BerriAI/litellm
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, Azure, OpenAI, Anthropic, OpenAI, VertexAI, vLLM, Nvidia NIM]
Older snapshot: check the original source for current information.
From the publisher
README & documentation
Source previewRead the project’s overview, installation instructions and usage examples. The original README is the source of truth.
LiteLLM Proxy Server (AI Gateway) | Hosted Proxy | Enterprise Tier | Website LiteLLM is an open source AI Gateway that gives you a single, unified interface to call 100+ LLM providers — OpenAI, Anthropic, Gemini, Bedrock, Azure, and more — using the OpenAI format. Use it as a Python SDK for direct library integration, or deploy the AI Gateway (Proxy Server) as a centralized service for your team or organization. Jump to LiteLLM Proxy (LLM Gateway) Docs Jump to Supported LLM Providers Managing LLM calls across providers gets complicated fast — different SDKs, auth patterns, request formats, and error types for every model. LiteLLM removes that friction: LLMs - Call 100+ LLMs (Python SDK + AI Gateway) All Supported Endpoints - /chat/completions, /responses, /embeddings, /images, /audio, /batches, /rerank, /a2a, /messages and more. An independent litellm-core distribution provides the Python SDK with the same import litellm API and runtime dependencies.…
Read the full README ↗ · Preview checked 2026-10-28T10:34:56.287Z
Inside the original README — Document outline
- What is LiteLLM
- Why LiteLLM
- OSS Adopters
- Features
- Python SDK
- AI Gateway (Proxy Server)
- Python SDK - A2A Protocol
- AI Gateway (Proxy Server)
- Python SDK - MCP Bridge
- AI Gateway - MCP Gateway
- Use with Cursor IDE
- Python SDK - Agents
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Links from the README
References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.
- Jump to LiteLLM Proxy (LLM Gateway) Docs
- Jump to Supported LLM Providers
- benchmarks
- All Supported Endpoints
- Getting Started - E2E Tutorial
- Supported Providers
- Add your Agent to the AI Gateway
- Docs: A2A Agent Gateway
- Add your MCP Server to the AI Gateway
- Docs: MCP Gateway
- Docs: Agent Harnesses
- Abliteration (abliteration)
Documentation belongs to its respective authors. Reported project/model license: Other. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
What this repository does
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, Azure, OpenAI, Anthropic, OpenAI, VertexAI, vLLM, Nvidia NIM]
Repository facts
- Owner
- BerriAI
- Primary language
- Python
- Stars
- 60,455
- Forks
- 12,171
- Open issues + pull requests
- 5,394
- License
- Other
- Archived
- No
- Default branch
- main
- Created
- 2023-07-27T00:09:52.000Z
- Last push
- 2026-10-09T12:02:35.000Z
Topics and intended use
Owner-supplied topics: ai-gateway, anthropic, azure-openai, bedrock, gateway, langchain, litellm, llm, llm-gateway, llmops, mcp-gateway, openai, openai-proxy, rust, rust-ai, vertex-ai
Review the README for scope, installation, examples and limitations. We do not run repository code or certify it.
Evaluate before installing
Review licensing and dependencies, inspect recent commits and unresolved issues, and test in an isolated environment before production use. Stars and forks alone cannot answer these questions.
Source and freshness
Source: GitHub. Metadata observed 2026-10-09T12:04:51.812Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.
Related repositories
EbookFoundation/free-programming-books
donnemartin/system-design-primer