BerriAI/litellm v1.65.8-nightly

on GitHub

What's Changed

• Revert avglogprobs change + Add azure/gpt-4o-realtime-audio cost tracking by @krrishdholakia in #9893
• Realtime API: Support 'base_model' cost tracking + show response in spend logs (if enabled) by @krrishdholakia in #9897
• Simplify calling gemini models w/ file id by @krrishdholakia in #9903
• feat: add extraEnvVars to the helm deployment by @mknet3 in #9292
• [Feat - UI] - Allow setting Default Team setting when LiteLLM SSO auto creates teams by @ishaan-jaff in #9918
• Fix typo: Entrata -> Entra in docs by @msabramo in #9921
• [Feat - PR1] Add xAI grok-3 models to LiteLLM by @ishaan-jaff in #9920
• [Feat - Team Member Permissions] - CRUD Endpoints for managing team member permissions by @ishaan-jaff in #9919
• [Feat] Add litellm.supports_reasoning() util to track if an llm supports reasoning by @ishaan-jaff in #9923
• [Feat] Add reasoning_effort support for xai/grok-3-mini-beta model family by @ishaan-jaff in #9932
• [UI] Render Reasoning content, ttft, usage metrics on test key page by @ishaan-jaff in #9931
• [UI] - Add Managing Team Member permissions on UI by @ishaan-jaff in #9927
• [UI] Linting fixes by @ishaan-jaff in #9933
• Support CRUD endpoints for Managed Files by @krrishdholakia in #9924
• fix(databricks/common_utils.py): fix custom endpoint check by @krrishdholakia in #9925
• fix(transformation.py): correctly translate 'thinking' param for lite… by @krrishdholakia in #9904

Full Changelog: v1.65.7-nightly...v1.65.8-nightly

Docker Run LiteLLM Proxy

docker run \
-e STORE_MODEL_IN_DB=True \
-p 4000:4000 \
ghcr.io/berriai/litellm:main-v1.65.8-nightly

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