BerriAI/litellm v1.77.1.dev.2

on GitHub

What's Changed

• added tags to langchain by @mubashir1osmani in #14391
• [Fix] Restore forgotten raise keyword in front of an exception_type() call by @teremterem in #14379
• Fix embeddings using azure_ad_token_provider. by @dworthen in #14374
• update: DeepInfra model data refresh [2025-09-08] by @Toy-97 in #14324
• fix: remove anthropic-beta header for Vertex AI requests with prompt caching by @swarna1101 in #14310
• feat: Add dependency injection support to BaseLLMAIOHTTPHandler by @dharamendrak in #14111
• OCI Provder: Update OCIPromptTokensDetails by @gotsysdba in #14092
• pass function tool description for databricks provider by @frankzye in #13886
• Update README.md by @krrishdholakia in #14410
• Revert "Use _PROXY_MaxParallelRequestsHandler_v3 by default (#14352)" by @Bobronium in #14420
• Revert "fix: remove anthropic-beta header for Vertex AI requests with prompt caching" by @ishaan-jaff in #14421
• [Bug]: Fix Authorization header not being sent to configured MCP servers by @ishaan-jaff in #14422
• Validate api key on generation by @ishaan-jaff in #14428
• [Fixes] Bug fixes to using LiteLLM MCP Gateway by @ishaan-jaff in #14392

New Contributors

• @teremterem made their first contribution in #14379
• @dworthen made their first contribution in #14374
• @swarna1101 made their first contribution in #14310
• @dharamendrak made their first contribution in #14111

Full Changelog: v1.77.1.dev.1...v1.77.1.dev.2

Docker Run LiteLLM Proxy

docker run \
-e STORE_MODEL_IN_DB=True \
-p 4000:4000 \
ghcr.io/berriai/litellm:main-v1.77.1.dev.2

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