LiteLLM

What is LiteLLM?

LiteLLM is an LLM Gateway (OpenAI Proxy) designed to manage authentication, load balancing, and spend tracking across 100+ LLMs, all while maintaining the OpenAI format. It simplifies the process of using LLM APIs from various providers like OpenAI, Azure, Cohere, Anthropic, Replicate, and Google. LiteLLM offers consistent outputs and exceptions for all LLM APIs, along with logging and error tracking for all models. It provides features like cost tracking, batches API, guardrails, model access, budgets, LLM observability, rate limiting, prompt management, S3 logging, and pass-through endpoints.

How to use LiteLLM?

Use LiteLLM by calling LLM APIs using the chatGPT format – completion(model, messages). It provides consistent outputs and exceptions for all LLM APIs. You can deploy LiteLLM open source or try LiteLLM Enterprise for more features.

LiteLLM’s Core Features

LLM Gateway for 100+ LLMs OpenAI-compatible API Cost Tracking and Budget Management LLM Fallbacks Load Balancing Rate Limiting Prompt Management Logging and Error Tracking

LiteLLM’s Use Cases

• Giving developers access to multiple LLMs
• Managing spend across different LLM providers
• Implementing LLM fallbacks for reliability
• Standardizing LLM API access across an organization