litellm-mirror/litellm/proxy/pass_through_endpoints
Krish Dholakia 543655adc7 Litellm dev 01 14 2025 p2 (#7772)
* feat(pass_through_endpoints.py): fix anthropic end user cost tracking

* fix(anthropic/chat/transformation.py): use returned provider model for anthropic

handles anthropic `-latest` tag in request body throwing cost calculation errors

ensures we can be accurate in our model cost tracking

* feat(model_prices_and_context_window.json): add gemini-2.0-flash-thinking-exp pricing

* test: update test to use assumption that user_api_key_dict can get anthropic user id

* test: fix test

* fix: fix test

* fix(anthropic_pass_through.py): uncomment previous anthropic end-user cost tracking code block

can't guarantee user api key dict always has end user id - too many code paths

* fix(user_api_key_auth.py): this allows end user id from request body to always be read and set in auth object

* fix(auth_check.py): fix linting error

* test: fix auth check

* fix(auth_utils.py): fix get end user id to handle metadata = None
2025-01-15 21:34:50 -08:00
..
llm_provider_handlers Litellm dev 01 14 2025 p2 (#7772) 2025-01-15 21:34:50 -08:00
llm_passthrough_endpoints.py Add /openai pass through route on litellm proxy (#7412) 2024-12-25 20:15:59 -08:00
pass_through_endpoints.py Litellm dev 01 14 2025 p2 (#7772) 2025-01-15 21:34:50 -08:00
streaming_handler.py (code quality) run ruff rule to ban unused imports (#7313) 2024-12-19 12:33:42 -08:00
success_handler.py (code quality) run ruff rule to ban unused imports (#7313) 2024-12-19 12:33:42 -08:00
types.py (feat) add usage / cost tracking for Anthropic passthrough routes (#6835) 2024-11-20 17:25:12 -08:00