LiteLLM

Call 100+ LLM providers with OpenAI-compatible API. Budget tracking and fallbacks built-in.

Essential glue layer when your stack uses more than one LLM provider.

Funciones clave

• Single OpenAI-compatible endpoint for 100+ providers
• Budget caps, rate limits, and fallback routing
• Spend tracking per API key and team
• Drop-in replacement for OpenAI SDK calls

Casos de uso

1. 01Multi-model routing (GPT-4o → Claude → local Ollama)
2. 02Centralized LLM gateway for microservices
3. 03Cost control for AI features in production SaaS

Inicio rápido

pip install litellm
litellm --model gpt-4o-mini

Compatibilidad de stack

Tags

• #llm
• #api
• #open-source