About LiteLLM
"Unified API gateway for 100+ LLMs with one consistent OpenAI-compatible interface"
LiteLLM is an open-source unified API that provides a single interface for calling 100+ LLM APIs including OpenAI, Anthropic, Gemini, Mistral, and local models, all in the OpenAI format. Developers can switch between providers with a single line change, implement fallbacks and load balancing, track costs across providers, and add rate limiting without changing their application logic. LiteLLM also provides a self-hosted proxy server for teams needing centralized API key management, budget controls, and access logging across their organization.
Key Features
- 100+ provider unified interface
- Automatic fallback and retry
- Cost tracking across providers
- Rate limiting and budgets
- Self-hosted proxy option
Best For
Official Links
SambaNova Cloud
Ultra-fast inference for large frontier AI models on custom dataflow processors
Together AI
High-speed inference and fine-tuning platform for open-source AI models
Phi-4 Mini
Microsoft's compact 3.8B reasoning model that punches above its weight class
Mistral AI
Powerful open-source and commercial language models from Europe
Aya Expanse
Cohere's multilingual LLM covering 23 languages with state-of-the-art performance
LangSmith
Production observability platform for debugging and monitoring LLM applications
