Ishaan Jaff 3682f661d8 (feat) add cost tracking for OpenAI prompt caching (#6055) ...

* add cache_read_input_token_cost for prompt caching models

* add prompt caching for latest models

* add openai cost calculator

* add openai prompt caching test

* fix lint check

* add not on how usage._cache_read_input_tokens is used

* fix cost calc whisper openai

* use output_cost_per_second

* add input_cost_per_second

2024-10-05 14:20:15 +05:30

..

.litellm_cache

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

example_config_yaml

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_configs

Litellm ruff linting enforcement (#5992)

2024-10-01 19:44:20 -04:00

test_model_response_typing

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

adroit-crow-413218-bc47f303efc9.json

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

azure_fine_tune.jsonl

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

batch_job_results_furniture.jsonl

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

conftest.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

data_map.txt

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

eagle.wav

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

gettysburg.wav

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

large_text.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

log.txt

LiteLLM Minor Fixes & Improvements (10/02/2024) (#6023)

2024-10-02 22:00:28 -04:00

messages_with_counts.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

model_cost.json

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

openai_batch_completions_router.jsonl

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

openai_batch_completions.jsonl

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

speech_vertex.mp3

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

stream_chunk_testdata.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_acompletion.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_acooldowns_router.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_add_function_to_prompt.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_add_update_models.py

Litellm ruff linting enforcement (#5992)

2024-10-01 19:44:20 -04:00

test_alangfuse.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_alerting.py

Litellm ruff linting enforcement (#5992)

2024-10-01 19:44:20 -04:00

test_amazing_s3_logs.py

Litellm ruff linting enforcement (#5992)

2024-10-01 19:44:20 -04:00

test_amazing_vertex_completion.py

(performance improvement - vertex embeddings) ~111.11% faster (#6000)

2024-10-01 14:16:21 -07:00

test_anthropic_prompt_caching.py

(feat proxy slack alerting) - allow opting in to getting key / internal user alerts (#5990)

2024-10-01 10:49:22 -07:00

test_aproxy_startup.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_arize_ai.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_assistants.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_async_fn.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_async_opentelemetry.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_audio_speech.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_auth_checks.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_azure_content_safety.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_azure_openai.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_azure_perf.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_bad_params.py

Litellm ruff linting enforcement (#5992)

2024-10-01 19:44:20 -04:00

test_banned_keyword_list.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_batch_completion_return_exceptions.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_batch_completions.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_bedrock_completion.py

LiteLLM Minor Fixes & Improvements (10/04/2024) (#6064)

2024-10-04 21:28:53 -04:00

test_blocked_user_list.py

Litellm ruff linting enforcement (#5992)

2024-10-01 19:44:20 -04:00

test_braintrust.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_budget_manager.py

Litellm ruff linting enforcement (#5992)

2024-10-01 19:44:20 -04:00

test_caching_ssl.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_caching.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_clarifai_completion.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_class.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_clickhouse_logger.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_cohere_completion.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_completion_cost.py

(feat) add cost tracking for OpenAI prompt caching (#6055)

2024-10-05 14:20:15 +05:30

test_completion_with_retries.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_completion.py

ci/cd run again

2024-10-04 17:19:26 +05:30

test_config.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_cost_calc.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_custom_api_logger.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_custom_callback_input.py

LiteLLM Minor Fixes & Improvements (10/04/2024) (#6064)

2024-10-04 21:28:53 -04:00

test_custom_callback_router.py

Litellm ruff linting enforcement (#5992)

2024-10-01 19:44:20 -04:00

test_custom_llm.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_custom_logger.py

Litellm ruff linting enforcement (#5992)

2024-10-01 19:44:20 -04:00

test_datadog.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_deployed_proxy_keygen.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_dynamic_rate_limit_handler.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_dynamodb_logs.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_embedding.py

(contributor PRs) oct 3rd, 2024 (#6034)

2024-10-03 17:12:34 +05:30

test_exceptions.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_file_types.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_fine_tuning_api.py

Litellm ruff linting enforcement (#5992)

2024-10-01 19:44:20 -04:00

test_function_call_parsing.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_function_calling.py

LiteLLM Minor Fixes & Improvements (10/02/2024) (#6023)

2024-10-02 22:00:28 -04:00

test_function_setup.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_gcs_bucket.py

(fixes) gcs bucket key based logging (#6044)

2024-10-04 11:56:10 +05:30

test_get_llm_provider.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_get_model_file.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_get_model_info.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_get_model_list.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_get_optional_params_embeddings.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_get_optional_params_functions_not_supported.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_get_secret.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_google_ai_studio_gemini.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_guardrails_config.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_health_check.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_helicone_integration.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_hf_prompt_templates.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_image_generation.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_img_resize.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_jwt.py

Litellm ruff linting enforcement (#5992)

2024-10-01 19:44:20 -04:00

test_key_generate_dynamodb.py

Litellm ruff linting enforcement (#5992)

2024-10-01 19:44:20 -04:00

test_key_generate_prisma.py

Litellm ruff linting enforcement (#5992)

2024-10-01 19:44:20 -04:00

test_lakera_ai_prompt_injection.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_langchain_ChatLiteLLM.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_langsmith.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_least_busy_routing.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_litellm_max_budget.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_literalai.py

Litellm Minor Fixes & Improvements (10/03/2024) (#6049)

2024-10-03 18:02:28 -04:00

test_llm_guard.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_load_test_router_s3.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_loadtest_router.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_logfire.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_logging.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_longer_context_fallback.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_lowest_cost_routing.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_lowest_latency_routing.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_lunary.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_max_tpm_rpm_limiter.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_mem_usage.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_mock_request.py

Litellm ruff linting enforcement (#5992)

2024-10-01 19:44:20 -04:00

test_model_alias_map.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_model_max_token_adjust.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_multiple_deployments.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_ollama_local_chat.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_ollama_local.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_ollama.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_openai_batches_and_files.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_openai_moderations_hook.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_parallel_request_limiter.py

Litellm ruff linting enforcement (#5992)

2024-10-01 19:44:20 -04:00

test_pass_through_endpoints.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_presidio_masking.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_profiling_router.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_prometheus_service.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_prometheus.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_prompt_caching.py

LiteLLM Minor Fixes & Improvements (10/04/2024) (#6064)

2024-10-04 21:28:53 -04:00

test_prompt_factory.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_prompt_injection_detection.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_promptlayer_integration.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_provider_specific_config.py

Litellm ruff linting enforcement (#5992)

2024-10-01 19:44:20 -04:00

test_proxy_custom_auth.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_proxy_custom_logger.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_proxy_encrypt_decrypt.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_proxy_exception_mapping.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_proxy_gunicorn.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_proxy_pass_user_config.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_proxy_reject_logging.py

Litellm ruff linting enforcement (#5992)

2024-10-01 19:44:20 -04:00

test_proxy_routes.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_proxy_server_caching.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_proxy_server_cost.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_proxy_server_keys.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_proxy_server_langfuse.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_proxy_server_spend.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_proxy_server.py

(fixes) gcs bucket key based logging (#6044)

2024-10-04 11:56:10 +05:30

test_proxy_setting_guardrails.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_proxy_token_counter.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_proxy_utils.py

test: refactor test

2024-09-28 21:08:15 -07:00

test_pydantic_namespaces.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_pydantic.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_python_38.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_register_model.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_rerank.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_router_batch_completion.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_router_caching.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_router_client_init.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_router_cooldowns.py

Litellm ruff linting enforcement (#5992)

2024-10-01 19:44:20 -04:00

test_router_custom_routing.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_router_debug_logs.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_router_fallbacks.py

Litellm ruff linting enforcement (#5992)

2024-10-01 19:44:20 -04:00

test_router_get_deployments.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_router_init.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_router_max_parallel_requests.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_router_policy_violation.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_router_retries.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_router_tag_routing.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_router_timeout.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_router_utils.py

Litellm ruff linting enforcement (#5992)

2024-10-01 19:44:20 -04:00

test_router_with_fallbacks.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_router.py

Litellm ruff linting enforcement (#5992)

2024-10-01 19:44:20 -04:00

test_rules.py

Litellm ruff linting enforcement (#5992)

2024-10-01 19:44:20 -04:00

test_sagemaker.py

LiteLLM Minor Fixes & Improvements (10/04/2024) (#6064)

2024-10-04 21:28:53 -04:00

test_scheduler.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_secret_detect_hook.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_secret_manager.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_simple_shuffle.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_spend_calculate_endpoint.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_spend_logs.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_stream_chunk_builder.py

fix(utils.py): return openai streaming prompt caching tokens (#6051)

2024-10-03 22:20:13 -04:00

test_streaming.py

Litellm ruff linting enforcement (#5992)

2024-10-01 19:44:20 -04:00

test_supabase_integration.py

Litellm ruff linting enforcement (#5992)

2024-10-01 19:44:20 -04:00

test_team_config.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_text_completion.py

LiteLLM Minor Fixes & Improvements (10/02/2024) (#6023)

2024-10-02 22:00:28 -04:00

test_timeout.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_together_ai.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_token_counter.py

(feat proxy slack alerting) - allow opting in to getting key / internal user alerts (#5990)

2024-10-01 10:49:22 -07:00

test_tpm_rpm_routing_v2.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_traceloop.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_triton.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_update_spend.py

Litellm ruff linting enforcement (#5992)

2024-10-01 19:44:20 -04:00

test_user_api_key_auth.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_utils.py

LiteLLM Minor Fixes & Improvements (10/04/2024) (#6064)

2024-10-04 21:28:53 -04:00

test_validate_environment.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_wandb.py

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

test_whisper.py

Litellm ruff linting enforcement (#5992)

2024-10-01 19:44:20 -04:00

user_cost.json

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

vertex_ai.jsonl

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00

vertex_key.json

refactor: move all testing to top-level of repo

2024-09-28 21:08:14 -07:00