litellm

Manage LLM provider interactions through a unified OpenAI-compatible API.

1|Updated Jun 4, 2026
One-click install
npx skills add https://github.com/hung-phan/ml-skills --skill litellm-hung-phan
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: litellm
Source: https://github.com/hung-phan/ml-skills/tree/main/skills/ml-review/references/ml-libraries/litellm
Command: npx skills add https://github.com/hung-phan/ml-skills --skill litellm-hung-phan

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires litellm, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill provides a unified interface for interacting with over 100 LLM providers, simplifying the process of switching between providers and handling fallbacks.

Core Features & Use Cases

  • Unified API: Access multiple LLM providers through a single, OpenAI-compatible API.
  • Provider Routing: Easily switch between providers with a simple string format.
  • Fallbacks and Retries: Automate fallbacks and retries across different providers.
  • Cost Tracking: Monitor costs and usage across all providers.
  • Use Case: If you are building a service that requires access to multiple LLM providers, this Skill can help you manage all interactions through a single API.

Quick Start

Use the litellm skill to generate a completion with the model 'openai/gpt-4o'.

Frequently Asked Questions about litellm

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I access multiple LLM providers through a single API?▼

You can access multiple LLM providers through a single API using a unified, OpenAI-compatible interface that routes requests to over 100 different providers based on a simple string format.

How do I set up fallbacks and retries across different LLM providers?▼

You can set up fallbacks and retries across different LLM providers by configuring a unified proxy interface that automates request routing and handles failures automatically.

What is the best way to track API costs and usage across multiple LLM providers?▼

The best way to track API costs and usage across multiple LLM providers is to route requests through a unified interface that includes built-in cost tracking and usage monitoring features.

Does the litellm unified API work with production proxy deployment?▼

Yes, the litellm unified API works with production proxy deployment, handling rate limiting, caching, and provider routing for services requiring access to multiple LLM providers.

Can I use a single OpenAI-compatible API call for different LLM models?▼

Yes, you can use a single OpenAI-compatible API call for different LLM models by specifying the provider and model in a simple string format within the unified interface.

How do I handle rate limiting and caching when switching between LLM providers?▼

You handle rate limiting and caching when switching between LLM providers by deploying a unified proxy that manages these constraints automatically across all provider interactions.