Introduction

Relay is an OpenAI-compatible API for the cheapest open and affordable models — with prompt caching, a batch lane and cheapest-provider routing built in, so your effective cost is the lowest possible. Transparent pricing, no silent downgrades.

Base URL

All endpoints live under one base URL:

https://api.relay.com/v1

Quickstart

  1. Create an account and grab your API key from the dashboard.
  2. Point your existing OpenAI SDK at our base_url.
  3. Pick any model id from the marketplace. Caching & routing happen automatically.

Why it's cheaper

Beyond picking the cheapest provider per model, the gateway lowers your effective cost automatically. See Caching, batch & routing.

New here? The fastest path: copy the cURL above, swap in your key, and you'll get a response from a cheap model in seconds.