Rate limits
The Prompting Company rate limits protect each authenticated principal. API keys are limited globally by key, and route-level limits can also apply to individual endpoints.Current defaults
API key rows can store a lower configured limit, but the platform cap remains 300 requests per 60 seconds.
429 response
When a caller exceeds its limit, the API returns429:
Retry-After is seconds until the current bucket resets.
The wrapper currently emits
Retry-After and x-request-id. It does not emit
X-RateLimit-Limit, X-RateLimit-Remaining, or X-RateLimit-Reset.Retry with backoff
UseRetry-After when it is present, then add exponential backoff with jitter for repeated 429 responses.