Skip to main content

​
Rate limits & Errors

Loom AI API returns OpenAI-like error objects, with a Loom-specific code and request_id field for tracing. 
{
  "error": {
    "message": "Rate limit exceeded",
    "type": "rate_limit_error",
    "code": "loom.rate_limit",
    "request_id": "req_12345"
  }
}

​
Rate limiting

  • Default rate limits: 60 requests per minute per key (varies by plan)
  • Burst allowance and retry-after headers will be present on 429 responses.

​
Best practices

  • Implement exponential backoff on 429 and 5xx codes
  • Include X-Request-ID in your requests if you need deterministic tracing
Contact Loom Labs support with your request_id to expedite debugging.