Home / Open source / litellm

litellm

MCP server

BerriAI/litellm · Enterprise stack · Enterprise

The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azu

Verified via GitHub API

  • anthropic
  • langchain
  • llm
  • llmops
  • openai
  • ai-gateway
  • azure-openai
  • bedrock
  • gateway
  • openai-proxy
  • vertex-ai
  • llm-gateway
  • litellm
  • mcp-gateway
  • rust
  • rust-ai

Data from GitHub API, refreshed Oct 17, 2026

Stars
61415
Forks
12424
License
Other
Language
Python
Last commit
Oct 17, 2026
Latest release
v1.105.1
Release date
Oct 14, 2026
Contributors
1825
Open issues
1854
GitHub Project website

Works with — from README

MCP
MCP server
Models
Bedrock, Claude, Gemini, Llama, Mistral, Ollama, OpenAI

Source: README.md keyword match (stated in README)

litellm FAQ

Is litellm free?

litellm is open source under the Other license. Hosted services and infrastructure may have separate costs.

How popular is litellm?

litellm has 61415 GitHub stars as of Oct 17, 2026.

Is there a hosted version of litellm?

A hosted alternative for litellm is unknown (—) in this data.

What does litellm work with?

From README: MCP server, Bedrock, Claude, Gemini, Llama, Mistral, Ollama, OpenAI.