BerriAI/litellm v1.41.24

on GitHub

What's Changed

• Add token counting for OpenAI tools/tool_choice by @pamelafox in #4716
• [UI] Clear cookies on logging out by @ishaan-jaff in #4743
• ui - allow admin viewer to view caching analytics page by @ishaan-jaff in #4741
• Docs - How to invite users to view usage, caching by @ishaan-jaff in #4744
• [Fix-Proxy] Slack Alerting Store Request Status in memory by @ishaan-jaff in #4732
• feat - use custom api key header name when using litellm virtual keys by @ishaan-jaff in #4739
• fix: enables batch embedding support for triton by @davidschuler-8451 in #4736
• [Fix + Test] anthropic raise litellm.AuthenticationError when no Anthropic API Key provided by @ishaan-jaff in #4747
• fix(proxy/utils.py): fix failure logging for rejected requests by @krrishdholakia in #4742
• fix(factory.py): use stronger typing for anthropic translation by @krrishdholakia in #4746
• ui-fix: clear token when user logging in by @ishaan-jaff in #4755
• [Fix] Langsmith - Don't Log Provider API Keys by @ishaan-jaff in #4754
• [Feat] Proxy + Langsmith - Log user_api_key_user_id, user_api_key_team_alias by @ishaan-jaff in #4757
• fix(litellm_logging.py): don't run async caching for sync streaming calls by @krrishdholakia in #4756
• [Feat] Use Async Httpx client for langsmith logging by @ishaan-jaff in #4758
• add new groq tool models by @themrzmaster in #4751
• Helicone headers to metadata by @maamalama in #4763
• Add Medlm cost calc by @skucherlapati in #4760
• Fix failing tests on PR-4760 by @skucherlapati in #4765

New Contributors

• @pamelafox made their first contribution in #4716
• @davidschuler-8451 made their first contribution in #4736
• @skucherlapati made their first contribution in #4760

Full Changelog: v1.41.23...v1.41.24

Docker Run LiteLLM Proxy

docker run \
-e STORE_MODEL_IN_DB=True \
-p 4000:4000 \
ghcr.io/berriai/litellm:main-v1.41.24

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