3 commits

Author	SHA1	Message	Date
Krish Dholakia	9c083e7d2c	Support Gemini audio token cost tracking + fix openai audio input token cost tracking (#9535) ... * fix(vertex_and_google_ai_studio_gemini.py): log gemini audio tokens in usage object enables accurate cost tracking * refactor(vertex_ai/cost_calculator.py): refactor 128k+ token cost calculation to only run if model info has it Google has moved away from this for gemini-2.0 models * refactor(vertex_ai/cost_calculator.py): migrate to usage object for more flexible data passthrough * fix(llm_cost_calc/utils.py): support audio token cost tracking in generic cost per token enables vertex ai cost tracking to work with audio tokens * fix(llm_cost_calc/utils.py): default to total prompt tokens if text tokens field not set * refactor(llm_cost_calc/utils.py): move openai cost tracking to generic cost per token more consistent behaviour across providers * test: add unit test for gemini audio token cost calculation * ci: bump ci config * test: fix test	2025-03-26 17:26:25 -07:00
Krish Dholakia	1ab5d49132	Support litellm.api_base for vertex_ai + gemini/ across completion, embedding, image_generation (#9516) ... * test(tests): add unit testing for litellm_proxy integration * fix(cost_calculator.py): fix tracking cost in sdk when calling proxy * fix(main.py): respect litellm.api_base on `vertex_ai/` and `gemini/` routes * fix(main.py): consistently support custom api base across gemini + vertexai on embedding + completion * feat(vertex_ai/): test * fix: fix linting error * test: set api base as None before starting loadtest	2025-03-25 23:46:20 -07:00
Krrish Dholakia	6779c44701	feat(cost_calculator.py): support reading litellm response cost header in client sdk ... allows consistent cost tracking when sdk is calling proxy	2025-03-17 15:12:01 -07:00