Docs / Core Concepts / How It Works

How RelayRouter Works

RelayRouter is a gateway between your application and the upstream model providers. You integrate one API and one key; the gateway forwards each request to the provider that serves the model you asked for.

#Request flow

1. Authentication: your API key is validated and your balance checked.
2. Routing: the request is forwarded to the upstream provider based on the model field.
3. Response: the provider's output is returned to you in a consistent format.

#OpenAI compatibility

The gateway exposes the OpenAI API shape, so any SDK, framework or tool that accepts a custom base URL works unchanged: set it to https://relayrouter.io/v1 and use your RelayRouter key. Switching providers is just a different model value, with no new credentials and no SDK changes.

#Upstream providers

Models from the world's leading AI labs:

#Billing

Usage is metered per request:

• Chat models: billed per input and output token
• Image generation: billed per generated image

Failed requests are not billed: you only pay for output that is successfully delivered.