AiCensus.

LiteLLM

Open-source LLM gateway for routing, logging, and cost control

4.5
Open sourceModels & Infrastructure

Pricing

Open source

Company

BerriAI

Founded

2023

Free open-source self-hosted; LiteLLM Cloud managed proxy with usage-based pricing

Who It's For
Platform engineers managing LLM infrastructureTeams needing provider-agnostic API layerStartups controlling AI API spend
Details
CompanyBerriAI
Founded2023
WebsiteVisit

About LiteLLM

LiteLLM is an open-source proxy that provides a unified OpenAI-compatible API across 100+ LLM providers. Teams self-host it to manage API keys, track spend, set rate limits, and failover between models. It is widely used as the infrastructure layer behind production AI applications that need provider flexibility.

Key Features

  • Unified API for 100+ LLM providers
  • Cost tracking and budget limits
  • Automatic failover and load balancing
  • OpenAI-compatible endpoint
  • Logging and observability dashboard

Pros & Cons

Pros

+ Eliminates vendor lock-in for LLM APIs

+ Production-grade logging and cost controls

+ Active open-source community

Cons

- Self-hosting requires DevOps expertise

- Adds latency vs direct provider calls

- Configuration complexity for advanced routing

Use Cases

Multi-provider LLM routing in production appsCost tracking across team API usageFailover between OpenAI, Anthropic, and open models

Featured in best-of guides

Editorial lists that include this tool

Best AI Infrastructure Tools in 2026

APIs, routing, inference, and model deployment.

More in Models & Infrastructure