​
Base URLs

The Relace API is organized into two distinct domain patterns: *.endpoint.relace.run domains for direct AI model access, and api.relace.run for general infrastructure services including source control.

​
Model Endpoints

https://*.endpoint.relace.run
To use our hosted models the url pattern follows the above convention — the * is a placeholder for the series of model you are using. e.g. instantapply, ranker, embeddings.

​
Infrastructure Endpoints

https://api.relace.run
For accessing our infrastructure (e.g. source control) you will use the routes specified in this API reference with our common base url.

​
Authentication

To authenticate you need to add an Authorization header with the contents of the header being your Relace API Key, which is a 32 digit key with with the prefix rlc-. 
Authorization: Bearer rlc-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx

​
Response Codes

Relace uses standard HTTP codes to indicate the success or failure of your requests. In general, 2xx HTTP codes correspond to success, 4xx codes are for user-related failures, and 5xx codes are for infrastructure issues.
StatusDescription
200Successful request.
201Resource created successfully.
204Successful request, no content returned.
400Check that the parameters were correct.
401The API key used was missing or invalid.
403The API key used was invalid or lacks permissions.
404The resource was not found.
423The resource is temporarily locked.
429The rate limit was exceeded.
5xxIndicates an error with Relace servers.
Check Error Codes for a comprehensive breakdown of all possible API errors.

​
Rate Limits

Rate limits vary by tier and range from 3 calls per minute for free testing access to unlimited calls for high-volume users. When you exceed your rate limit, you’ll receive a 429 response error code. See the full rate limits table for detailed information about each tier’s limits.