Rate limits

Limits protect every customer from a burst by one. They apply per API key.

When you pass a limit, the API returns 429 with a Retry-After header in seconds:

HTTP/1.1 429 Too Many Requests
Retry-After: 4

{ "error": { "type": "rate_limit_error", "code": "rate_limited", "message": "Too many requests. Retry in 4 seconds." } }

Tasks above the running limit are not rejected: they wait as queued and start as others finish.

Need higher limits? Write to sales@tovano.ai with your expected volume.