LiteLLM

Unified Python interface for calling 100+ LLM APIs using consistent OpenAI format. Provides standardized exception handling, retry/fallback logic, and cost tracking across multiple providers.

When to Use This Skill

Use this skill when:

• Integrating with multiple LLM providers through a single interface
• Routing requests to local llamafile servers using OpenAI-compatible endpoints
• Implementing retry and fallback logic for LLM calls
• Building applications requiring consistent error handling across providers
• Tracking LLM usage costs across different providers
• Converting between provider-specific APIs and OpenAI format
• Deploying LLM proxy servers with unified configuration
• Testing applications against both cloud and local LLM endpoints

Core Capabilities