm_provider": "dashscope", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "mode": "chat", - "tiered_pricing": [ - {"range": [0, 256e3], "input_cost_per_token": 4e-07, "output_cost_per_token": 1.2e-06, "output_cost_per_reasoning_token": 4e-06}, - {"range": [256e3, 1e6], "input_cost_per_token": 1.2e-06, "output_cost_per_token": 3.6e-06, "output_cost_per_reasoning_token": 1.2e-05} - ], - "source": "https://www.alibabacloud.com/help/en/model-studio/models" - }, - "dashscope/qwen-plus-2025-07-14": { - "max_tokens": 131072, - "max_input_tokens": 129024, - "max_output_tokens": 16384, - "input_cost_per_token": 4e-07, - "output_cost_per_token": 1.2e-06, - "output_cost_per_reasoning_token": 4e-06, - "litellm_provider": "dashscope", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "mode": "chat", - "source": "https://www.alibabacloud.com/help/en/model-studio/models" - }, - "dashscope/qwen-plus-2025-04-28": { - "max_tokens": 131072, - "max_input_tokens": 129024, - "max_output_tokens": 16384, - "input_cost_per_token": 4e-07, - "output_cost_per_token": 1.2e-06, - "output_cost_per_reasoning_token": 4e-06, - "litellm_provider": "dashscope", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "mode": "chat", - "source": "https://www.alibabacloud.com/help/en/model-studio/models" - }, - "dashscope/qwen-plus-2025-01-25": { - "max_tokens": 131072, - "max_input_tokens": 129024, - "max_output_tokens": 8192, - "input_cost_per_token": 4e-07, - "output_cost_per_token": 1.2e-06, - "litellm_provider": "dashscope", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "mode": "chat", - "source": "https://www.alibabacloud.com/help/en/model-studio/models" - }, - "dashscope/qwen-flash-2025-07-28": { - "max_tokens": 1000000, - "max_input_tokens": 997952, - "max_output_tokens": 32768, - "litellm_provider": "dashscope", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "mode": "chat", - "tiered_pricing": [ - {"range": [0, 256e3], "input_cost_per_token": 5e-08, "output_cost_per_token": 4e-07}, - {"range": [256e3, 1e6], "input_cost_per_token": 2.5e-07, "output_cost_per_token": 2e-06} - ], - "source": "https://www.alibabacloud.com/help/en/model-studio/models" - }, - "dashscope/qwen-turbo": { - "max_tokens": 131072, - "max_input_tokens": 129024, - "max_output_tokens": 16384, - "input_cost_per_token": 5e-08, - "output_cost_per_token": 2e-07, - "output_cost_per_reasoning_token": 5e-07, - "litellm_provider": "dashscope", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "mode": "chat", - "source": "https://www.alibabacloud.com/help/en/model-studio/models" - }, - "dashscope/qwen-turbo-2025-04-28": { - "max_tokens": 1000000, - "max_input_tokens": 1000000, - "max_output_tokens": 16384, - "input_cost_per_token": 5e-08, - "output_cost_per_token": 2e-07, - "output_cost_per_reasoning_token": 5e-07, - "litellm_provider": "dashscope", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "mode": "chat", - "source": "https://www.alibabacloud.com/help/en/model-studio/models" - }, - "dashscope/qwen-turbo-2024-11-01": { - "max_tokens": 1000000, - "max_input_tokens": 1000000, - "max_output_tokens": 8192, - "input_cost_per_token": 5e-08, - "output_cost_per_token": 2e-07, - "litellm_provider": "dashscope", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "mode": "chat", - "source": "https://www.alibabacloud.com/help/en/model-studio/models" - }, - "dashscope/qwq-plus": { - "max_tokens": 131072, - "max_input_tokens": 98304, - "max_output_tokens": 8192, - "input_cost_per_token": 8e-07, - "output_cost_per_token": 2.4e-06, - "litellm_provider": "dashscope", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "mode": "chat", - "source": "https://www.alibabacloud.com/help/en/model-studio/models" - }, - "moonshot/moonshot-v1-8k": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 2e-07, - "output_cost_per_token": 2e-06, - "litellm_provider": "moonshot", - "supports_function_calling": true, - "supports_tool_choice": true, - "mode": "chat", - "source": "https://platform.moonshot.ai/docs/pricing" - }, - "moonshot/moonshot-v1-32k": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "input_cost_per_token": 1e-06, - "output_cost_per_token": 3e-06, - "litellm_provider": "moonshot", - "supports_function_calling": true, - "supports_tool_choice": true, - "mode": "chat", - "source": "https://platform.moonshot.ai/docs/pricing" - }, - "moonshot/moonshot-v1-128k": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 5e-06, - "litellm_provider": "moonshot", - "supports_function_calling": true, - "supports_tool_choice": true, - "mode": "chat", - "source": "https://platform.moonshot.ai/docs/pricing" - }, - "moonshot/moonshot-v1-auto": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 5e-06, - "litellm_provider": "moonshot", - "supports_function_calling": true, - "supports_tool_choice": true, - "mode": "chat", - "source": "https://platform.moonshot.ai/docs/pricing" - }, - "moonshot/kimi-k2-0711-preview": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 6e-07, - "output_cost_per_token": 2.5e-06, - "cache_read_input_token_cost": 1.5e-07, - "litellm_provider": "moonshot", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_web_search": true, - "mode": "chat", - "source": "https://platform.moonshot.ai/docs/pricing/chat#generation-model-kimi-k2" - }, - "moonshot/moonshot-v1-32k-0430": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "input_cost_per_token": 1e-06, - "output_cost_per_token": 3e-06, - "litellm_provider": "moonshot", - "supports_function_calling": true, - "supports_tool_choice": true, - "mode": "chat", - "source": "https://platform.moonshot.ai/docs/pricing" - }, - "moonshot/moonshot-v1-128k-0430": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 5e-06, - "litellm_provider": "moonshot", - "supports_function_calling": true, - "supports_tool_choice": true, - "mode": "chat", - "source": "https://platform.moonshot.ai/docs/pricing" - }, - "moonshot/moonshot-v1-8k-0430": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 2e-07, - "output_cost_per_token": 2e-06, - "litellm_provider": "moonshot", - "supports_function_calling": true, - "supports_tool_choice": true, - "mode": "chat", - "source": "https://platform.moonshot.ai/docs/pricing" - }, - "moonshot/kimi-latest": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 5e-06, - "cache_read_input_token_cost": 1.5e-07, - "litellm_provider": "moonshot", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_vision": true, - "mode": "chat", - "source": "https://platform.moonshot.ai/docs/pricing" - }, - "moonshot/kimi-latest-8k": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 2e-07, - "output_cost_per_token": 2e-06, - "cache_read_input_token_cost": 1.5e-07, - "litellm_provider": "moonshot", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_vision": true, - "mode": "chat", - "source": "https://platform.moonshot.ai/docs/pricing" - }, - "moonshot/kimi-latest-32k": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "input_cost_per_token": 1e-06, - "output_cost_per_token": 3e-06, - "cache_read_input_token_cost": 1.5e-07, - "litellm_provider": "moonshot", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_vision": true, - "mode": "chat", - "source": "https://platform.moonshot.ai/docs/pricing" - }, - "moonshot/kimi-latest-128k": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 5e-06, - "cache_read_input_token_cost": 1.5e-07, - "litellm_provider": "moonshot", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_vision": true, - "mode": "chat", - "source": "https://platform.moonshot.ai/docs/pricing" - }, - "moonshot/kimi-thinking-preview": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 3e-05, - "output_cost_per_token": 3e-05, - "litellm_provider": "moonshot", - "supports_vision": true, - "mode": "chat", - "source": "https://platform.moonshot.ai/docs/pricing" - }, - "moonshot/moonshot-v1-8k-vision-preview": { - "max_tokens": 8192, - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "input_cost_per_token": 2e-07, - "output_cost_per_token": 2e-06, - "litellm_provider": "moonshot", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_vision": true, - "mode": "chat", - "source": "https://platform.moonshot.ai/docs/pricing" - }, - "moonshot/moonshot-v1-32k-vision-preview": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "input_cost_per_token": 1e-06, - "output_cost_per_token": 3e-06, - "litellm_provider": "moonshot", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_vision": true, - "mode": "chat", - "source": "https://platform.moonshot.ai/docs/pricing" - }, - "moonshot/moonshot-v1-128k-vision-preview": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 5e-06, - "litellm_provider": "moonshot", - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_vision": true, - "mode": "chat", - "source": "https://platform.moonshot.ai/docs/pricing" - }, - "recraft/recraftv3": { - "mode": "image_generation", - "output_cost_per_image": 0.04, - "litellm_provider": "recraft", - "supported_endpoints": [ - "/v1/images/generations" - ], - "source": "https://www.recraft.ai/docs#pricing" - }, - "recraft/recraftv2": { - "mode": "image_generation", - "output_cost_per_image": 0.022, - "litellm_provider": "recraft", - "supported_endpoints": [ - "/v1/images/generations" - ], - "source": "https://www.recraft.ai/docs#pricing" - }, - "morph/morph-v3-fast": { - "max_tokens": 16000, - "max_input_tokens": 16000, - "max_output_tokens": 16000, - "input_cost_per_token": 8e-07, - "output_cost_per_token": 1.2e-06, - "litellm_provider": "morph", - "mode": "chat", "supports_function_calling": false, - "supports_parallel_function_calling": false, - "supports_vision": false, - "supports_system_messages": true, + "supports_response_schema": true, "supports_tool_choice": false }, - "morph/morph-v3-large": { - "max_tokens": 16000, - "max_input_tokens": 16000, - "max_output_tokens": 16000, + "groq/llama-3.1-405b-reasoning": { + "input_cost_per_token": 5.9e-07, + "litellm_provider": "groq", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 7.9e-07, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "groq/llama-3.1-70b-versatile": { + "deprecation_date": "2025-01-24", + "input_cost_per_token": 5.9e-07, + "litellm_provider": "groq", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 7.9e-07, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "groq/llama-3.1-8b-instant": { + "input_cost_per_token": 5e-08, + "litellm_provider": "groq", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 8e-08, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "groq/llama-3.2-11b-text-preview": { + "deprecation_date": "2024-10-28", + "input_cost_per_token": 1.8e-07, + "litellm_provider": "groq", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.8e-07, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "groq/llama-3.2-11b-vision-preview": { + "deprecation_date": "2025-04-14", + "input_cost_per_token": 1.8e-07, + "litellm_provider": "groq", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.8e-07, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "groq/llama-3.2-1b-preview": { + "deprecation_date": "2025-04-14", + "input_cost_per_token": 4e-08, + "litellm_provider": "groq", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 4e-08, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "groq/llama-3.2-3b-preview": { + "deprecation_date": "2025-04-14", + "input_cost_per_token": 6e-08, + "litellm_provider": "groq", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 6e-08, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "groq/llama-3.2-90b-text-preview": { + "deprecation_date": "2024-11-25", "input_cost_per_token": 9e-07, - "output_cost_per_token": 1.9e-06, - "litellm_provider": "morph", - "mode": "chat", - "supports_function_calling": false, - "supports_parallel_function_calling": false, - "supports_vision": false, - "supports_system_messages": true, - "supports_tool_choice": false - }, - "heroku/claude-4-sonnet": { + "litellm_provider": "groq", + "max_input_tokens": 8192, + "max_output_tokens": 8192, "max_tokens": 8192, - "litellm_provider": "heroku", "mode": "chat", + "output_cost_per_token": 9e-07, "supports_function_calling": true, - "supports_system_messages": true, + "supports_response_schema": true, "supports_tool_choice": true }, - "heroku/claude-3-7-sonnet": { + "groq/llama-3.2-90b-vision-preview": { + "deprecation_date": "2025-04-14", + "input_cost_per_token": 9e-07, + "litellm_provider": "groq", + "max_input_tokens": 8192, + "max_output_tokens": 8192, "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 9e-07, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "groq/llama-3.3-70b-specdec": { + "deprecation_date": "2025-04-14", + "input_cost_per_token": 5.9e-07, + "litellm_provider": "groq", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 9.9e-07, + "supports_tool_choice": true + }, + "groq/llama-3.3-70b-versatile": { + "input_cost_per_token": 5.9e-07, + "litellm_provider": "groq", + "max_input_tokens": 128000, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 7.9e-07, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "groq/llama-guard-3-8b": { + "input_cost_per_token": 2e-07, + "litellm_provider": "groq", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 2e-07 + }, + "groq/llama2-70b-4096": { + "input_cost_per_token": 7e-07, + "litellm_provider": "groq", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 8e-07, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "groq/llama3-groq-70b-8192-tool-use-preview": { + "deprecation_date": "2025-01-06", + "input_cost_per_token": 8.9e-07, + "litellm_provider": "groq", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 8.9e-07, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "groq/llama3-groq-8b-8192-tool-use-preview": { + "deprecation_date": "2025-01-06", + "input_cost_per_token": 1.9e-07, + "litellm_provider": "groq", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.9e-07, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "groq/meta-llama/llama-4-maverick-17b-128e-instruct": { + "input_cost_per_token": 2e-07, + "litellm_provider": "groq", + "max_input_tokens": 131072, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 6e-07, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "groq/meta-llama/llama-4-scout-17b-16e-instruct": { + "input_cost_per_token": 1.1e-07, + "litellm_provider": "groq", + "max_input_tokens": 131072, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 3.4e-07, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "groq/mistral-saba-24b": { + "input_cost_per_token": 7.9e-07, + "litellm_provider": "groq", + "max_input_tokens": 32000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 7.9e-07 + }, + "groq/mixtral-8x7b-32768": { + "deprecation_date": "2025-03-20", + "input_cost_per_token": 2.4e-07, + "litellm_provider": "groq", + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 2.4e-07, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "groq/moonshotai/kimi-k2-instruct": { + "input_cost_per_token": 1e-06, + "litellm_provider": "groq", + "max_input_tokens": 131072, + "max_output_tokens": 16384, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 3e-06, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "groq/openai/gpt-oss-120b": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "groq", + "max_input_tokens": 131072, + "max_output_tokens": 32766, + "max_tokens": 32766, + "mode": "chat", + "output_cost_per_token": 7.5e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_web_search": true + }, + "groq/openai/gpt-oss-20b": { + "input_cost_per_token": 1e-07, + "litellm_provider": "groq", + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 5e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_web_search": true + }, + "groq/playai-tts": { + "input_cost_per_character": 5e-05, + "litellm_provider": "groq", + "max_input_tokens": 10000, + "max_output_tokens": 10000, + "max_tokens": 10000, + "mode": "audio_speech" + }, + "groq/qwen/qwen3-32b": { + "input_cost_per_token": 2.9e-07, + "litellm_provider": "groq", + "max_input_tokens": 131000, + "max_output_tokens": 131000, + "max_tokens": 131000, + "mode": "chat", + "output_cost_per_token": 5.9e-07, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "groq/whisper-large-v3": { + "input_cost_per_second": 3.083e-05, + "litellm_provider": "groq", + "mode": "audio_transcription", + "output_cost_per_second": 0.0 + }, + "groq/whisper-large-v3-turbo": { + "input_cost_per_second": 1.111e-05, + "litellm_provider": "groq", + "mode": "audio_transcription", + "output_cost_per_second": 0.0 + }, + "hd/1024-x-1024/dall-e-3": { + "input_cost_per_pixel": 7.629e-08, + "litellm_provider": "openai", + "mode": "image_generation", + "output_cost_per_pixel": 0.0 + }, + "hd/1024-x-1792/dall-e-3": { + "input_cost_per_pixel": 6.539e-08, + "litellm_provider": "openai", + "mode": "image_generation", + "output_cost_per_pixel": 0.0 + }, + "hd/1792-x-1024/dall-e-3": { + "input_cost_per_pixel": 6.539e-08, + "litellm_provider": "openai", + "mode": "image_generation", + "output_cost_per_pixel": 0.0 + }, + "heroku/claude-3-5-haiku": { "litellm_provider": "heroku", + "max_tokens": 4096, "mode": "chat", "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true }, "heroku/claude-3-5-sonnet-latest": { - "max_tokens": 8192, "litellm_provider": "heroku", + "max_tokens": 8192, "mode": "chat", "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true }, - "heroku/claude-3-5-haiku": { - "max_tokens": 4096, + "heroku/claude-3-7-sonnet": { "litellm_provider": "heroku", + "max_tokens": 8192, "mode": "chat", "supports_function_calling": true, "supports_system_messages": true, "supports_tool_choice": true }, - "vercel_ai_gateway/alibaba/qwen3-coder": { - "max_tokens": 262144, - "input_cost_per_token": 4e-07, - "output_cost_per_token": 1.6e-06, - "max_output_tokens": 66536, - "max_input_tokens": 262144, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/mistral/codestral-embed": { - "max_tokens": 0, - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 0.0, - "max_output_tokens": 0, - "max_input_tokens": 0, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/google/gemini-2.5-pro": { - "max_tokens": 1048576, - "input_cost_per_token": 2.5e-06, - "output_cost_per_token": 1e-05, - "max_output_tokens": 65536, - "max_input_tokens": 1048576, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/deepseek/deepseek-v3": { - "max_tokens": 128000, - "input_cost_per_token": 9e-07, - "output_cost_per_token": 9e-07, - "max_output_tokens": 8192, - "max_input_tokens": 128000, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/amazon/nova-lite": { - "max_tokens": 300000, - "input_cost_per_token": 6e-08, - "output_cost_per_token": 2.4e-07, - "max_output_tokens": 8192, - "max_input_tokens": 300000, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/meta/llama-4-scout": { - "max_tokens": 131072, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 3e-07, - "max_output_tokens": 8192, - "max_input_tokens": 131072, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/meta/llama-3.2-1b": { - "max_tokens": 128000, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 1e-07, - "max_output_tokens": 8192, - "max_input_tokens": 128000, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/mistral/mistral-small": { - "max_tokens": 32000, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 3e-07, - "max_output_tokens": 4000, - "max_input_tokens": 32000, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/google/gemini-2.5-flash": { - "max_tokens": 1000000, - "input_cost_per_token": 3e-07, - "output_cost_per_token": 2.5e-06, - "max_output_tokens": 65536, - "max_input_tokens": 1000000, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/inception/mercury-coder-small": { - "max_tokens": 32000, - "input_cost_per_token": 2.5e-07, - "output_cost_per_token": 1e-06, - "max_output_tokens": 16384, - "max_input_tokens": 32000, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/openai/text-embedding-3-small": { - "max_tokens": 0, - "input_cost_per_token": 2e-08, - "output_cost_per_token": 0.0, - "max_output_tokens": 0, - "max_input_tokens": 0, - "litellm_provider": "vercel_ai_gateway", - "mode": "embedding" - }, - "vercel_ai_gateway/xai/grok-2-vision": { - "max_tokens": 32768, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 1e-05, - "max_output_tokens": 32768, - "max_input_tokens": 32768, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/xai/grok-2": { - "max_tokens": 131072, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 1e-05, - "max_output_tokens": 4000, - "max_input_tokens": 131072, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/deepseek/deepseek-r1-distill-llama-70b": { - "max_tokens": 131072, - "input_cost_per_token": 7.5e-07, - "output_cost_per_token": 9.9e-07, - "max_output_tokens": 131072, - "max_input_tokens": 131072, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/meta/llama-3.1-70b": { - "max_tokens": 128000, - "input_cost_per_token": 7.2e-07, - "output_cost_per_token": 7.2e-07, - "max_output_tokens": 8192, - "max_input_tokens": 128000, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/xai/grok-3": { - "max_tokens": 131072, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "max_output_tokens": 131072, - "max_input_tokens": 131072, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/alibaba/qwen-3-235b": { - "max_tokens": 40960, - "input_cost_per_token": 2e-07, - "output_cost_per_token": 6e-07, - "max_output_tokens": 16384, - "max_input_tokens": 40960, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/xai/grok-3-fast": { - "max_tokens": 131072, - "input_cost_per_token": 5e-06, - "output_cost_per_token": 2.5e-05, - "max_output_tokens": 131072, - "max_input_tokens": 131072, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/vercel/v0-1.5-md": { - "max_tokens": 128000, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "max_output_tokens": 32768, - "max_input_tokens": 128000, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/openai/o4-mini": { - "max_tokens": 200000, - "input_cost_per_token": 1.1e-06, - "output_cost_per_token": 4.4e-06, - "max_output_tokens": 100000, - "max_input_tokens": 200000, - "cache_read_input_token_cost": 2.75e-07, - "cache_creation_input_token_cost": 0.0, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/mistral/magistral-medium": { - "max_tokens": 128000, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 5e-06, - "max_output_tokens": 64000, - "max_input_tokens": 128000, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/amazon/titan-embed-text-v2": { - "max_tokens": 0, - "input_cost_per_token": 2e-08, - "output_cost_per_token": 0.0, - "max_output_tokens": 0, - "max_input_tokens": 0, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/alibaba/qwen-3-30b": { - "max_tokens": 40960, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 3e-07, - "max_output_tokens": 16384, - "max_input_tokens": 40960, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/zai/glm-4.5-air": { - "max_tokens": 128000, - "input_cost_per_token": 2e-07, - "output_cost_per_token": 1.1e-06, - "max_output_tokens": 96000, - "max_input_tokens": 128000, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/openai/gpt-4-turbo": { - "max_tokens": 128000, - "input_cost_per_token": 1e-05, - "output_cost_per_token": 3e-05, - "max_output_tokens": 4096, - "max_input_tokens": 128000, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/mistral/mistral-large": { - "max_tokens": 32000, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 6e-06, - "max_output_tokens": 4000, - "max_input_tokens": 32000, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/perplexity/sonar-pro": { - "max_tokens": 200000, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "max_output_tokens": 8000, - "max_input_tokens": 200000, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/meta/llama-3.2-90b": { - "max_tokens": 128000, - "input_cost_per_token": 7.2e-07, - "output_cost_per_token": 7.2e-07, - "max_output_tokens": 8192, - "max_input_tokens": 128000, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/meta/llama-3-8b": { + "heroku/claude-4-sonnet": { + "litellm_provider": "heroku", "max_tokens": 8192, - "input_cost_per_token": 5e-08, - "output_cost_per_token": 8e-08, - "max_output_tokens": 8192, - "max_input_tokens": 8192, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" + "mode": "chat", + "supports_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true }, - "vercel_ai_gateway/google/text-embedding-005": { - "max_tokens": 0, - "input_cost_per_token": 2.5e-08, - "output_cost_per_token": 0.0, - "max_output_tokens": 0, - "max_input_tokens": 0, - "litellm_provider": "vercel_ai_gateway", - "mode": "embedding" + "high/1024-x-1024/gpt-image-1": { + "input_cost_per_pixel": 1.59263611e-07, + "litellm_provider": "openai", + "mode": "image_generation", + "output_cost_per_pixel": 0.0, + "supported_endpoints": [ + "/v1/images/generations" + ] }, - "vercel_ai_gateway/mistral/pixtral-large": { - "max_tokens": 128000, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 6e-06, - "max_output_tokens": 4000, - "max_input_tokens": 128000, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" + "high/1024-x-1536/gpt-image-1": { + "input_cost_per_pixel": 1.58945719e-07, + "litellm_provider": "openai", + "mode": "image_generation", + "output_cost_per_pixel": 0.0, + "supported_endpoints": [ + "/v1/images/generations" + ] }, - "vercel_ai_gateway/anthropic/claude-3.5-sonnet": { - "max_tokens": 200000, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "max_output_tokens": 8192, - "max_input_tokens": 200000, - "cache_read_input_token_cost": 3e-07, - "cache_creation_input_token_cost": 3.75e-06, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" + "high/1536-x-1024/gpt-image-1": { + "input_cost_per_pixel": 1.58945719e-07, + "litellm_provider": "openai", + "mode": "image_generation", + "output_cost_per_pixel": 0.0, + "supported_endpoints": [ + "/v1/images/generations" + ] }, - "vercel_ai_gateway/amazon/nova-micro": { - "max_tokens": 128000, - "input_cost_per_token": 3.5e-08, - "output_cost_per_token": 1.4e-07, - "max_output_tokens": 8192, - "max_input_tokens": 128000, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/cohere/command-r": { - "max_tokens": 128000, - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 6e-07, - "max_output_tokens": 4096, - "max_input_tokens": 128000, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/morph/morph-v3-large": { - "max_tokens": 32768, - "input_cost_per_token": 9e-07, - "output_cost_per_token": 1.9e-06, - "max_output_tokens": 16384, - "max_input_tokens": 32768, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/mistral/mixtral-8x22b-instruct": { - "max_tokens": 65536, - "input_cost_per_token": 1.2e-06, - "output_cost_per_token": 1.2e-06, - "max_output_tokens": 2048, - "max_input_tokens": 65536, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/xai/grok-4": { - "max_tokens": 256000, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "max_output_tokens": 256000, - "max_input_tokens": 256000, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/meta/llama-3.1-8b": { - "max_tokens": 131000, - "input_cost_per_token": 5e-08, - "output_cost_per_token": 8e-08, - "max_output_tokens": 131072, - "max_input_tokens": 131000, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/anthropic/claude-3-opus": { - "max_tokens": 200000, - "input_cost_per_token": 1.5e-05, - "output_cost_per_token": 7.5e-05, - "max_output_tokens": 4096, - "max_input_tokens": 200000, - "cache_read_input_token_cost": 1.5e-06, - "cache_creation_input_token_cost": 1.875e-05, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/zai/glm-4.5": { - "max_tokens": 131072, - "input_cost_per_token": 6e-07, - "output_cost_per_token": 2.2e-06, - "max_output_tokens": 131072, - "max_input_tokens": 131072, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/openai/gpt-4o": { - "max_tokens": 128000, - "input_cost_per_token": 2.5e-06, - "output_cost_per_token": 1e-05, - "max_output_tokens": 16384, - "max_input_tokens": 128000, - "cache_read_input_token_cost": 1.25e-06, - "cache_creation_input_token_cost": 0.0, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/openai/o3-mini": { - "max_tokens": 200000, - "input_cost_per_token": 1.1e-06, - "output_cost_per_token": 4.4e-06, - "max_output_tokens": 100000, - "max_input_tokens": 200000, - "cache_read_input_token_cost": 5.5e-07, - "cache_creation_input_token_cost": 0.0, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/mistral/ministral-8b": { - "max_tokens": 128000, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 1e-07, - "max_output_tokens": 4000, - "max_input_tokens": 128000, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/openai/o3": { - "max_tokens": 200000, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 8e-06, - "max_output_tokens": 100000, - "max_input_tokens": 200000, - "cache_read_input_token_cost": 5e-07, - "cache_creation_input_token_cost": 0.0, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/vercel/v0-1.0-md": { - "max_tokens": 128000, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "max_output_tokens": 32000, - "max_input_tokens": 128000, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/google/text-multilingual-embedding-002": { - "max_tokens": 0, - "input_cost_per_token": 2.5e-08, - "output_cost_per_token": 0.0, - "max_output_tokens": 0, - "max_input_tokens": 0, - "litellm_provider": "vercel_ai_gateway", - "mode": "embedding" - }, - "vercel_ai_gateway/amazon/nova-pro": { - "max_tokens": 300000, - "input_cost_per_token": 8e-07, - "output_cost_per_token": 3.2e-06, - "max_output_tokens": 8192, - "max_input_tokens": 300000, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/morph/morph-v3-fast": { - "max_tokens": 32768, - "input_cost_per_token": 8e-07, - "output_cost_per_token": 1.2e-06, - "max_output_tokens": 16384, - "max_input_tokens": 32768, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/openai/gpt-3.5-turbo": { - "max_tokens": 16385, - "input_cost_per_token": 5e-07, - "output_cost_per_token": 1.5e-06, - "max_output_tokens": 4096, - "max_input_tokens": 16385, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/mistral/codestral": { - "max_tokens": 256000, - "input_cost_per_token": 3e-07, - "output_cost_per_token": 9e-07, - "max_output_tokens": 4000, - "max_input_tokens": 256000, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/meta/llama-3.2-11b": { - "max_tokens": 128000, - "input_cost_per_token": 1.6e-07, - "output_cost_per_token": 1.6e-07, - "max_output_tokens": 8192, - "max_input_tokens": 128000, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/meta/llama-3-70b": { - "max_tokens": 8192, - "input_cost_per_token": 5.9e-07, - "output_cost_per_token": 7.9e-07, - "max_output_tokens": 8192, - "max_input_tokens": 8192, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/xai/grok-3-mini-fast": { - "max_tokens": 131072, - "input_cost_per_token": 6e-07, - "output_cost_per_token": 4e-06, - "max_output_tokens": 131072, - "max_input_tokens": 131072, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/openai/text-embedding-3-large": { - "max_tokens": 0, - "input_cost_per_token": 1.3e-07, - "output_cost_per_token": 0.0, - "max_output_tokens": 0, - "max_input_tokens": 0, - "litellm_provider": "vercel_ai_gateway", - "mode": "embedding" - }, - "vercel_ai_gateway/google/gemini-2.0-flash-lite": { - "max_tokens": 1048576, - "input_cost_per_token": 7.5e-08, - "output_cost_per_token": 3e-07, - "max_output_tokens": 8192, - "max_input_tokens": 1048576, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/mistral/ministral-3b": { - "max_tokens": 128000, - "input_cost_per_token": 4e-08, - "output_cost_per_token": 4e-08, - "max_output_tokens": 4000, - "max_input_tokens": 128000, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/perplexity/sonar-reasoning-pro": { - "max_tokens": 127000, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 8e-06, - "max_output_tokens": 8000, - "max_input_tokens": 127000, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/google/gemini-embedding-001": { - "max_tokens": 0, - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 0.0, - "max_output_tokens": 0, - "max_input_tokens": 0, - "litellm_provider": "vercel_ai_gateway", - "mode": "embedding" - }, - "vercel_ai_gateway/anthropic/claude-3-haiku": { - "max_tokens": 200000, - "input_cost_per_token": 2.5e-07, - "output_cost_per_token": 1.25e-06, - "max_output_tokens": 4096, - "max_input_tokens": 200000, - "cache_read_input_token_cost": 3e-08, - "cache_creation_input_token_cost": 3e-07, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/openai/o1": { - "max_tokens": 200000, - "input_cost_per_token": 1.5e-05, - "output_cost_per_token": 6e-05, - "max_output_tokens": 100000, - "max_input_tokens": 200000, - "cache_read_input_token_cost": 7.5e-06, - "cache_creation_input_token_cost": 0.0, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/deepseek/deepseek-r1": { - "max_tokens": 128000, - "input_cost_per_token": 5.5e-07, - "output_cost_per_token": 2.19e-06, - "max_output_tokens": 8192, - "max_input_tokens": 128000, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/mistral/mistral-embed": { - "max_tokens": 0, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 0.0, - "max_output_tokens": 0, - "max_input_tokens": 0, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/openai/gpt-4.1-mini": { - "max_tokens": 1047576, - "input_cost_per_token": 4e-07, - "output_cost_per_token": 1.6e-06, - "max_output_tokens": 32768, - "max_input_tokens": 1047576, - "cache_read_input_token_cost": 1e-07, - "cache_creation_input_token_cost": 0.0, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/openai/gpt-4o-mini": { - "max_tokens": 128000, - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 6e-07, - "max_output_tokens": 16384, - "max_input_tokens": 128000, - "cache_read_input_token_cost": 7.5e-08, - "cache_creation_input_token_cost": 0.0, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/alibaba/qwen-3-14b": { - "max_tokens": 40960, - "input_cost_per_token": 8e-08, - "output_cost_per_token": 2.4e-07, - "max_output_tokens": 16384, - "max_input_tokens": 40960, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/anthropic/claude-4-opus": { - "max_tokens": 200000, - "input_cost_per_token": 1.5e-05, - "output_cost_per_token": 7.5e-05, - "max_output_tokens": 32000, - "max_input_tokens": 200000, - "cache_read_input_token_cost": 1.5e-06, - "cache_creation_input_token_cost": 1.875e-05, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/mistral/mistral-saba-24b": { - "max_tokens": 32768, - "input_cost_per_token": 7.9e-07, - "output_cost_per_token": 7.9e-07, - "max_output_tokens": 32768, - "max_input_tokens": 32768, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/perplexity/sonar-reasoning": { - "max_tokens": 127000, - "input_cost_per_token": 1e-06, - "output_cost_per_token": 5e-06, - "max_output_tokens": 8000, - "max_input_tokens": 127000, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/anthropic/claude-3.5-haiku": { - "max_tokens": 200000, - "input_cost_per_token": 8e-07, - "output_cost_per_token": 4e-06, - "max_output_tokens": 8192, - "max_input_tokens": 200000, - "cache_read_input_token_cost": 8e-08, - "cache_creation_input_token_cost": 1e-06, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/cohere/command-a": { - "max_tokens": 256000, - "input_cost_per_token": 2.5e-06, - "output_cost_per_token": 1e-05, - "max_output_tokens": 8000, - "max_input_tokens": 256000, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/google/gemma-2-9b": { - "max_tokens": 8192, - "input_cost_per_token": 2e-07, - "output_cost_per_token": 2e-07, - "max_output_tokens": 8192, - "max_input_tokens": 8192, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/meta/llama-3.2-3b": { - "max_tokens": 128000, - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 1.5e-07, - "max_output_tokens": 8192, - "max_input_tokens": 128000, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/openai/gpt-4.1-nano": { - "max_tokens": 1047576, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 4e-07, - "max_output_tokens": 32768, - "max_input_tokens": 1047576, - "cache_read_input_token_cost": 2.5e-08, - "cache_creation_input_token_cost": 0.0, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/anthropic/claude-4-sonnet": { - "max_tokens": 200000, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "max_output_tokens": 64000, - "max_input_tokens": 200000, - "cache_read_input_token_cost": 3e-07, - "cache_creation_input_token_cost": 3.75e-06, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/perplexity/sonar": { - "max_tokens": 127000, - "input_cost_per_token": 1e-06, - "output_cost_per_token": 1e-06, - "max_output_tokens": 8000, - "max_input_tokens": 127000, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/meta/llama-4-maverick": { - "max_tokens": 131072, - "input_cost_per_token": 2e-07, - "output_cost_per_token": 6e-07, - "max_output_tokens": 8192, - "max_input_tokens": 131072, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/openai/text-embedding-ada-002": { - "max_tokens": 0, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 0.0, - "max_output_tokens": 0, - "max_input_tokens": 0, - "litellm_provider": "vercel_ai_gateway", - "mode": "embedding" - }, - "vercel_ai_gateway/xai/grok-3-mini": { - "max_tokens": 131072, - "input_cost_per_token": 3e-07, - "output_cost_per_token": 5e-07, - "max_output_tokens": 131072, - "max_input_tokens": 131072, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/cohere/embed-v4.0": { - "max_tokens": 0, + "hyperbolic/NousResearch/Hermes-3-Llama-3.1-70B": { "input_cost_per_token": 1.2e-07, - "output_cost_per_token": 0.0, - "max_output_tokens": 0, - "max_input_tokens": 0, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/meta/llama-3.3-70b": { - "max_tokens": 128000, - "input_cost_per_token": 7.2e-07, - "output_cost_per_token": 7.2e-07, - "max_output_tokens": 8192, - "max_input_tokens": 128000, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/cohere/command-r-plus": { - "max_tokens": 128000, - "input_cost_per_token": 2.5e-06, - "output_cost_per_token": 1e-05, - "max_output_tokens": 4096, - "max_input_tokens": 128000, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/openai/gpt-3.5-turbo-instruct": { - "max_tokens": 8192, - "input_cost_per_token": 1.5e-06, - "output_cost_per_token": 2e-06, - "max_output_tokens": 4096, - "max_input_tokens": 8192, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/mistral/devstral-small": { - "max_tokens": 128000, - "input_cost_per_token": 7e-08, - "output_cost_per_token": 2.8e-07, - "max_output_tokens": 128000, - "max_input_tokens": 128000, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/anthropic/claude-3.7-sonnet": { - "max_tokens": 200000, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 1.5e-05, - "max_output_tokens": 64000, - "max_input_tokens": 200000, - "cache_read_input_token_cost": 3e-07, - "cache_creation_input_token_cost": 3.75e-06, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/google/gemini-2.0-flash": { - "max_tokens": 1048576, - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 6e-07, - "max_output_tokens": 8192, - "max_input_tokens": 1048576, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/mistral/pixtral-12b": { - "max_tokens": 128000, - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 1.5e-07, - "max_output_tokens": 4000, - "max_input_tokens": 128000, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/mistral/magistral-small": { - "max_tokens": 128000, - "input_cost_per_token": 5e-07, - "output_cost_per_token": 1.5e-06, - "max_output_tokens": 64000, - "max_input_tokens": 128000, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/moonshotai/kimi-k2": { - "max_tokens": 131072, - "input_cost_per_token": 5.5e-07, - "output_cost_per_token": 2.2e-06, - "max_output_tokens": 16384, - "max_input_tokens": 131072, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/alibaba/qwen-3-32b": { - "max_tokens": 40960, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 3e-07, - "max_output_tokens": 16384, - "max_input_tokens": 40960, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "vercel_ai_gateway/openai/gpt-4.1": { - "max_tokens": 1047576, - "input_cost_per_token": 2e-06, - "output_cost_per_token": 8e-06, + "litellm_provider": "hyperbolic", + "max_input_tokens": 32768, "max_output_tokens": 32768, - "max_input_tokens": 1047576, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 3e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "hyperbolic/Qwen/QwQ-32B": { + "input_cost_per_token": 2e-07, + "litellm_provider": "hyperbolic", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "hyperbolic/Qwen/Qwen2.5-72B-Instruct": { + "input_cost_per_token": 1.2e-07, + "litellm_provider": "hyperbolic", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 3e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "hyperbolic/Qwen/Qwen2.5-Coder-32B-Instruct": { + "input_cost_per_token": 1.2e-07, + "litellm_provider": "hyperbolic", + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 3e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "hyperbolic/Qwen/Qwen3-235B-A22B": { + "input_cost_per_token": 2e-06, + "litellm_provider": "hyperbolic", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2e-06, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "hyperbolic/deepseek-ai/DeepSeek-R1": { + "input_cost_per_token": 4e-07, + "litellm_provider": "hyperbolic", + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 4e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "hyperbolic/deepseek-ai/DeepSeek-R1-0528": { + "input_cost_per_token": 2.5e-07, + "litellm_provider": "hyperbolic", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2.5e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "hyperbolic/deepseek-ai/DeepSeek-V3": { + "input_cost_per_token": 2e-07, + "litellm_provider": "hyperbolic", + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 2e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "hyperbolic/deepseek-ai/DeepSeek-V3-0324": { + "input_cost_per_token": 4e-07, + "litellm_provider": "hyperbolic", + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 4e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "hyperbolic/meta-llama/Llama-3.2-3B-Instruct": { + "input_cost_per_token": 1.2e-07, + "litellm_provider": "hyperbolic", + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 3e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "hyperbolic/meta-llama/Llama-3.3-70B-Instruct": { + "input_cost_per_token": 1.2e-07, + "litellm_provider": "hyperbolic", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 3e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "hyperbolic/meta-llama/Meta-Llama-3-70B-Instruct": { + "input_cost_per_token": 1.2e-07, + "litellm_provider": "hyperbolic", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 3e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "hyperbolic/meta-llama/Meta-Llama-3.1-405B-Instruct": { + "input_cost_per_token": 1.2e-07, + "litellm_provider": "hyperbolic", + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 3e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "hyperbolic/meta-llama/Meta-Llama-3.1-70B-Instruct": { + "input_cost_per_token": 1.2e-07, + "litellm_provider": "hyperbolic", + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 3e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "hyperbolic/meta-llama/Meta-Llama-3.1-8B-Instruct": { + "input_cost_per_token": 1.2e-07, + "litellm_provider": "hyperbolic", + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 3e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "hyperbolic/moonshotai/Kimi-K2-Instruct": { + "input_cost_per_token": 2e-06, + "litellm_provider": "hyperbolic", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2e-06, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "j2-light": { + "input_cost_per_token": 3e-06, + "litellm_provider": "ai21", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "completion", + "output_cost_per_token": 3e-06 + }, + "j2-mid": { + "input_cost_per_token": 1e-05, + "litellm_provider": "ai21", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "completion", + "output_cost_per_token": 1e-05 + }, + "j2-ultra": { + "input_cost_per_token": 1.5e-05, + "litellm_provider": "ai21", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "completion", + "output_cost_per_token": 1.5e-05 + }, + "jamba-1.5": { + "input_cost_per_token": 2e-07, + "litellm_provider": "ai21", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 4e-07, + "supports_tool_choice": true + }, + "jamba-1.5-large": { + "input_cost_per_token": 2e-06, + "litellm_provider": "ai21", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 8e-06, + "supports_tool_choice": true + }, + "jamba-1.5-large@001": { + "input_cost_per_token": 2e-06, + "litellm_provider": "ai21", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 8e-06, + "supports_tool_choice": true + }, + "jamba-1.5-mini": { + "input_cost_per_token": 2e-07, + "litellm_provider": "ai21", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 4e-07, + "supports_tool_choice": true + }, + "jamba-1.5-mini@001": { + "input_cost_per_token": 2e-07, + "litellm_provider": "ai21", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 4e-07, + "supports_tool_choice": true + }, + "jamba-large-1.6": { + "input_cost_per_token": 2e-06, + "litellm_provider": "ai21", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 8e-06, + "supports_tool_choice": true + }, + "jamba-large-1.7": { + "input_cost_per_token": 2e-06, + "litellm_provider": "ai21", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 8e-06, + "supports_tool_choice": true + }, + "jamba-mini-1.6": { + "input_cost_per_token": 2e-07, + "litellm_provider": "ai21", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 4e-07, + "supports_tool_choice": true + }, + "jamba-mini-1.7": { + "input_cost_per_token": 2e-07, + "litellm_provider": "ai21", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 4e-07, + "supports_tool_choice": true + }, + "jina-reranker-v2-base-multilingual": { + "input_cost_per_token": 1.8e-08, + "litellm_provider": "jina_ai", + "max_document_chunks_per_query": 2048, + "max_input_tokens": 1024, + "max_output_tokens": 1024, + "max_tokens": 1024, + "mode": "rerank", + "output_cost_per_token": 1.8e-08 + }, + "lambda_ai/deepseek-llama3.3-70b": { + "input_cost_per_token": 2e-07, + "litellm_provider": "lambda_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 6e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "lambda_ai/deepseek-r1-0528": { + "input_cost_per_token": 2e-07, + "litellm_provider": "lambda_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 6e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "lambda_ai/deepseek-r1-671b": { + "input_cost_per_token": 8e-07, + "litellm_provider": "lambda_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 8e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "lambda_ai/deepseek-v3-0324": { + "input_cost_per_token": 2e-07, + "litellm_provider": "lambda_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 6e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "lambda_ai/hermes3-405b": { + "input_cost_per_token": 8e-07, + "litellm_provider": "lambda_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 8e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "lambda_ai/hermes3-70b": { + "input_cost_per_token": 1.2e-07, + "litellm_provider": "lambda_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 3e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "lambda_ai/hermes3-8b": { + "input_cost_per_token": 2.5e-08, + "litellm_provider": "lambda_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4e-08, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "lambda_ai/lfm-40b": { + "input_cost_per_token": 1e-07, + "litellm_provider": "lambda_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "lambda_ai/lfm-7b": { + "input_cost_per_token": 2.5e-08, + "litellm_provider": "lambda_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4e-08, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "lambda_ai/llama-4-maverick-17b-128e-instruct-fp8": { + "input_cost_per_token": 5e-08, + "litellm_provider": "lambda_ai", + "max_input_tokens": 131072, + "max_output_tokens": 8192, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "lambda_ai/llama-4-scout-17b-16e-instruct": { + "input_cost_per_token": 5e-08, + "litellm_provider": "lambda_ai", + "max_input_tokens": 16384, + "max_output_tokens": 8192, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "lambda_ai/llama3.1-405b-instruct-fp8": { + "input_cost_per_token": 8e-07, + "litellm_provider": "lambda_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 8e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "lambda_ai/llama3.1-70b-instruct-fp8": { + "input_cost_per_token": 1.2e-07, + "litellm_provider": "lambda_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 3e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "lambda_ai/llama3.1-8b-instruct": { + "input_cost_per_token": 2.5e-08, + "litellm_provider": "lambda_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4e-08, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "lambda_ai/llama3.1-nemotron-70b-instruct-fp8": { + "input_cost_per_token": 1.2e-07, + "litellm_provider": "lambda_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 3e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "lambda_ai/llama3.2-11b-vision-instruct": { + "input_cost_per_token": 1.5e-08, + "litellm_provider": "lambda_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2.5e-08, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "lambda_ai/llama3.2-3b-instruct": { + "input_cost_per_token": 1.5e-08, + "litellm_provider": "lambda_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2.5e-08, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "lambda_ai/llama3.3-70b-instruct-fp8": { + "input_cost_per_token": 1.2e-07, + "litellm_provider": "lambda_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 3e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "lambda_ai/qwen25-coder-32b-instruct": { + "input_cost_per_token": 5e-08, + "litellm_provider": "lambda_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "lambda_ai/qwen3-32b-fp8": { + "input_cost_per_token": 5e-08, + "litellm_provider": "lambda_ai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "low/1024-x-1024/gpt-image-1": { + "input_cost_per_pixel": 1.0490417e-08, + "litellm_provider": "openai", + "mode": "image_generation", + "output_cost_per_pixel": 0.0, + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "low/1024-x-1536/gpt-image-1": { + "input_cost_per_pixel": 1.0172526e-08, + "litellm_provider": "openai", + "mode": "image_generation", + "output_cost_per_pixel": 0.0, + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "low/1536-x-1024/gpt-image-1": { + "input_cost_per_pixel": 1.0172526e-08, + "litellm_provider": "openai", + "mode": "image_generation", + "output_cost_per_pixel": 0.0, + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "luminous-base": { + "input_cost_per_token": 3e-05, + "litellm_provider": "aleph_alpha", + "max_tokens": 2048, + "mode": "completion", + "output_cost_per_token": 3.3e-05 + }, + "luminous-base-control": { + "input_cost_per_token": 3.75e-05, + "litellm_provider": "aleph_alpha", + "max_tokens": 2048, + "mode": "chat", + "output_cost_per_token": 4.125e-05 + }, + "luminous-extended": { + "input_cost_per_token": 4.5e-05, + "litellm_provider": "aleph_alpha", + "max_tokens": 2048, + "mode": "completion", + "output_cost_per_token": 4.95e-05 + }, + "luminous-extended-control": { + "input_cost_per_token": 5.625e-05, + "litellm_provider": "aleph_alpha", + "max_tokens": 2048, + "mode": "chat", + "output_cost_per_token": 6.1875e-05 + }, + "luminous-supreme": { + "input_cost_per_token": 0.000175, + "litellm_provider": "aleph_alpha", + "max_tokens": 2048, + "mode": "completion", + "output_cost_per_token": 0.0001925 + }, + "luminous-supreme-control": { + "input_cost_per_token": 0.00021875, + "litellm_provider": "aleph_alpha", + "max_tokens": 2048, + "mode": "chat", + "output_cost_per_token": 0.000240625 + }, + "max-x-max/50-steps/stability.stable-diffusion-xl-v0": { + "litellm_provider": "bedrock", + "max_input_tokens": 77, + "max_tokens": 77, + "mode": "image_generation", + "output_cost_per_image": 0.036 + }, + "max-x-max/max-steps/stability.stable-diffusion-xl-v0": { + "litellm_provider": "bedrock", + "max_input_tokens": 77, + "max_tokens": 77, + "mode": "image_generation", + "output_cost_per_image": 0.072 + }, + "medium/1024-x-1024/gpt-image-1": { + "input_cost_per_pixel": 4.0054321e-08, + "litellm_provider": "openai", + "mode": "image_generation", + "output_cost_per_pixel": 0.0, + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "medium/1024-x-1536/gpt-image-1": { + "input_cost_per_pixel": 4.0054321e-08, + "litellm_provider": "openai", + "mode": "image_generation", + "output_cost_per_pixel": 0.0, + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "medium/1536-x-1024/gpt-image-1": { + "input_cost_per_pixel": 4.0054321e-08, + "litellm_provider": "openai", + "mode": "image_generation", + "output_cost_per_pixel": 0.0, + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "medlm-large": { + "input_cost_per_character": 5e-06, + "litellm_provider": "vertex_ai-language-models", + "max_input_tokens": 8192, + "max_output_tokens": 1024, + "max_tokens": 1024, + "mode": "chat", + "output_cost_per_character": 1.5e-05, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "supports_tool_choice": true + }, + "medlm-medium": { + "input_cost_per_character": 5e-07, + "litellm_provider": "vertex_ai-language-models", + "max_input_tokens": 32768, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_character": 1e-06, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", + "supports_tool_choice": true + }, + "meta.llama2-13b-chat-v1": { + "input_cost_per_token": 7.5e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1e-06 + }, + "meta.llama2-70b-chat-v1": { + "input_cost_per_token": 1.95e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 2.56e-06 + }, + "meta.llama3-1-405b-instruct-v1:0": { + "input_cost_per_token": 5.32e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.6e-05, + "supports_function_calling": true, + "supports_tool_choice": false + }, + "meta.llama3-1-70b-instruct-v1:0": { + "input_cost_per_token": 9.9e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 128000, + "max_output_tokens": 2048, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 9.9e-07, + "supports_function_calling": true, + "supports_tool_choice": false + }, + "meta.llama3-1-8b-instruct-v1:0": { + "input_cost_per_token": 2.2e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 128000, + "max_output_tokens": 2048, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2.2e-07, + "supports_function_calling": true, + "supports_tool_choice": false + }, + "meta.llama3-2-11b-instruct-v1:0": { + "input_cost_per_token": 3.5e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 3.5e-07, + "supports_function_calling": true, + "supports_tool_choice": false, + "supports_vision": true + }, + "meta.llama3-2-1b-instruct-v1:0": { + "input_cost_per_token": 1e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-07, + "supports_function_calling": true, + "supports_tool_choice": false + }, + "meta.llama3-2-3b-instruct-v1:0": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.5e-07, + "supports_function_calling": true, + "supports_tool_choice": false + }, + "meta.llama3-2-90b-instruct-v1:0": { + "input_cost_per_token": 2e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2e-06, + "supports_function_calling": true, + "supports_tool_choice": false, + "supports_vision": true + }, + "meta.llama3-3-70b-instruct-v1:0": { + "input_cost_per_token": 7.2e-07, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 7.2e-07, + "supports_function_calling": true, + "supports_tool_choice": false + }, + "meta.llama3-70b-instruct-v1:0": { + "input_cost_per_token": 2.65e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 3.5e-06 + }, + "meta.llama3-8b-instruct-v1:0": { + "input_cost_per_token": 3e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 6e-07 + }, + "meta.llama4-maverick-17b-instruct-v1:0": { + "input_cost_per_token": 2.4e-07, + "input_cost_per_token_batches": 1.2e-07, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 9.7e-07, + "output_cost_per_token_batches": 4.85e-07, + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text", + "code" + ], + "supports_function_calling": true, + "supports_tool_choice": false + }, + "meta.llama4-scout-17b-instruct-v1:0": { + "input_cost_per_token": 1.7e-07, + "input_cost_per_token_batches": 8.5e-08, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 6.6e-07, + "output_cost_per_token_batches": 3.3e-07, + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text", + "code" + ], + "supports_function_calling": true, + "supports_tool_choice": false + }, + "meta_llama/Llama-3.3-70B-Instruct": { + "litellm_provider": "meta_llama", + "max_input_tokens": 128000, + "max_output_tokens": 4028, + "max_tokens": 128000, + "mode": "chat", + "source": "https://llama.developer.meta.com/docs/models", + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_tool_choice": true + }, + "meta_llama/Llama-3.3-8B-Instruct": { + "litellm_provider": "meta_llama", + "max_input_tokens": 128000, + "max_output_tokens": 4028, + "max_tokens": 128000, + "mode": "chat", + "source": "https://llama.developer.meta.com/docs/models", + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_tool_choice": true + }, + "meta_llama/Llama-4-Maverick-17B-128E-Instruct-FP8": { + "litellm_provider": "meta_llama", + "max_input_tokens": 1000000, + "max_output_tokens": 4028, + "max_tokens": 128000, + "mode": "chat", + "source": "https://llama.developer.meta.com/docs/models", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_tool_choice": true + }, + "meta_llama/Llama-4-Scout-17B-16E-Instruct-FP8": { + "litellm_provider": "meta_llama", + "max_input_tokens": 10000000, + "max_output_tokens": 4028, + "max_tokens": 128000, + "mode": "chat", + "source": "https://llama.developer.meta.com/docs/models", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_tool_choice": true + }, + "mistral.mistral-7b-instruct-v0:2": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 2e-07, + "supports_tool_choice": true + }, + "mistral.mistral-large-2402-v1:0": { + "input_cost_per_token": 8e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 2.4e-05, + "supports_function_calling": true + }, + "mistral.mistral-large-2407-v1:0": { + "input_cost_per_token": 3e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 128000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 9e-06, + "supports_function_calling": true, + "supports_tool_choice": true + }, + "mistral.mistral-small-2402-v1:0": { + "input_cost_per_token": 1e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 3e-06, + "supports_function_calling": true + }, + "mistral.mixtral-8x7b-instruct-v0:1": { + "input_cost_per_token": 4.5e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 7e-07, + "supports_tool_choice": true + }, + "mistral/codestral-2405": { + "input_cost_per_token": 1e-06, + "litellm_provider": "mistral", + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 3e-06, + "supports_assistant_prefill": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "mistral/codestral-latest": { + "input_cost_per_token": 1e-06, + "litellm_provider": "mistral", + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 3e-06, + "supports_assistant_prefill": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "mistral/codestral-mamba-latest": { + "input_cost_per_token": 2.5e-07, + "litellm_provider": "mistral", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 2.5e-07, + "source": "https://mistral.ai/technology/", + "supports_assistant_prefill": true, + "supports_tool_choice": true + }, + "mistral/devstral-medium-2507": { + "input_cost_per_token": 4e-07, + "litellm_provider": "mistral", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2e-06, + "source": "https://mistral.ai/news/devstral", + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "mistral/devstral-small-2505": { + "input_cost_per_token": 1e-07, + "litellm_provider": "mistral", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 3e-07, + "source": "https://mistral.ai/news/devstral", + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "mistral/devstral-small-2507": { + "input_cost_per_token": 1e-07, + "litellm_provider": "mistral", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 3e-07, + "source": "https://mistral.ai/news/devstral", + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "mistral/magistral-medium-2506": { + "input_cost_per_token": 2e-06, + "litellm_provider": "mistral", + "max_input_tokens": 40000, + "max_output_tokens": 40000, + "max_tokens": 40000, + "mode": "chat", + "output_cost_per_token": 5e-06, + "source": "https://mistral.ai/news/magistral", + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "mistral/magistral-medium-latest": { + "input_cost_per_token": 2e-06, + "litellm_provider": "mistral", + "max_input_tokens": 40000, + "max_output_tokens": 40000, + "max_tokens": 40000, + "mode": "chat", + "output_cost_per_token": 5e-06, + "source": "https://mistral.ai/news/magistral", + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "mistral/magistral-small-2506": { + "input_cost_per_token": 5e-07, + "litellm_provider": "mistral", + "max_input_tokens": 40000, + "max_output_tokens": 40000, + "max_tokens": 40000, + "mode": "chat", + "output_cost_per_token": 1.5e-06, + "source": "https://mistral.ai/pricing#api-pricing", + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "mistral/magistral-small-latest": { + "input_cost_per_token": 5e-07, + "litellm_provider": "mistral", + "max_input_tokens": 40000, + "max_output_tokens": 40000, + "max_tokens": 40000, + "mode": "chat", + "output_cost_per_token": 1.5e-06, + "source": "https://mistral.ai/pricing#api-pricing", + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "mistral/mistral-embed": { + "input_cost_per_token": 1e-07, + "litellm_provider": "mistral", + "max_input_tokens": 8192, + "max_tokens": 8192, + "mode": "embedding" + }, + "mistral/mistral-large-2402": { + "input_cost_per_token": 4e-06, + "litellm_provider": "mistral", + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 1.2e-05, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "mistral/mistral-large-2407": { + "input_cost_per_token": 3e-06, + "litellm_provider": "mistral", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 9e-06, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "mistral/mistral-large-2411": { + "input_cost_per_token": 2e-06, + "litellm_provider": "mistral", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 6e-06, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "mistral/mistral-large-latest": { + "input_cost_per_token": 2e-06, + "litellm_provider": "mistral", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 6e-06, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "mistral/mistral-medium": { + "input_cost_per_token": 2.7e-06, + "litellm_provider": "mistral", + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 8.1e-06, + "supports_assistant_prefill": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "mistral/mistral-medium-2312": { + "input_cost_per_token": 2.7e-06, + "litellm_provider": "mistral", + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 8.1e-06, + "supports_assistant_prefill": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "mistral/mistral-medium-2505": { + "input_cost_per_token": 4e-07, + "litellm_provider": "mistral", + "max_input_tokens": 131072, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 2e-06, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "mistral/mistral-medium-latest": { + "input_cost_per_token": 4e-07, + "litellm_provider": "mistral", + "max_input_tokens": 131072, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 2e-06, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "mistral/mistral-small": { + "input_cost_per_token": 1e-07, + "litellm_provider": "mistral", + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 3e-07, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "mistral/mistral-small-latest": { + "input_cost_per_token": 1e-07, + "litellm_provider": "mistral", + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 3e-07, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "mistral/mistral-tiny": { + "input_cost_per_token": 2.5e-07, + "litellm_provider": "mistral", + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 2.5e-07, + "supports_assistant_prefill": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "mistral/open-codestral-mamba": { + "input_cost_per_token": 2.5e-07, + "litellm_provider": "mistral", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 2.5e-07, + "source": "https://mistral.ai/technology/", + "supports_assistant_prefill": true, + "supports_tool_choice": true + }, + "mistral/open-mistral-7b": { + "input_cost_per_token": 2.5e-07, + "litellm_provider": "mistral", + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 2.5e-07, + "supports_assistant_prefill": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "mistral/open-mistral-nemo": { + "input_cost_per_token": 3e-07, + "litellm_provider": "mistral", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 3e-07, + "source": "https://mistral.ai/technology/", + "supports_assistant_prefill": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "mistral/open-mistral-nemo-2407": { + "input_cost_per_token": 3e-07, + "litellm_provider": "mistral", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 3e-07, + "source": "https://mistral.ai/technology/", + "supports_assistant_prefill": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "mistral/open-mixtral-8x22b": { + "input_cost_per_token": 2e-06, + "litellm_provider": "mistral", + "max_input_tokens": 65336, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 6e-06, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "mistral/open-mixtral-8x7b": { + "input_cost_per_token": 7e-07, + "litellm_provider": "mistral", + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 7e-07, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "mistral/pixtral-12b-2409": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "mistral", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.5e-07, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "mistral/pixtral-large-2411": { + "input_cost_per_token": 2e-06, + "litellm_provider": "mistral", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 6e-06, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "mistral/pixtral-large-latest": { + "input_cost_per_token": 2e-06, + "litellm_provider": "mistral", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 6e-06, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "moonshot/kimi-k2-0711-preview": { + "cache_read_input_token_cost": 1.5e-07, + "input_cost_per_token": 6e-07, + "litellm_provider": "moonshot", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2.5e-06, + "source": "https://platform.moonshot.ai/docs/pricing/chat#generation-model-kimi-k2", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_web_search": true + }, + "moonshot/kimi-latest": { + "cache_read_input_token_cost": 1.5e-07, + "input_cost_per_token": 2e-06, + "litellm_provider": "moonshot", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 5e-06, + "source": "https://platform.moonshot.ai/docs/pricing", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "moonshot/kimi-latest-128k": { + "cache_read_input_token_cost": 1.5e-07, + "input_cost_per_token": 2e-06, + "litellm_provider": "moonshot", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 5e-06, + "source": "https://platform.moonshot.ai/docs/pricing", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "moonshot/kimi-latest-32k": { + "cache_read_input_token_cost": 1.5e-07, + "input_cost_per_token": 1e-06, + "litellm_provider": "moonshot", + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 3e-06, + "source": "https://platform.moonshot.ai/docs/pricing", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "moonshot/kimi-latest-8k": { + "cache_read_input_token_cost": 1.5e-07, + "input_cost_per_token": 2e-07, + "litellm_provider": "moonshot", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 2e-06, + "source": "https://platform.moonshot.ai/docs/pricing", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "moonshot/kimi-thinking-preview": { + "input_cost_per_token": 3e-05, + "litellm_provider": "moonshot", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 3e-05, + "source": "https://platform.moonshot.ai/docs/pricing", + "supports_vision": true + }, + "moonshot/moonshot-v1-128k": { + "input_cost_per_token": 2e-06, + "litellm_provider": "moonshot", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 5e-06, + "source": "https://platform.moonshot.ai/docs/pricing", + "supports_function_calling": true, + "supports_tool_choice": true + }, + "moonshot/moonshot-v1-128k-0430": { + "input_cost_per_token": 2e-06, + "litellm_provider": "moonshot", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 5e-06, + "source": "https://platform.moonshot.ai/docs/pricing", + "supports_function_calling": true, + "supports_tool_choice": true + }, + "moonshot/moonshot-v1-128k-vision-preview": { + "input_cost_per_token": 2e-06, + "litellm_provider": "moonshot", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 5e-06, + "source": "https://platform.moonshot.ai/docs/pricing", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "moonshot/moonshot-v1-32k": { + "input_cost_per_token": 1e-06, + "litellm_provider": "moonshot", + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 3e-06, + "source": "https://platform.moonshot.ai/docs/pricing", + "supports_function_calling": true, + "supports_tool_choice": true + }, + "moonshot/moonshot-v1-32k-0430": { + "input_cost_per_token": 1e-06, + "litellm_provider": "moonshot", + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 3e-06, + "source": "https://platform.moonshot.ai/docs/pricing", + "supports_function_calling": true, + "supports_tool_choice": true + }, + "moonshot/moonshot-v1-32k-vision-preview": { + "input_cost_per_token": 1e-06, + "litellm_provider": "moonshot", + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 3e-06, + "source": "https://platform.moonshot.ai/docs/pricing", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "moonshot/moonshot-v1-8k": { + "input_cost_per_token": 2e-07, + "litellm_provider": "moonshot", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 2e-06, + "source": "https://platform.moonshot.ai/docs/pricing", + "supports_function_calling": true, + "supports_tool_choice": true + }, + "moonshot/moonshot-v1-8k-0430": { + "input_cost_per_token": 2e-07, + "litellm_provider": "moonshot", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 2e-06, + "source": "https://platform.moonshot.ai/docs/pricing", + "supports_function_calling": true, + "supports_tool_choice": true + }, + "moonshot/moonshot-v1-8k-vision-preview": { + "input_cost_per_token": 2e-07, + "litellm_provider": "moonshot", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 2e-06, + "source": "https://platform.moonshot.ai/docs/pricing", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "moonshot/moonshot-v1-auto": { + "input_cost_per_token": 2e-06, + "litellm_provider": "moonshot", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 5e-06, + "source": "https://platform.moonshot.ai/docs/pricing", + "supports_function_calling": true, + "supports_tool_choice": true + }, + "morph/morph-v3-fast": { + "input_cost_per_token": 8e-07, + "litellm_provider": "morph", + "max_input_tokens": 16000, + "max_output_tokens": 16000, + "max_tokens": 16000, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "supports_function_calling": false, + "supports_parallel_function_calling": false, + "supports_system_messages": true, + "supports_tool_choice": false, + "supports_vision": false + }, + "morph/morph-v3-large": { + "input_cost_per_token": 9e-07, + "litellm_provider": "morph", + "max_input_tokens": 16000, + "max_output_tokens": 16000, + "max_tokens": 16000, + "mode": "chat", + "output_cost_per_token": 1.9e-06, + "supports_function_calling": false, + "supports_parallel_function_calling": false, + "supports_system_messages": true, + "supports_tool_choice": false, + "supports_vision": false + }, + "multimodalembedding": { + "input_cost_per_character": 2e-07, + "input_cost_per_image": 0.0001, + "input_cost_per_token": 8e-07, + "input_cost_per_video_per_second": 0.0005, + "input_cost_per_video_per_second_above_15s_interval": 0.002, + "input_cost_per_video_per_second_above_8s_interval": 0.001, + "litellm_provider": "vertex_ai-embedding-models", + "max_input_tokens": 2048, + "max_tokens": 2048, + "mode": "embedding", + "output_cost_per_token": 0, + "output_vector_size": 768, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models", + "supported_endpoints": [ + "/v1/embeddings" + ], + "supported_modalities": [ + "text", + "image", + "video" + ] + }, + "multimodalembedding@001": { + "input_cost_per_character": 2e-07, + "input_cost_per_image": 0.0001, + "input_cost_per_token": 8e-07, + "input_cost_per_video_per_second": 0.0005, + "input_cost_per_video_per_second_above_15s_interval": 0.002, + "input_cost_per_video_per_second_above_8s_interval": 0.001, + "litellm_provider": "vertex_ai-embedding-models", + "max_input_tokens": 2048, + "max_tokens": 2048, + "mode": "embedding", + "output_cost_per_token": 0, + "output_vector_size": 768, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models", + "supported_endpoints": [ + "/v1/embeddings" + ], + "supported_modalities": [ + "text", + "image", + "video" + ] + }, + "nscale/Qwen/QwQ-32B": { + "input_cost_per_token": 1.8e-07, + "litellm_provider": "nscale", + "mode": "chat", + "output_cost_per_token": 2e-07, + "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" + }, + "nscale/Qwen/Qwen2.5-Coder-32B-Instruct": { + "input_cost_per_token": 6e-08, + "litellm_provider": "nscale", + "mode": "chat", + "output_cost_per_token": 2e-07, + "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" + }, + "nscale/Qwen/Qwen2.5-Coder-3B-Instruct": { + "input_cost_per_token": 1e-08, + "litellm_provider": "nscale", + "mode": "chat", + "output_cost_per_token": 3e-08, + "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" + }, + "nscale/Qwen/Qwen2.5-Coder-7B-Instruct": { + "input_cost_per_token": 1e-08, + "litellm_provider": "nscale", + "mode": "chat", + "output_cost_per_token": 3e-08, + "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" + }, + "nscale/black-forest-labs/FLUX.1-schnell": { + "input_cost_per_pixel": 1.3e-09, + "litellm_provider": "nscale", + "mode": "image_generation", + "output_cost_per_pixel": 0.0, + "source": "https://docs.nscale.com/docs/inference/serverless-models/current#image-models", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "nscale/deepseek-ai/DeepSeek-R1-Distill-Llama-70B": { + "input_cost_per_token": 3.75e-07, + "litellm_provider": "nscale", + "metadata": { + "notes": "Pricing listed as $0.75/1M tokens total. Assumed 50/50 split for input/output." + }, + "mode": "chat", + "output_cost_per_token": 3.75e-07, + "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" + }, + "nscale/deepseek-ai/DeepSeek-R1-Distill-Llama-8B": { + "input_cost_per_token": 2.5e-08, + "litellm_provider": "nscale", + "metadata": { + "notes": "Pricing listed as $0.05/1M tokens total. Assumed 50/50 split for input/output." + }, + "mode": "chat", + "output_cost_per_token": 2.5e-08, + "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" + }, + "nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B": { + "input_cost_per_token": 9e-08, + "litellm_provider": "nscale", + "metadata": { + "notes": "Pricing listed as $0.18/1M tokens total. Assumed 50/50 split for input/output." + }, + "mode": "chat", + "output_cost_per_token": 9e-08, + "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" + }, + "nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B": { + "input_cost_per_token": 7e-08, + "litellm_provider": "nscale", + "metadata": { + "notes": "Pricing listed as $0.14/1M tokens total. Assumed 50/50 split for input/output." + }, + "mode": "chat", + "output_cost_per_token": 7e-08, + "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" + }, + "nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "nscale", + "metadata": { + "notes": "Pricing listed as $0.30/1M tokens total. Assumed 50/50 split for input/output." + }, + "mode": "chat", + "output_cost_per_token": 1.5e-07, + "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" + }, + "nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B": { + "input_cost_per_token": 2e-07, + "litellm_provider": "nscale", + "metadata": { + "notes": "Pricing listed as $0.40/1M tokens total. Assumed 50/50 split for input/output." + }, + "mode": "chat", + "output_cost_per_token": 2e-07, + "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" + }, + "nscale/meta-llama/Llama-3.1-8B-Instruct": { + "input_cost_per_token": 3e-08, + "litellm_provider": "nscale", + "metadata": { + "notes": "Pricing listed as $0.06/1M tokens total. Assumed 50/50 split for input/output." + }, + "mode": "chat", + "output_cost_per_token": 3e-08, + "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" + }, + "nscale/meta-llama/Llama-3.3-70B-Instruct": { + "input_cost_per_token": 2e-07, + "litellm_provider": "nscale", + "metadata": { + "notes": "Pricing listed as $0.40/1M tokens total. Assumed 50/50 split for input/output." + }, + "mode": "chat", + "output_cost_per_token": 2e-07, + "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" + }, + "nscale/meta-llama/Llama-4-Scout-17B-16E-Instruct": { + "input_cost_per_token": 9e-08, + "litellm_provider": "nscale", + "mode": "chat", + "output_cost_per_token": 2.9e-07, + "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" + }, + "nscale/mistralai/mixtral-8x22b-instruct-v0.1": { + "input_cost_per_token": 6e-07, + "litellm_provider": "nscale", + "metadata": { + "notes": "Pricing listed as $1.20/1M tokens total. Assumed 50/50 split for input/output." + }, + "mode": "chat", + "output_cost_per_token": 6e-07, + "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models" + }, + "nscale/stabilityai/stable-diffusion-xl-base-1.0": { + "input_cost_per_pixel": 3e-09, + "litellm_provider": "nscale", + "mode": "image_generation", + "output_cost_per_pixel": 0.0, + "source": "https://docs.nscale.com/docs/inference/serverless-models/current#image-models", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "o1": { + "cache_read_input_token_cost": 7.5e-06, + "input_cost_per_token": 1.5e-05, + "litellm_provider": "openai", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 6e-05, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "o1-2024-12-17": { + "cache_read_input_token_cost": 7.5e-06, + "input_cost_per_token": 1.5e-05, + "litellm_provider": "openai", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 6e-05, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "o1-mini": { + "cache_read_input_token_cost": 5.5e-07, + "input_cost_per_token": 1.1e-06, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_vision": true + }, + "o1-mini-2024-09-12": { + "cache_read_input_token_cost": 1.5e-06, + "input_cost_per_token": 3e-06, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 1.2e-05, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_vision": true + }, + "o1-preview": { + "cache_read_input_token_cost": 7.5e-06, + "input_cost_per_token": 1.5e-05, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 6e-05, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_vision": true + }, + "o1-preview-2024-09-12": { + "cache_read_input_token_cost": 7.5e-06, + "input_cost_per_token": 1.5e-05, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 6e-05, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_vision": true + }, + "o1-pro": { + "input_cost_per_token": 0.00015, + "input_cost_per_token_batches": 7.5e-05, + "litellm_provider": "openai", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "responses", + "output_cost_per_token": 0.0006, + "output_cost_per_token_batches": 0.0003, + "supported_endpoints": [ + "/v1/responses", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": false, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "o1-pro-2025-03-19": { + "input_cost_per_token": 0.00015, + "input_cost_per_token_batches": 7.5e-05, + "litellm_provider": "openai", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "responses", + "output_cost_per_token": 0.0006, + "output_cost_per_token_batches": 0.0003, + "supported_endpoints": [ + "/v1/responses", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": false, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "o3": { "cache_read_input_token_cost": 5e-07, - "cache_creation_input_token_cost": 0.0, - "litellm_provider": "vercel_ai_gateway", - "mode": "chat" - }, - "oci/meta.llama-4-maverick-17b-128e-instruct-fp8": { - "max_tokens": 512000, - "max_input_tokens": 512000, - "max_output_tokens": 4000, - "input_cost_per_token": 7.2e-07, - "output_cost_per_token": 7.2e-07, - "litellm_provider": "oci", + "input_cost_per_token": 2e-06, + "litellm_provider": "openai", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, "mode": "chat", + "output_cost_per_token": 8e-06, + "supported_endpoints": [ + "/v1/responses", + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], "supports_function_calling": true, - "supports_response_schema": false, - "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing" + "supports_parallel_function_calling": false, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true }, - "oci/meta.llama-4-scout-17b-16e-instruct": { - "max_tokens": 192000, - "max_input_tokens": 192000, - "max_output_tokens": 4000, - "input_cost_per_token": 7.2e-07, - "output_cost_per_token": 7.2e-07, - "litellm_provider": "oci", + "o3-2025-04-16": { + "cache_read_input_token_cost": 5e-07, + "input_cost_per_token": 2e-06, + "litellm_provider": "openai", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, "mode": "chat", + "output_cost_per_token": 8e-06, + "supported_endpoints": [ + "/v1/responses", + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], "supports_function_calling": true, - "supports_response_schema": false, - "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing" + "supports_parallel_function_calling": false, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true }, - "oci/meta.llama-3.3-70b-instruct": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 4000, - "input_cost_per_token": 7.2e-07, - "output_cost_per_token": 7.2e-07, - "litellm_provider": "oci", - "mode": "chat", + "o3-deep-research": { + "cache_read_input_token_cost": 2.5e-06, + "input_cost_per_token": 1e-05, + "input_cost_per_token_batches": 5e-06, + "litellm_provider": "openai", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "responses", + "output_cost_per_token": 4e-05, + "output_cost_per_token_batches": 2e-05, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], "supports_function_calling": true, - "supports_response_schema": false, - "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing" + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true }, - "oci/meta.llama-3.2-90b-vision-instruct": { - "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 4000, - "input_cost_per_token": 2.0e-06, - "output_cost_per_token": 2.0e-06, - "litellm_provider": "oci", - "mode": "chat", + "o3-deep-research-2025-06-26": { + "cache_read_input_token_cost": 2.5e-06, + "input_cost_per_token": 1e-05, + "input_cost_per_token_batches": 5e-06, + "litellm_provider": "openai", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "responses", + "output_cost_per_token": 4e-05, + "output_cost_per_token_batches": 2e-05, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], "supports_function_calling": true, - "supports_response_schema": false, - "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing" + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "o3-mini": { + "cache_read_input_token_cost": 5.5e-07, + "input_cost_per_token": 1.1e-06, + "litellm_provider": "openai", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "supports_function_calling": true, + "supports_parallel_function_calling": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "o3-mini-2025-01-31": { + "cache_read_input_token_cost": 5.5e-07, + "input_cost_per_token": 1.1e-06, + "litellm_provider": "openai", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "supports_function_calling": true, + "supports_parallel_function_calling": false, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "o3-pro": { + "input_cost_per_token": 2e-05, + "input_cost_per_token_batches": 1e-05, + "litellm_provider": "openai", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "responses", + "output_cost_per_token": 8e-05, + "output_cost_per_token_batches": 4e-05, + "supported_endpoints": [ + "/v1/responses", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": false, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "o3-pro-2025-06-10": { + "input_cost_per_token": 2e-05, + "input_cost_per_token_batches": 1e-05, + "litellm_provider": "openai", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "responses", + "output_cost_per_token": 8e-05, + "output_cost_per_token_batches": 4e-05, + "supported_endpoints": [ + "/v1/responses", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": false, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "o4-mini": { + "cache_read_input_token_cost": 2.75e-07, + "input_cost_per_token": 1.1e-06, + "litellm_provider": "openai", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "supports_function_calling": true, + "supports_parallel_function_calling": false, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "o4-mini-2025-04-16": { + "cache_read_input_token_cost": 2.75e-07, + "input_cost_per_token": 1.1e-06, + "litellm_provider": "openai", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "supports_function_calling": true, + "supports_parallel_function_calling": false, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "o4-mini-deep-research": { + "cache_read_input_token_cost": 5e-07, + "input_cost_per_token": 2e-06, + "input_cost_per_token_batches": 1e-06, + "litellm_provider": "openai", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "responses", + "output_cost_per_token": 8e-06, + "output_cost_per_token_batches": 4e-06, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "o4-mini-deep-research-2025-06-26": { + "cache_read_input_token_cost": 5e-07, + "input_cost_per_token": 2e-06, + "input_cost_per_token_batches": 1e-06, + "litellm_provider": "openai", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "responses", + "output_cost_per_token": 8e-06, + "output_cost_per_token_batches": 4e-06, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true }, "oci/meta.llama-3.1-405b-instruct": { - "max_tokens": 128000, + "input_cost_per_token": 1.068e-05, + "litellm_provider": "oci", "max_input_tokens": 128000, "max_output_tokens": 4000, - "input_cost_per_token": 1.068e-05, - "output_cost_per_token": 1.068e-05, - "litellm_provider": "oci", - "mode": "chat", - "supports_function_calling": true, - "supports_response_schema": false, - "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing" - }, - - "oci/xai.grok-4": { "max_tokens": 128000, - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "input_cost_per_token": 3.0e-06, - "output_cost_per_token": 1.5e-07, - "litellm_provider": "oci", "mode": "chat", + "output_cost_per_token": 1.068e-05, + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, - "supports_response_schema": false, - "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing" + "supports_response_schema": false + }, + "oci/meta.llama-3.2-90b-vision-instruct": { + "input_cost_per_token": 2e-06, + "litellm_provider": "oci", + "max_input_tokens": 128000, + "max_output_tokens": 4000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2e-06, + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", + "supports_function_calling": true, + "supports_response_schema": false + }, + "oci/meta.llama-3.3-70b-instruct": { + "input_cost_per_token": 7.2e-07, + "litellm_provider": "oci", + "max_input_tokens": 128000, + "max_output_tokens": 4000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 7.2e-07, + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", + "supports_function_calling": true, + "supports_response_schema": false + }, + "oci/meta.llama-4-maverick-17b-128e-instruct-fp8": { + "input_cost_per_token": 7.2e-07, + "litellm_provider": "oci", + "max_input_tokens": 512000, + "max_output_tokens": 4000, + "max_tokens": 512000, + "mode": "chat", + "output_cost_per_token": 7.2e-07, + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", + "supports_function_calling": true, + "supports_response_schema": false + }, + "oci/meta.llama-4-scout-17b-16e-instruct": { + "input_cost_per_token": 7.2e-07, + "litellm_provider": "oci", + "max_input_tokens": 192000, + "max_output_tokens": 4000, + "max_tokens": 192000, + "mode": "chat", + "output_cost_per_token": 7.2e-07, + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", + "supports_function_calling": true, + "supports_response_schema": false }, "oci/xai.grok-3": { - "max_tokens": 131072, + "input_cost_per_token": 3e-06, + "litellm_provider": "oci", "max_input_tokens": 131072, "max_output_tokens": 131072, - "input_cost_per_token": 3.0e-06, + "max_tokens": 131072, + "mode": "chat", "output_cost_per_token": 1.5e-07, - "litellm_provider": "oci", - "mode": "chat", + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, - "supports_response_schema": false, - "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing" - }, - "oci/xai.grok-3-mini": { - "max_tokens": 131072, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "input_cost_per_token": 3.0e-07, - "output_cost_per_token": 5.0e-07, - "litellm_provider": "oci", - "mode": "chat", - "supports_function_calling": true, - "supports_response_schema": false, - "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing" + "supports_response_schema": false }, "oci/xai.grok-3-fast": { - "max_tokens": 131072, + "input_cost_per_token": 5e-06, + "litellm_provider": "oci", "max_input_tokens": 131072, "max_output_tokens": 131072, - "input_cost_per_token": 5.0e-06, - "output_cost_per_token": 2.5e-05, - "litellm_provider": "oci", + "max_tokens": 131072, "mode": "chat", + "output_cost_per_token": 2.5e-05, + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", "supports_function_calling": true, - "supports_response_schema": false, - "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing" + "supports_response_schema": false + }, + "oci/xai.grok-3-mini": { + "input_cost_per_token": 3e-07, + "litellm_provider": "oci", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 5e-07, + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", + "supports_function_calling": true, + "supports_response_schema": false }, "oci/xai.grok-3-mini-fast": { - "max_tokens": 131072, + "input_cost_per_token": 6e-07, + "litellm_provider": "oci", "max_input_tokens": 131072, "max_output_tokens": 131072, - "input_cost_per_token": 6.0e-07, - "output_cost_per_token": 4.0e-06, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4e-06, + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", + "supports_function_calling": true, + "supports_response_schema": false + }, + "oci/xai.grok-4": { + "input_cost_per_token": 3e-06, "litellm_provider": "oci", - "mode": "chat", - "supports_function_calling": true, - "supports_response_schema": false, - "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing" - }, - "aiml/flux/kontext-pro/text-to-image":{ - "output_cost_per_image": 0.042, - "litellm_provider": "aiml", - "mode": "image_generation", - "supported_endpoints": [ - "/v1/images/generations" - ], - "source": "https://docs.aimlapi.com/", - "metadata": { - "notes": "Flux Pro v1.1 - Enhanced version with improved capabilities and 6x faster inference speed" - } - - }, - "aiml/flux/kontext-max/text-to-image": { - "output_cost_per_image": 0.084, - "litellm_provider": "aiml", - "mode": "image_generation", - "supported_endpoints": [ - "/v1/images/generations" - ], - "source": "https://docs.aimlapi.com/", - "metadata": { - "notes": "Flux Pro v1.1 - Enhanced version with improved capabilities and 6x faster inference speed" - } - }, - "aiml/flux-pro/v1.1-ultra": { - "output_cost_per_image": 0.063, - "litellm_provider": "aiml", - "mode": "image_generation", - "supported_endpoints": [ - "/v1/images/generations" - ] - }, - "aiml/flux-pro/v1.1": { - "output_cost_per_image": 0.042, - "litellm_provider": "aiml", - "mode": "image_generation", - "supported_endpoints": [ - "/v1/images/generations" - ] - }, - "aiml/flux-realism": { - "output_cost_per_image": 0.037, - "litellm_provider": "aiml", - "mode": "image_generation", - "supported_endpoints": [ - "/v1/images/generations" - ], - "source": "https://docs.aimlapi.com/", - "metadata": { - "notes": "Flux Pro - Professional-grade image generation model" - } - }, - "aiml/flux/schnell": { - "output_cost_per_image": 0.003, - "litellm_provider": "aiml", - "mode": "image_generation", - "supported_endpoints": [ - "/v1/images/generations" - ], - "source": "https://docs.aimlapi.com/", - "metadata": { - "notes": "Flux Schnell - Fast generation model optimized for speed" - } - }, - "aiml/flux/dev": { - "output_cost_per_image": 0.026, - "litellm_provider": "aiml", - "mode": "image_generation", - "supported_endpoints": [ - "/v1/images/generations" - ], - "source": "https://docs.aimlapi.com/", - "metadata": { - "notes": "Flux Dev - Development version optimized for experimentation" - } - }, - "aiml/flux-pro": { - "output_cost_per_image": 0.053, - "litellm_provider": "aiml", - "mode": "image_generation", - "supported_endpoints": [ - "/v1/images/generations" - ], - "source": "https://docs.aimlapi.com/", - "metadata": { - "notes": "Flux Dev - Development version optimized for experimentation" - } - }, - "aiml/dall-e-3": { - "output_cost_per_image": 0.042, - "litellm_provider": "aiml", - "mode": "image_generation", - "supported_endpoints": [ - "/v1/images/generations" - ], - "source": "https://docs.aimlapi.com/", - "metadata": { - "notes": "DALL-E 3 via AI/ML API - High-quality text-to-image generation" - } - }, - "aiml/dall-e-2": { - "output_cost_per_image": 0.021, - "litellm_provider": "aiml", - "mode": "image_generation", - "supported_endpoints": [ - "/v1/images/generations" - ], - "source": "https://docs.aimlapi.com/", - "metadata": { - "notes": "DALL-E 2 via AI/ML API - Reliable text-to-image generation" - } - }, - "doubao-embedding-large": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "output_vector_size": 2048, - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "volcengine", - "mode": "embedding", - "metadata": { - "notes": "Volcengine Doubao embedding model - large version with 2048 dimensions" - } - }, - "doubao-embedding-large-text-250515": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "output_vector_size": 2048, - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "volcengine", - "mode": "embedding", - "metadata": { - "notes": "Volcengine Doubao embedding model - text-250515 version with 2048 dimensions" - } - }, - "doubao-embedding-large-text-240915": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "output_vector_size": 4096, - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "volcengine", - "mode": "embedding", - "metadata": { - "notes": "Volcengine Doubao embedding model - text-240915 version with 4096 dimensions" - } - }, - "doubao-embedding": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "output_vector_size": 2560, - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "volcengine", - "mode": "embedding", - "metadata": { - "notes": "Volcengine Doubao embedding model - standard version with 2560 dimensions" - } - }, - "doubao-embedding-text-240715": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "output_vector_size": 2560, - "input_cost_per_token": 0.0, - "output_cost_per_token": 0.0, - "litellm_provider": "volcengine", - "mode": "embedding", - "metadata": { - "notes": "Volcengine Doubao embedding model - text-240715 version with 2560 dimensions" - } - }, - "ovhcloud/Qwen2.5-VL-72B-Instruct": { - "max_tokens": 32000, - "max_input_tokens": 32000, - "max_output_tokens": 32000, - "input_cost_per_token": 9.1e-07, - "output_cost_per_token": 9.1e-07, - "litellm_provider": "ovhcloud", - "mode": "chat", - "supports_function_calling": false, - "supports_response_schema": true, - "supports_tool_choice": false, - "supports_vision": true, - "source": "https://endpoints.ai.cloud.ovh.net/models/qwen2-5-vl-72b-instruct" - }, - "ovhcloud/llava-v1.6-mistral-7b-hf": { - "max_tokens": 32000, - "max_input_tokens": 32000, - "max_output_tokens": 32000, - "input_cost_per_token": 2.9e-07, - "output_cost_per_token": 2.9e-07, - "litellm_provider": "ovhcloud", - "mode": "chat", - "supports_function_calling": false, - "supports_response_schema": true, - "supports_tool_choice": false, - "supports_vision": true, - "source": "https://endpoints.ai.cloud.ovh.net/models/llava-next-mistral-7b" - }, - "ovhcloud/gpt-oss-120b": { - "max_tokens": 131000, - "max_input_tokens": 131000, - "max_output_tokens": 131000, - "input_cost_per_token": 8e-08, - "output_cost_per_token": 4e-07, - "litellm_provider": "ovhcloud", - "mode": "chat", - "supports_function_calling": false, - "supports_response_schema": true, - "supports_tool_choice": false, - "supports_reasoning": true, - "source": "https://endpoints.ai.cloud.ovh.net/models/gpt-oss-120b" - }, - "ovhcloud/Meta-Llama-3_3-70B-Instruct": { - "max_tokens": 131000, - "max_input_tokens": 131000, - "max_output_tokens": 131000, - "input_cost_per_token": 6.7e-07, - "output_cost_per_token": 6.7e-07, - "litellm_provider": "ovhcloud", - "mode": "chat", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "source": "https://endpoints.ai.cloud.ovh.net/models/meta-llama-3-3-70b-instruct" - }, - "ovhcloud/Qwen2.5-Coder-32B-Instruct": { - "max_tokens": 32000, - "max_input_tokens": 32000, - "max_output_tokens": 32000, - "input_cost_per_token": 8.7e-07, - "output_cost_per_token": 8.7e-07, - "litellm_provider": "ovhcloud", - "mode": "chat", - "supports_function_calling": false, - "supports_response_schema": true, - "supports_tool_choice": false, - "source": "https://endpoints.ai.cloud.ovh.net/models/qwen2-5-coder-32b-instruct" - }, - "ovhcloud/Mixtral-8x7B-Instruct-v0.1": { - "max_tokens": 32000, - "max_input_tokens": 32000, - "max_output_tokens": 32000, - "input_cost_per_token": 6.3e-07, - "output_cost_per_token": 6.3e-07, - "litellm_provider": "ovhcloud", - "mode": "chat", - "supports_function_calling": false, - "supports_response_schema": true, - "supports_tool_choice": false, - "source": "https://endpoints.ai.cloud.ovh.net/models/mixtral-8x7b-instruct-v0-1" - }, - "ovhcloud/Meta-Llama-3_1-70B-Instruct": { - "max_tokens": 131000, - "max_input_tokens": 131000, - "max_output_tokens": 131000, - "input_cost_per_token": 6.7e-07, - "output_cost_per_token": 6.7e-07, - "litellm_provider": "ovhcloud", - "mode": "chat", - "supports_function_calling": false, - "supports_response_schema": false, - "supports_tool_choice": false, - "source": "https://endpoints.ai.cloud.ovh.net/models/meta-llama-3-1-70b-instruct" - }, - "ovhcloud/Mistral-Small-3.2-24B-Instruct-2506": { - "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, - "input_cost_per_token": 9e-08, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.5e-07, + "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing", + "supports_function_calling": true, + "supports_response_schema": false + }, + "ollama/codegeex4": { + "input_cost_per_token": 0.0, + "litellm_provider": "ollama", + "max_input_tokens": 32768, + "max_output_tokens": 8192, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 0.0, + "supports_function_calling": false + }, + "ollama/codegemma": { + "input_cost_per_token": 0.0, + "litellm_provider": "ollama", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "completion", + "output_cost_per_token": 0.0 + }, + "ollama/codellama": { + "input_cost_per_token": 0.0, + "litellm_provider": "ollama", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "completion", + "output_cost_per_token": 0.0 + }, + "ollama/deepseek-coder-v2-base": { + "input_cost_per_token": 0.0, + "litellm_provider": "ollama", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "completion", + "output_cost_per_token": 0.0, + "supports_function_calling": true + }, + "ollama/deepseek-coder-v2-instruct": { + "input_cost_per_token": 0.0, + "litellm_provider": "ollama", + "max_input_tokens": 32768, + "max_output_tokens": 8192, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 0.0, + "supports_function_calling": true + }, + "ollama/deepseek-coder-v2-lite-base": { + "input_cost_per_token": 0.0, + "litellm_provider": "ollama", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "completion", + "output_cost_per_token": 0.0, + "supports_function_calling": true + }, + "ollama/deepseek-coder-v2-lite-instruct": { + "input_cost_per_token": 0.0, + "litellm_provider": "ollama", + "max_input_tokens": 32768, + "max_output_tokens": 8192, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 0.0, + "supports_function_calling": true + }, + "ollama/internlm2_5-20b-chat": { + "input_cost_per_token": 0.0, + "litellm_provider": "ollama", + "max_input_tokens": 32768, + "max_output_tokens": 8192, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 0.0, + "supports_function_calling": true + }, + "ollama/llama2": { + "input_cost_per_token": 0.0, + "litellm_provider": "ollama", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.0 + }, + "ollama/llama2-uncensored": { + "input_cost_per_token": 0.0, + "litellm_provider": "ollama", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "completion", + "output_cost_per_token": 0.0 + }, + "ollama/llama2:13b": { + "input_cost_per_token": 0.0, + "litellm_provider": "ollama", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.0 + }, + "ollama/llama2:70b": { + "input_cost_per_token": 0.0, + "litellm_provider": "ollama", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.0 + }, + "ollama/llama2:7b": { + "input_cost_per_token": 0.0, + "litellm_provider": "ollama", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.0 + }, + "ollama/llama3": { + "input_cost_per_token": 0.0, + "litellm_provider": "ollama", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.0 + }, + "ollama/llama3.1": { + "input_cost_per_token": 0.0, + "litellm_provider": "ollama", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 0.0, + "supports_function_calling": true + }, + "ollama/llama3:70b": { + "input_cost_per_token": 0.0, + "litellm_provider": "ollama", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.0 + }, + "ollama/llama3:8b": { + "input_cost_per_token": 0.0, + "litellm_provider": "ollama", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.0 + }, + "ollama/mistral": { + "input_cost_per_token": 0.0, + "litellm_provider": "ollama", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "completion", + "output_cost_per_token": 0.0, + "supports_function_calling": true + }, + "ollama/mistral-7B-Instruct-v0.1": { + "input_cost_per_token": 0.0, + "litellm_provider": "ollama", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.0, + "supports_function_calling": true + }, + "ollama/mistral-7B-Instruct-v0.2": { + "input_cost_per_token": 0.0, + "litellm_provider": "ollama", + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 0.0, + "supports_function_calling": true + }, + "ollama/mistral-large-instruct-2407": { + "input_cost_per_token": 0.0, + "litellm_provider": "ollama", + "max_input_tokens": 65536, + "max_output_tokens": 8192, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 0.0, + "supports_function_calling": true + }, + "ollama/mixtral-8x22B-Instruct-v0.1": { + "input_cost_per_token": 0.0, + "litellm_provider": "ollama", + "max_input_tokens": 65536, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 0.0, + "supports_function_calling": true + }, + "ollama/mixtral-8x7B-Instruct-v0.1": { + "input_cost_per_token": 0.0, + "litellm_provider": "ollama", + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 0.0, + "supports_function_calling": true + }, + "ollama/orca-mini": { + "input_cost_per_token": 0.0, + "litellm_provider": "ollama", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "completion", + "output_cost_per_token": 0.0 + }, + "ollama/vicuna": { + "input_cost_per_token": 0.0, + "litellm_provider": "ollama", + "max_input_tokens": 2048, + "max_output_tokens": 2048, + "max_tokens": 2048, + "mode": "completion", + "output_cost_per_token": 0.0 + }, + "omni-moderation-2024-09-26": { + "input_cost_per_token": 0.0, + "litellm_provider": "openai", + "max_input_tokens": 32768, + "max_output_tokens": 0, + "max_tokens": 32768, + "mode": "moderation", + "output_cost_per_token": 0.0 + }, + "omni-moderation-latest": { + "input_cost_per_token": 0.0, + "litellm_provider": "openai", + "max_input_tokens": 32768, + "max_output_tokens": 0, + "max_tokens": 32768, + "mode": "moderation", + "output_cost_per_token": 0.0 + }, + "omni-moderation-latest-intents": { + "input_cost_per_token": 0.0, + "litellm_provider": "openai", + "max_input_tokens": 32768, + "max_output_tokens": 0, + "max_tokens": 32768, + "mode": "moderation", + "output_cost_per_token": 0.0 + }, + "openai.gpt-oss-120b-1:0": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 6e-07, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "openai.gpt-oss-20b-1:0": { + "input_cost_per_token": 7e-08, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 3e-07, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "openrouter/anthropic/claude-2": { + "input_cost_per_token": 1.102e-05, + "litellm_provider": "openrouter", + "max_output_tokens": 8191, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 3.268e-05, + "supports_tool_choice": true + }, + "openrouter/anthropic/claude-3-5-haiku": { + "input_cost_per_token": 1e-06, + "litellm_provider": "openrouter", + "max_tokens": 200000, + "mode": "chat", + "output_cost_per_token": 5e-06, + "supports_function_calling": true, + "supports_tool_choice": true + }, + "openrouter/anthropic/claude-3-5-haiku-20241022": { + "input_cost_per_token": 1e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 5e-06, + "supports_function_calling": true, + "supports_tool_choice": true, + "tool_use_system_prompt_tokens": 264 + }, + "openrouter/anthropic/claude-3-haiku": { + "input_cost_per_image": 0.0004, + "input_cost_per_token": 2.5e-07, + "litellm_provider": "openrouter", + "max_tokens": 200000, + "mode": "chat", + "output_cost_per_token": 1.25e-06, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "openrouter/anthropic/claude-3-haiku-20240307": { + "input_cost_per_token": 2.5e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.25e-06, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 264 + }, + "openrouter/anthropic/claude-3-opus": { + "input_cost_per_token": 1.5e-05, + "litellm_provider": "openrouter", + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 7.5e-05, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 395 + }, + "openrouter/anthropic/claude-3-sonnet": { + "input_cost_per_image": 0.0048, + "input_cost_per_token": 3e-06, + "litellm_provider": "openrouter", + "max_tokens": 200000, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "openrouter/anthropic/claude-3.5-sonnet": { + "input_cost_per_token": 3e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159 + }, + "openrouter/anthropic/claude-3.5-sonnet:beta": { + "input_cost_per_token": 3e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159 + }, + "openrouter/anthropic/claude-3.7-sonnet": { + "input_cost_per_image": 0.0048, + "input_cost_per_token": 3e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 200000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159 + }, + "openrouter/anthropic/claude-3.7-sonnet:beta": { + "input_cost_per_image": 0.0048, + "input_cost_per_token": 3e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 200000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159 + }, + "openrouter/anthropic/claude-instant-v1": { + "input_cost_per_token": 1.63e-06, + "litellm_provider": "openrouter", + "max_output_tokens": 8191, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 5.51e-06, + "supports_tool_choice": true + }, + "openrouter/anthropic/claude-opus-4": { + "input_cost_per_image": 0.0048, + "input_cost_per_token": 1.5e-05, + "litellm_provider": "openrouter", + "max_input_tokens": 200000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 7.5e-05, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159 + }, + "openrouter/anthropic/claude-opus-4.1": { + "input_cost_per_image": 0.0048, + "input_cost_per_token": 1.5e-05, + "litellm_provider": "openrouter", + "max_input_tokens": 200000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 7.5e-05, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159 + }, + "openrouter/anthropic/claude-sonnet-4": { + "input_cost_per_image": 0.0048, + "input_cost_per_token": 3e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159 + }, + "openrouter/bytedance/ui-tars-1.5-7b": { + "input_cost_per_token": 1e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 2048, + "max_tokens": 2048, + "mode": "chat", + "output_cost_per_token": 2e-07, + "source": "https://openrouter.ai/api/v1/models/bytedance/ui-tars-1.5-7b", + "supports_tool_choice": true + }, + "openrouter/cognitivecomputations/dolphin-mixtral-8x7b": { + "input_cost_per_token": 5e-07, + "litellm_provider": "openrouter", + "max_tokens": 32769, + "mode": "chat", + "output_cost_per_token": 5e-07, + "supports_tool_choice": true + }, + "openrouter/cohere/command-r-plus": { + "input_cost_per_token": 3e-06, + "litellm_provider": "openrouter", + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "supports_tool_choice": true + }, + "openrouter/databricks/dbrx-instruct": { + "input_cost_per_token": 6e-07, + "litellm_provider": "openrouter", + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 6e-07, + "supports_tool_choice": true + }, + "openrouter/deepseek/deepseek-chat": { + "input_cost_per_token": 1.4e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 65536, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", "output_cost_per_token": 2.8e-07, + "supports_prompt_caching": true, + "supports_tool_choice": true + }, + "openrouter/deepseek/deepseek-chat-v3-0324": { + "input_cost_per_token": 1.4e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 65536, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 2.8e-07, + "supports_prompt_caching": true, + "supports_tool_choice": true + }, + "openrouter/deepseek/deepseek-chat-v3.1": { + "input_cost_per_token": 2e-07, + "input_cost_per_token_cache_hit": 2e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 163840, + "max_output_tokens": 163840, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 8e-07, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "openrouter/deepseek/deepseek-coder": { + "input_cost_per_token": 1.4e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 66000, + "max_output_tokens": 4096, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 2.8e-07, + "supports_prompt_caching": true, + "supports_tool_choice": true + }, + "openrouter/deepseek/deepseek-r1": { + "input_cost_per_token": 5.5e-07, + "input_cost_per_token_cache_hit": 1.4e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 65336, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 2.19e-06, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "openrouter/deepseek/deepseek-r1-0528": { + "input_cost_per_token": 5e-07, + "input_cost_per_token_cache_hit": 1.4e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 65336, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 2.15e-06, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "openrouter/fireworks/firellava-13b": { + "input_cost_per_token": 2e-07, + "litellm_provider": "openrouter", + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 2e-07, + "supports_tool_choice": true + }, + "openrouter/google/gemini-2.0-flash-001": { + "input_cost_per_audio_token": 7e-07, + "input_cost_per_token": 1e-07, + "litellm_provider": "openrouter", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_token": 4e-07, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "openrouter/google/gemini-2.5-flash": { + "input_cost_per_audio_token": 7e-07, + "input_cost_per_token": 3e-07, + "litellm_provider": "openrouter", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_token": 2.5e-06, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "openrouter/google/gemini-2.5-pro": { + "input_cost_per_audio_token": 7e-07, + "input_cost_per_token": 1.25e-06, + "litellm_provider": "openrouter", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_pdf_size_mb": 30, + "max_tokens": 8192, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_token": 1e-05, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "openrouter/google/gemini-pro-1.5": { + "input_cost_per_image": 0.00265, + "input_cost_per_token": 2.5e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 7.5e-06, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "openrouter/google/gemini-pro-vision": { + "input_cost_per_image": 0.0025, + "input_cost_per_token": 1.25e-07, + "litellm_provider": "openrouter", + "max_tokens": 45875, + "mode": "chat", + "output_cost_per_token": 3.75e-07, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "openrouter/google/palm-2-chat-bison": { + "input_cost_per_token": 5e-07, + "litellm_provider": "openrouter", + "max_tokens": 25804, + "mode": "chat", + "output_cost_per_token": 5e-07, + "supports_tool_choice": true + }, + "openrouter/google/palm-2-codechat-bison": { + "input_cost_per_token": 5e-07, + "litellm_provider": "openrouter", + "max_tokens": 20070, + "mode": "chat", + "output_cost_per_token": 5e-07, + "supports_tool_choice": true + }, + "openrouter/gryphe/mythomax-l2-13b": { + "input_cost_per_token": 1.875e-06, + "litellm_provider": "openrouter", + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.875e-06, + "supports_tool_choice": true + }, + "openrouter/jondurbin/airoboros-l2-70b-2.1": { + "input_cost_per_token": 1.3875e-05, + "litellm_provider": "openrouter", + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.3875e-05, + "supports_tool_choice": true + }, + "openrouter/mancer/weaver": { + "input_cost_per_token": 5.625e-06, + "litellm_provider": "openrouter", + "max_tokens": 8000, + "mode": "chat", + "output_cost_per_token": 5.625e-06, + "supports_tool_choice": true + }, + "openrouter/meta-llama/codellama-34b-instruct": { + "input_cost_per_token": 5e-07, + "litellm_provider": "openrouter", + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 5e-07, + "supports_tool_choice": true + }, + "openrouter/meta-llama/llama-2-13b-chat": { + "input_cost_per_token": 2e-07, + "litellm_provider": "openrouter", + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 2e-07, + "supports_tool_choice": true + }, + "openrouter/meta-llama/llama-2-70b-chat": { + "input_cost_per_token": 1.5e-06, + "litellm_provider": "openrouter", + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.5e-06, + "supports_tool_choice": true + }, + "openrouter/meta-llama/llama-3-70b-instruct": { + "input_cost_per_token": 5.9e-07, + "litellm_provider": "openrouter", + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 7.9e-07, + "supports_tool_choice": true + }, + "openrouter/meta-llama/llama-3-70b-instruct:nitro": { + "input_cost_per_token": 9e-07, + "litellm_provider": "openrouter", + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 9e-07, + "supports_tool_choice": true + }, + "openrouter/meta-llama/llama-3-8b-instruct:extended": { + "input_cost_per_token": 2.25e-07, + "litellm_provider": "openrouter", + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 2.25e-06, + "supports_tool_choice": true + }, + "openrouter/meta-llama/llama-3-8b-instruct:free": { + "input_cost_per_token": 0.0, + "litellm_provider": "openrouter", + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.0, + "supports_tool_choice": true + }, + "openrouter/microsoft/wizardlm-2-8x22b:nitro": { + "input_cost_per_token": 1e-06, + "litellm_provider": "openrouter", + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 1e-06, + "supports_tool_choice": true + }, + "openrouter/mistralai/mistral-7b-instruct": { + "input_cost_per_token": 1.3e-07, + "litellm_provider": "openrouter", + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.3e-07, + "supports_tool_choice": true + }, + "openrouter/mistralai/mistral-7b-instruct:free": { + "input_cost_per_token": 0.0, + "litellm_provider": "openrouter", + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.0, + "supports_tool_choice": true + }, + "openrouter/mistralai/mistral-large": { + "input_cost_per_token": 8e-06, + "litellm_provider": "openrouter", + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 2.4e-05, + "supports_tool_choice": true + }, + "openrouter/mistralai/mistral-small-3.1-24b-instruct": { + "input_cost_per_token": 1e-07, + "litellm_provider": "openrouter", + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 3e-07, + "supports_tool_choice": true + }, + "openrouter/mistralai/mistral-small-3.2-24b-instruct": { + "input_cost_per_token": 1e-07, + "litellm_provider": "openrouter", + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 3e-07, + "supports_tool_choice": true + }, + "openrouter/mistralai/mixtral-8x22b-instruct": { + "input_cost_per_token": 6.5e-07, + "litellm_provider": "openrouter", + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 6.5e-07, + "supports_tool_choice": true + }, + "openrouter/nousresearch/nous-hermes-llama2-13b": { + "input_cost_per_token": 2e-07, + "litellm_provider": "openrouter", + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 2e-07, + "supports_tool_choice": true + }, + "openrouter/openai/gpt-3.5-turbo": { + "input_cost_per_token": 1.5e-06, + "litellm_provider": "openrouter", + "max_tokens": 4095, + "mode": "chat", + "output_cost_per_token": 2e-06, + "supports_tool_choice": true + }, + "openrouter/openai/gpt-3.5-turbo-16k": { + "input_cost_per_token": 3e-06, + "litellm_provider": "openrouter", + "max_tokens": 16383, + "mode": "chat", + "output_cost_per_token": 4e-06, + "supports_tool_choice": true + }, + "openrouter/openai/gpt-4": { + "input_cost_per_token": 3e-05, + "litellm_provider": "openrouter", + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 6e-05, + "supports_tool_choice": true + }, + "openrouter/openai/gpt-4-vision-preview": { + "input_cost_per_image": 0.01445, + "input_cost_per_token": 1e-05, + "litellm_provider": "openrouter", + "max_tokens": 130000, + "mode": "chat", + "output_cost_per_token": 3e-05, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "openrouter/openai/gpt-4.1": { + "cache_read_input_token_cost": 5e-07, + "input_cost_per_token": 2e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 8e-06, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "openrouter/openai/gpt-4.1-2025-04-14": { + "cache_read_input_token_cost": 5e-07, + "input_cost_per_token": 2e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 8e-06, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "openrouter/openai/gpt-4.1-mini": { + "cache_read_input_token_cost": 1e-07, + "input_cost_per_token": 4e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 1.6e-06, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "openrouter/openai/gpt-4.1-mini-2025-04-14": { + "cache_read_input_token_cost": 1e-07, + "input_cost_per_token": 4e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 1.6e-06, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "openrouter/openai/gpt-4.1-nano": { + "cache_read_input_token_cost": 2.5e-08, + "input_cost_per_token": 1e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 4e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "openrouter/openai/gpt-4.1-nano-2025-04-14": { + "cache_read_input_token_cost": 2.5e-08, + "input_cost_per_token": 1e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 4e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "openrouter/openai/gpt-4o": { + "input_cost_per_token": 2.5e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1e-05, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "openrouter/openai/gpt-4o-2024-05-13": { + "input_cost_per_token": 5e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "openrouter/openai/gpt-5-chat": { + "cache_read_input_token_cost": 1.25e-07, + "input_cost_per_token": 1.25e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_reasoning": true, + "supports_tool_choice": true + }, + "openrouter/openai/gpt-5-mini": { + "cache_read_input_token_cost": 2.5e-08, + "input_cost_per_token": 2.5e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2e-06, + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_reasoning": true, + "supports_tool_choice": true + }, + "openrouter/openai/gpt-5-nano": { + "cache_read_input_token_cost": 5e-09, + "input_cost_per_token": 5e-08, + "litellm_provider": "openrouter", + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4e-07, + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_reasoning": true, + "supports_tool_choice": true + }, + "openrouter/openai/gpt-oss-120b": { + "input_cost_per_token": 1.8e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 8e-07, + "source": "https://openrouter.ai/openai/gpt-oss-120b", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "openrouter/openai/gpt-oss-20b": { + "input_cost_per_token": 1.8e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 8e-07, + "source": "https://openrouter.ai/openai/gpt-oss-20b", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "openrouter/openai/o1": { + "cache_read_input_token_cost": 7.5e-06, + "input_cost_per_token": 1.5e-05, + "litellm_provider": "openrouter", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 100000, + "mode": "chat", + "output_cost_per_token": 6e-05, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "openrouter/openai/o1-mini": { + "input_cost_per_token": 3e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 128000, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 1.2e-05, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "openrouter/openai/o1-mini-2024-09-12": { + "input_cost_per_token": 3e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 128000, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 1.2e-05, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "openrouter/openai/o1-preview": { + "input_cost_per_token": 1.5e-05, + "litellm_provider": "openrouter", + "max_input_tokens": 128000, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 6e-05, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "openrouter/openai/o1-preview-2024-09-12": { + "input_cost_per_token": 1.5e-05, + "litellm_provider": "openrouter", + "max_input_tokens": 128000, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 6e-05, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "openrouter/openai/o3-mini": { + "input_cost_per_token": 1.1e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 128000, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "openrouter/openai/o3-mini-high": { + "input_cost_per_token": 1.1e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 128000, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "openrouter/pygmalionai/mythalion-13b": { + "input_cost_per_token": 1.875e-06, + "litellm_provider": "openrouter", + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.875e-06, + "supports_tool_choice": true + }, + "openrouter/qwen/qwen-2.5-coder-32b-instruct": { + "input_cost_per_token": 1.8e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 33792, + "max_output_tokens": 33792, + "max_tokens": 33792, + "mode": "chat", + "output_cost_per_token": 1.8e-07, + "supports_tool_choice": true + }, + "openrouter/qwen/qwen-vl-plus": { + "input_cost_per_token": 2.1e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 8192, + "max_output_tokens": 2048, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 6.3e-07, + "supports_tool_choice": true + }, + "openrouter/qwen/qwen3-coder": { + "input_cost_per_token": 1e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "max_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 5e-06, + "source": "https://openrouter.ai/qwen/qwen3-coder", + "supports_tool_choice": true + }, + "openrouter/switchpoint/router": { + "input_cost_per_token": 8.5e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 3.4e-06, + "source": "https://openrouter.ai/switchpoint/router", + "supports_tool_choice": true + }, + "openrouter/undi95/remm-slerp-l2-13b": { + "input_cost_per_token": 1.875e-06, + "litellm_provider": "openrouter", + "max_tokens": 6144, + "mode": "chat", + "output_cost_per_token": 1.875e-06, + "supports_tool_choice": true + }, + "openrouter/x-ai/grok-4": { + "input_cost_per_token": 3e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "source": "https://openrouter.ai/x-ai/grok-4", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_web_search": true + }, + "ovhcloud/DeepSeek-R1-Distill-Llama-70B": { + "input_cost_per_token": 6.7e-07, "litellm_provider": "ovhcloud", + "max_input_tokens": 131000, + "max_output_tokens": 131000, + "max_tokens": 131000, + "mode": "chat", + "output_cost_per_token": 6.7e-07, + "source": "https://endpoints.ai.cloud.ovh.net/models/deepseek-r1-distill-llama-70b", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "ovhcloud/Llama-3.1-8B-Instruct": { + "input_cost_per_token": 1e-07, + "litellm_provider": "ovhcloud", + "max_input_tokens": 131000, + "max_output_tokens": 131000, + "max_tokens": 131000, + "mode": "chat", + "output_cost_per_token": 1e-07, + "source": "https://endpoints.ai.cloud.ovh.net/models/llama-3-1-8b-instruct", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "ovhcloud/Meta-Llama-3_1-70B-Instruct": { + "input_cost_per_token": 6.7e-07, + "litellm_provider": "ovhcloud", + "max_input_tokens": 131000, + "max_output_tokens": 131000, + "max_tokens": 131000, + "mode": "chat", + "output_cost_per_token": 6.7e-07, + "source": "https://endpoints.ai.cloud.ovh.net/models/meta-llama-3-1-70b-instruct", + "supports_function_calling": false, + "supports_response_schema": false, + "supports_tool_choice": false + }, + "ovhcloud/Meta-Llama-3_3-70B-Instruct": { + "input_cost_per_token": 6.7e-07, + "litellm_provider": "ovhcloud", + "max_input_tokens": 131000, + "max_output_tokens": 131000, + "max_tokens": 131000, + "mode": "chat", + "output_cost_per_token": 6.7e-07, + "source": "https://endpoints.ai.cloud.ovh.net/models/meta-llama-3-3-70b-instruct", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "ovhcloud/Mistral-7B-Instruct-v0.3": { + "input_cost_per_token": 1e-07, + "litellm_provider": "ovhcloud", + "max_input_tokens": 127000, + "max_output_tokens": 127000, + "max_tokens": 127000, + "mode": "chat", + "output_cost_per_token": 1e-07, + "source": "https://endpoints.ai.cloud.ovh.net/models/mistral-7b-instruct-v0-3", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "ovhcloud/Mistral-Nemo-Instruct-2407": { + "input_cost_per_token": 1.3e-07, + "litellm_provider": "ovhcloud", + "max_input_tokens": 118000, + "max_output_tokens": 118000, + "max_tokens": 118000, + "mode": "chat", + "output_cost_per_token": 1.3e-07, + "source": "https://endpoints.ai.cloud.ovh.net/models/mistral-nemo-instruct-2407", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "ovhcloud/Mistral-Small-3.2-24B-Instruct-2506": { + "input_cost_per_token": 9e-08, + "litellm_provider": "ovhcloud", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2.8e-07, + "source": "https://endpoints.ai.cloud.ovh.net/models/mistral-small-3-2-24b-instruct-2506", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "ovhcloud/Mixtral-8x7B-Instruct-v0.1": { + "input_cost_per_token": 6.3e-07, + "litellm_provider": "ovhcloud", + "max_input_tokens": 32000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 6.3e-07, + "source": "https://endpoints.ai.cloud.ovh.net/models/mixtral-8x7b-instruct-v0-1", + "supports_function_calling": false, + "supports_response_schema": true, + "supports_tool_choice": false + }, + "ovhcloud/Qwen2.5-Coder-32B-Instruct": { + "input_cost_per_token": 8.7e-07, + "litellm_provider": "ovhcloud", + "max_input_tokens": 32000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 8.7e-07, + "source": "https://endpoints.ai.cloud.ovh.net/models/qwen2-5-coder-32b-instruct", + "supports_function_calling": false, + "supports_response_schema": true, + "supports_tool_choice": false + }, + "ovhcloud/Qwen2.5-VL-72B-Instruct": { + "input_cost_per_token": 9.1e-07, + "litellm_provider": "ovhcloud", + "max_input_tokens": 32000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 9.1e-07, + "source": "https://endpoints.ai.cloud.ovh.net/models/qwen2-5-vl-72b-instruct", + "supports_function_calling": false, + "supports_response_schema": true, + "supports_tool_choice": false, + "supports_vision": true + }, + "ovhcloud/Qwen3-32B": { + "input_cost_per_token": 8e-08, + "litellm_provider": "ovhcloud", + "max_input_tokens": 32000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 2.3e-07, + "source": "https://endpoints.ai.cloud.ovh.net/models/qwen3-32b", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "ovhcloud/gpt-oss-120b": { + "input_cost_per_token": 8e-08, + "litellm_provider": "ovhcloud", + "max_input_tokens": 131000, + "max_output_tokens": 131000, + "max_tokens": 131000, + "mode": "chat", + "output_cost_per_token": 4e-07, + "source": "https://endpoints.ai.cloud.ovh.net/models/gpt-oss-120b", + "supports_function_calling": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": false + }, + "ovhcloud/gpt-oss-20b": { + "input_cost_per_token": 4e-08, + "litellm_provider": "ovhcloud", + "max_input_tokens": 131000, + "max_output_tokens": 131000, + "max_tokens": 131000, + "mode": "chat", + "output_cost_per_token": 1.5e-07, + "source": "https://endpoints.ai.cloud.ovh.net/models/gpt-oss-20b", + "supports_function_calling": false, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": false + }, + "ovhcloud/llava-v1.6-mistral-7b-hf": { + "input_cost_per_token": 2.9e-07, + "litellm_provider": "ovhcloud", + "max_input_tokens": 32000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 2.9e-07, + "source": "https://endpoints.ai.cloud.ovh.net/models/llava-next-mistral-7b", + "supports_function_calling": false, + "supports_response_schema": true, + "supports_tool_choice": false, + "supports_vision": true + }, + "ovhcloud/mamba-codestral-7B-v0.1": { + "input_cost_per_token": 1.9e-07, + "litellm_provider": "ovhcloud", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 1.9e-07, + "source": "https://endpoints.ai.cloud.ovh.net/models/mamba-codestral-7b-v0-1", + "supports_function_calling": false, + "supports_response_schema": true, + "supports_tool_choice": false + }, + "palm/chat-bison": { + "input_cost_per_token": 1.25e-07, + "litellm_provider": "palm", + "max_input_tokens": 8192, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.25e-07, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" + }, + "palm/chat-bison-001": { + "input_cost_per_token": 1.25e-07, + "litellm_provider": "palm", + "max_input_tokens": 8192, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.25e-07, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" + }, + "palm/text-bison": { + "input_cost_per_token": 1.25e-07, + "litellm_provider": "palm", + "max_input_tokens": 8192, + "max_output_tokens": 1024, + "max_tokens": 1024, + "mode": "completion", + "output_cost_per_token": 1.25e-07, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" + }, + "palm/text-bison-001": { + "input_cost_per_token": 1.25e-07, + "litellm_provider": "palm", + "max_input_tokens": 8192, + "max_output_tokens": 1024, + "max_tokens": 1024, + "mode": "completion", + "output_cost_per_token": 1.25e-07, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" + }, + "palm/text-bison-safety-off": { + "input_cost_per_token": 1.25e-07, + "litellm_provider": "palm", + "max_input_tokens": 8192, + "max_output_tokens": 1024, + "max_tokens": 1024, + "mode": "completion", + "output_cost_per_token": 1.25e-07, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" + }, + "palm/text-bison-safety-recitation-off": { + "input_cost_per_token": 1.25e-07, + "litellm_provider": "palm", + "max_input_tokens": 8192, + "max_output_tokens": 1024, + "max_tokens": 1024, + "mode": "completion", + "output_cost_per_token": 1.25e-07, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" + }, + "perplexity/codellama-34b-instruct": { + "input_cost_per_token": 3.5e-07, + "litellm_provider": "perplexity", + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1.4e-06 + }, + "perplexity/codellama-70b-instruct": { + "input_cost_per_token": 7e-07, + "litellm_provider": "perplexity", + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 2.8e-06 + }, + "perplexity/llama-2-70b-chat": { + "input_cost_per_token": 7e-07, + "litellm_provider": "perplexity", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 2.8e-06 + }, + "perplexity/llama-3.1-70b-instruct": { + "input_cost_per_token": 1e-06, + "litellm_provider": "perplexity", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1e-06 + }, + "perplexity/llama-3.1-8b-instruct": { + "input_cost_per_token": 2e-07, + "litellm_provider": "perplexity", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2e-07 + }, + "perplexity/llama-3.1-sonar-huge-128k-online": { + "deprecation_date": "2025-02-22", + "input_cost_per_token": 5e-06, + "litellm_provider": "perplexity", + "max_input_tokens": 127072, + "max_output_tokens": 127072, + "max_tokens": 127072, + "mode": "chat", + "output_cost_per_token": 5e-06 + }, + "perplexity/llama-3.1-sonar-large-128k-chat": { + "deprecation_date": "2025-02-22", + "input_cost_per_token": 1e-06, + "litellm_provider": "perplexity", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1e-06 + }, + "perplexity/llama-3.1-sonar-large-128k-online": { + "deprecation_date": "2025-02-22", + "input_cost_per_token": 1e-06, + "litellm_provider": "perplexity", + "max_input_tokens": 127072, + "max_output_tokens": 127072, + "max_tokens": 127072, + "mode": "chat", + "output_cost_per_token": 1e-06 + }, + "perplexity/llama-3.1-sonar-small-128k-chat": { + "deprecation_date": "2025-02-22", + "input_cost_per_token": 2e-07, + "litellm_provider": "perplexity", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2e-07 + }, + "perplexity/llama-3.1-sonar-small-128k-online": { + "deprecation_date": "2025-02-22", + "input_cost_per_token": 2e-07, + "litellm_provider": "perplexity", + "max_input_tokens": 127072, + "max_output_tokens": 127072, + "max_tokens": 127072, + "mode": "chat", + "output_cost_per_token": 2e-07 + }, + "perplexity/mistral-7b-instruct": { + "input_cost_per_token": 7e-08, + "litellm_provider": "perplexity", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 2.8e-07 + }, + "perplexity/mixtral-8x7b-instruct": { + "input_cost_per_token": 7e-08, + "litellm_provider": "perplexity", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 2.8e-07 + }, + "perplexity/pplx-70b-chat": { + "input_cost_per_token": 7e-07, + "litellm_provider": "perplexity", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 2.8e-06 + }, + "perplexity/pplx-70b-online": { + "input_cost_per_request": 0.005, + "input_cost_per_token": 0.0, + "litellm_provider": "perplexity", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 2.8e-06 + }, + "perplexity/pplx-7b-chat": { + "input_cost_per_token": 7e-08, + "litellm_provider": "perplexity", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 2.8e-07 + }, + "perplexity/pplx-7b-online": { + "input_cost_per_request": 0.005, + "input_cost_per_token": 0.0, + "litellm_provider": "perplexity", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 2.8e-07 + }, + "perplexity/sonar": { + "input_cost_per_token": 1e-06, + "litellm_provider": "perplexity", + "max_input_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.012, + "search_context_size_low": 0.005, + "search_context_size_medium": 0.008 + }, + "supports_web_search": true + }, + "perplexity/sonar-deep-research": { + "citation_cost_per_token": 2e-06, + "input_cost_per_token": 2e-06, + "litellm_provider": "perplexity", + "max_input_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_reasoning_token": 3e-06, + "output_cost_per_token": 8e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.005, + "search_context_size_low": 0.005, + "search_context_size_medium": 0.005 + }, + "supports_reasoning": true, + "supports_web_search": true + }, + "perplexity/sonar-medium-chat": { + "input_cost_per_token": 6e-07, + "litellm_provider": "perplexity", + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1.8e-06 + }, + "perplexity/sonar-medium-online": { + "input_cost_per_request": 0.005, + "input_cost_per_token": 0, + "litellm_provider": "perplexity", + "max_input_tokens": 12000, + "max_output_tokens": 12000, + "max_tokens": 12000, + "mode": "chat", + "output_cost_per_token": 1.8e-06 + }, + "perplexity/sonar-pro": { + "input_cost_per_token": 3e-06, + "litellm_provider": "perplexity", + "max_input_tokens": 200000, + "max_output_tokens": 8000, + "max_tokens": 8000, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.006, + "search_context_size_medium": 0.01 + }, + "supports_web_search": true + }, + "perplexity/sonar-reasoning": { + "input_cost_per_token": 1e-06, + "litellm_provider": "perplexity", + "max_input_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.005, + "search_context_size_medium": 0.008 + }, + "supports_reasoning": true, + "supports_web_search": true + }, + "perplexity/sonar-reasoning-pro": { + "input_cost_per_token": 2e-06, + "litellm_provider": "perplexity", + "max_input_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 8e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.014, + "search_context_size_low": 0.006, + "search_context_size_medium": 0.01 + }, + "supports_reasoning": true, + "supports_web_search": true + }, + "perplexity/sonar-small-chat": { + "input_cost_per_token": 7e-08, + "litellm_provider": "perplexity", + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 2.8e-07 + }, + "perplexity/sonar-small-online": { + "input_cost_per_request": 0.005, + "input_cost_per_token": 0, + "litellm_provider": "perplexity", + "max_input_tokens": 12000, + "max_output_tokens": 12000, + "max_tokens": 12000, + "mode": "chat", + "output_cost_per_token": 2.8e-07 + }, + "recraft/recraftv2": { + "litellm_provider": "recraft", + "mode": "image_generation", + "output_cost_per_image": 0.022, + "source": "https://www.recraft.ai/docs#pricing", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "recraft/recraftv3": { + "litellm_provider": "recraft", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://www.recraft.ai/docs#pricing", + "supported_endpoints": [ + "/v1/images/generations" + ] + }, + "replicate/meta/llama-2-13b": { + "input_cost_per_token": 1e-07, + "litellm_provider": "replicate", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 5e-07, + "supports_tool_choice": true + }, + "replicate/meta/llama-2-13b-chat": { + "input_cost_per_token": 1e-07, + "litellm_provider": "replicate", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 5e-07, + "supports_tool_choice": true + }, + "replicate/meta/llama-2-70b": { + "input_cost_per_token": 6.5e-07, + "litellm_provider": "replicate", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 2.75e-06, + "supports_tool_choice": true + }, + "replicate/meta/llama-2-70b-chat": { + "input_cost_per_token": 6.5e-07, + "litellm_provider": "replicate", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 2.75e-06, + "supports_tool_choice": true + }, + "replicate/meta/llama-2-7b": { + "input_cost_per_token": 5e-08, + "litellm_provider": "replicate", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 2.5e-07, + "supports_tool_choice": true + }, + "replicate/meta/llama-2-7b-chat": { + "input_cost_per_token": 5e-08, + "litellm_provider": "replicate", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 2.5e-07, + "supports_tool_choice": true + }, + "replicate/meta/llama-3-70b": { + "input_cost_per_token": 6.5e-07, + "litellm_provider": "replicate", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 2.75e-06, + "supports_tool_choice": true + }, + "replicate/meta/llama-3-70b-instruct": { + "input_cost_per_token": 6.5e-07, + "litellm_provider": "replicate", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 2.75e-06, + "supports_tool_choice": true + }, + "replicate/meta/llama-3-8b": { + "input_cost_per_token": 5e-08, + "litellm_provider": "replicate", + "max_input_tokens": 8086, + "max_output_tokens": 8086, + "max_tokens": 8086, + "mode": "chat", + "output_cost_per_token": 2.5e-07, + "supports_tool_choice": true + }, + "replicate/meta/llama-3-8b-instruct": { + "input_cost_per_token": 5e-08, + "litellm_provider": "replicate", + "max_input_tokens": 8086, + "max_output_tokens": 8086, + "max_tokens": 8086, + "mode": "chat", + "output_cost_per_token": 2.5e-07, + "supports_tool_choice": true + }, + "replicate/mistralai/mistral-7b-instruct-v0.2": { + "input_cost_per_token": 5e-08, + "litellm_provider": "replicate", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 2.5e-07, + "supports_tool_choice": true + }, + "replicate/mistralai/mistral-7b-v0.1": { + "input_cost_per_token": 5e-08, + "litellm_provider": "replicate", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 2.5e-07, + "supports_tool_choice": true + }, + "replicate/mistralai/mixtral-8x7b-instruct-v0.1": { + "input_cost_per_token": 3e-07, + "litellm_provider": "replicate", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1e-06, + "supports_tool_choice": true + }, + "rerank-english-v2.0": { + "input_cost_per_query": 0.002, + "input_cost_per_token": 0.0, + "litellm_provider": "cohere", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_query_tokens": 2048, + "max_tokens": 4096, + "mode": "rerank", + "output_cost_per_token": 0.0 + }, + "rerank-english-v3.0": { + "input_cost_per_query": 0.002, + "input_cost_per_token": 0.0, + "litellm_provider": "cohere", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_query_tokens": 2048, + "max_tokens": 4096, + "mode": "rerank", + "output_cost_per_token": 0.0 + }, + "rerank-multilingual-v2.0": { + "input_cost_per_query": 0.002, + "input_cost_per_token": 0.0, + "litellm_provider": "cohere", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_query_tokens": 2048, + "max_tokens": 4096, + "mode": "rerank", + "output_cost_per_token": 0.0 + }, + "rerank-multilingual-v3.0": { + "input_cost_per_query": 0.002, + "input_cost_per_token": 0.0, + "litellm_provider": "cohere", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_query_tokens": 2048, + "max_tokens": 4096, + "mode": "rerank", + "output_cost_per_token": 0.0 + }, + "rerank-v3.5": { + "input_cost_per_query": 0.002, + "input_cost_per_token": 0.0, + "litellm_provider": "cohere", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_query_tokens": 2048, + "max_tokens": 4096, + "mode": "rerank", + "output_cost_per_token": 0.0 + }, + "sagemaker/meta-textgeneration-llama-2-13b": { + "input_cost_per_token": 0.0, + "litellm_provider": "sagemaker", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "completion", + "output_cost_per_token": 0.0 + }, + "sagemaker/meta-textgeneration-llama-2-13b-f": { + "input_cost_per_token": 0.0, + "litellm_provider": "sagemaker", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.0 + }, + "sagemaker/meta-textgeneration-llama-2-70b": { + "input_cost_per_token": 0.0, + "litellm_provider": "sagemaker", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "completion", + "output_cost_per_token": 0.0 + }, + "sagemaker/meta-textgeneration-llama-2-70b-b-f": { + "input_cost_per_token": 0.0, + "litellm_provider": "sagemaker", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.0 + }, + "sagemaker/meta-textgeneration-llama-2-7b": { + "input_cost_per_token": 0.0, + "litellm_provider": "sagemaker", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "completion", + "output_cost_per_token": 0.0 + }, + "sagemaker/meta-textgeneration-llama-2-7b-f": { + "input_cost_per_token": 0.0, + "litellm_provider": "sagemaker", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.0 + }, + "sambanova/DeepSeek-R1": { + "input_cost_per_token": 5e-06, + "litellm_provider": "sambanova", + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 7e-06, + "source": "https://cloud.sambanova.ai/plans/pricing" + }, + "sambanova/DeepSeek-R1-Distill-Llama-70B": { + "input_cost_per_token": 7e-07, + "litellm_provider": "sambanova", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.4e-06, + "source": "https://cloud.sambanova.ai/plans/pricing" + }, + "sambanova/DeepSeek-V3-0324": { + "input_cost_per_token": 3e-06, + "litellm_provider": "sambanova", + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 4.5e-06, + "source": "https://cloud.sambanova.ai/plans/pricing", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "sambanova/Llama-4-Maverick-17B-128E-Instruct": { + "input_cost_per_token": 6.3e-07, + "litellm_provider": "sambanova", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "metadata": { + "notes": "For vision models, images are converted to 6432 input tokens and are billed at that amount" + }, + "mode": "chat", + "output_cost_per_token": 1.8e-06, + "source": "https://cloud.sambanova.ai/plans/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "sambanova/Llama-4-Scout-17B-16E-Instruct": { + "input_cost_per_token": 4e-07, + "litellm_provider": "sambanova", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "metadata": { + "notes": "For vision models, images are converted to 6432 input tokens and are billed at that amount" + }, + "mode": "chat", + "output_cost_per_token": 7e-07, + "source": "https://cloud.sambanova.ai/plans/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "sambanova/Meta-Llama-3.1-405B-Instruct": { + "input_cost_per_token": 5e-06, + "litellm_provider": "sambanova", + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1e-05, + "source": "https://cloud.sambanova.ai/plans/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "sambanova/Meta-Llama-3.1-8B-Instruct": { + "input_cost_per_token": 1e-07, + "litellm_provider": "sambanova", + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 2e-07, + "source": "https://cloud.sambanova.ai/plans/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "sambanova/Meta-Llama-3.2-1B-Instruct": { + "input_cost_per_token": 4e-08, + "litellm_provider": "sambanova", + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 8e-08, + "source": "https://cloud.sambanova.ai/plans/pricing" + }, + "sambanova/Meta-Llama-3.2-3B-Instruct": { + "input_cost_per_token": 8e-08, + "litellm_provider": "sambanova", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.6e-07, + "source": "https://cloud.sambanova.ai/plans/pricing" + }, + "sambanova/Meta-Llama-3.3-70B-Instruct": { + "input_cost_per_token": 6e-07, + "litellm_provider": "sambanova", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://cloud.sambanova.ai/plans/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "sambanova/Meta-Llama-Guard-3-8B": { + "input_cost_per_token": 3e-07, + "litellm_provider": "sambanova", + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 3e-07, + "source": "https://cloud.sambanova.ai/plans/pricing" + }, + "sambanova/QwQ-32B": { + "input_cost_per_token": 5e-07, + "litellm_provider": "sambanova", + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1e-06, + "source": "https://cloud.sambanova.ai/plans/pricing" + }, + "sambanova/Qwen2-Audio-7B-Instruct": { + "input_cost_per_token": 5e-07, + "litellm_provider": "sambanova", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 0.0001, + "source": "https://cloud.sambanova.ai/plans/pricing", + "supports_audio_input": true + }, + "sambanova/Qwen3-32B": { + "input_cost_per_token": 4e-07, + "litellm_provider": "sambanova", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 8e-07, + "source": "https://cloud.sambanova.ai/plans/pricing", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "sample_spec": { + "code_interpreter_cost_per_session": 0.0, + "computer_use_input_cost_per_1k_tokens": 0.0, + "computer_use_output_cost_per_1k_tokens": 0.0, + "deprecation_date": "date when the model becomes deprecated in the format YYYY-MM-DD", + "file_search_cost_per_1k_calls": 0.0, + "file_search_cost_per_gb_per_day": 0.0, + "input_cost_per_audio_token": 0.0, + "input_cost_per_token": 0.0, + "litellm_provider": "one of https://docs.litellm.ai/docs/providers", + "max_input_tokens": "max input tokens, if the provider specifies it. if not default to max_tokens", + "max_output_tokens": "max output tokens, if the provider specifies it. if not default to max_tokens", + "max_tokens": "LEGACY parameter. set to max_output_tokens if provider specifies it. IF not set to max_input_tokens, if provider specifies it.", + "mode": "one of: chat, embedding, completion, image_generation, audio_transcription, audio_speech, image_generation, moderation, rerank", + "output_cost_per_reasoning_token": 0.0, + "output_cost_per_token": 0.0, + "search_context_cost_per_query": { + "search_context_size_high": 0.0, + "search_context_size_low": 0.0, + "search_context_size_medium": 0.0 + }, + "supported_regions": [ + "global", + "us-west-2", + "eu-west-1", + "ap-southeast-1", + "ap-northeast-1" + ], + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_vision": true, + "supports_web_search": true, + "vector_store_cost_per_gb_per_day": 0.0 + }, + "snowflake/claude-3-5-sonnet": { + "litellm_provider": "snowflake", + "max_input_tokens": 18000, + "max_output_tokens": 8192, + "max_tokens": 18000, + "mode": "chat", + "supports_computer_use": true + }, + "snowflake/deepseek-r1": { + "litellm_provider": "snowflake", + "max_input_tokens": 32768, + "max_output_tokens": 8192, + "max_tokens": 32768, + "mode": "chat", + "supports_reasoning": true + }, + "snowflake/gemma-7b": { + "litellm_provider": "snowflake", + "max_input_tokens": 8000, + "max_output_tokens": 8192, + "max_tokens": 8000, + "mode": "chat" + }, + "snowflake/jamba-1.5-large": { + "litellm_provider": "snowflake", + "max_input_tokens": 256000, + "max_output_tokens": 8192, + "max_tokens": 256000, + "mode": "chat" + }, + "snowflake/jamba-1.5-mini": { + "litellm_provider": "snowflake", + "max_input_tokens": 256000, + "max_output_tokens": 8192, + "max_tokens": 256000, + "mode": "chat" + }, + "snowflake/jamba-instruct": { + "litellm_provider": "snowflake", + "max_input_tokens": 256000, + "max_output_tokens": 8192, + "max_tokens": 256000, + "mode": "chat" + }, + "snowflake/llama2-70b-chat": { + "litellm_provider": "snowflake", + "max_input_tokens": 4096, + "max_output_tokens": 8192, + "max_tokens": 4096, + "mode": "chat" + }, + "snowflake/llama3-70b": { + "litellm_provider": "snowflake", + "max_input_tokens": 8000, + "max_output_tokens": 8192, + "max_tokens": 8000, + "mode": "chat" + }, + "snowflake/llama3-8b": { + "litellm_provider": "snowflake", + "max_input_tokens": 8000, + "max_output_tokens": 8192, + "max_tokens": 8000, + "mode": "chat" + }, + "snowflake/llama3.1-405b": { + "litellm_provider": "snowflake", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 128000, + "mode": "chat" + }, + "snowflake/llama3.1-70b": { + "litellm_provider": "snowflake", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 128000, + "mode": "chat" + }, + "snowflake/llama3.1-8b": { + "litellm_provider": "snowflake", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 128000, + "mode": "chat" + }, + "snowflake/llama3.2-1b": { + "litellm_provider": "snowflake", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 128000, + "mode": "chat" + }, + "snowflake/llama3.2-3b": { + "litellm_provider": "snowflake", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 128000, + "mode": "chat" + }, + "snowflake/llama3.3-70b": { + "litellm_provider": "snowflake", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 128000, + "mode": "chat" + }, + "snowflake/mistral-7b": { + "litellm_provider": "snowflake", + "max_input_tokens": 32000, + "max_output_tokens": 8192, + "max_tokens": 32000, + "mode": "chat" + }, + "snowflake/mistral-large": { + "litellm_provider": "snowflake", + "max_input_tokens": 32000, + "max_output_tokens": 8192, + "max_tokens": 32000, + "mode": "chat" + }, + "snowflake/mistral-large2": { + "litellm_provider": "snowflake", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 128000, + "mode": "chat" + }, + "snowflake/mixtral-8x7b": { + "litellm_provider": "snowflake", + "max_input_tokens": 32000, + "max_output_tokens": 8192, + "max_tokens": 32000, + "mode": "chat" + }, + "snowflake/reka-core": { + "litellm_provider": "snowflake", + "max_input_tokens": 32000, + "max_output_tokens": 8192, + "max_tokens": 32000, + "mode": "chat" + }, + "snowflake/reka-flash": { + "litellm_provider": "snowflake", + "max_input_tokens": 100000, + "max_output_tokens": 8192, + "max_tokens": 100000, + "mode": "chat" + }, + "snowflake/snowflake-arctic": { + "litellm_provider": "snowflake", + "max_input_tokens": 4096, + "max_output_tokens": 8192, + "max_tokens": 4096, + "mode": "chat" + }, + "snowflake/snowflake-llama-3.1-405b": { + "litellm_provider": "snowflake", + "max_input_tokens": 8000, + "max_output_tokens": 8192, + "max_tokens": 8000, + "mode": "chat" + }, + "snowflake/snowflake-llama-3.3-70b": { + "litellm_provider": "snowflake", + "max_input_tokens": 8000, + "max_output_tokens": 8192, + "max_tokens": 8000, + "mode": "chat" + }, + "stability.sd3-5-large-v1:0": { + "litellm_provider": "bedrock", + "max_input_tokens": 77, + "max_tokens": 77, + "mode": "image_generation", + "output_cost_per_image": 0.08 + }, + "stability.sd3-large-v1:0": { + "litellm_provider": "bedrock", + "max_input_tokens": 77, + "max_tokens": 77, + "mode": "image_generation", + "output_cost_per_image": 0.08 + }, + "stability.stable-image-core-v1:0": { + "litellm_provider": "bedrock", + "max_input_tokens": 77, + "max_tokens": 77, + "mode": "image_generation", + "output_cost_per_image": 0.04 + }, + "stability.stable-image-core-v1:1": { + "litellm_provider": "bedrock", + "max_input_tokens": 77, + "max_tokens": 77, + "mode": "image_generation", + "output_cost_per_image": 0.04 + }, + "stability.stable-image-ultra-v1:0": { + "litellm_provider": "bedrock", + "max_input_tokens": 77, + "max_tokens": 77, + "mode": "image_generation", + "output_cost_per_image": 0.14 + }, + "stability.stable-image-ultra-v1:1": { + "litellm_provider": "bedrock", + "max_input_tokens": 77, + "max_tokens": 77, + "mode": "image_generation", + "output_cost_per_image": 0.14 + }, + "standard/1024-x-1024/dall-e-3": { + "input_cost_per_pixel": 3.81469e-08, + "litellm_provider": "openai", + "mode": "image_generation", + "output_cost_per_pixel": 0.0 + }, + "standard/1024-x-1792/dall-e-3": { + "input_cost_per_pixel": 4.359e-08, + "litellm_provider": "openai", + "mode": "image_generation", + "output_cost_per_pixel": 0.0 + }, + "standard/1792-x-1024/dall-e-3": { + "input_cost_per_pixel": 4.359e-08, + "litellm_provider": "openai", + "mode": "image_generation", + "output_cost_per_pixel": 0.0 + }, + "text-bison": { + "input_cost_per_character": 2.5e-07, + "litellm_provider": "vertex_ai-text-models", + "max_input_tokens": 8192, + "max_output_tokens": 2048, + "max_tokens": 2048, + "mode": "completion", + "output_cost_per_character": 5e-07, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" + }, + "text-bison32k": { + "input_cost_per_character": 2.5e-07, + "input_cost_per_token": 1.25e-07, + "litellm_provider": "vertex_ai-text-models", + "max_input_tokens": 8192, + "max_output_tokens": 1024, + "max_tokens": 1024, + "mode": "completion", + "output_cost_per_character": 5e-07, + "output_cost_per_token": 1.25e-07, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" + }, + "text-bison32k@002": { + "input_cost_per_character": 2.5e-07, + "input_cost_per_token": 1.25e-07, + "litellm_provider": "vertex_ai-text-models", + "max_input_tokens": 8192, + "max_output_tokens": 1024, + "max_tokens": 1024, + "mode": "completion", + "output_cost_per_character": 5e-07, + "output_cost_per_token": 1.25e-07, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" + }, + "text-bison@001": { + "input_cost_per_character": 2.5e-07, + "litellm_provider": "vertex_ai-text-models", + "max_input_tokens": 8192, + "max_output_tokens": 1024, + "max_tokens": 1024, + "mode": "completion", + "output_cost_per_character": 5e-07, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" + }, + "text-bison@002": { + "input_cost_per_character": 2.5e-07, + "litellm_provider": "vertex_ai-text-models", + "max_input_tokens": 8192, + "max_output_tokens": 1024, + "max_tokens": 1024, + "mode": "completion", + "output_cost_per_character": 5e-07, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" + }, + "text-completion-codestral/codestral-2405": { + "input_cost_per_token": 0.0, + "litellm_provider": "text-completion-codestral", + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "completion", + "output_cost_per_token": 0.0, + "source": "https://docs.mistral.ai/capabilities/code_generation/" + }, + "text-completion-codestral/codestral-latest": { + "input_cost_per_token": 0.0, + "litellm_provider": "text-completion-codestral", + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "completion", + "output_cost_per_token": 0.0, + "source": "https://docs.mistral.ai/capabilities/code_generation/" + }, + "text-embedding-004": { + "input_cost_per_character": 2.5e-08, + "input_cost_per_token": 1e-07, + "litellm_provider": "vertex_ai-embedding-models", + "max_input_tokens": 2048, + "max_tokens": 2048, + "mode": "embedding", + "output_cost_per_token": 0, + "output_vector_size": 768, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models" + }, + "text-embedding-005": { + "input_cost_per_character": 2.5e-08, + "input_cost_per_token": 1e-07, + "litellm_provider": "vertex_ai-embedding-models", + "max_input_tokens": 2048, + "max_tokens": 2048, + "mode": "embedding", + "output_cost_per_token": 0, + "output_vector_size": 768, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models" + }, + "text-embedding-3-large": { + "input_cost_per_token": 1.3e-07, + "input_cost_per_token_batches": 6.5e-08, + "litellm_provider": "openai", + "max_input_tokens": 8191, + "max_tokens": 8191, + "mode": "embedding", + "output_cost_per_token": 0.0, + "output_cost_per_token_batches": 0.0, + "output_vector_size": 3072 + }, + "text-embedding-3-small": { + "input_cost_per_token": 2e-08, + "input_cost_per_token_batches": 1e-08, + "litellm_provider": "openai", + "max_input_tokens": 8191, + "max_tokens": 8191, + "mode": "embedding", + "output_cost_per_token": 0.0, + "output_cost_per_token_batches": 0.0, + "output_vector_size": 1536 + }, + "text-embedding-ada-002": { + "input_cost_per_token": 1e-07, + "litellm_provider": "openai", + "max_input_tokens": 8191, + "max_tokens": 8191, + "mode": "embedding", + "output_cost_per_token": 0.0, + "output_vector_size": 1536 + }, + "text-embedding-ada-002-v2": { + "input_cost_per_token": 1e-07, + "input_cost_per_token_batches": 5e-08, + "litellm_provider": "openai", + "max_input_tokens": 8191, + "max_tokens": 8191, + "mode": "embedding", + "output_cost_per_token": 0.0, + "output_cost_per_token_batches": 0.0 + }, + "text-embedding-large-exp-03-07": { + "input_cost_per_character": 2.5e-08, + "input_cost_per_token": 1e-07, + "litellm_provider": "vertex_ai-embedding-models", + "max_input_tokens": 8192, + "max_tokens": 8192, + "mode": "embedding", + "output_cost_per_token": 0, + "output_vector_size": 3072, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models" + }, + "text-embedding-preview-0409": { + "input_cost_per_token": 6.25e-09, + "input_cost_per_token_batch_requests": 5e-09, + "litellm_provider": "vertex_ai-embedding-models", + "max_input_tokens": 3072, + "max_tokens": 3072, + "mode": "embedding", + "output_cost_per_token": 0, + "output_vector_size": 768, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" + }, + "text-moderation-007": { + "input_cost_per_token": 0.0, + "litellm_provider": "openai", + "max_input_tokens": 32768, + "max_output_tokens": 0, + "max_tokens": 32768, + "mode": "moderation", + "output_cost_per_token": 0.0 + }, + "text-moderation-latest": { + "input_cost_per_token": 0.0, + "litellm_provider": "openai", + "max_input_tokens": 32768, + "max_output_tokens": 0, + "max_tokens": 32768, + "mode": "moderation", + "output_cost_per_token": 0.0 + }, + "text-moderation-stable": { + "input_cost_per_token": 0.0, + "litellm_provider": "openai", + "max_input_tokens": 32768, + "max_output_tokens": 0, + "max_tokens": 32768, + "mode": "moderation", + "output_cost_per_token": 0.0 + }, + "text-multilingual-embedding-002": { + "input_cost_per_character": 2.5e-08, + "input_cost_per_token": 1e-07, + "litellm_provider": "vertex_ai-embedding-models", + "max_input_tokens": 2048, + "max_tokens": 2048, + "mode": "embedding", + "output_cost_per_token": 0, + "output_vector_size": 768, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models" + }, + "text-multilingual-embedding-preview-0409": { + "input_cost_per_token": 6.25e-09, + "litellm_provider": "vertex_ai-embedding-models", + "max_input_tokens": 3072, + "max_tokens": 3072, + "mode": "embedding", + "output_cost_per_token": 0, + "output_vector_size": 768, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" + }, + "text-unicorn": { + "input_cost_per_token": 1e-05, + "litellm_provider": "vertex_ai-text-models", + "max_input_tokens": 8192, + "max_output_tokens": 1024, + "max_tokens": 1024, + "mode": "completion", + "output_cost_per_token": 2.8e-05, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" + }, + "text-unicorn@001": { + "input_cost_per_token": 1e-05, + "litellm_provider": "vertex_ai-text-models", + "max_input_tokens": 8192, + "max_output_tokens": 1024, + "max_tokens": 1024, + "mode": "completion", + "output_cost_per_token": 2.8e-05, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" + }, + "textembedding-gecko": { + "input_cost_per_character": 2.5e-08, + "input_cost_per_token": 1e-07, + "litellm_provider": "vertex_ai-embedding-models", + "max_input_tokens": 3072, + "max_tokens": 3072, + "mode": "embedding", + "output_cost_per_token": 0, + "output_vector_size": 768, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" + }, + "textembedding-gecko-multilingual": { + "input_cost_per_character": 2.5e-08, + "input_cost_per_token": 1e-07, + "litellm_provider": "vertex_ai-embedding-models", + "max_input_tokens": 3072, + "max_tokens": 3072, + "mode": "embedding", + "output_cost_per_token": 0, + "output_vector_size": 768, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" + }, + "textembedding-gecko-multilingual@001": { + "input_cost_per_character": 2.5e-08, + "input_cost_per_token": 1e-07, + "litellm_provider": "vertex_ai-embedding-models", + "max_input_tokens": 3072, + "max_tokens": 3072, + "mode": "embedding", + "output_cost_per_token": 0, + "output_vector_size": 768, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" + }, + "textembedding-gecko@001": { + "input_cost_per_character": 2.5e-08, + "input_cost_per_token": 1e-07, + "litellm_provider": "vertex_ai-embedding-models", + "max_input_tokens": 3072, + "max_tokens": 3072, + "mode": "embedding", + "output_cost_per_token": 0, + "output_vector_size": 768, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" + }, + "textembedding-gecko@003": { + "input_cost_per_character": 2.5e-08, + "input_cost_per_token": 1e-07, + "litellm_provider": "vertex_ai-embedding-models", + "max_input_tokens": 3072, + "max_tokens": 3072, + "mode": "embedding", + "output_cost_per_token": 0, + "output_vector_size": 768, + "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models" + }, + "together-ai-21.1b-41b": { + "input_cost_per_token": 8e-07, + "litellm_provider": "together_ai", + "mode": "chat", + "output_cost_per_token": 8e-07 + }, + "together-ai-4.1b-8b": { + "input_cost_per_token": 2e-07, + "litellm_provider": "together_ai", + "mode": "chat", + "output_cost_per_token": 2e-07 + }, + "together-ai-41.1b-80b": { + "input_cost_per_token": 9e-07, + "litellm_provider": "together_ai", + "mode": "chat", + "output_cost_per_token": 9e-07 + }, + "together-ai-8.1b-21b": { + "input_cost_per_token": 3e-07, + "litellm_provider": "together_ai", + "max_tokens": 1000, + "mode": "chat", + "output_cost_per_token": 3e-07 + }, + "together-ai-81.1b-110b": { + "input_cost_per_token": 1.8e-06, + "litellm_provider": "together_ai", + "mode": "chat", + "output_cost_per_token": 1.8e-06 + }, + "together-ai-embedding-151m-to-350m": { + "input_cost_per_token": 1.6e-08, + "litellm_provider": "together_ai", + "mode": "embedding", + "output_cost_per_token": 0.0 + }, + "together-ai-embedding-up-to-150m": { + "input_cost_per_token": 8e-09, + "litellm_provider": "together_ai", + "mode": "embedding", + "output_cost_per_token": 0.0 + }, + "together-ai-up-to-4b": { + "input_cost_per_token": 1e-07, + "litellm_provider": "together_ai", + "mode": "chat", + "output_cost_per_token": 1e-07 + }, + "together_ai/Qwen/Qwen2.5-72B-Instruct-Turbo": { + "litellm_provider": "together_ai", "mode": "chat", "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true + }, + "together_ai/Qwen/Qwen2.5-7B-Instruct-Turbo": { + "litellm_provider": "together_ai", + "mode": "chat", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true + }, + "together_ai/Qwen/Qwen3-235B-A22B-Instruct-2507-tput": { + "input_cost_per_token": 2e-07, + "litellm_provider": "together_ai", + "max_input_tokens": 262000, + "mode": "chat", + "output_cost_per_token": 6e-06, + "source": "https://www.together.ai/models/qwen3-235b-a22b-instruct-2507-fp8", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true + }, + "together_ai/Qwen/Qwen3-235B-A22B-Thinking-2507": { + "input_cost_per_token": 6.5e-07, + "litellm_provider": "together_ai", + "max_input_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 3e-06, + "source": "https://www.together.ai/models/qwen3-235b-a22b-thinking-2507", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true + }, + "together_ai/Qwen/Qwen3-235B-A22B-fp8-tput": { + "input_cost_per_token": 2e-07, + "litellm_provider": "together_ai", + "max_input_tokens": 40000, + "mode": "chat", + "output_cost_per_token": 6e-07, + "source": "https://www.together.ai/models/qwen3-235b-a22b-fp8-tput", + "supports_function_calling": false, + "supports_parallel_function_calling": false, + "supports_tool_choice": false + }, + "together_ai/Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8": { + "input_cost_per_token": 2e-06, + "litellm_provider": "together_ai", + "max_input_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 2e-06, + "source": "https://www.together.ai/models/qwen3-coder-480b-a35b-instruct", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true + }, + "together_ai/deepseek-ai/DeepSeek-R1": { + "input_cost_per_token": 3e-06, + "litellm_provider": "together_ai", + "max_input_tokens": 128000, + "max_output_tokens": 20480, + "max_tokens": 20480, + "mode": "chat", + "output_cost_per_token": 7e-06, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true + }, + "together_ai/deepseek-ai/DeepSeek-R1-0528-tput": { + "input_cost_per_token": 5.5e-07, + "litellm_provider": "together_ai", + "max_input_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2.19e-06, + "source": "https://www.together.ai/models/deepseek-r1-0528-throughput", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true + }, + "together_ai/deepseek-ai/DeepSeek-V3": { + "input_cost_per_token": 1.25e-06, + "litellm_provider": "together_ai", + "max_input_tokens": 65536, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.25e-06, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true + }, + "together_ai/deepseek-ai/DeepSeek-V3.1": { + "input_cost_per_token": 6e-07, + "litellm_provider": "together_ai", + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.7e-06, + "source": "https://www.together.ai/models/deepseek-v3-1", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "together_ai/meta-llama/Llama-3.2-3B-Instruct-Turbo": { + "litellm_provider": "together_ai", + "mode": "chat", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true + }, + "together_ai/meta-llama/Llama-3.3-70B-Instruct-Turbo": { + "input_cost_per_token": 8.8e-07, + "litellm_provider": "together_ai", + "mode": "chat", + "output_cost_per_token": 8.8e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "together_ai/meta-llama/Llama-3.3-70B-Instruct-Turbo-Free": { + "input_cost_per_token": 0, + "litellm_provider": "together_ai", + "mode": "chat", + "output_cost_per_token": 0, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "together_ai/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8": { + "input_cost_per_token": 2.7e-07, + "litellm_provider": "together_ai", + "mode": "chat", + "output_cost_per_token": 8.5e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true + }, + "together_ai/meta-llama/Llama-4-Scout-17B-16E-Instruct": { + "input_cost_per_token": 1.8e-07, + "litellm_provider": "together_ai", + "mode": "chat", + "output_cost_per_token": 5.9e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true + }, + "together_ai/meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo": { + "input_cost_per_token": 3.5e-06, + "litellm_provider": "together_ai", + "mode": "chat", + "output_cost_per_token": 3.5e-06, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true + }, + "together_ai/meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo": { + "input_cost_per_token": 8.8e-07, + "litellm_provider": "together_ai", + "mode": "chat", + "output_cost_per_token": 8.8e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "together_ai/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo": { + "input_cost_per_token": 1.8e-07, + "litellm_provider": "together_ai", + "mode": "chat", + "output_cost_per_token": 1.8e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "together_ai/mistralai/Mistral-7B-Instruct-v0.1": { + "litellm_provider": "together_ai", + "mode": "chat", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "together_ai/mistralai/Mistral-Small-24B-Instruct-2501": { + "litellm_provider": "together_ai", + "mode": "chat", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true + }, + "together_ai/mistralai/Mixtral-8x7B-Instruct-v0.1": { + "input_cost_per_token": 6e-07, + "litellm_provider": "together_ai", + "mode": "chat", + "output_cost_per_token": 6e-07, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "together_ai/moonshotai/Kimi-K2-Instruct": { + "input_cost_per_token": 1e-06, + "litellm_provider": "together_ai", + "mode": "chat", + "output_cost_per_token": 3e-06, + "source": "https://www.together.ai/models/kimi-k2-instruct", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true + }, + "together_ai/openai/gpt-oss-120b": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "together_ai", + "max_input_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 6e-07, + "source": "https://www.together.ai/models/gpt-oss-120b", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true + }, + "together_ai/openai/gpt-oss-20b": { + "input_cost_per_token": 5e-08, + "litellm_provider": "together_ai", + "max_input_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2e-07, + "source": "https://www.together.ai/models/gpt-oss-20b", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true + }, + "together_ai/togethercomputer/CodeLlama-34b-Instruct": { + "litellm_provider": "together_ai", + "mode": "chat", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true + }, + "together_ai/zai-org/GLM-4.5-Air-FP8": { + "input_cost_per_token": 2e-07, + "litellm_provider": "together_ai", + "max_input_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.1e-06, + "source": "https://www.together.ai/models/glm-4-5-air", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true + }, + "tts-1": { + "input_cost_per_character": 1.5e-05, + "litellm_provider": "openai", + "mode": "audio_speech", + "supported_endpoints": [ + "/v1/audio/speech" + ] + }, + "tts-1-hd": { + "input_cost_per_character": 3e-05, + "litellm_provider": "openai", + "mode": "audio_speech", + "supported_endpoints": [ + "/v1/audio/speech" + ] + }, + "us.amazon.nova-lite-v1:0": { + "input_cost_per_token": 6e-08, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 300000, + "max_output_tokens": 10000, + "max_tokens": 10000, + "mode": "chat", + "output_cost_per_token": 2.4e-07, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_vision": true + }, + "us.amazon.nova-micro-v1:0": { + "input_cost_per_token": 3.5e-08, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 128000, + "max_output_tokens": 10000, + "max_tokens": 10000, + "mode": "chat", + "output_cost_per_token": 1.4e-07, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true + }, + "us.amazon.nova-premier-v1:0": { + "input_cost_per_token": 2.5e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 10000, + "max_tokens": 10000, + "mode": "chat", + "output_cost_per_token": 1.25e-05, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": false, + "supports_response_schema": true, + "supports_vision": true + }, + "us.amazon.nova-pro-v1:0": { + "input_cost_per_token": 8e-07, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 300000, + "max_output_tokens": 10000, + "max_tokens": 10000, + "mode": "chat", + "output_cost_per_token": 3.2e-06, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_vision": true + }, + "us.anthropic.claude-3-5-haiku-20241022-v1:0": { + "cache_creation_input_token_cost": 1e-06, + "cache_read_input_token_cost": 8e-08, + "input_cost_per_token": 8e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 4e-06, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "us.anthropic.claude-3-5-sonnet-20240620-v1:0": { + "input_cost_per_token": 3e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "us.anthropic.claude-3-5-sonnet-20241022-v2:0": { + "cache_creation_input_token_cost": 3.75e-06, + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 3e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "us.anthropic.claude-3-7-sonnet-20250219-v1:0": { + "cache_creation_input_token_cost": 3.75e-06, + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 3e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "us.anthropic.claude-3-haiku-20240307-v1:0": { + "input_cost_per_token": 2.5e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.25e-06, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "us.anthropic.claude-3-opus-20240229-v1:0": { + "input_cost_per_token": 1.5e-05, + "litellm_provider": "bedrock", + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 7.5e-05, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "us.anthropic.claude-3-sonnet-20240229-v1:0": { + "input_cost_per_token": 3e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "us.anthropic.claude-opus-4-1-20250805-v1:0": { + "cache_creation_input_token_cost": 1.875e-05, + "cache_read_input_token_cost": 1.5e-06, + "input_cost_per_token": 1.5e-05, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 200000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 7.5e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "source": "https://endpoints.ai.cloud.ovh.net/models/mistral-small-3-2-24b-instruct-2506" + "tool_use_system_prompt_tokens": 159 }, - "ovhcloud/DeepSeek-R1-Distill-Llama-70B": { - "max_tokens": 131000, - "max_input_tokens": 131000, - "max_output_tokens": 131000, - "input_cost_per_token": 6.7e-07, - "output_cost_per_token": 6.7e-07, - "litellm_provider": "ovhcloud", - "mode": "chat", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_reasoning": true, - "source": "https://endpoints.ai.cloud.ovh.net/models/deepseek-r1-distill-llama-70b" - }, - "ovhcloud/Llama-3.1-8B-Instruct": { - "max_tokens": 131000, - "max_input_tokens": 131000, - "max_output_tokens": 131000, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 1e-07, - "litellm_provider": "ovhcloud", - "mode": "chat", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "source": "https://endpoints.ai.cloud.ovh.net/models/llama-3-1-8b-instruct" - }, - "ovhcloud/Mistral-7B-Instruct-v0.3": { - "max_tokens": 127000, - "max_input_tokens": 127000, - "max_output_tokens": 127000, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 1e-07, - "litellm_provider": "ovhcloud", - "mode": "chat", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "source": "https://endpoints.ai.cloud.ovh.net/models/mistral-7b-instruct-v0-3" - }, - "ovhcloud/gpt-oss-20b": { - "max_tokens": 131000, - "max_input_tokens": 131000, - "max_output_tokens": 131000, - "input_cost_per_token": 4e-08, - "output_cost_per_token": 1.5e-07, - "litellm_provider": "ovhcloud", - "mode": "chat", - "supports_function_calling": false, - "supports_response_schema": true, - "supports_tool_choice": false, - "supports_reasoning": true, - "source": "https://endpoints.ai.cloud.ovh.net/models/gpt-oss-20b" - }, - "ovhcloud/Mistral-Nemo-Instruct-2407": { - "max_tokens": 118000, - "max_input_tokens": 118000, - "max_output_tokens": 118000, - "input_cost_per_token": 1.3e-07, - "output_cost_per_token": 1.3e-07, - "litellm_provider": "ovhcloud", - "mode": "chat", - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "source": "https://endpoints.ai.cloud.ovh.net/models/mistral-nemo-instruct-2407" - }, - "ovhcloud/Qwen3-32B": { - "max_tokens": 32000, - "max_input_tokens": 32000, + "us.anthropic.claude-opus-4-20250514-v1:0": { + "cache_creation_input_token_cost": 1.875e-05, + "cache_read_input_token_cost": 1.5e-06, + "input_cost_per_token": 1.5e-05, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 200000, "max_output_tokens": 32000, - "input_cost_per_token": 8e-08, - "output_cost_per_token": 2.3e-07, - "litellm_provider": "ovhcloud", + "max_tokens": 32000, "mode": "chat", + "output_cost_per_token": 7.5e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_reasoning": true, - "source": "https://endpoints.ai.cloud.ovh.net/models/qwen3-32b" + "supports_vision": true, + "tool_use_system_prompt_tokens": 159 }, - "ovhcloud/mamba-codestral-7B-v0.1": { + "us.anthropic.claude-sonnet-4-20250514-v1:0": { + "cache_creation_input_token_cost": 3.75e-06, + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 3e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159 + }, + "us.deepseek.r1-v1:0": { + "input_cost_per_token": 1.35e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 5.4e-06, + "supports_function_calling": false, + "supports_reasoning": true, + "supports_tool_choice": false + }, + "us.meta.llama3-1-405b-instruct-v1:0": { + "input_cost_per_token": 5.32e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.6e-05, + "supports_function_calling": true, + "supports_tool_choice": false + }, + "us.meta.llama3-1-70b-instruct-v1:0": { + "input_cost_per_token": 9.9e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 128000, + "max_output_tokens": 2048, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 9.9e-07, + "supports_function_calling": true, + "supports_tool_choice": false + }, + "us.meta.llama3-1-8b-instruct-v1:0": { + "input_cost_per_token": 2.2e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 128000, + "max_output_tokens": 2048, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2.2e-07, + "supports_function_calling": true, + "supports_tool_choice": false + }, + "us.meta.llama3-2-11b-instruct-v1:0": { + "input_cost_per_token": 3.5e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 3.5e-07, + "supports_function_calling": true, + "supports_tool_choice": false, + "supports_vision": true + }, + "us.meta.llama3-2-1b-instruct-v1:0": { + "input_cost_per_token": 1e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-07, + "supports_function_calling": true, + "supports_tool_choice": false + }, + "us.meta.llama3-2-3b-instruct-v1:0": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.5e-07, + "supports_function_calling": true, + "supports_tool_choice": false + }, + "us.meta.llama3-2-90b-instruct-v1:0": { + "input_cost_per_token": 2e-06, + "litellm_provider": "bedrock", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2e-06, + "supports_function_calling": true, + "supports_tool_choice": false, + "supports_vision": true + }, + "us.meta.llama3-3-70b-instruct-v1:0": { + "input_cost_per_token": 7.2e-07, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 7.2e-07, + "supports_function_calling": true, + "supports_tool_choice": false + }, + "us.meta.llama4-maverick-17b-instruct-v1:0": { + "input_cost_per_token": 2.4e-07, + "input_cost_per_token_batches": 1.2e-07, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 9.7e-07, + "output_cost_per_token_batches": 4.85e-07, + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text", + "code" + ], + "supports_function_calling": true, + "supports_tool_choice": false + }, + "us.meta.llama4-scout-17b-instruct-v1:0": { + "input_cost_per_token": 1.7e-07, + "input_cost_per_token_batches": 8.5e-08, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 6.6e-07, + "output_cost_per_token_batches": 3.3e-07, + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text", + "code" + ], + "supports_function_calling": true, + "supports_tool_choice": false + }, + "us.mistral.pixtral-large-2502-v1:0": { + "input_cost_per_token": 2e-06, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 6e-06, + "supports_function_calling": true, + "supports_tool_choice": false + }, + "v0/v0-1.0-md": { + "input_cost_per_token": 3e-06, + "litellm_provider": "v0", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "v0/v0-1.5-lg": { + "input_cost_per_token": 1.5e-05, + "litellm_provider": "v0", + "max_input_tokens": 512000, + "max_output_tokens": 512000, + "max_tokens": 512000, + "mode": "chat", + "output_cost_per_token": 7.5e-05, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "v0/v0-1.5-md": { + "input_cost_per_token": 3e-06, + "litellm_provider": "v0", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "vercel_ai_gateway/alibaba/qwen-3-14b": { + "input_cost_per_token": 8e-08, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 40960, + "max_output_tokens": 16384, + "max_tokens": 40960, + "mode": "chat", + "output_cost_per_token": 2.4e-07 + }, + "vercel_ai_gateway/alibaba/qwen-3-235b": { + "input_cost_per_token": 2e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 40960, + "max_output_tokens": 16384, + "max_tokens": 40960, + "mode": "chat", + "output_cost_per_token": 6e-07 + }, + "vercel_ai_gateway/alibaba/qwen-3-30b": { + "input_cost_per_token": 1e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 40960, + "max_output_tokens": 16384, + "max_tokens": 40960, + "mode": "chat", + "output_cost_per_token": 3e-07 + }, + "vercel_ai_gateway/alibaba/qwen-3-32b": { + "input_cost_per_token": 1e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 40960, + "max_output_tokens": 16384, + "max_tokens": 40960, + "mode": "chat", + "output_cost_per_token": 3e-07 + }, + "vercel_ai_gateway/alibaba/qwen3-coder": { + "input_cost_per_token": 4e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 262144, + "max_output_tokens": 66536, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 1.6e-06 + }, + "vercel_ai_gateway/amazon/nova-lite": { + "input_cost_per_token": 6e-08, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 300000, + "max_output_tokens": 8192, + "max_tokens": 300000, + "mode": "chat", + "output_cost_per_token": 2.4e-07 + }, + "vercel_ai_gateway/amazon/nova-micro": { + "input_cost_per_token": 3.5e-08, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.4e-07 + }, + "vercel_ai_gateway/amazon/nova-pro": { + "input_cost_per_token": 8e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 300000, + "max_output_tokens": 8192, + "max_tokens": 300000, + "mode": "chat", + "output_cost_per_token": 3.2e-06 + }, + "vercel_ai_gateway/amazon/titan-embed-text-v2": { + "input_cost_per_token": 2e-08, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 0, + "max_output_tokens": 0, + "max_tokens": 0, + "mode": "chat", + "output_cost_per_token": 0.0 + }, + "vercel_ai_gateway/anthropic/claude-3-haiku": { + "cache_creation_input_token_cost": 3e-07, + "cache_read_input_token_cost": 3e-08, + "input_cost_per_token": 2.5e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 200000, + "mode": "chat", + "output_cost_per_token": 1.25e-06 + }, + "vercel_ai_gateway/anthropic/claude-3-opus": { + "cache_creation_input_token_cost": 1.875e-05, + "cache_read_input_token_cost": 1.5e-06, + "input_cost_per_token": 1.5e-05, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 200000, + "mode": "chat", + "output_cost_per_token": 7.5e-05 + }, + "vercel_ai_gateway/anthropic/claude-3.5-haiku": { + "cache_creation_input_token_cost": 1e-06, + "cache_read_input_token_cost": 8e-08, + "input_cost_per_token": 8e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 200000, + "mode": "chat", + "output_cost_per_token": 4e-06 + }, + "vercel_ai_gateway/anthropic/claude-3.5-sonnet": { + "cache_creation_input_token_cost": 3.75e-06, + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 3e-06, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 200000, + "mode": "chat", + "output_cost_per_token": 1.5e-05 + }, + "vercel_ai_gateway/anthropic/claude-3.7-sonnet": { + "cache_creation_input_token_cost": 3.75e-06, + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 3e-06, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 200000, + "mode": "chat", + "output_cost_per_token": 1.5e-05 + }, + "vercel_ai_gateway/anthropic/claude-4-opus": { + "cache_creation_input_token_cost": 1.875e-05, + "cache_read_input_token_cost": 1.5e-06, + "input_cost_per_token": 1.5e-05, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 200000, + "max_output_tokens": 32000, + "max_tokens": 200000, + "mode": "chat", + "output_cost_per_token": 7.5e-05 + }, + "vercel_ai_gateway/anthropic/claude-4-sonnet": { + "cache_creation_input_token_cost": 3.75e-06, + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 3e-06, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 200000, + "mode": "chat", + "output_cost_per_token": 1.5e-05 + }, + "vercel_ai_gateway/cohere/command-a": { + "input_cost_per_token": 2.5e-06, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 256000, + "max_output_tokens": 8000, "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 1e-05 + }, + "vercel_ai_gateway/cohere/command-r": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 6e-07 + }, + "vercel_ai_gateway/cohere/command-r-plus": { + "input_cost_per_token": 2.5e-06, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05 + }, + "vercel_ai_gateway/cohere/embed-v4.0": { + "input_cost_per_token": 1.2e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 0, + "max_output_tokens": 0, + "max_tokens": 0, + "mode": "chat", + "output_cost_per_token": 0.0 + }, + "vercel_ai_gateway/deepseek/deepseek-r1": { + "input_cost_per_token": 5.5e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2.19e-06 + }, + "vercel_ai_gateway/deepseek/deepseek-r1-distill-llama-70b": { + "input_cost_per_token": 7.5e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 9.9e-07 + }, + "vercel_ai_gateway/deepseek/deepseek-v3": { + "input_cost_per_token": 9e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 9e-07 + }, + "vercel_ai_gateway/google/gemini-2.0-flash": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 6e-07 + }, + "vercel_ai_gateway/google/gemini-2.0-flash-lite": { + "input_cost_per_token": 7.5e-08, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 1048576, + "max_output_tokens": 8192, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 3e-07 + }, + "vercel_ai_gateway/google/gemini-2.5-flash": { + "input_cost_per_token": 3e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 1000000, + "max_output_tokens": 65536, + "max_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 2.5e-06 + }, + "vercel_ai_gateway/google/gemini-2.5-pro": { + "input_cost_per_token": 2.5e-06, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 1e-05 + }, + "vercel_ai_gateway/google/gemini-embedding-001": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 0, + "max_output_tokens": 0, + "max_tokens": 0, + "mode": "embedding", + "output_cost_per_token": 0.0 + }, + "vercel_ai_gateway/google/gemma-2-9b": { + "input_cost_per_token": 2e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 2e-07 + }, + "vercel_ai_gateway/google/text-embedding-005": { + "input_cost_per_token": 2.5e-08, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 0, + "max_output_tokens": 0, + "max_tokens": 0, + "mode": "embedding", + "output_cost_per_token": 0.0 + }, + "vercel_ai_gateway/google/text-multilingual-embedding-002": { + "input_cost_per_token": 2.5e-08, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 0, + "max_output_tokens": 0, + "max_tokens": 0, + "mode": "embedding", + "output_cost_per_token": 0.0 + }, + "vercel_ai_gateway/inception/mercury-coder-small": { + "input_cost_per_token": 2.5e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 32000, + "max_output_tokens": 16384, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 1e-06 + }, + "vercel_ai_gateway/meta/llama-3-70b": { + "input_cost_per_token": 5.9e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 7.9e-07 + }, + "vercel_ai_gateway/meta/llama-3-8b": { + "input_cost_per_token": 5e-08, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 8e-08 + }, + "vercel_ai_gateway/meta/llama-3.1-70b": { + "input_cost_per_token": 7.2e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 7.2e-07 + }, + "vercel_ai_gateway/meta/llama-3.1-8b": { + "input_cost_per_token": 5e-08, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 131000, + "max_output_tokens": 131072, + "max_tokens": 131000, + "mode": "chat", + "output_cost_per_token": 8e-08 + }, + "vercel_ai_gateway/meta/llama-3.2-11b": { + "input_cost_per_token": 1.6e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.6e-07 + }, + "vercel_ai_gateway/meta/llama-3.2-1b": { + "input_cost_per_token": 1e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-07 + }, + "vercel_ai_gateway/meta/llama-3.2-3b": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.5e-07 + }, + "vercel_ai_gateway/meta/llama-3.2-90b": { + "input_cost_per_token": 7.2e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 7.2e-07 + }, + "vercel_ai_gateway/meta/llama-3.3-70b": { + "input_cost_per_token": 7.2e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 7.2e-07 + }, + "vercel_ai_gateway/meta/llama-4-maverick": { + "input_cost_per_token": 2e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 131072, + "max_output_tokens": 8192, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 6e-07 + }, + "vercel_ai_gateway/meta/llama-4-scout": { + "input_cost_per_token": 1e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 131072, + "max_output_tokens": 8192, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 3e-07 + }, + "vercel_ai_gateway/mistral/codestral": { + "input_cost_per_token": 3e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 256000, + "max_output_tokens": 4000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 9e-07 + }, + "vercel_ai_gateway/mistral/codestral-embed": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 0, + "max_output_tokens": 0, + "max_tokens": 0, + "mode": "chat", + "output_cost_per_token": 0.0 + }, + "vercel_ai_gateway/mistral/devstral-small": { + "input_cost_per_token": 7e-08, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2.8e-07 + }, + "vercel_ai_gateway/mistral/magistral-medium": { + "input_cost_per_token": 2e-06, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 128000, + "max_output_tokens": 64000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5e-06 + }, + "vercel_ai_gateway/mistral/magistral-small": { + "input_cost_per_token": 5e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 128000, + "max_output_tokens": 64000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.5e-06 + }, + "vercel_ai_gateway/mistral/ministral-3b": { + "input_cost_per_token": 4e-08, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 128000, + "max_output_tokens": 4000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4e-08 + }, + "vercel_ai_gateway/mistral/ministral-8b": { + "input_cost_per_token": 1e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 128000, + "max_output_tokens": 4000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-07 + }, + "vercel_ai_gateway/mistral/mistral-embed": { + "input_cost_per_token": 1e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 0, + "max_output_tokens": 0, + "max_tokens": 0, + "mode": "chat", + "output_cost_per_token": 0.0 + }, + "vercel_ai_gateway/mistral/mistral-large": { + "input_cost_per_token": 2e-06, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 32000, + "max_output_tokens": 4000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 6e-06 + }, + "vercel_ai_gateway/mistral/mistral-saba-24b": { + "input_cost_per_token": 7.9e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 7.9e-07 + }, + "vercel_ai_gateway/mistral/mistral-small": { + "input_cost_per_token": 1e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 32000, + "max_output_tokens": 4000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 3e-07 + }, + "vercel_ai_gateway/mistral/mixtral-8x22b-instruct": { + "input_cost_per_token": 1.2e-06, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 65536, + "max_output_tokens": 2048, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 1.2e-06 + }, + "vercel_ai_gateway/mistral/pixtral-12b": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 128000, + "max_output_tokens": 4000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.5e-07 + }, + "vercel_ai_gateway/mistral/pixtral-large": { + "input_cost_per_token": 2e-06, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 128000, + "max_output_tokens": 4000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 6e-06 + }, + "vercel_ai_gateway/moonshotai/kimi-k2": { + "input_cost_per_token": 5.5e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 131072, + "max_output_tokens": 16384, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2.2e-06 + }, + "vercel_ai_gateway/morph/morph-v3-fast": { + "input_cost_per_token": 8e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 32768, + "max_output_tokens": 16384, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 1.2e-06 + }, + "vercel_ai_gateway/morph/morph-v3-large": { + "input_cost_per_token": 9e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 32768, + "max_output_tokens": 16384, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 1.9e-06 + }, + "vercel_ai_gateway/openai/gpt-3.5-turbo": { + "input_cost_per_token": 5e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 16385, + "max_output_tokens": 4096, + "max_tokens": 16385, + "mode": "chat", + "output_cost_per_token": 1.5e-06 + }, + "vercel_ai_gateway/openai/gpt-3.5-turbo-instruct": { + "input_cost_per_token": 1.5e-06, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 8192, + "max_output_tokens": 4096, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 2e-06 + }, + "vercel_ai_gateway/openai/gpt-4-turbo": { + "input_cost_per_token": 1e-05, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 3e-05 + }, + "vercel_ai_gateway/openai/gpt-4.1": { + "cache_creation_input_token_cost": 0.0, + "cache_read_input_token_cost": 5e-07, + "input_cost_per_token": 2e-06, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 1047576, + "mode": "chat", + "output_cost_per_token": 8e-06 + }, + "vercel_ai_gateway/openai/gpt-4.1-mini": { + "cache_creation_input_token_cost": 0.0, + "cache_read_input_token_cost": 1e-07, + "input_cost_per_token": 4e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 1047576, + "mode": "chat", + "output_cost_per_token": 1.6e-06 + }, + "vercel_ai_gateway/openai/gpt-4.1-nano": { + "cache_creation_input_token_cost": 0.0, + "cache_read_input_token_cost": 2.5e-08, + "input_cost_per_token": 1e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 1047576, + "max_output_tokens": 32768, + "max_tokens": 1047576, + "mode": "chat", + "output_cost_per_token": 4e-07 + }, + "vercel_ai_gateway/openai/gpt-4o": { + "cache_creation_input_token_cost": 0.0, + "cache_read_input_token_cost": 1.25e-06, + "input_cost_per_token": 2.5e-06, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05 + }, + "vercel_ai_gateway/openai/gpt-4o-mini": { + "cache_creation_input_token_cost": 0.0, + "cache_read_input_token_cost": 7.5e-08, + "input_cost_per_token": 1.5e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 6e-07 + }, + "vercel_ai_gateway/openai/o1": { + "cache_creation_input_token_cost": 0.0, + "cache_read_input_token_cost": 7.5e-06, + "input_cost_per_token": 1.5e-05, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 200000, + "mode": "chat", + "output_cost_per_token": 6e-05 + }, + "vercel_ai_gateway/openai/o3": { + "cache_creation_input_token_cost": 0.0, + "cache_read_input_token_cost": 5e-07, + "input_cost_per_token": 2e-06, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 200000, + "mode": "chat", + "output_cost_per_token": 8e-06 + }, + "vercel_ai_gateway/openai/o3-mini": { + "cache_creation_input_token_cost": 0.0, + "cache_read_input_token_cost": 5.5e-07, + "input_cost_per_token": 1.1e-06, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 200000, + "mode": "chat", + "output_cost_per_token": 4.4e-06 + }, + "vercel_ai_gateway/openai/o4-mini": { + "cache_creation_input_token_cost": 0.0, + "cache_read_input_token_cost": 2.75e-07, + "input_cost_per_token": 1.1e-06, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "max_tokens": 200000, + "mode": "chat", + "output_cost_per_token": 4.4e-06 + }, + "vercel_ai_gateway/openai/text-embedding-3-large": { + "input_cost_per_token": 1.3e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 0, + "max_output_tokens": 0, + "max_tokens": 0, + "mode": "embedding", + "output_cost_per_token": 0.0 + }, + "vercel_ai_gateway/openai/text-embedding-3-small": { + "input_cost_per_token": 2e-08, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 0, + "max_output_tokens": 0, + "max_tokens": 0, + "mode": "embedding", + "output_cost_per_token": 0.0 + }, + "vercel_ai_gateway/openai/text-embedding-ada-002": { + "input_cost_per_token": 1e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 0, + "max_output_tokens": 0, + "max_tokens": 0, + "mode": "embedding", + "output_cost_per_token": 0.0 + }, + "vercel_ai_gateway/perplexity/sonar": { + "input_cost_per_token": 1e-06, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 127000, + "max_output_tokens": 8000, + "max_tokens": 127000, + "mode": "chat", + "output_cost_per_token": 1e-06 + }, + "vercel_ai_gateway/perplexity/sonar-pro": { + "input_cost_per_token": 3e-06, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 200000, + "max_output_tokens": 8000, + "max_tokens": 200000, + "mode": "chat", + "output_cost_per_token": 1.5e-05 + }, + "vercel_ai_gateway/perplexity/sonar-reasoning": { + "input_cost_per_token": 1e-06, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 127000, + "max_output_tokens": 8000, + "max_tokens": 127000, + "mode": "chat", + "output_cost_per_token": 5e-06 + }, + "vercel_ai_gateway/perplexity/sonar-reasoning-pro": { + "input_cost_per_token": 2e-06, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 127000, + "max_output_tokens": 8000, + "max_tokens": 127000, + "mode": "chat", + "output_cost_per_token": 8e-06 + }, + "vercel_ai_gateway/vercel/v0-1.0-md": { + "input_cost_per_token": 3e-06, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 128000, + "max_output_tokens": 32000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.5e-05 + }, + "vercel_ai_gateway/vercel/v0-1.5-md": { + "input_cost_per_token": 3e-06, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 128000, + "max_output_tokens": 32768, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.5e-05 + }, + "vercel_ai_gateway/xai/grok-2": { + "input_cost_per_token": 2e-06, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 131072, + "max_output_tokens": 4000, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1e-05 + }, + "vercel_ai_gateway/xai/grok-2-vision": { + "input_cost_per_token": 2e-06, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 1e-05 + }, + "vercel_ai_gateway/xai/grok-3": { + "input_cost_per_token": 3e-06, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.5e-05 + }, + "vercel_ai_gateway/xai/grok-3-fast": { + "input_cost_per_token": 5e-06, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2.5e-05 + }, + "vercel_ai_gateway/xai/grok-3-mini": { + "input_cost_per_token": 3e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 5e-07 + }, + "vercel_ai_gateway/xai/grok-3-mini-fast": { + "input_cost_per_token": 6e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4e-06 + }, + "vercel_ai_gateway/xai/grok-4": { + "input_cost_per_token": 3e-06, + "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 256000, "max_output_tokens": 256000, - "input_cost_per_token": 1.9e-07, - "output_cost_per_token": 1.9e-07, - "litellm_provider": "ovhcloud", + "max_tokens": 256000, "mode": "chat", - "supports_function_calling": false, + "output_cost_per_token": 1.5e-05 + }, + "vercel_ai_gateway/zai/glm-4.5": { + "input_cost_per_token": 6e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2.2e-06 + }, + "vercel_ai_gateway/zai/glm-4.5-air": { + "input_cost_per_token": 2e-07, + "litellm_provider": "vercel_ai_gateway", + "max_input_tokens": 128000, + "max_output_tokens": 96000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.1e-06 + }, + "vertex_ai/claude-3-5-haiku": { + "input_cost_per_token": 1e-06, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 5e-06, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_tool_choice": true + }, + "vertex_ai/claude-3-5-haiku@20241022": { + "input_cost_per_token": 1e-06, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 5e-06, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_tool_choice": true + }, + "vertex_ai/claude-3-5-sonnet": { + "input_cost_per_token": 3e-06, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "vertex_ai/claude-3-5-sonnet-v2": { + "input_cost_per_token": 3e-06, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "vertex_ai/claude-3-5-sonnet-v2@20241022": { + "input_cost_per_token": 3e-06, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "vertex_ai/claude-3-5-sonnet@20240620": { + "input_cost_per_token": 3e-06, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "vertex_ai/claude-3-7-sonnet@20250219": { + "cache_creation_input_token_cost": 3.75e-06, + "cache_read_input_token_cost": 3e-07, + "deprecation_date": "2025-06-01", + "input_cost_per_token": 3e-06, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 200000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, "supports_response_schema": true, - "supports_tool_choice": false, - "source": "https://endpoints.ai.cloud.ovh.net/models/mamba-codestral-7b-v0-1" + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159 + }, + "vertex_ai/claude-3-haiku": { + "input_cost_per_token": 2.5e-07, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.25e-06, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "vertex_ai/claude-3-haiku@20240307": { + "input_cost_per_token": 2.5e-07, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.25e-06, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "vertex_ai/claude-3-opus": { + "input_cost_per_token": 1.5e-05, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 7.5e-05, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "vertex_ai/claude-3-opus@20240229": { + "input_cost_per_token": 1.5e-05, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 7.5e-05, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "vertex_ai/claude-3-sonnet": { + "input_cost_per_token": 3e-06, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "vertex_ai/claude-3-sonnet@20240229": { + "input_cost_per_token": 3e-06, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "vertex_ai/claude-opus-4": { + "cache_creation_input_token_cost": 1.875e-05, + "cache_read_input_token_cost": 1.5e-06, + "input_cost_per_token": 1.5e-05, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 200000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 7.5e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159 + }, + "vertex_ai/claude-opus-4-1": { + "cache_creation_input_token_cost": 1.875e-05, + "cache_read_input_token_cost": 1.5e-06, + "input_cost_per_token": 1.5e-05, + "input_cost_per_token_batches": 7.5e-06, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 7.5e-05, + "output_cost_per_token_batches": 3.75e-05, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "vertex_ai/claude-opus-4-1@20250805": { + "cache_creation_input_token_cost": 1.875e-05, + "cache_read_input_token_cost": 1.5e-06, + "input_cost_per_token": 1.5e-05, + "input_cost_per_token_batches": 7.5e-06, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 200000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 7.5e-05, + "output_cost_per_token_batches": 3.75e-05, + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "vertex_ai/claude-opus-4@20250514": { + "cache_creation_input_token_cost": 1.875e-05, + "cache_read_input_token_cost": 1.5e-06, + "input_cost_per_token": 1.5e-05, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 200000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 7.5e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159 + }, + "vertex_ai/claude-sonnet-4": { + "cache_creation_input_token_cost": 3.75e-06, + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 3e-06, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159 + }, + "vertex_ai/claude-sonnet-4@20250514": { + "cache_creation_input_token_cost": 3.75e-06, + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 3e-06, + "litellm_provider": "vertex_ai-anthropic_models", + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159 + }, + "vertex_ai/codestral-2501": { + "input_cost_per_token": 2e-07, + "litellm_provider": "vertex_ai-mistral_models", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 6e-07, + "supports_function_calling": true, + "supports_tool_choice": true + }, + "vertex_ai/codestral@2405": { + "input_cost_per_token": 2e-07, + "litellm_provider": "vertex_ai-mistral_models", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 6e-07, + "supports_function_calling": true, + "supports_tool_choice": true + }, + "vertex_ai/codestral@latest": { + "input_cost_per_token": 2e-07, + "litellm_provider": "vertex_ai-mistral_models", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 6e-07, + "supports_function_calling": true, + "supports_tool_choice": true + }, + "vertex_ai/deepseek-ai/deepseek-r1-0528-maas": { + "input_cost_per_token": 1.35e-06, + "litellm_provider": "vertex_ai-deepseek_models", + "max_input_tokens": 65336, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 5.4e-06, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "vertex_ai/imagegeneration@006": { + "litellm_provider": "vertex_ai-image-models", + "mode": "image_generation", + "output_cost_per_image": 0.02, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" + }, + "vertex_ai/imagen-3.0-fast-generate-001": { + "litellm_provider": "vertex_ai-image-models", + "mode": "image_generation", + "output_cost_per_image": 0.02, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" + }, + "vertex_ai/imagen-3.0-generate-001": { + "litellm_provider": "vertex_ai-image-models", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" + }, + "vertex_ai/imagen-3.0-generate-002": { + "litellm_provider": "vertex_ai-image-models", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" + }, + "vertex_ai/imagen-4.0-fast-generate-001": { + "litellm_provider": "vertex_ai-image-models", + "mode": "image_generation", + "output_cost_per_image": 0.02, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" + }, + "vertex_ai/imagen-4.0-generate-001": { + "litellm_provider": "vertex_ai-image-models", + "mode": "image_generation", + "output_cost_per_image": 0.04, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" + }, + "vertex_ai/imagen-4.0-ultra-generate-001": { + "litellm_provider": "vertex_ai-image-models", + "mode": "image_generation", + "output_cost_per_image": 0.06, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" + }, + "vertex_ai/jamba-1.5": { + "input_cost_per_token": 2e-07, + "litellm_provider": "vertex_ai-ai21_models", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 4e-07, + "supports_tool_choice": true + }, + "vertex_ai/jamba-1.5-large": { + "input_cost_per_token": 2e-06, + "litellm_provider": "vertex_ai-ai21_models", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 8e-06, + "supports_tool_choice": true + }, + "vertex_ai/jamba-1.5-large@001": { + "input_cost_per_token": 2e-06, + "litellm_provider": "vertex_ai-ai21_models", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 8e-06, + "supports_tool_choice": true + }, + "vertex_ai/jamba-1.5-mini": { + "input_cost_per_token": 2e-07, + "litellm_provider": "vertex_ai-ai21_models", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 4e-07, + "supports_tool_choice": true + }, + "vertex_ai/jamba-1.5-mini@001": { + "input_cost_per_token": 2e-07, + "litellm_provider": "vertex_ai-ai21_models", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 4e-07, + "supports_tool_choice": true + }, + "vertex_ai/meta/llama-3.1-405b-instruct-maas": { + "input_cost_per_token": 5e-06, + "litellm_provider": "vertex_ai-llama_models", + "max_input_tokens": 128000, + "max_output_tokens": 2048, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.6e-05, + "source": "https://console.cloud.google.com/vertex-ai/publishers/meta/model-garden/llama-3.2-90b-vision-instruct-maas", + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "vertex_ai/meta/llama-3.1-70b-instruct-maas": { + "input_cost_per_token": 0.0, + "litellm_provider": "vertex_ai-llama_models", + "max_input_tokens": 128000, + "max_output_tokens": 2048, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 0.0, + "source": "https://console.cloud.google.com/vertex-ai/publishers/meta/model-garden/llama-3.2-90b-vision-instruct-maas", + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "vertex_ai/meta/llama-3.1-8b-instruct-maas": { + "input_cost_per_token": 0.0, + "litellm_provider": "vertex_ai-llama_models", + "max_input_tokens": 128000, + "max_output_tokens": 2048, + "max_tokens": 128000, + "metadata": { + "notes": "VertexAI states that The Llama 3.1 API service for llama-3.1-70b-instruct-maas and llama-3.1-8b-instruct-maas are in public preview and at no cost." + }, + "mode": "chat", + "output_cost_per_token": 0.0, + "source": "https://console.cloud.google.com/vertex-ai/publishers/meta/model-garden/llama-3.2-90b-vision-instruct-maas", + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "vertex_ai/meta/llama-3.2-90b-vision-instruct-maas": { + "input_cost_per_token": 0.0, + "litellm_provider": "vertex_ai-llama_models", + "max_input_tokens": 128000, + "max_output_tokens": 2048, + "max_tokens": 128000, + "metadata": { + "notes": "VertexAI states that The Llama 3.2 API service is at no cost during public preview, and will be priced as per dollar-per-1M-tokens at GA." + }, + "mode": "chat", + "output_cost_per_token": 0.0, + "source": "https://console.cloud.google.com/vertex-ai/publishers/meta/model-garden/llama-3.2-90b-vision-instruct-maas", + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "vertex_ai/meta/llama-4-maverick-17b-128e-instruct-maas": { + "input_cost_per_token": 3.5e-07, + "litellm_provider": "vertex_ai-llama_models", + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "max_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 1.15e-06, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text", + "code" + ], + "supports_function_calling": true, + "supports_tool_choice": true + }, + "vertex_ai/meta/llama-4-maverick-17b-16e-instruct-maas": { + "input_cost_per_token": 3.5e-07, + "litellm_provider": "vertex_ai-llama_models", + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "max_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 1.15e-06, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text", + "code" + ], + "supports_function_calling": true, + "supports_tool_choice": true + }, + "vertex_ai/meta/llama-4-scout-17b-128e-instruct-maas": { + "input_cost_per_token": 2.5e-07, + "litellm_provider": "vertex_ai-llama_models", + "max_input_tokens": 10000000, + "max_output_tokens": 10000000, + "max_tokens": 10000000, + "mode": "chat", + "output_cost_per_token": 7e-07, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text", + "code" + ], + "supports_function_calling": true, + "supports_tool_choice": true + }, + "vertex_ai/meta/llama-4-scout-17b-16e-instruct-maas": { + "input_cost_per_token": 2.5e-07, + "litellm_provider": "vertex_ai-llama_models", + "max_input_tokens": 10000000, + "max_output_tokens": 10000000, + "max_tokens": 10000000, + "mode": "chat", + "output_cost_per_token": 7e-07, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text", + "code" + ], + "supports_function_calling": true, + "supports_tool_choice": true + }, + "vertex_ai/meta/llama3-405b-instruct-maas": { + "input_cost_per_token": 0.0, + "litellm_provider": "vertex_ai-llama_models", + "max_input_tokens": 32000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 0.0, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", + "supports_tool_choice": true + }, + "vertex_ai/meta/llama3-70b-instruct-maas": { + "input_cost_per_token": 0.0, + "litellm_provider": "vertex_ai-llama_models", + "max_input_tokens": 32000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 0.0, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", + "supports_tool_choice": true + }, + "vertex_ai/meta/llama3-8b-instruct-maas": { + "input_cost_per_token": 0.0, + "litellm_provider": "vertex_ai-llama_models", + "max_input_tokens": 32000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 0.0, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", + "supports_tool_choice": true + }, + "vertex_ai/mistral-large-2411": { + "input_cost_per_token": 2e-06, + "litellm_provider": "vertex_ai-mistral_models", + "max_input_tokens": 128000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 6e-06, + "supports_function_calling": true, + "supports_tool_choice": true + }, + "vertex_ai/mistral-large@2407": { + "input_cost_per_token": 2e-06, + "litellm_provider": "vertex_ai-mistral_models", + "max_input_tokens": 128000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 6e-06, + "supports_function_calling": true, + "supports_tool_choice": true + }, + "vertex_ai/mistral-large@2411-001": { + "input_cost_per_token": 2e-06, + "litellm_provider": "vertex_ai-mistral_models", + "max_input_tokens": 128000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 6e-06, + "supports_function_calling": true, + "supports_tool_choice": true + }, + "vertex_ai/mistral-large@latest": { + "input_cost_per_token": 2e-06, + "litellm_provider": "vertex_ai-mistral_models", + "max_input_tokens": 128000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 6e-06, + "supports_function_calling": true, + "supports_tool_choice": true + }, + "vertex_ai/mistral-nemo@2407": { + "input_cost_per_token": 3e-06, + "litellm_provider": "vertex_ai-mistral_models", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 3e-06, + "supports_function_calling": true, + "supports_tool_choice": true + }, + "vertex_ai/mistral-nemo@latest": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "vertex_ai-mistral_models", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.5e-07, + "supports_function_calling": true, + "supports_tool_choice": true + }, + "vertex_ai/mistral-small-2503": { + "input_cost_per_token": 1e-06, + "litellm_provider": "vertex_ai-mistral_models", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 3e-06, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "vertex_ai/mistral-small-2503@001": { + "input_cost_per_token": 1e-06, + "litellm_provider": "vertex_ai-mistral_models", + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "max_tokens": 8191, + "mode": "chat", + "output_cost_per_token": 3e-06, + "supports_function_calling": true, + "supports_tool_choice": true + }, + "vertex_ai/openai/gpt-oss-120b-maas": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "vertex_ai-openai_models", + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 6e-07, + "source": "https://console.cloud.google.com/vertex-ai/publishers/openai/model-garden/gpt-oss-120b-maas", + "supports_reasoning": true + }, + "vertex_ai/openai/gpt-oss-20b-maas": { + "input_cost_per_token": 7.5e-08, + "litellm_provider": "vertex_ai-openai_models", + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 3e-07, + "source": "https://console.cloud.google.com/vertex-ai/publishers/openai/model-garden/gpt-oss-120b-maas", + "supports_reasoning": true + }, + "vertex_ai/qwen/qwen3-235b-a22b-instruct-2507-maas": { + "input_cost_per_token": 2.5e-07, + "litellm_provider": "vertex_ai-qwen_models", + "max_input_tokens": 262144, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1e-06, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "supports_function_calling": true, + "supports_tool_choice": true + }, + "vertex_ai/qwen/qwen3-coder-480b-a35b-instruct-maas": { + "input_cost_per_token": 1e-06, + "litellm_provider": "vertex_ai-qwen_models", + "max_input_tokens": 262144, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 4e-06, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "supports_function_calling": true, + "supports_tool_choice": true + }, + "vertex_ai/veo-2.0-generate-001": { + "litellm_provider": "vertex_ai-video-models", + "max_input_tokens": 1024, + "max_tokens": 1024, + "mode": "video_generation", + "output_cost_per_second": 0.35, + "source": "https://ai.google.dev/gemini-api/docs/video", + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "vertex_ai/veo-3.0-fast-generate-preview": { + "litellm_provider": "vertex_ai-video-models", + "max_input_tokens": 1024, + "max_tokens": 1024, + "mode": "video_generation", + "output_cost_per_second": 0.4, + "source": "https://ai.google.dev/gemini-api/docs/video", + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "vertex_ai/veo-3.0-generate-preview": { + "litellm_provider": "vertex_ai-video-models", + "max_input_tokens": 1024, + "max_tokens": 1024, + "mode": "video_generation", + "output_cost_per_second": 0.75, + "source": "https://ai.google.dev/gemini-api/docs/video", + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "voyage/rerank-2": { + "input_cost_per_query": 5e-08, + "input_cost_per_token": 5e-08, + "litellm_provider": "voyage", + "max_input_tokens": 16000, + "max_output_tokens": 16000, + "max_query_tokens": 16000, + "max_tokens": 16000, + "mode": "rerank", + "output_cost_per_token": 0.0 + }, + "voyage/rerank-2-lite": { + "input_cost_per_query": 2e-08, + "input_cost_per_token": 2e-08, + "litellm_provider": "voyage", + "max_input_tokens": 8000, + "max_output_tokens": 8000, + "max_query_tokens": 8000, + "max_tokens": 8000, + "mode": "rerank", + "output_cost_per_token": 0.0 + }, + "voyage/voyage-2": { + "input_cost_per_token": 1e-07, + "litellm_provider": "voyage", + "max_input_tokens": 4000, + "max_tokens": 4000, + "mode": "embedding", + "output_cost_per_token": 0.0 + }, + "voyage/voyage-3": { + "input_cost_per_token": 6e-08, + "litellm_provider": "voyage", + "max_input_tokens": 32000, + "max_tokens": 32000, + "mode": "embedding", + "output_cost_per_token": 0.0 + }, + "voyage/voyage-3-large": { + "input_cost_per_token": 1.8e-07, + "litellm_provider": "voyage", + "max_input_tokens": 32000, + "max_tokens": 32000, + "mode": "embedding", + "output_cost_per_token": 0.0 + }, + "voyage/voyage-3-lite": { + "input_cost_per_token": 2e-08, + "litellm_provider": "voyage", + "max_input_tokens": 32000, + "max_tokens": 32000, + "mode": "embedding", + "output_cost_per_token": 0.0 + }, + "voyage/voyage-code-2": { + "input_cost_per_token": 1.2e-07, + "litellm_provider": "voyage", + "max_input_tokens": 16000, + "max_tokens": 16000, + "mode": "embedding", + "output_cost_per_token": 0.0 + }, + "voyage/voyage-code-3": { + "input_cost_per_token": 1.8e-07, + "litellm_provider": "voyage", + "max_input_tokens": 32000, + "max_tokens": 32000, + "mode": "embedding", + "output_cost_per_token": 0.0 + }, + "voyage/voyage-context-3": { + "input_cost_per_token": 1.8e-07, + "litellm_provider": "voyage", + "max_input_tokens": 120000, + "max_tokens": 120000, + "mode": "embedding", + "output_cost_per_token": 0.0 + }, + "voyage/voyage-finance-2": { + "input_cost_per_token": 1.2e-07, + "litellm_provider": "voyage", + "max_input_tokens": 32000, + "max_tokens": 32000, + "mode": "embedding", + "output_cost_per_token": 0.0 + }, + "voyage/voyage-large-2": { + "input_cost_per_token": 1.2e-07, + "litellm_provider": "voyage", + "max_input_tokens": 16000, + "max_tokens": 16000, + "mode": "embedding", + "output_cost_per_token": 0.0 + }, + "voyage/voyage-law-2": { + "input_cost_per_token": 1.2e-07, + "litellm_provider": "voyage", + "max_input_tokens": 16000, + "max_tokens": 16000, + "mode": "embedding", + "output_cost_per_token": 0.0 + }, + "voyage/voyage-lite-01": { + "input_cost_per_token": 1e-07, + "litellm_provider": "voyage", + "max_input_tokens": 4096, + "max_tokens": 4096, + "mode": "embedding", + "output_cost_per_token": 0.0 + }, + "voyage/voyage-lite-02-instruct": { + "input_cost_per_token": 1e-07, + "litellm_provider": "voyage", + "max_input_tokens": 4000, + "max_tokens": 4000, + "mode": "embedding", + "output_cost_per_token": 0.0 + }, + "voyage/voyage-multimodal-3": { + "input_cost_per_token": 1.2e-07, + "litellm_provider": "voyage", + "max_input_tokens": 32000, + "max_tokens": 32000, + "mode": "embedding", + "output_cost_per_token": 0.0 + }, + "watsonx/ibm/granite-3-8b-instruct": { + "input_cost_per_token": 0.0002, + "litellm_provider": "watsonx", + "max_input_tokens": 8192, + "max_output_tokens": 1024, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 0.0002, + "supports_audio_input": false, + "supports_audio_output": false, + "supports_function_calling": true, + "supports_parallel_function_calling": false, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "watsonx/mistralai/mistral-large": { + "input_cost_per_token": 3e-06, + "litellm_provider": "watsonx", + "max_input_tokens": 131072, + "max_output_tokens": 16384, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1e-05, + "supports_audio_input": false, + "supports_audio_output": false, + "supports_function_calling": true, + "supports_parallel_function_calling": false, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "whisper-1": { + "input_cost_per_second": 0.0001, + "litellm_provider": "openai", + "mode": "audio_transcription", + "output_cost_per_second": 0.0001, + "supported_endpoints": [ + "/v1/audio/transcriptions" + ] + }, + "xai/grok-2": { + "input_cost_per_token": 2e-06, + "litellm_provider": "xai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1e-05, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_web_search": true + }, + "xai/grok-2-1212": { + "input_cost_per_token": 2e-06, + "litellm_provider": "xai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1e-05, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_web_search": true + }, + "xai/grok-2-latest": { + "input_cost_per_token": 2e-06, + "litellm_provider": "xai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1e-05, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_web_search": true + }, + "xai/grok-2-vision": { + "input_cost_per_image": 2e-06, + "input_cost_per_token": 2e-06, + "litellm_provider": "xai", + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 1e-05, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "xai/grok-2-vision-1212": { + "input_cost_per_image": 2e-06, + "input_cost_per_token": 2e-06, + "litellm_provider": "xai", + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 1e-05, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "xai/grok-2-vision-latest": { + "input_cost_per_image": 2e-06, + "input_cost_per_token": 2e-06, + "litellm_provider": "xai", + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 1e-05, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "xai/grok-3": { + "input_cost_per_token": 3e-06, + "litellm_provider": "xai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "source": "https://x.ai/api#pricing", + "supports_function_calling": true, + "supports_response_schema": false, + "supports_tool_choice": true, + "supports_web_search": true + }, + "xai/grok-3-beta": { + "input_cost_per_token": 3e-06, + "litellm_provider": "xai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "source": "https://x.ai/api#pricing", + "supports_function_calling": true, + "supports_response_schema": false, + "supports_tool_choice": true, + "supports_web_search": true + }, + "xai/grok-3-fast-beta": { + "input_cost_per_token": 5e-06, + "litellm_provider": "xai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2.5e-05, + "source": "https://x.ai/api#pricing", + "supports_function_calling": true, + "supports_response_schema": false, + "supports_tool_choice": true, + "supports_web_search": true + }, + "xai/grok-3-fast-latest": { + "input_cost_per_token": 5e-06, + "litellm_provider": "xai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2.5e-05, + "source": "https://x.ai/api#pricing", + "supports_function_calling": true, + "supports_response_schema": false, + "supports_tool_choice": true, + "supports_web_search": true + }, + "xai/grok-3-latest": { + "input_cost_per_token": 3e-06, + "litellm_provider": "xai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "source": "https://x.ai/api#pricing", + "supports_function_calling": true, + "supports_response_schema": false, + "supports_tool_choice": true, + "supports_web_search": true + }, + "xai/grok-3-mini": { + "input_cost_per_token": 3e-07, + "litellm_provider": "xai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 5e-07, + "source": "https://x.ai/api#pricing", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": false, + "supports_tool_choice": true, + "supports_web_search": true + }, + "xai/grok-3-mini-beta": { + "input_cost_per_token": 3e-07, + "litellm_provider": "xai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 5e-07, + "source": "https://x.ai/api#pricing", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": false, + "supports_tool_choice": true, + "supports_web_search": true + }, + "xai/grok-3-mini-fast": { + "input_cost_per_token": 6e-07, + "litellm_provider": "xai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4e-06, + "source": "https://x.ai/api#pricing", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": false, + "supports_tool_choice": true, + "supports_web_search": true + }, + "xai/grok-3-mini-fast-beta": { + "input_cost_per_token": 6e-07, + "litellm_provider": "xai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4e-06, + "source": "https://x.ai/api#pricing", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": false, + "supports_tool_choice": true, + "supports_web_search": true + }, + "xai/grok-3-mini-fast-latest": { + "input_cost_per_token": 6e-07, + "litellm_provider": "xai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4e-06, + "source": "https://x.ai/api#pricing", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": false, + "supports_tool_choice": true, + "supports_web_search": true + }, + "xai/grok-3-mini-latest": { + "input_cost_per_token": 3e-07, + "litellm_provider": "xai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 5e-07, + "source": "https://x.ai/api#pricing", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": false, + "supports_tool_choice": true, + "supports_web_search": true + }, + "xai/grok-4": { + "input_cost_per_token": 3e-06, + "litellm_provider": "xai", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "source": "https://docs.x.ai/docs/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_web_search": true + }, + "xai/grok-4-0709": { + "input_cost_per_token": 3e-06, + "litellm_provider": "xai", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "source": "https://docs.x.ai/docs/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_web_search": true + }, + "xai/grok-4-latest": { + "input_cost_per_token": 3e-06, + "litellm_provider": "xai", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "source": "https://docs.x.ai/docs/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_web_search": true + }, + "xai/grok-beta": { + "input_cost_per_token": 5e-06, + "litellm_provider": "xai", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "xai/grok-code-fast": { + "cache_read_input_token_cost": 2e-08, + "input_cost_per_token": 2e-07, + "litellm_provider": "xai", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 1.5e-06, + "source": "https://docs.x.ai/docs/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "xai/grok-code-fast-1": { + "cache_read_input_token_cost": 2e-08, + "input_cost_per_token": 2e-07, + "litellm_provider": "xai", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 1.5e-06, + "source": "https://docs.x.ai/docs/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "xai/grok-code-fast-1-0825": { + "cache_read_input_token_cost": 2e-08, + "input_cost_per_token": 2e-07, + "litellm_provider": "xai", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 1.5e-06, + "source": "https://docs.x.ai/docs/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "xai/grok-vision-beta": { + "input_cost_per_image": 5e-06, + "input_cost_per_token": 5e-06, + "litellm_provider": "xai", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true } -} +} \ No newline at end of file From a2bfd3e4764e9504c0d090b2b22cc3b1e6abf21b Mon Sep 17 00:00:00 2001 From: Krrish Dholakia Date: Tue, 16 Sep 2025 18:53:56 -0700 Subject: [PATCH 21/34] build(model_prices_and_context_window.json): add claude-opus-4-1 "cache_creation_input_token_cost_above_1hr" pricing --- litellm/model_prices_and_context_window_backup.json | 2 ++ model_prices_and_context_window.json | 2 ++ 2 files changed, 4 insertions(+) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 1452f1465d..1c85c208f5 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -4637,6 +4637,7 @@ }, "claude-opus-4-1": { "cache_creation_input_token_cost": 1.875e-05, + "cache_creation_input_token_cost_above_1hr": 3e-05, "cache_read_input_token_cost": 1.5e-06, "input_cost_per_token": 1.5e-05, "litellm_provider": "anthropic", @@ -4663,6 +4664,7 @@ }, "claude-opus-4-1-20250805": { "cache_creation_input_token_cost": 1.875e-05, + "cache_creation_input_token_cost_above_1hr": 3e-05, "cache_read_input_token_cost": 1.5e-06, "input_cost_per_token": 1.5e-05, "litellm_provider": "anthropic", diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 1452f1465d..1c85c208f5 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -4637,6 +4637,7 @@ }, "claude-opus-4-1": { "cache_creation_input_token_cost": 1.875e-05, + "cache_creation_input_token_cost_above_1hr": 3e-05, "cache_read_input_token_cost": 1.5e-06, "input_cost_per_token": 1.5e-05, "litellm_provider": "anthropic", @@ -4663,6 +4664,7 @@ }, "claude-opus-4-1-20250805": { "cache_creation_input_token_cost": 1.875e-05, + "cache_creation_input_token_cost_above_1hr": 3e-05, "cache_read_input_token_cost": 1.5e-06, "input_cost_per_token": 1.5e-05, "litellm_provider": "anthropic", From 3188ae92813ad2be12e9cdbd74703a25c419bbca Mon Sep 17 00:00:00 2001 From: Krrish Dholakia Date: Tue, 16 Sep 2025 18:56:24 -0700 Subject: [PATCH 22/34] build(model_prices_and_context_window.json): add claude-opus-4, claude-3-7-sonnet, claude-sonnet-4 "cache_creation_input_token_cost_above_1hr" pricing --- litellm/model_prices_and_context_window_backup.json | 4 ++++ model_prices_and_context_window.json | 4 ++++ 2 files changed, 8 insertions(+) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 1c85c208f5..c0ee3703d1 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -4469,6 +4469,7 @@ }, "claude-3-7-sonnet-20250219": { "cache_creation_input_token_cost": 3.75e-06, + "cache_creation_input_token_cost_above_1hr": 6e-06, "cache_read_input_token_cost": 3e-07, "deprecation_date": "2026-02-01", "input_cost_per_token": 3e-06, @@ -4497,6 +4498,7 @@ }, "claude-3-7-sonnet-latest": { "cache_creation_input_token_cost": 3.75e-06, + "cache_creation_input_token_cost_above_1hr": 6e-06, "cache_read_input_token_cost": 3e-07, "deprecation_date": "2025-06-01", "input_cost_per_token": 3e-06, @@ -4691,6 +4693,7 @@ }, "claude-opus-4-20250514": { "cache_creation_input_token_cost": 1.875e-05, + "cache_creation_input_token_cost_above_1hr": 3e-05, "cache_read_input_token_cost": 1.5e-06, "input_cost_per_token": 1.5e-05, "litellm_provider": "anthropic", @@ -4717,6 +4720,7 @@ }, "claude-sonnet-4-20250514": { "cache_creation_input_token_cost": 3.75e-06, + "cache_creation_input_token_cost_above_1hr": 6e-06, "cache_read_input_token_cost": 3e-07, "input_cost_per_token": 3e-06, "litellm_provider": "anthropic", diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 1c85c208f5..c0ee3703d1 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -4469,6 +4469,7 @@ }, "claude-3-7-sonnet-20250219": { "cache_creation_input_token_cost": 3.75e-06, + "cache_creation_input_token_cost_above_1hr": 6e-06, "cache_read_input_token_cost": 3e-07, "deprecation_date": "2026-02-01", "input_cost_per_token": 3e-06, @@ -4497,6 +4498,7 @@ }, "claude-3-7-sonnet-latest": { "cache_creation_input_token_cost": 3.75e-06, + "cache_creation_input_token_cost_above_1hr": 6e-06, "cache_read_input_token_cost": 3e-07, "deprecation_date": "2025-06-01", "input_cost_per_token": 3e-06, @@ -4691,6 +4693,7 @@ }, "claude-opus-4-20250514": { "cache_creation_input_token_cost": 1.875e-05, + "cache_creation_input_token_cost_above_1hr": 3e-05, "cache_read_input_token_cost": 1.5e-06, "input_cost_per_token": 1.5e-05, "litellm_provider": "anthropic", @@ -4717,6 +4720,7 @@ }, "claude-sonnet-4-20250514": { "cache_creation_input_token_cost": 3.75e-06, + "cache_creation_input_token_cost_above_1hr": 6e-06, "cache_read_input_token_cost": 3e-07, "input_cost_per_token": 3e-06, "litellm_provider": "anthropic", From 97cc5f55d633df86c27a2fcc446dff02234e1f21 Mon Sep 17 00:00:00 2001 From: Krrish Dholakia Date: Tue, 16 Sep 2025 18:58:49 -0700 Subject: [PATCH 23/34] build(model_prices_and_context_window.json): add claude-3-5 haiku, claude-3-5 sonnet, claude-opus 3, claude-haiku 3 "cache_creation_input_token_cost_above_1hr" pricing --- litellm/model_prices_and_context_window_backup.json | 12 ++++++++---- model_prices_and_context_window.json | 12 ++++++++---- 2 files changed, 16 insertions(+), 8 deletions(-) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index c0ee3703d1..5e5bccb81e 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -4339,7 +4339,7 @@ }, "claude-3-5-haiku-20241022": { "cache_creation_input_token_cost": 1e-06, - "cache_creation_input_token_cost_above_1hr": 1.6e-06, + "cache_creation_input_token_cost_above_1hr": 6e-06, "cache_read_input_token_cost": 8e-08, "deprecation_date": "2025-10-01", "input_cost_per_token": 8e-07, @@ -4366,6 +4366,7 @@ }, "claude-3-5-haiku-latest": { "cache_creation_input_token_cost": 1.25e-06, + "cache_creation_input_token_cost_above_1hr": 6e-06, "cache_read_input_token_cost": 1e-07, "deprecation_date": "2025-10-01", "input_cost_per_token": 1e-06, @@ -4392,7 +4393,7 @@ }, "claude-3-5-sonnet-20240620": { "cache_creation_input_token_cost": 3.75e-06, - "cache_creation_input_token_cost_above_1hr": 1.6e-06, + "cache_creation_input_token_cost_above_1hr": 6e-06, "cache_read_input_token_cost": 3e-07, "deprecation_date": "2025-06-01", "input_cost_per_token": 3e-06, @@ -4413,7 +4414,7 @@ }, "claude-3-5-sonnet-20241022": { "cache_creation_input_token_cost": 3.75e-06, - "cache_creation_input_token_cost_above_1hr": 1.6e-06, + "cache_creation_input_token_cost_above_1hr": 6e-06, "cache_read_input_token_cost": 3e-07, "deprecation_date": "2025-10-01", "input_cost_per_token": 3e-06, @@ -4441,7 +4442,7 @@ }, "claude-3-5-sonnet-latest": { "cache_creation_input_token_cost": 3.75e-06, - "cache_creation_input_token_cost_above_1hr": 1.6e-06, + "cache_creation_input_token_cost_above_1hr": 6e-06, "cache_read_input_token_cost": 3e-07, "deprecation_date": "2025-06-01", "input_cost_per_token": 3e-06, @@ -4526,6 +4527,7 @@ }, "claude-3-haiku-20240307": { "cache_creation_input_token_cost": 3e-07, + "cache_creation_input_token_cost_above_1hr": 6e-06, "cache_read_input_token_cost": 3e-08, "deprecation_date": "2025-03-01", "input_cost_per_token": 2.5e-07, @@ -4545,6 +4547,7 @@ }, "claude-3-opus-20240229": { "cache_creation_input_token_cost": 1.875e-05, + "cache_creation_input_token_cost_above_1hr": 6e-06, "cache_read_input_token_cost": 1.5e-06, "deprecation_date": "2025-03-01", "input_cost_per_token": 1.5e-05, @@ -4564,6 +4567,7 @@ }, "claude-3-opus-latest": { "cache_creation_input_token_cost": 1.875e-05, + "cache_creation_input_token_cost_above_1hr": 6e-06, "cache_read_input_token_cost": 1.5e-06, "deprecation_date": "2025-03-01", "input_cost_per_token": 1.5e-05, diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index c0ee3703d1..5e5bccb81e 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -4339,7 +4339,7 @@ }, "claude-3-5-haiku-20241022": { "cache_creation_input_token_cost": 1e-06, - "cache_creation_input_token_cost_above_1hr": 1.6e-06, + "cache_creation_input_token_cost_above_1hr": 6e-06, "cache_read_input_token_cost": 8e-08, "deprecation_date": "2025-10-01", "input_cost_per_token": 8e-07, @@ -4366,6 +4366,7 @@ }, "claude-3-5-haiku-latest": { "cache_creation_input_token_cost": 1.25e-06, + "cache_creation_input_token_cost_above_1hr": 6e-06, "cache_read_input_token_cost": 1e-07, "deprecation_date": "2025-10-01", "input_cost_per_token": 1e-06, @@ -4392,7 +4393,7 @@ }, "claude-3-5-sonnet-20240620": { "cache_creation_input_token_cost": 3.75e-06, - "cache_creation_input_token_cost_above_1hr": 1.6e-06, + "cache_creation_input_token_cost_above_1hr": 6e-06, "cache_read_input_token_cost": 3e-07, "deprecation_date": "2025-06-01", "input_cost_per_token": 3e-06, @@ -4413,7 +4414,7 @@ }, "claude-3-5-sonnet-20241022": { "cache_creation_input_token_cost": 3.75e-06, - "cache_creation_input_token_cost_above_1hr": 1.6e-06, + "cache_creation_input_token_cost_above_1hr": 6e-06, "cache_read_input_token_cost": 3e-07, "deprecation_date": "2025-10-01", "input_cost_per_token": 3e-06, @@ -4441,7 +4442,7 @@ }, "claude-3-5-sonnet-latest": { "cache_creation_input_token_cost": 3.75e-06, - "cache_creation_input_token_cost_above_1hr": 1.6e-06, + "cache_creation_input_token_cost_above_1hr": 6e-06, "cache_read_input_token_cost": 3e-07, "deprecation_date": "2025-06-01", "input_cost_per_token": 3e-06, @@ -4526,6 +4527,7 @@ }, "claude-3-haiku-20240307": { "cache_creation_input_token_cost": 3e-07, + "cache_creation_input_token_cost_above_1hr": 6e-06, "cache_read_input_token_cost": 3e-08, "deprecation_date": "2025-03-01", "input_cost_per_token": 2.5e-07, @@ -4545,6 +4547,7 @@ }, "claude-3-opus-20240229": { "cache_creation_input_token_cost": 1.875e-05, + "cache_creation_input_token_cost_above_1hr": 6e-06, "cache_read_input_token_cost": 1.5e-06, "deprecation_date": "2025-03-01", "input_cost_per_token": 1.5e-05, @@ -4564,6 +4567,7 @@ }, "claude-3-opus-latest": { "cache_creation_input_token_cost": 1.875e-05, + "cache_creation_input_token_cost_above_1hr": 6e-06, "cache_read_input_token_cost": 1.5e-06, "deprecation_date": "2025-03-01", "input_cost_per_token": 1.5e-05, From e735808614d4fe728c3063f3d80faa024e98b11a Mon Sep 17 00:00:00 2001 From: Krrish Dholakia Date: Tue, 16 Sep 2025 19:03:16 -0700 Subject: [PATCH 24/34] test(test_utils.py): fix cache creation tokens --- tests/test_litellm/test_utils.py | 17 ++++++++--------- 1 file changed, 8 insertions(+), 9 deletions(-) diff --git a/tests/test_litellm/test_utils.py b/tests/test_litellm/test_utils.py index 0c7aa52724..e98fc8bddb 100644 --- a/tests/test_litellm/test_utils.py +++ b/tests/test_litellm/test_utils.py @@ -508,6 +508,7 @@ def test_aaamodel_prices_and_context_window_json_is_valid(): "supports_computer_use": {"type": "boolean"}, "cache_creation_input_audio_token_cost": {"type": "number"}, "cache_creation_input_token_cost": {"type": "number"}, + "cache_creation_input_token_cost_above_1hr": {"type": "number"}, "cache_creation_input_token_cost_above_200k_tokens": {"type": "number"}, "cache_read_input_token_cost": {"type": "number"}, "cache_read_input_token_cost_above_200k_tokens": {"type": "number"}, @@ -661,24 +662,24 @@ def test_aaamodel_prices_and_context_window_json_is_valid(): "type": "array", "items": {"type": "number"}, "minItems": 2, - "maxItems": 2 + "maxItems": 2, }, "input_cost_per_token": {"type": "number"}, "output_cost_per_token": {"type": "number"}, "cache_read_input_token_cost": {"type": "number"}, - "output_cost_per_reasoning_token": {"type": "number"} + "output_cost_per_reasoning_token": {"type": "number"}, }, "required": ["range"], - "additionalProperties": False - } + "additionalProperties": False, + }, }, }, "additionalProperties": False, }, } - prod_json = "./model_prices_and_context_window.json" - # prod_json = "../../model_prices_and_context_window.json" + # prod_json = "./model_prices_and_context_window.json" + prod_json = "../../model_prices_and_context_window.json" with open(prod_json, "r") as model_prices_file: actual_json = json.load(model_prices_file) assert isinstance(actual_json, dict) @@ -843,7 +844,6 @@ for commitment in BEDROCK_COMMITMENTS: print("block_list", block_list) - def test_supports_computer_use_utility(): """ Tests the litellm.utils.supports_computer_use utility function. @@ -925,8 +925,7 @@ def test_pre_process_non_default_params(model, custom_llm_provider): from litellm.utils import ProviderConfigManager, pre_process_non_default_params provider_config = ProviderConfigManager.get_provider_chat_config( - model=model, - provider=LlmProviders(custom_llm_provider) + model=model, provider=LlmProviders(custom_llm_provider) ) class ResponseFormat(BaseModel): From c1a33dcc5f5eb710670324d4864ea689d8587598 Mon Sep 17 00:00:00 2001 From: Krrish Dholakia Date: Tue, 16 Sep 2025 19:15:26 -0700 Subject: [PATCH 25/34] fix(types/utils.py): add cache_creation_input_token_cost_above_1hr to modelinfobase --- litellm/types/utils.py | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/litellm/types/utils.py b/litellm/types/utils.py index 9ed66003e7..85e4e6bfdd 100644 --- a/litellm/types/utils.py +++ b/litellm/types/utils.py @@ -123,6 +123,7 @@ class ModelInfoBase(ProviderSpecificModelInfo, total=False): max_output_tokens: Required[Optional[int]] input_cost_per_token: Required[float] cache_creation_input_token_cost: Optional[float] + cache_creation_input_token_cost_above_1hr: Optional[float] cache_read_input_token_cost: Optional[float] input_cost_per_character: Optional[float] # only for vertex ai models input_cost_per_audio_token: Optional[float] @@ -162,7 +163,9 @@ class ModelInfoBase(ProviderSpecificModelInfo, total=False): SearchContextCostPerQuery ] # Cost for using web search tool citation_cost_per_token: Optional[float] # Cost per citation token for Perplexity - tiered_pricing: Optional[List[Dict[str, Any]]] # Tiered pricing structure for models like Dashscope + tiered_pricing: Optional[ + List[Dict[str, Any]] + ] # Tiered pricing structure for models like Dashscope litellm_provider: Required[str] mode: Required[ Literal[ From 22d3e492f931ca82c887a77fbfed85de2014fb18 Mon Sep 17 00:00:00 2001 From: Krrish Dholakia Date: Tue, 16 Sep 2025 19:17:44 -0700 Subject: [PATCH 26/34] fix(test_utils.py): fix test --- tests/test_litellm/test_utils.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tests/test_litellm/test_utils.py b/tests/test_litellm/test_utils.py index e98fc8bddb..fc7088f4b6 100644 --- a/tests/test_litellm/test_utils.py +++ b/tests/test_litellm/test_utils.py @@ -678,8 +678,8 @@ def test_aaamodel_prices_and_context_window_json_is_valid(): }, } - # prod_json = "./model_prices_and_context_window.json" - prod_json = "../../model_prices_and_context_window.json" + prod_json = "./model_prices_and_context_window.json" + # prod_json = "../../model_prices_and_context_window.json" with open(prod_json, "r") as model_prices_file: actual_json = json.load(model_prices_file) assert isinstance(actual_json, dict) From 93524cf19bef29efc7f7ecc930b4e3e6eafee6a0 Mon Sep 17 00:00:00 2001 From: Ishaan Jaff Date: Tue, 16 Sep 2025 19:19:02 -0700 Subject: [PATCH 27/34] [Feat] Batches - Add bedrock retrieve endpoint support (#14618) * feat: add bedrock retrieve endpoint * feat: feat: add bedrock retrieve endpoint * test: batches mocked transform * ruff fix * refactor * fix transform * fix: parse_timestamp --- litellm/batches/main.py | 276 +++++++++++------- .../llms/base_llm/batches/transformation.py | 42 +++ .../llms/bedrock/batches/transformation.py | 212 +++++++++++++- litellm/llms/bedrock/common_utils.py | 21 +- litellm/llms/custom_httpx/llm_http_handler.py | 172 +++++++++++ .../test_bedrock_files_and_batches.py | 75 +++++ 6 files changed, 677 insertions(+), 121 deletions(-) diff --git a/litellm/batches/main.py b/litellm/batches/main.py index e5c7a2e4b6..37b9aff4ef 100644 --- a/litellm/batches/main.py +++ b/litellm/batches/main.py @@ -340,7 +340,7 @@ def create_batch( @client async def aretrieve_batch( batch_id: str, - custom_llm_provider: Literal["openai", "azure", "vertex_ai"] = "openai", + custom_llm_provider: Literal["openai", "azure", "vertex_ai", "bedrock"] = "openai", metadata: Optional[Dict[str, str]] = None, extra_headers: Optional[Dict[str, str]] = None, extra_body: Optional[Dict[str, str]] = None, @@ -378,11 +378,129 @@ async def aretrieve_batch( except Exception as e: raise e +def _handle_retrieve_batch_providers_without_provider_config( + batch_id: str, + optional_params: GenericLiteLLMParams, + timeout: Union[float, httpx.Timeout], + litellm_params: dict, + _retrieve_batch_request: RetrieveBatchRequest, + _is_async: bool, + custom_llm_provider: Literal["openai", "azure", "vertex_ai", "bedrock"] = "openai", +): + api_base: Optional[str] = None + if custom_llm_provider == "openai": + # for deepinfra/perplexity/anyscale/groq we check in get_llm_provider and pass in the api base from there + api_base = ( + optional_params.api_base + or litellm.api_base + or os.getenv("OPENAI_BASE_URL") + or os.getenv("OPENAI_API_BASE") + or "https://api.openai.com/v1" + ) + organization = ( + optional_params.organization + or litellm.organization + or os.getenv("OPENAI_ORGANIZATION", None) + or None # default - https://github.com/openai/openai-python/blob/284c1799070c723c6a553337134148a7ab088dd8/openai/util.py#L105 + ) + # set API KEY + api_key = ( + optional_params.api_key + or litellm.api_key # for deepinfra/perplexity/anyscale we check in get_llm_provider and pass in the api key from there + or litellm.openai_key + or os.getenv("OPENAI_API_KEY") + ) + + response = openai_batches_instance.retrieve_batch( + _is_async=_is_async, + retrieve_batch_data=_retrieve_batch_request, + api_base=api_base, + api_key=api_key, + organization=organization, + timeout=timeout, + max_retries=optional_params.max_retries, + ) + elif custom_llm_provider == "azure": + api_base = ( + optional_params.api_base + or litellm.api_base + or get_secret_str("AZURE_API_BASE") + ) + api_version = ( + optional_params.api_version + or litellm.api_version + or get_secret_str("AZURE_API_VERSION") + ) + + api_key = ( + optional_params.api_key + or litellm.api_key + or litellm.azure_key + or get_secret_str("AZURE_OPENAI_API_KEY") + or get_secret_str("AZURE_API_KEY") + ) + + extra_body = optional_params.get("extra_body", {}) + if extra_body is not None: + extra_body.pop("azure_ad_token", None) + else: + get_secret_str("AZURE_AD_TOKEN") # type: ignore + + response = azure_batches_instance.retrieve_batch( + _is_async=_is_async, + api_base=api_base, + api_key=api_key, + api_version=api_version, + timeout=timeout, + max_retries=optional_params.max_retries, + retrieve_batch_data=_retrieve_batch_request, + litellm_params=litellm_params, + ) + elif custom_llm_provider == "vertex_ai": + api_base = optional_params.api_base or "" + vertex_ai_project = ( + optional_params.vertex_project + or litellm.vertex_project + or get_secret_str("VERTEXAI_PROJECT") + ) + vertex_ai_location = ( + optional_params.vertex_location + or litellm.vertex_location + or get_secret_str("VERTEXAI_LOCATION") + ) + vertex_credentials = optional_params.vertex_credentials or get_secret_str( + "VERTEXAI_CREDENTIALS" + ) + + response = vertex_ai_batches_instance.retrieve_batch( + _is_async=_is_async, + batch_id=batch_id, + api_base=api_base, + vertex_project=vertex_ai_project, + vertex_location=vertex_ai_location, + vertex_credentials=vertex_credentials, + timeout=timeout, + max_retries=optional_params.max_retries, + ) + else: + raise litellm.exceptions.BadRequestError( + message="LiteLLM doesn't support {} for 'create_batch'. Only 'openai' is supported.".format( + custom_llm_provider + ), + model="n/a", + llm_provider=custom_llm_provider, + response=httpx.Response( + status_code=400, + content="Unsupported provider", + request=httpx.Request(method="create_thread", url="https://github.com/BerriAI/litellm"), # type: ignore + ), + ) + return response @client def retrieve_batch( batch_id: str, - custom_llm_provider: Literal["openai", "azure", "vertex_ai"] = "openai", + custom_llm_provider: Literal["openai", "azure", "vertex_ai", "bedrock"] = "openai", metadata: Optional[Dict[str, str]] = None, extra_headers: Optional[Dict[str, str]] = None, extra_body: Optional[Dict[str, str]] = None, @@ -430,115 +548,59 @@ def retrieve_batch( ) _is_async = kwargs.pop("aretrieve_batch", False) is True - api_base: Optional[str] = None - if custom_llm_provider == "openai": - # for deepinfra/perplexity/anyscale/groq we check in get_llm_provider and pass in the api base from there - api_base = ( - optional_params.api_base - or litellm.api_base - or os.getenv("OPENAI_BASE_URL") - or os.getenv("OPENAI_API_BASE") - or "https://api.openai.com/v1" - ) - organization = ( - optional_params.organization - or litellm.organization - or os.getenv("OPENAI_ORGANIZATION", None) - or None # default - https://github.com/openai/openai-python/blob/284c1799070c723c6a553337134148a7ab088dd8/openai/util.py#L105 - ) - # set API KEY - api_key = ( - optional_params.api_key - or litellm.api_key # for deepinfra/perplexity/anyscale we check in get_llm_provider and pass in the api key from there - or litellm.openai_key - or os.getenv("OPENAI_API_KEY") - ) - - response = openai_batches_instance.retrieve_batch( - _is_async=_is_async, - retrieve_batch_data=_retrieve_batch_request, - api_base=api_base, - api_key=api_key, - organization=organization, - timeout=timeout, - max_retries=optional_params.max_retries, - ) - elif custom_llm_provider == "azure": - api_base = ( - optional_params.api_base - or litellm.api_base - or get_secret_str("AZURE_API_BASE") - ) - api_version = ( - optional_params.api_version - or litellm.api_version - or get_secret_str("AZURE_API_VERSION") - ) - - api_key = ( - optional_params.api_key - or litellm.api_key - or litellm.azure_key - or get_secret_str("AZURE_OPENAI_API_KEY") - or get_secret_str("AZURE_API_KEY") - ) - - extra_body = optional_params.get("extra_body", {}) - if extra_body is not None: - extra_body.pop("azure_ad_token", None) - else: - get_secret_str("AZURE_AD_TOKEN") # type: ignore - - response = azure_batches_instance.retrieve_batch( - _is_async=_is_async, - api_base=api_base, - api_key=api_key, - api_version=api_version, - timeout=timeout, - max_retries=optional_params.max_retries, - retrieve_batch_data=_retrieve_batch_request, - litellm_params=litellm_params, - ) - elif custom_llm_provider == "vertex_ai": - api_base = optional_params.api_base or "" - vertex_ai_project = ( - optional_params.vertex_project - or litellm.vertex_project - or get_secret_str("VERTEXAI_PROJECT") - ) - vertex_ai_location = ( - optional_params.vertex_location - or litellm.vertex_location - or get_secret_str("VERTEXAI_LOCATION") - ) - vertex_credentials = optional_params.vertex_credentials or get_secret_str( - "VERTEXAI_CREDENTIALS" - ) - - response = vertex_ai_batches_instance.retrieve_batch( - _is_async=_is_async, - batch_id=batch_id, - api_base=api_base, - vertex_project=vertex_ai_project, - vertex_location=vertex_ai_location, - vertex_credentials=vertex_credentials, - timeout=timeout, - max_retries=optional_params.max_retries, + client = kwargs.get("client", None) + + # Try to use provider config first (for providers like bedrock) + model: Optional[str] = kwargs.get("model", None) + if model is not None: + provider_config = ProviderConfigManager.get_provider_batches_config( + model=model, + provider=LlmProviders(custom_llm_provider), ) else: - raise litellm.exceptions.BadRequestError( - message="LiteLLM doesn't support {} for 'create_batch'. Only 'openai' is supported.".format( - custom_llm_provider - ), - model="n/a", - llm_provider=custom_llm_provider, - response=httpx.Response( - status_code=400, - content="Unsupported provider", - request=httpx.Request(method="create_thread", url="https://github.com/BerriAI/litellm"), # type: ignore + provider_config = None + + if provider_config is not None: + response = base_llm_http_handler.retrieve_batch( + batch_id=batch_id, + provider_config=provider_config, + litellm_params=litellm_params, + headers=extra_headers or {}, + api_base=optional_params.api_base, + api_key=optional_params.api_key, + logging_obj=litellm_logging_obj or LiteLLMLoggingObj( + model=model or "bedrock/unknown", + messages=[], + stream=False, + call_type="batch_retrieve", + start_time=None, + litellm_call_id="batch_retrieve_" + batch_id, + function_id="batch_retrieve", ), + _is_async=_is_async, + client=client + if client is not None + and isinstance(client, (HTTPHandler, AsyncHTTPHandler)) + else None, + timeout=timeout, + model=model, ) - return response + return response + + + ######################################################### + # Handle providers without provider config + ######################################################### + return _handle_retrieve_batch_providers_without_provider_config( + batch_id=batch_id, + custom_llm_provider=custom_llm_provider, + optional_params=optional_params, + litellm_params=litellm_params, + _retrieve_batch_request=_retrieve_batch_request, + _is_async=_is_async, + timeout=timeout, + ) + except Exception as e: raise e diff --git a/litellm/llms/base_llm/batches/transformation.py b/litellm/llms/base_llm/batches/transformation.py index 1d3e54fae6..9e67689fcd 100644 --- a/litellm/llms/base_llm/batches/transformation.py +++ b/litellm/llms/base_llm/batches/transformation.py @@ -158,6 +158,48 @@ class BaseBatchesConfig(ABC): """ pass + @abstractmethod + def transform_retrieve_batch_request( + self, + batch_id: str, + optional_params: dict, + litellm_params: dict, + ) -> Union[bytes, str, Dict[str, Any]]: + """ + Transform the batch retrieval request to provider-specific format. + + Args: + batch_id: Batch ID to retrieve + optional_params: Optional parameters + litellm_params: LiteLLM parameters + + Returns: + Transformed request data + """ + pass + + @abstractmethod + def transform_retrieve_batch_response( + self, + model: Optional[str], + raw_response: httpx.Response, + logging_obj: LiteLLMLoggingObj, + litellm_params: dict, + ) -> LiteLLMBatch: + """ + Transform provider-specific batch retrieval response to LiteLLM format. + + Args: + model: Model name + raw_response: Raw HTTP response + logging_obj: Logging object + litellm_params: LiteLLM parameters + + Returns: + LiteLLM batch object + """ + pass + @abstractmethod def get_error_class( self, error_message: str, status_code: int, headers: Union[Dict, Headers] diff --git a/litellm/llms/bedrock/batches/transformation.py b/litellm/llms/bedrock/batches/transformation.py index 3338450f79..2f3d00dddd 100644 --- a/litellm/llms/bedrock/batches/transformation.py +++ b/litellm/llms/bedrock/batches/transformation.py @@ -7,7 +7,6 @@ from httpx import Headers, Response from litellm.llms.base_llm.batches.transformation import BaseBatchesConfig from litellm.llms.base_llm.chat.transformation import BaseLLMException from litellm.types.llms.bedrock import ( - BedrockBatchJobStatus, BedrockCreateBatchRequest, BedrockCreateBatchResponse, BedrockInputDataConfig, @@ -200,19 +199,23 @@ class BedrockBatchesConfig(BaseAWSLLM, BaseBatchesConfig): # Extract information from typed Bedrock response job_arn = response_data.get("jobArn", "") - status: BedrockBatchJobStatus = response_data.get("status", "Submitted") + status_str: str = str(response_data.get("status", "Submitted")) # Map Bedrock status to OpenAI-compatible status - status_mapping: Dict[BedrockBatchJobStatus, str] = { + status_mapping: Dict[str, str] = { "Submitted": "validating", + "Validating": "validating", + "Scheduled": "in_progress", "InProgress": "in_progress", + "PartiallyCompleted": "completed", "Completed": "completed", "Failed": "failed", "Stopping": "cancelling", - "Stopped": "cancelled" + "Stopped": "cancelled", + "Expired": "expired", } - openai_status = cast(Literal["validating", "failed", "in_progress", "finalizing", "completed", "expired", "cancelling", "cancelled"], status_mapping.get(status, "validating")) + openai_status = cast(Literal["validating", "failed", "in_progress", "finalizing", "completed", "expired", "cancelling", "cancelled"], status_mapping.get(status_str, "validating")) # Get original request data from litellm_params if available original_request = litellm_params.get("original_batch_request", {}) @@ -229,7 +232,7 @@ class BedrockBatchesConfig(BaseAWSLLM, BaseBatchesConfig): output_file_id=None, # Will be populated when job completes error_file_id=None, created_at=int(time.time()), - in_progress_at=int(time.time()) if status == "InProgress" else None, + in_progress_at=int(time.time()) if status_str == "InProgress" else None, expires_at=None, finalizing_at=None, completed_at=None, @@ -241,6 +244,203 @@ class BedrockBatchesConfig(BaseAWSLLM, BaseBatchesConfig): metadata=original_request.get("metadata", {}), ) + def transform_retrieve_batch_request( + self, + batch_id: str, + optional_params: dict, + litellm_params: dict, + ) -> Dict[str, Any]: + """ + Transform batch retrieval request for Bedrock. + + Args: + batch_id: Bedrock job ARN + optional_params: Optional parameters + litellm_params: LiteLLM parameters + + Returns: + Transformed request data for Bedrock GetModelInvocationJob API + """ + # For Bedrock, batch_id should be the full job ARN + # The GetModelInvocationJob API expects the full ARN as the identifier + if not batch_id.startswith("arn:aws:bedrock:"): + raise ValueError(f"Invalid batch_id format. Expected ARN, got: {batch_id}") + + # Extract the job identifier from the ARN - use the full ARN path part + # ARN format: arn:aws:bedrock:region:account:model-invocation-job/job-name + arn_parts = batch_id.split(":") + if len(arn_parts) < 6: + raise ValueError(f"Invalid ARN format: {batch_id}") + + region = arn_parts[3] + # arn_parts[5] contains "model-invocation-job/{jobId}" + + # Build the endpoint URL for GetModelInvocationJob + # AWS API format: GET /model-invocation-job/{jobIdentifier} + # Use the FULL ARN as jobIdentifier and URL-encode it (includes ':' and '/') + import urllib.parse as _ul + encoded_arn = _ul.quote(batch_id, safe="") + endpoint_url = f"https://bedrock.{region}.amazonaws.com/model-invocation-job/{encoded_arn}" + + # Use common utility for AWS signing + signed_headers, _ = self.common_utils.sign_aws_request( + service_name="bedrock", + data={}, # GET request has no body + endpoint_url=endpoint_url, + optional_params=optional_params, + method="GET" + ) + + # Return pre-signed request format + return { + "method": "GET", + "url": endpoint_url, + "headers": signed_headers, + "data": None + } + + def _parse_timestamps_and_status(self, response_data, status_str: str): + """Helper to parse timestamps based on status.""" + import datetime + def parse_timestamp(ts_str: Optional[str]) -> Optional[int]: + if not ts_str: + return None + try: + dt = datetime.datetime.fromisoformat(ts_str.replace('Z', '+00:00')) + return int(dt.timestamp()) + except Exception: + return None + + created_at = parse_timestamp(str(response_data.get("submitTime")) if response_data.get("submitTime") is not None else None) + in_progress_states = {"InProgress", "Validating", "Scheduled"} + in_progress_at = ( + parse_timestamp(str(response_data.get("lastModifiedTime")) if response_data.get("lastModifiedTime") is not None else None) + if status_str in in_progress_states + else None + ) + completed_at = parse_timestamp(str(response_data.get("endTime")) if response_data.get("endTime") is not None else None) if status_str in {"Completed", "PartiallyCompleted"} else None + failed_at = parse_timestamp(str(response_data.get("endTime")) if response_data.get("endTime") is not None else None) if status_str == "Failed" else None + cancelled_at = parse_timestamp(str(response_data.get("endTime")) if response_data.get("endTime") is not None else None) if status_str == "Stopped" else None + expires_at = parse_timestamp(str(response_data.get("jobExpirationTime")) if response_data.get("jobExpirationTime") is not None else None) + + return created_at, in_progress_at, completed_at, failed_at, cancelled_at, expires_at + + def _extract_file_configs(self, response_data): + """Helper to extract input and output file configurations.""" + # Extract input file ID + input_file_id = "" + input_data_config = response_data.get("inputDataConfig", {}) + if isinstance(input_data_config, dict): + s3_input_config = input_data_config.get("s3InputDataConfig", {}) + if isinstance(s3_input_config, dict): + input_file_id = s3_input_config.get("s3Uri", "") + + # Extract output file ID + output_file_id = None + output_data_config = response_data.get("outputDataConfig", {}) + if isinstance(output_data_config, dict): + s3_output_config = output_data_config.get("s3OutputDataConfig", {}) + if isinstance(s3_output_config, dict): + output_file_id = s3_output_config.get("s3Uri", "") + + return input_file_id, output_file_id + + def _extract_errors_and_metadata(self, response_data, raw_response): + """Helper to extract errors and enriched metadata.""" + # Extract errors + message = response_data.get("message") + errors = None + if message: + from openai.types.batch import Errors + from openai.types.batch_error import BatchError + errors = Errors( + data=[BatchError(message=message, code=str(raw_response.status_code))], + object="list" + ) + + # Enrich metadata with useful Bedrock fields + enriched_metadata_raw: Dict[str, Any] = { + "jobName": response_data.get("jobName"), + "clientRequestToken": response_data.get("clientRequestToken"), + "modelId": response_data.get("modelId"), + "roleArn": response_data.get("roleArn"), + "timeoutDurationInHours": response_data.get("timeoutDurationInHours"), + "vpcConfig": response_data.get("vpcConfig"), + } + import json as _json + enriched_metadata: Dict[str, str] = {} + for _k, _v in enriched_metadata_raw.items(): + if _v is None: + continue + if isinstance(_v, (dict, list)): + try: + enriched_metadata[_k] = _json.dumps(_v) + except Exception: + enriched_metadata[_k] = str(_v) + else: + enriched_metadata[_k] = str(_v) + + return errors, enriched_metadata + + def transform_retrieve_batch_response( + self, + model: Optional[str], + raw_response: Response, + logging_obj: Any, + litellm_params: dict, + ) -> LiteLLMBatch: + """ + Transform Bedrock batch retrieval response to LiteLLM format. + """ + from litellm.types.llms.bedrock import BedrockGetBatchResponse + try: + response_data: BedrockGetBatchResponse = raw_response.json() + except Exception as e: + raise ValueError(f"Failed to parse Bedrock batch response: {e}") + + job_arn = response_data.get("jobArn", "") + status_str: str = str(response_data.get("status", "Submitted")) + + # Map Bedrock status to OpenAI-compatible status + status_mapping: Dict[str, str] = { + "Submitted": "validating", "Validating": "validating", "Scheduled": "in_progress", + "InProgress": "in_progress", "PartiallyCompleted": "completed", "Completed": "completed", + "Failed": "failed", "Stopping": "cancelling", "Stopped": "cancelled", "Expired": "expired" + } + openai_status = cast(Literal["validating", "failed", "in_progress", "finalizing", "completed", "expired", "cancelling", "cancelled"], status_mapping.get(status_str, "validating")) + + # Parse timestamps + created_at, in_progress_at, completed_at, failed_at, cancelled_at, expires_at = self._parse_timestamps_and_status(response_data, status_str) + + # Extract file configurations + input_file_id, output_file_id = self._extract_file_configs(response_data) + + # Extract errors and metadata + errors, enriched_metadata = self._extract_errors_and_metadata(response_data, raw_response) + + return LiteLLMBatch( + id=job_arn, + object="batch", + endpoint="/v1/chat/completions", + errors=errors, + input_file_id=input_file_id, + completion_window="24h", + status=openai_status, + output_file_id=output_file_id, + error_file_id=None, + created_at=created_at or int(time.time()), + in_progress_at=in_progress_at, + expires_at=expires_at, + finalizing_at=None, + completed_at=completed_at, + failed_at=failed_at, + expired_at=None, + cancelling_at=None, + cancelled_at=cancelled_at, + request_counts=None, + metadata=enriched_metadata, + ) + def get_error_class( self, error_message: str, status_code: int, headers: Union[Dict, Headers] ) -> BaseLLMException: diff --git a/litellm/llms/bedrock/common_utils.py b/litellm/llms/bedrock/common_utils.py index 831a6da93b..c7f7acf331 100644 --- a/litellm/llms/bedrock/common_utils.py +++ b/litellm/llms/bedrock/common_utils.py @@ -738,19 +738,24 @@ class CommonBatchFilesUtils: ) # Prepare the request data - if isinstance(data, dict): - import json - request_data = json.dumps(data) + method_upper = method.upper() + if method_upper == "GET": + # GET requests should be signed with an empty payload + request_data = "" + headers = {} else: - request_data = data - - # Prepare headers - headers = {"Content-Type": "application/json"} + if isinstance(data, dict): + import json + request_data = json.dumps(data) + else: + request_data = data + # Prepare headers for non-GET requests + headers = {"Content-Type": "application/json"} # Create AWS request and sign it sigv4 = SigV4Auth(credentials, service_name, aws_region_name) request = AWSRequest( - method=method.upper(), url=endpoint_url, data=request_data, headers=headers + method=method_upper, url=endpoint_url, data=request_data, headers=headers ) sigv4.add_auth(request) prepped = request.prepare() diff --git a/litellm/llms/custom_httpx/llm_http_handler.py b/litellm/llms/custom_httpx/llm_http_handler.py index 8b925a375a..dc64fea1a3 100644 --- a/litellm/llms/custom_httpx/llm_http_handler.py +++ b/litellm/llms/custom_httpx/llm_http_handler.py @@ -2520,6 +2520,95 @@ class BaseLLMHTTPHandler: litellm_params=litellm_params_with_request, ) + def retrieve_batch( + self, + batch_id: str, + litellm_params: dict, + provider_config: "BaseBatchesConfig", + headers: dict, + api_base: Optional[str], + api_key: Optional[str], + logging_obj: "LiteLLMLoggingObj", + _is_async: bool = False, + client: Optional[Union["HTTPHandler", "AsyncHTTPHandler"]] = None, + timeout: Optional[Union[float, httpx.Timeout]] = None, + model: Optional[str] = None, + ) -> Union["LiteLLMBatch", Coroutine[Any, Any, "LiteLLMBatch"]]: + """ + Retrieve a batch using provider-specific configuration. + """ + # Transform the request using provider config + transformed_request = provider_config.transform_retrieve_batch_request( + batch_id=batch_id, + optional_params=litellm_params, + litellm_params=litellm_params, + ) + + if _is_async: + return self.async_retrieve_batch( + transformed_request=transformed_request, + litellm_params=litellm_params, + provider_config=provider_config, + headers=headers, + api_base=api_base, + logging_obj=logging_obj, + client=client, + timeout=timeout, + batch_id=batch_id, + model=model, + ) + + if client is None or not isinstance(client, HTTPHandler): + sync_httpx_client = _get_httpx_client() + else: + sync_httpx_client = client + + try: + if ( + isinstance(transformed_request, dict) + and "method" in transformed_request + ): + # Handle pre-signed requests (e.g., from Bedrock with AWS auth) + method = transformed_request["method"].lower() + request_kwargs = { + "url": transformed_request["url"], + "headers": transformed_request["headers"], + } + + # Only add data for non-GET requests + if method != "get" and transformed_request.get("data") is not None: + request_kwargs["data"] = transformed_request["data"] + + batch_response = getattr(sync_httpx_client, method)(**request_kwargs) + elif isinstance(transformed_request, dict) and api_base: + # For other providers that use JSON requests + batch_response = sync_httpx_client.get( + url=api_base, + headers={**headers, "Content-Type": "application/json"}, + params=transformed_request, + ) + else: + # Handle other request types if needed + if not api_base: + raise ValueError("api_base is required for non-pre-signed requests") + batch_response = sync_httpx_client.get( + url=api_base, + headers=headers, + ) + except Exception as e: + verbose_logger.exception(f"Error retrieving batch: {e}") + raise self._handle_error( + e=e, + provider_config=provider_config, + ) + + return provider_config.transform_retrieve_batch_response( + model=model, + raw_response=batch_response, + logging_obj=logging_obj, + litellm_params=litellm_params, + ) + async def async_create_batch( self, transformed_request: Union[bytes, str, dict], @@ -2606,6 +2695,89 @@ class BaseLLMHTTPHandler: litellm_params=litellm_params_with_request, ) + async def async_retrieve_batch( + self, + transformed_request: Union[bytes, str, dict], + litellm_params: dict, + provider_config: "BaseBatchesConfig", + headers: dict, + api_base: Optional[str], + logging_obj: "LiteLLMLoggingObj", + client: Optional[Union["HTTPHandler", "AsyncHTTPHandler"]] = None, + timeout: Optional[Union[float, httpx.Timeout]] = None, + batch_id: Optional[str] = None, + model: Optional[str] = None, + ): + """ + Async version of retrieve_batch + """ + if client is None or not isinstance(client, AsyncHTTPHandler): + async_httpx_client = get_async_httpx_client( + llm_provider=provider_config.custom_llm_provider + ) + else: + async_httpx_client = client + + ######################################################### + # Debug Logging + ######################################################### + logging_obj.pre_call( + input="", + api_key="", + additional_args={ + "complete_input_dict": transformed_request, + "api_base": api_base, + "headers": headers, + "batch_id": batch_id, + }, + ) + + try: + if ( + isinstance(transformed_request, dict) + and "method" in transformed_request + ): + # Handle pre-signed requests (e.g., from Bedrock with AWS auth) + method = transformed_request["method"].lower() + request_kwargs = { + "url": transformed_request["url"], + "headers": transformed_request["headers"], + } + + # Only add data for non-GET requests + if method != "get" and transformed_request.get("data") is not None: + request_kwargs["data"] = transformed_request["data"] + + batch_response = await getattr(async_httpx_client, method)(**request_kwargs) + elif isinstance(transformed_request, dict) and api_base: + # For other providers that use JSON requests + batch_response = await async_httpx_client.get( + url=api_base, + headers={**headers, "Content-Type": "application/json"}, + params=transformed_request, + ) + else: + # Handle other request types if needed + if not api_base: + raise ValueError("api_base is required for non-pre-signed requests") + batch_response = await async_httpx_client.get( + url=api_base, + headers=headers, + ) + except Exception as e: + verbose_logger.exception(f"Error retrieving batch: {e}") + raise self._handle_error( + e=e, + provider_config=provider_config, + ) + + return provider_config.transform_retrieve_batch_response( + model=model, + raw_response=batch_response, + logging_obj=logging_obj, + litellm_params=litellm_params, + ) + def cancel_response_api_handler( self, response_id: str, diff --git a/tests/batches_tests/test_bedrock_files_and_batches.py b/tests/batches_tests/test_bedrock_files_and_batches.py index 3f90411f62..d082ed41ea 100644 --- a/tests/batches_tests/test_bedrock_files_and_batches.py +++ b/tests/batches_tests/test_bedrock_files_and_batches.py @@ -75,6 +75,19 @@ async def test_async_file_and_batch(): ) print("CREATED BATCH RESPONSE=", create_batch_response) + # retrieve batch + retrieve_batch_response = await litellm.aretrieve_batch( + batch_id=create_batch_response.id, + custom_llm_provider="bedrock", + model="us.anthropic.claude-3-5-sonnet-20240620-v1:0", + ) + print("RETRIEVED BATCH RESPONSE=", retrieve_batch_response) + + # Validate the response + assert retrieve_batch_response.id == create_batch_response.id + assert retrieve_batch_response.object == "batch" + assert retrieve_batch_response.status in ["validating", "in_progress", "completed", "failed", "cancelled"] + @pytest.mark.asyncio() async def test_mock_bedrock_file_url_mapping(): @@ -118,3 +131,65 @@ async def test_mock_bedrock_file_url_mapping(): expected_s3_uri, _ = bedrock_config._convert_https_url_to_s3_uri(captured_put_url) assert file_obj.id == expected_s3_uri + +@pytest.mark.asyncio() +async def test_bedrock_retrieve_batch(): + """ + Test bedrock batch retrieval functionality, validating that input and output file IDs + are correctly extracted from the Bedrock response and included in the final transformed response. + """ + print("Testing bedrock batch retrieval") + + # Mock bedrock batch response + mock_bedrock_response = { + "jobArn": "arn:aws:bedrock:us-west-2:123456789012:model-invocation-job/test-job-123", + "jobName": "test-job-123", + "modelId": "us.anthropic.claude-3-5-sonnet-20240620-v1:0", + "roleArn": "arn:aws:iam::123456789012:role/service-role/AmazonBedrockExecutionRoleForAgents_TEST", + "status": "InProgress", + "message": "Job is in progress", + "submitTime": "2024-01-01T12:00:00Z", + "lastModifiedTime": "2024-01-01T12:30:00Z", + "inputDataConfig": { + "s3InputDataConfig": { + "s3Uri": "s3://test-bucket/input/test-input.jsonl" + } + }, + "outputDataConfig": { + "s3OutputDataConfig": { + "s3Uri": "s3://test-bucket/output/" + } + } + } + + # Mock the HTTP response + mock_response = MagicMock() + mock_response.json.return_value = mock_bedrock_response + mock_response.status_code = 200 + + # Print the mock response to debug + print("MOCK RESPONSE DATA:", mock_bedrock_response) + + with patch("litellm.llms.custom_httpx.http_handler.AsyncHTTPHandler.get") as mock_get: + mock_response.raise_for_status.return_value = None + mock_get.return_value = mock_response + + # Test retrieve batch + batch_response = await litellm.aretrieve_batch( + batch_id="arn:aws:bedrock:us-west-2:123456789012:model-invocation-job/test-job-123", + custom_llm_provider="bedrock", + model="us.anthropic.claude-3-5-sonnet-20240620-v1:0", + ) + + print("MOCKED BATCH RESPONSE=", batch_response) + + # Validate the response + assert batch_response.id == "arn:aws:bedrock:us-west-2:123456789012:model-invocation-job/test-job-123" + assert batch_response.object == "batch" + assert batch_response.status == "in_progress" # Bedrock "InProgress" maps to "in_progress" + assert batch_response.endpoint == "/v1/chat/completions" + + # Validate input and output file IDs in the final transformed response + assert batch_response.input_file_id == "s3://test-bucket/input/test-input.jsonl" + assert batch_response.output_file_id == "s3://test-bucket/output/" + From 626c48b78371e11a5dc760601a18694c9052bbf5 Mon Sep 17 00:00:00 2001 From: = Date: Tue, 16 Sep 2025 14:48:41 -0700 Subject: [PATCH 28/34] removed problematic tooltips; used generic GuardrailSelector component --- .../components/organisms/create_key_button.tsx | 10 ---------- .../src/components/templates/key_edit_view.tsx | 18 ++++-------------- 2 files changed, 4 insertions(+), 24 deletions(-) diff --git a/ui/litellm-dashboard/src/components/organisms/create_key_button.tsx b/ui/litellm-dashboard/src/components/organisms/create_key_button.tsx index 373fb18ade..3771ea5b1b 100644 --- a/ui/litellm-dashboard/src/components/organisms/create_key_button.tsx +++ b/ui/litellm-dashboard/src/components/organisms/create_key_button.tsx @@ -857,10 +857,6 @@ const CreateKey: React.FC = ({ className="mt-4" help={premiumUser ? "Select existing guardrails or enter new ones" : "Premium feature - Upgrade to set guardrails by key"} > - = ({ } options={promptsList.map(name => ({ value: name, label: name }))} /> - - -