litellm-rs 0.3.0

A high-performance AI Gateway written in Rust, providing OpenAI-compatible APIs with intelligent routing, load balancing, and enterprise features
Documentation

LiteLLM-RS

A high-performance AI gateway written in Rust that provides OpenAI-compatible APIs with intelligent routing across 100+ providers.

Features

  • OpenAI-compatible HTTP APIs (chat, completions, embeddings, images)
  • Multi-provider routing, load balancing, and failover
  • Streaming, tool/function calling, and response formatting
  • Caching, authentication (API keys/JWT), rate limiting, and observability
  • Extensible provider system and protocol gateways (MCP, A2A)

Getting Started

  • Documentation: see docs/README.md
  • Configuration: copy templates from config/*.example or config/*.template
  • Run locally: make dev or cargo run

Library Usage

The crate exposes Rust helpers for OpenAI-style calls. For end-to-end usage, run the gateway binary and configure providers via the config file.

License

MIT. See LICENSE.