BerriAI/litellm v1.72.2.devMCP

on GitHub

What's Changed

• fix inference endpoints (#11630) by @ishaan-jaff in #11631
• [UI] Add Deepgram provider to supported providers list and mappings by @ishaan-jaff in #11634
• [Bug Fix] Add audio/ogg mapping for Audio MIME types by @ishaan-jaff in #11635
• [Feat] Add Background mode for Responses API - OpenAI, AzureOpenAI by @ishaan-jaff in #11640
• [Feat] Add provider specific params for deepgram/ by @ishaan-jaff in #11638
• [Feat] MCP - Add support for streamablehttp_client MCP Servers by @ishaan-jaff in #11628
• [Feat] Perf fix - ensure deepgram provider uses async httpx calls by @ishaan-jaff in #11641
• Trim the long user ids on the the keys page by @NANDINI-star in #11488
• Enable System Proxy Support for aiohttp Transport by @idootop in #11616
• GA Multi-instance rate limiting v2 Requirements + New - specify token rate limit type - output / input / total by @krrishdholakia in #11646
• Add bridge for /chat/completion -> /responses API by @krrishdholakia in #11632
• Convert scientific notation str to int + Bubble up azure content filter results by @krrishdholakia in #11655
• feat(helm): [#11648] support extraContainers in migrations-job.yaml by @stevenaldinger in #11649
• Correct success message when user creates new budget by @vuanhtu52 in #11608
• fix: Do not add default model on tag based-routing when valid tag by @thiagosalvatore in #11454
• Fix default user settings by @NANDINI-star in #11674
• [Pricing] add azure/gpt-4o-mini-transcribe models by @ishaan-jaff in #11676
• Enhance Mistral model support with reasoning capabilities by @colesmcintosh in #11642
• [Feat] MCP expose streamable https endpoint for LiteLLM Proxy by @ishaan-jaff in #11645
• change space_key header to space_id for Arize by @vanities in #11595
• Add performance indexes to LiteLLM_SpendLogs for analytics queries by @colesmcintosh in #11675
• Revert "Add performance indexes to LiteLLM_SpendLogs for analytics queries" by @krrishdholakia in #11683
• [Feat] Use dedicated Rest endpoints for list, calling MCP tools by @ishaan-jaff in #11684
• Chat Completions <-> Responses API Bridge Improvements by @krrishdholakia in #11685
• [UI] Fix MCP Server Table to Match Existing Table Pattern by @ishaan-jaff in #11691
• Logging: prevent double logging logs when bridge is used (anthropic <-> chat completion OR chat completion <-> responses api) by @krrishdholakia in #11687
• fix(vertex_ai): support global location in vertex ai passthrough by @alvarosevilla95 in #11661
• [Feat] UI Allow editing mcp servers by @ishaan-jaff in #11693
• [Feat] UI - Allow setting MCP servers when creating keys, teams by @ishaan-jaff in #11711
• [Feat] Add Authentication + Permission Management for MCP List, Call Tool Ops by @ishaan-jaff in #11682
• Add Live Tail Feature to Logs View by @NANDINI-star in #11712
• [Feat] Add Connect to MCP Page by @ishaan-jaff in #11716
• Enterprise feature preview improvement on Audit Logs by @NANDINI-star in #11715

New Contributors

• @idootop made their first contribution in #11616
• @stevenaldinger made their first contribution in #11649
• @thiagosalvatore made their first contribution in #11454
• @vanities made their first contribution in #11595
• @alvarosevilla95 made their first contribution in #11661

Full Changelog: v1.72.5.dev1...v1.72.2.devMCP

Docker Run LiteLLM Proxy

docker run \
-e STORE_MODEL_IN_DB=True \
-p 4000:4000 \
ghcr.io/berriai/litellm:main-v1.72.2.devMCP

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