Helicone/ai-gateway

The fastest, lightest, and easiest-to-integrate AI gateway on the market. Fully open-sourced.

46
/ 100
Emerging

This tool helps developers and ML engineers manage interactions with multiple Large Language Models (LLMs) from different providers using a single, unified interface. It takes requests using familiar OpenAI syntax, routes them intelligently to the best LLM based on speed, cost, or reliability, and outputs the LLM's response. It's ideal for anyone building applications that rely on various LLM services.

549 stars.

Use this if you are building an AI application and need a robust, performant way to connect to many LLM providers while optimizing for cost, speed, or reliability.

Not ideal if your application only uses a single LLM provider and doesn't require advanced routing, caching, or rate limiting features.

AI application development LLM operations API management AI infrastructure MLOps
No Package No Dependents
Maintenance 6 / 25
Adoption 10 / 25
Maturity 15 / 25
Community 15 / 25

How are scores calculated?

Stars

549

Forks

44

Language

Rust

License

GPL-3.0

Category

llm-api-gateways

Last pushed

Nov 21, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/Helicone/ai-gateway"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.