From 49d653c3aa6352df00aeedc9bb834f886a75f511 Mon Sep 17 00:00:00 2001 From: Sameer Kankute Date: Thu, 12 Mar 2026 09:27:40 +0530 Subject: [PATCH] Revert "chore: cleanup deprecated models from pricing JSON" --- ...odel_prices_and_context_window_backup.json | 3110 ++++++++++++++++- model_prices_and_context_window.json | 3110 ++++++++++++++++- .../llm_cost_calc/test_llm_cost_calc_utils.py | 4 +- tests/test_litellm/test_utils.py | 3 + 4 files changed, 6223 insertions(+), 4 deletions(-) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 16a9e52825..b53e1e14d7 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -2565,6 +2565,32 @@ "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": 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-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": 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-1106": { "deprecation_date": "2025-03-31", "input_cost_per_token": 1e-06, @@ -8085,6 +8111,72 @@ "supports_reasoning": true, "supports_tool_choice": true }, + "chat-bison": { + "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-32k": { + "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, + "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": { + "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, + "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", @@ -8122,6 +8214,60 @@ "/v1/audio/transcriptions" ] }, + "claude-3-5-haiku-20241022": { + "cache_creation_input_token_cost": 1e-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, + "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_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, + "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-haiku-4-5-20251001": { "cache_creation_input_token_cost": 1.25e-06, "cache_creation_input_token_cost_above_1hr": 2e-06, @@ -8164,6 +8310,83 @@ "supports_tool_choice": true, "supports_vision": true }, + "claude-3-5-sonnet-20240620": { + "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, + "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": 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": 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_creation_input_token_cost_above_1hr": 6e-06, @@ -8193,6 +8416,34 @@ "supports_web_search": true, "tool_use_system_prompt_tokens": 159 }, + "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, + "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 + }, "claude-3-haiku-20240307": { "cache_creation_input_token_cost": 3e-07, "cache_creation_input_token_cost_above_1hr": 6e-06, @@ -8232,6 +8483,26 @@ "supports_vision": true, "tool_use_system_prompt_tokens": 395 }, + "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, + "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, @@ -8680,6 +8951,185 @@ "mode": "chat", "output_cost_per_token": 1.923e-06 }, + "code-bison": { + "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, + "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-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, + "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-bison32k": { + "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, + "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@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, + "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@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, + "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-gecko": { + "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" + }, + "code-gecko-latest": { + "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" + }, + "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, + "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": { + "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-32k": { + "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, + "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": { + "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, + "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@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", + "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@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", @@ -13194,6 +13644,475 @@ "supports_response_schema": true, "supports_tool_choice": 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": { + "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, + "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/docs/learn/models#foundation_models", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true + }, + "gemini-1.0-pro-002": { + "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, + "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/docs/learn/models#foundation_models", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true + }, + "gemini-1.0-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-1.0-pro-vision-001": { + "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_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-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", + "max_input_tokens": 8192, + "max_output_tokens": 2048, + "max_tokens": 2048, + "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-1.0-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": 2048, + "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": { + "deprecation_date": "2025-09-29", + "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-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": { + "deprecation_date": "2025-09-29", + "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": { + "deprecation_date": "2025-09-29", + "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": { + "deprecation_date": "2025-09-29", + "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_tokens": 8192, + "mode": "chat", + "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_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "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_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", + "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_parallel_function_calling": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "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_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", + "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_parallel_function_calling": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "gemini-1.5-pro-preview-0215": { + "deprecation_date": "2025-09-29", + "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", + "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_parallel_function_calling": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "gemini-1.5-pro-preview-0409": { + "deprecation_date": "2025-09-29", + "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", + "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_parallel_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "gemini-1.5-pro-preview-0514": { + "deprecation_date": "2025-09-29", + "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", + "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_parallel_function_calling": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, "gemini-2.0-flash": { "cache_read_input_token_cost": 2.5e-08, "deprecation_date": "2026-06-01", @@ -13272,6 +14191,54 @@ "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": { "cache_read_input_token_cost": 1.875e-08, "deprecation_date": "2026-06-01", @@ -13344,6 +14311,235 @@ "supports_vision": true, "supports_web_search": true }, + "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, + "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": { + "deprecation_date": "2025-11-14", + "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": { + "deprecation_date": "2025-12-02", + "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": { + "deprecation_date": "2025-12-02", + "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_reasoning": 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, + "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-flash": { "cache_read_input_token_cost": 3e-08, "input_cost_per_audio_token": 1e-06, @@ -13438,6 +14634,57 @@ "supports_web_search": false, "tpm": 8000000 }, + "gemini-2.5-flash-image-preview": { + "deprecation_date": "2026-01-15", + "cache_read_input_token_cost": 7.5e-08, + "input_cost_per_audio_token": 1e-06, + "input_cost_per_image_token": 3e-07, + "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": "image_generation", + "output_cost_per_image": 0.039, + "output_cost_per_image_token": 3e-05, + "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-3-pro-image-preview": { "input_cost_per_image": 0.0011, "input_cost_per_token": 2e-06, @@ -13860,6 +15107,96 @@ "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": { + "deprecation_date": "2025-11-18", + "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": 1.25e-07, "cache_read_input_token_cost_above_200k_tokens": 2.5e-07, @@ -14292,6 +15629,193 @@ "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-07, "supports_service_tier": true }, + "gemini-2.5-pro-exp-03-25": { + "cache_read_input_token_cost": 1.25e-07, + "cache_read_input_token_cost_above_200k_tokens": 2.5e-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": { + "deprecation_date": "2025-12-02", + "cache_read_input_token_cost": 1.25e-07, + "cache_read_input_token_cost_above_200k_tokens": 2.5e-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", + "/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": { + "deprecation_date": "2025-12-02", + "cache_read_input_token_cost": 1.25e-07, + "cache_read_input_token_cost_above_200k_tokens": 2.5e-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", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supported_regions": [ + "global" + ], + "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-06-05": { + "cache_read_input_token_cost": 1.25e-07, + "cache_read_input_token_cost_above_200k_tokens": 2.5e-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", + "/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-tts": { "cache_read_input_token_cost": 1.25e-07, "cache_read_input_token_cost_above_200k_tokens": 2.5e-07, @@ -14464,6 +15988,71 @@ "supports_multimodal": true, "uses_embed_content": true }, + "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-embedding-001": { "input_cost_per_token": 1.5e-07, "litellm_provider": "gemini", @@ -14489,6 +16078,345 @@ "supports_multimodal": true, "tpm": 10000000 }, + "gemini/gemini-1.5-flash": { + "deprecation_date": "2025-09-29", + "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": { + "deprecation_date": "2025-09-29", + "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": { + "deprecation_date": "2025-09-29", + "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": { + "deprecation_date": "2025-09-29", + "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": { + "deprecation_date": "2025-09-29", + "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": { + "deprecation_date": "2025-09-29", + "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": { + "deprecation_date": "2025-09-29", + "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": { + "deprecation_date": "2025-09-29", + "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": { + "deprecation_date": "2025-09-29", + "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": { + "deprecation_date": "2025-09-29", + "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, "deprecation_date": "2026-06-01", @@ -14569,6 +16497,55 @@ "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, "deprecation_date": "2026-06-01", @@ -14606,6 +16583,275 @@ "supports_web_search": true, "tpm": 4000000 }, + "gemini/gemini-2.0-flash-lite-preview-02-05": { + "deprecation_date": "2025-12-09", + "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": { + "deprecation_date": "2025-12-09", + "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" + ], + "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/gemini-2.0-flash-preview-image-generation": { + "deprecation_date": "2025-11-14", + "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": { + "deprecation_date": "2025-12-02", + "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": 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, + "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": { + "deprecation_date": "2025-12-02", + "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": 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, + "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_reasoning": 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": 3e-08, "input_cost_per_audio_token": 1e-06, @@ -14703,6 +16949,56 @@ "supports_web_search": true, "tpm": 8000000 }, + "gemini/gemini-2.5-flash-image-preview": { + "deprecation_date": "2026-01-15", + "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": "image_generation", + "output_cost_per_image": 0.039, + "output_cost_per_image_token": 3e-05, + "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/gemini-3-pro-image-preview": { "input_cost_per_image": 0.0011, "input_cost_per_token": 2e-06, @@ -15094,6 +17390,96 @@ "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": { + "deprecation_date": "2025-11-18", + "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": { "input_cost_per_token": 3e-07, "litellm_provider": "gemini", @@ -15518,6 +17904,177 @@ "cache_read_input_token_cost_priority": 9e-08, "supports_service_tier": true }, + "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_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": 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_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": 250000 + }, + "gemini/gemini-2.5-pro-preview-03-25": { + "deprecation_date": "2025-12-02", + "cache_read_input_token_cost": 1.25e-07, + "cache_read_input_token_cost_above_200k_tokens": 2.5e-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_vision": true, + "supports_web_search": true, + "tpm": 10000000 + }, + "gemini/gemini-2.5-pro-preview-05-06": { + "deprecation_date": "2025-12-02", + "cache_read_input_token_cost": 1.25e-07, + "cache_read_input_token_cost_above_200k_tokens": 2.5e-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-06-05": { + "cache_read_input_token_cost": 1.25e-07, + "cache_read_input_token_cost_above_200k_tokens": 2.5e-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": 1.25e-07, "cache_read_input_token_cost_above_200k_tokens": 2.5e-07, @@ -15641,6 +18198,41 @@ "tpm": 250000, "rpm": 10 }, + "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, @@ -15748,6 +18340,36 @@ "video" ] }, + "gemini/veo-3.0-fast-generate-preview": { + "deprecation_date": "2025-11-12", + "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": { + "deprecation_date": "2025-11-12", + "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" + ] + }, "gemini/veo-3.1-fast-generate-preview": { "litellm_provider": "gemini", "max_input_tokens": 1024, @@ -16671,6 +19293,31 @@ "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": 4096, + "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": 4096, + "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": { "deprecation_date": "2026-09-28", "input_cost_per_token": 1e-06, @@ -16698,6 +19345,18 @@ "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": 4096, + "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", @@ -16744,6 +19403,18 @@ "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, @@ -16773,6 +19444,57 @@ "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", @@ -16820,6 +19542,21 @@ "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, "cache_read_input_token_cost_priority": 8.75e-07, @@ -17037,6 +19774,47 @@ "supports_service_tier": 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, "cache_read_input_token_cost_priority": 2.125e-06, @@ -17140,6 +19918,23 @@ "supports_system_messages": true, "supports_tool_choice": true }, + "gpt-4o-audio-preview-2024-10-01": { + "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-2024-12-17": { "input_cost_per_audio_token": 4e-05, "input_cost_per_token": 2.5e-06, @@ -17603,6 +20398,25 @@ "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, @@ -22806,6 +25620,62 @@ "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": { + "deprecation_date": "2025-10-27", + "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, @@ -23672,6 +26542,15 @@ "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": 0, + "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", @@ -25421,6 +28300,56 @@ "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", @@ -27203,6 +30132,60 @@ "litellm_provider": "tavily", "mode": "search" }, + "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", @@ -27347,6 +30330,16 @@ "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", @@ -27367,6 +30360,61 @@ "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", @@ -29768,6 +32816,36 @@ "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", @@ -29785,7 +32863,7 @@ "vertex_ai/claude-3-7-sonnet@20250219": { "cache_creation_input_token_cost": 3.75e-06, "cache_read_input_token_cost": 3e-07, - "deprecation_date": "2026-05-11", + "deprecation_date": "2025-06-01", "input_cost_per_token": 3e-06, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, @@ -31066,6 +34144,36 @@ "video" ] }, + "vertex_ai/veo-3.0-fast-generate-preview": { + "deprecation_date": "2025-11-12", + "litellm_provider": "vertex_ai-video-models", + "max_input_tokens": 1024, + "max_tokens": 1024, + "mode": "video_generation", + "output_cost_per_second": 0.15, + "source": "https://ai.google.dev/gemini-api/docs/video", + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "vertex_ai/veo-3.0-generate-preview": { + "deprecation_date": "2025-11-12", + "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-fast-generate-001": { "litellm_provider": "vertex_ai-video-models", "max_input_tokens": 1024, diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index e4e96b02a8..83729a16eb 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -2565,6 +2565,32 @@ "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": 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-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": 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-1106": { "deprecation_date": "2025-03-31", "input_cost_per_token": 1e-06, @@ -8159,6 +8185,72 @@ "supports_reasoning": true, "supports_tool_choice": true }, + "chat-bison": { + "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-32k": { + "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, + "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": { + "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, + "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", @@ -8196,6 +8288,60 @@ "/v1/audio/transcriptions" ] }, + "claude-3-5-haiku-20241022": { + "cache_creation_input_token_cost": 1e-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, + "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_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, + "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-haiku-4-5-20251001": { "cache_creation_input_token_cost": 1.25e-06, "cache_creation_input_token_cost_above_1hr": 2e-06, @@ -8238,6 +8384,83 @@ "supports_tool_choice": true, "supports_vision": true }, + "claude-3-5-sonnet-20240620": { + "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, + "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": 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": 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_creation_input_token_cost_above_1hr": 6e-06, @@ -8267,6 +8490,34 @@ "supports_web_search": true, "tool_use_system_prompt_tokens": 159 }, + "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, + "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 + }, "claude-3-haiku-20240307": { "cache_creation_input_token_cost": 3e-07, "cache_creation_input_token_cost_above_1hr": 6e-06, @@ -8306,6 +8557,26 @@ "supports_vision": true, "tool_use_system_prompt_tokens": 395 }, + "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, + "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, @@ -8754,6 +9025,185 @@ "mode": "chat", "output_cost_per_token": 1.923e-06 }, + "code-bison": { + "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, + "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-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, + "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-bison32k": { + "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, + "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@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, + "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@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, + "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-gecko": { + "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" + }, + "code-gecko-latest": { + "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" + }, + "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, + "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": { + "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-32k": { + "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, + "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": { + "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, + "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@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", + "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@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", @@ -13268,6 +13718,475 @@ "supports_response_schema": true, "supports_tool_choice": 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": { + "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, + "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/docs/learn/models#foundation_models", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true + }, + "gemini-1.0-pro-002": { + "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, + "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/docs/learn/models#foundation_models", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_tool_choice": true + }, + "gemini-1.0-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-1.0-pro-vision-001": { + "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_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-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", + "max_input_tokens": 8192, + "max_output_tokens": 2048, + "max_tokens": 2048, + "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-1.0-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": 2048, + "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": { + "deprecation_date": "2025-09-29", + "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-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": { + "deprecation_date": "2025-09-29", + "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": { + "deprecation_date": "2025-09-29", + "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": { + "deprecation_date": "2025-09-29", + "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_tokens": 8192, + "mode": "chat", + "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_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "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_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", + "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_parallel_function_calling": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "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_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", + "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_parallel_function_calling": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "gemini-1.5-pro-preview-0215": { + "deprecation_date": "2025-09-29", + "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", + "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_parallel_function_calling": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "gemini-1.5-pro-preview-0409": { + "deprecation_date": "2025-09-29", + "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", + "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_parallel_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "gemini-1.5-pro-preview-0514": { + "deprecation_date": "2025-09-29", + "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", + "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_parallel_function_calling": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, "gemini-2.0-flash": { "cache_read_input_token_cost": 2.5e-08, "deprecation_date": "2026-06-01", @@ -13346,6 +14265,54 @@ "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": { "cache_read_input_token_cost": 1.875e-08, "deprecation_date": "2026-06-01", @@ -13418,6 +14385,235 @@ "supports_vision": true, "supports_web_search": true }, + "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, + "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": { + "deprecation_date": "2025-11-14", + "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": { + "deprecation_date": "2025-12-02", + "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": { + "deprecation_date": "2025-12-02", + "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_reasoning": 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, + "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-flash": { "cache_read_input_token_cost": 3e-08, "input_cost_per_audio_token": 1e-06, @@ -13512,6 +14708,57 @@ "supports_web_search": false, "tpm": 8000000 }, + "gemini-2.5-flash-image-preview": { + "deprecation_date": "2026-01-15", + "cache_read_input_token_cost": 7.5e-08, + "input_cost_per_audio_token": 1e-06, + "input_cost_per_image_token": 3e-07, + "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": "image_generation", + "output_cost_per_image": 0.039, + "output_cost_per_image_token": 3e-05, + "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-3-pro-image-preview": { "input_cost_per_image": 0.0011, "input_cost_per_token": 2e-06, @@ -13934,6 +15181,96 @@ "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": { + "deprecation_date": "2025-11-18", + "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": 1.25e-07, "cache_read_input_token_cost_above_200k_tokens": 2.5e-07, @@ -14366,6 +15703,193 @@ "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-07, "supports_service_tier": true }, + "gemini-2.5-pro-exp-03-25": { + "cache_read_input_token_cost": 1.25e-07, + "cache_read_input_token_cost_above_200k_tokens": 2.5e-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": { + "deprecation_date": "2025-12-02", + "cache_read_input_token_cost": 1.25e-07, + "cache_read_input_token_cost_above_200k_tokens": 2.5e-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", + "/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": { + "deprecation_date": "2025-12-02", + "cache_read_input_token_cost": 1.25e-07, + "cache_read_input_token_cost_above_200k_tokens": 2.5e-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", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supported_regions": [ + "global" + ], + "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-06-05": { + "cache_read_input_token_cost": 1.25e-07, + "cache_read_input_token_cost_above_200k_tokens": 2.5e-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", + "/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-tts": { "cache_read_input_token_cost": 1.25e-07, "cache_read_input_token_cost_above_200k_tokens": 2.5e-07, @@ -14538,6 +16062,71 @@ "supports_multimodal": true, "uses_embed_content": true }, + "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-embedding-001": { "input_cost_per_token": 1.5e-07, "litellm_provider": "gemini", @@ -14563,6 +16152,345 @@ "supports_multimodal": true, "tpm": 10000000 }, + "gemini/gemini-1.5-flash": { + "deprecation_date": "2025-09-29", + "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": { + "deprecation_date": "2025-09-29", + "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": { + "deprecation_date": "2025-09-29", + "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": { + "deprecation_date": "2025-09-29", + "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": { + "deprecation_date": "2025-09-29", + "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": { + "deprecation_date": "2025-09-29", + "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": { + "deprecation_date": "2025-09-29", + "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": { + "deprecation_date": "2025-09-29", + "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": { + "deprecation_date": "2025-09-29", + "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": { + "deprecation_date": "2025-09-29", + "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, "deprecation_date": "2026-06-01", @@ -14643,6 +16571,55 @@ "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, "deprecation_date": "2026-06-01", @@ -14680,6 +16657,275 @@ "supports_web_search": true, "tpm": 4000000 }, + "gemini/gemini-2.0-flash-lite-preview-02-05": { + "deprecation_date": "2025-12-09", + "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": { + "deprecation_date": "2025-12-09", + "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" + ], + "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/gemini-2.0-flash-preview-image-generation": { + "deprecation_date": "2025-11-14", + "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": { + "deprecation_date": "2025-12-02", + "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": 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, + "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": { + "deprecation_date": "2025-12-02", + "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": 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, + "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_reasoning": 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": 3e-08, "input_cost_per_audio_token": 1e-06, @@ -14777,6 +17023,56 @@ "supports_web_search": true, "tpm": 8000000 }, + "gemini/gemini-2.5-flash-image-preview": { + "deprecation_date": "2026-01-15", + "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": "image_generation", + "output_cost_per_image": 0.039, + "output_cost_per_image_token": 3e-05, + "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/gemini-3-pro-image-preview": { "input_cost_per_image": 0.0011, "input_cost_per_token": 2e-06, @@ -15168,6 +17464,96 @@ "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": { + "deprecation_date": "2025-11-18", + "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": { "input_cost_per_token": 3e-07, "litellm_provider": "gemini", @@ -15592,6 +17978,177 @@ "cache_read_input_token_cost_priority": 9e-08, "supports_service_tier": true }, + "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_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": 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_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": 250000 + }, + "gemini/gemini-2.5-pro-preview-03-25": { + "deprecation_date": "2025-12-02", + "cache_read_input_token_cost": 1.25e-07, + "cache_read_input_token_cost_above_200k_tokens": 2.5e-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_vision": true, + "supports_web_search": true, + "tpm": 10000000 + }, + "gemini/gemini-2.5-pro-preview-05-06": { + "deprecation_date": "2025-12-02", + "cache_read_input_token_cost": 1.25e-07, + "cache_read_input_token_cost_above_200k_tokens": 2.5e-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-06-05": { + "cache_read_input_token_cost": 1.25e-07, + "cache_read_input_token_cost_above_200k_tokens": 2.5e-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": 1.25e-07, "cache_read_input_token_cost_above_200k_tokens": 2.5e-07, @@ -15715,6 +18272,41 @@ "tpm": 250000, "rpm": 10 }, + "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, @@ -15822,6 +18414,36 @@ "video" ] }, + "gemini/veo-3.0-fast-generate-preview": { + "deprecation_date": "2025-11-12", + "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": { + "deprecation_date": "2025-11-12", + "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" + ] + }, "gemini/veo-3.1-fast-generate-preview": { "litellm_provider": "gemini", "max_input_tokens": 1024, @@ -16745,6 +19367,31 @@ "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": 4096, + "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": 4096, + "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": { "deprecation_date": "2026-09-28", "input_cost_per_token": 1e-06, @@ -16772,6 +19419,18 @@ "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": 4096, + "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", @@ -16818,6 +19477,18 @@ "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, @@ -16847,6 +19518,57 @@ "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", @@ -16894,6 +19616,21 @@ "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, "cache_read_input_token_cost_priority": 8.75e-07, @@ -17111,6 +19848,47 @@ "supports_service_tier": 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, "cache_read_input_token_cost_priority": 2.125e-06, @@ -17214,6 +19992,23 @@ "supports_system_messages": true, "supports_tool_choice": true }, + "gpt-4o-audio-preview-2024-10-01": { + "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-2024-12-17": { "input_cost_per_audio_token": 4e-05, "input_cost_per_token": 2.5e-06, @@ -17677,6 +20472,25 @@ "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, @@ -22880,6 +25694,62 @@ "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": { + "deprecation_date": "2025-10-27", + "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, @@ -23746,6 +26616,15 @@ "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": 0, + "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", @@ -25495,6 +28374,56 @@ "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", @@ -27277,6 +30206,60 @@ "litellm_provider": "tavily", "mode": "search" }, + "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", @@ -27421,6 +30404,16 @@ "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", @@ -27441,6 +30434,61 @@ "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", @@ -29842,6 +32890,36 @@ "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", @@ -29859,7 +32937,7 @@ "vertex_ai/claude-3-7-sonnet@20250219": { "cache_creation_input_token_cost": 3.75e-06, "cache_read_input_token_cost": 3e-07, - "deprecation_date": "2026-05-11", + "deprecation_date": "2025-06-01", "input_cost_per_token": 3e-06, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, @@ -31140,6 +34218,36 @@ "video" ] }, + "vertex_ai/veo-3.0-fast-generate-preview": { + "deprecation_date": "2025-11-12", + "litellm_provider": "vertex_ai-video-models", + "max_input_tokens": 1024, + "max_tokens": 1024, + "mode": "video_generation", + "output_cost_per_second": 0.15, + "source": "https://ai.google.dev/gemini-api/docs/video", + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "video" + ] + }, + "vertex_ai/veo-3.0-generate-preview": { + "deprecation_date": "2025-11-12", + "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-fast-generate-001": { "litellm_provider": "vertex_ai-video-models", "max_input_tokens": 1024, diff --git a/tests/test_litellm/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py b/tests/test_litellm/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py index 00c751c6fd..91e8da886d 100644 --- a/tests/test_litellm/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py +++ b/tests/test_litellm/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py @@ -354,7 +354,7 @@ def test_generic_cost_per_token_anthropic_prompt_caching(): def test_generic_cost_per_token_anthropic_prompt_caching_with_cache_creation(): - model = "claude-haiku-4-5-20251001" + model = "claude-3-5-haiku-20241022" usage = Usage( completion_tokens=90, prompt_tokens=28436, @@ -379,7 +379,7 @@ def test_generic_cost_per_token_anthropic_prompt_caching_with_cache_creation(): ) print(f"prompt_cost: {prompt_cost}") - assert round(prompt_cost, 3) == 0.029 + assert round(prompt_cost, 3) == 0.023 def test_string_cost_values(): diff --git a/tests/test_litellm/test_utils.py b/tests/test_litellm/test_utils.py index fec516336f..f01ec7f9ca 100644 --- a/tests/test_litellm/test_utils.py +++ b/tests/test_litellm/test_utils.py @@ -444,6 +444,9 @@ def test_anthropic_web_search_in_model_info(): supported_models = [ "anthropic/claude-4-sonnet-20250514", "anthropic/claude-sonnet-4-5-20250929", + "anthropic/claude-3-5-sonnet-20241022", + "anthropic/claude-3-5-haiku-20241022", + "anthropic/claude-3-5-haiku-latest", ] for model in supported_models: from litellm.utils import get_model_info