LiteLLM

Unified API proxy for 100+ LLM providers — one interface, any model
LLM APIs & InferenceFree (open-source), hosted proxy available16,000Works with OpenClaw

About LiteLLM

LiteLLM provides a unified OpenAI-compatible interface to call 100+ LLM APIs including OpenAI, Anthropic, Cohere, Replicate, local models, and more. Acts as a proxy that handles auth, load balancing, fallbacks, and spend tracking across all providers.

Features

Unified API for 100+ LLM providers
Load balancing across multiple API keys/providers
Automatic fallbacks when providers fail
Spend tracking and budget alerts per team/project
Rate limiting and retry logic built-in
OpenAI SDK compatible — zero code changes
Self-hostable proxy server
Supports streaming, function calling, vision

The tally

FOR
  • +One API for 100+ providers
  • +Built-in load balancing and fallbacks
  • +Spend tracking and rate limiting
  • +OpenAI SDK compatible
AGAINST
  • Adds a proxy layer (slight latency)
  • Complex config for advanced features

Related concepts

Kept nearby

Browse all LLM APIs & Inference tools →

Featured in