★ 43,693 stars
Python
🤖 AI/LLM
Updated 1mo ago
Python SDK, Proxy Server (AI Gateway) to call 100+ LLM APIs in OpenAI (or native) format, with cost tracking, guardrails, loadbalancing and logging. [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, VLLM, NVIDIA NIM]
View on GitHub →
Try with Claude — $10 free →
Quick Install
Copy the config for your editor. Some servers may need additional setup — check the README.
Add to claude_desktop_config.json:
{
"mcpServers": {
"litellm": {
"command": "uvx",
"args": [
"litellm"
]
}
}
}
Run in terminal:
claude mcp add litellm uvx litellm
Add to .cursor/mcp.json:
{
"mcpServers": {
"litellm": {
"command": "uvx",
"args": [
"litellm"
]
}
}
}
Or install with pip: pip install litellm
Topics
ai-gatewayanthropicazure-openaibedrockgatewaylangchainlitellmllmllm-gatewayllmopsmcp-gatewayopenaiopenai-proxyvertex-ai