Introduction - Relace

Base URL

https://models.relace.ai

All hosted models are served from this base url — the route determines which model you are using. e.g. /v1/code/apply, /v1/code/compact, /v1/search/chat/completions.

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 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.

Status	Description
`200`	Successful request.
`400`	Check that the parameters were correct.
`401`	The API key used was missing or invalid.
`402`	The account is out of credits, or has no payment method attached.
`404`	The resource was not found.
`405`	The route does not accept this HTTP method.
`413`	The request body was too large.
`429`	The rate limit was exceeded, or the model is at capacity.
`5xx`	Indicates an error with Relace servers. `502`, `503`, and `504` are transient and safe to retry.

Check Errors for the response bodies, the canonical messages, and retry guidance.

Rate Limits

Rate limits are a per-key request budget over a rolling 60 second window. Free accounts start at 15 requests per minute, and the budget scales with your account tier up to unlimited for high-volume users. When you exceed your rate limit, you’ll receive a 429 response with a Retry-After header. To raise your limits, contact support.