BerriAI/litellm v1.77.3-stable

on GitHub

What's Changed

• Enrich rate limit error message with details by @ishaan-jaff in #14736
• UI SSO - consider token info endpoint on generic SSO route for access control groups + (fix) allow unsetting access groups by @krrishdholakia in #14738
• UI - Add team-level sampling setting for tracing Langsmith by @krrishdholakia in #14740
• fix(prometheus.py): make prometheus work for multiple workers by @krrishdholakia in #14530
• docs: add Vertex batch provider documentation and sidebar entry by @FelipeRodriguesGare in #14742
• chore(docker): remove redundant Admin UI build step by @mritunjaysharma394 in #14678
• Fix: Updated error message for Gemini API by @timelfrink in #14589
• Fix: Bedrock inference profiles for Nova Canvas image generation by @timelfrink in #14578
• rename aim headers + tests by @hxdror in #14438
• Fix API key passing for Gemini token counting endpoints by @eycjur in #14744
• fix(model_connection_test.tsx): pass modelinfo to `/health/test_conne… by @krrishdholakia in #14752
• [Docs] - v1.77.3 by @ishaan-jaff in #14751

New Contributors

• @mritunjaysharma394 made their first contribution in #14678

Full Changelog: v1.77.3.dynamic_rates...v1.77.3-stable

Docker Run LiteLLM Proxy

docker run \
-e STORE_MODEL_IN_DB=True \
-p 4000:4000 \
ghcr.io/berriai/litellm:litellm_stable_release_branch-v1.77.3-stable

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