BerriAI/litellm v1.40.1

on GitHub

What's Changed

• [Feat] return num_retries and max_retries in exceptions by @ishaan-jaff in #3962
• [FEAT]- set custom AllowedFailsPolicy on litellm.Router by @ishaan-jaff in #3963
• feat(proxy_server.py): log litellm api version to langfuse by @krrishdholakia in #3969
• feat - add batches api to docs by @ishaan-jaff in #3973
• [Fix] Traceloop / OTEL logging fixes + easier docs by @ishaan-jaff in #3970
• add dall-e 3 required comment by @rhtenhove in #3984
• [Feat] Log Raw Request from LiteLLM on Langfuse - when "log_raw_request": true by @ishaan-jaff in #3983
• [Feat] Admin UI - Multi-Select Tags, Viewing spend by tags by @ishaan-jaff in #3994
• [Feat] UI - Filter model latency by API Key Alias by @ishaan-jaff in #3995
• feat(assistants/main.py): Azure Assistants API support by @krrishdholakia in #3996
• [Admin UI] Filter Model Latency by Customer, API Key by @ishaan-jaff in #3997
• fix(router.py): use litellm.request_timeout as default for router clients by @krrishdholakia in #3992
• [Doc] - Spend tracking with litellm by @ishaan-jaff in #3991

New Contributors

• @rhtenhove made their first contribution in #3984

Full Changelog: v1.40.0...v1.40.1

Docker Run LiteLLM Proxy

docker run \
-e STORE_MODEL_IN_DB=True \
-p 4000:4000 \
ghcr.io/berriai/litellm:main-v1.40.1

Don't want to maintain your internal proxy? get in touch 🎉

Hosted Proxy Alpha: https://calendly.com/d/4mp-gd3-k5k/litellm-1-1-onboarding-chat

Docker Run LiteLLM Proxy

docker run \
-e STORE_MODEL_IN_DB=True \
-p 4000:4000 \
ghcr.io/berriai/litellm:main-v1.40.1

Don't want to maintain your internal proxy? get in touch 🎉

Hosted Proxy Alpha: https://calendly.com/d/4mp-gd3-k5k/litellm-1-1-onboarding-chat

Load Test LiteLLM Proxy Results