LiteLLM logo

LiteLLM

coding
No ratings yet

Open-source LLM proxy and unified API that lets you call 100+ LLM providers using the OpenAI format, with 50k+ GitHub stars.

LiteLLM is a lightweight Python library and hosted proxy server that translates LLM calls to a unified OpenAI-compatible API, supporting 100+ providers including Anthropic, Google, Cohere, and Azure. It handles load balancing, fallbacks, rate limiting, spend tracking, and logging across multiple LLM deployments from a single config file. Used by engineering teams at Airbnb, Instacart, and other enterprise organizations, LiteLLM processes millions of API calls daily. The project crossed 50,000 GitHub stars in 2025 and offers a managed proxy service alongside the open-source library for teams that want zero-ops deployment.

#llm
#api
#open-source
#developer-tools
#ai-development
#proxy
Freemium

Free plan available

Update Tool
litellm.ai
Freemium
Pricing Model
Code & Development
Category
2023
Since
Free Plan
Access

Key Features

  • Call 100+ LLMs via unified OpenAI-compatible API with a single code interface
  • Load balancing and automatic fallbacks across providers and models
  • Spend tracking and budget limits per API key or team deployment
  • Built-in support for streaming, function calling, and vision models across providers
  • Prometheus metrics and logging integrations for Langfuse, Helicone, and Langsmith
  • Proxy server mode for deploying a team-wide LLM gateway with access controls

Use Cases

  • Engineering teams standardizing on a single API client across multiple LLM providers
  • MLOps teams enforcing spend limits and routing policies across LLM deployments
  • Developers testing prompt compatibility across GPT-4o, Claude, and Gemini simultaneously
  • Enterprises needing an internal LLM gateway with audit logging and rate limiting

Pros

  • 100+ providers in one library - switch models with a single line change
  • Active maintainer with rapid releases and a responsive issue tracker
  • Native load balancing, fallbacks, and retries built in with no extra configuration

Cons

  • Proxy server mode adds infrastructure complexity for teams wanting zero-ops deployment
  • Some provider-specific features require custom params outside the unified interface
  • Self-hosted proxy needs a separate monitoring stack to match managed cloud alternatives

LiteLLM Alternatives

Explore similar tools and alternatives

Ready to try LiteLLM?

Visit the official website to explore all features and get started with LiteLLM today.

Reviews

0 reviews for LiteLLM

-

Based on 0 reviews

5
0
4
0
3
0
2
0
1
0

Share your experience

Log in to write a review for LiteLLM

Log In to Review

More Code & Development Tools

Discover similar tools in this category

Have an AI Tool?

List your AI tool for free, or go featured for top placement in your category - and reach thousands of potential users.

Submit Your Tool