Request limits
Handle request, upload, and concurrency limits reliably.
Limits protect shared capacity and apply to authenticated requests. They may vary with account configuration, so build clients that handle the response instead of depending on a fixed number.
When a request is limited
The API returns 429 with an OpenAI-compatible error object. For rate-limit and failed-authentication throttles, the response includes Retry-After. Wait at least that long before retrying.
429 rate_limit_error
Retry-After: 60Use exponential backoff with jitter, and bound the number of retries. Do not immediately retry a request that was rejected for concurrent work; wait for an in-flight request to finish first.
Request sizes
Speech input and request bodies are validated before processing. Split long material into logical segments and upload only supported, complete audio files.
Capacity
Limits are enforced at the account level, including when several keys belong to the same account. If your production workload needs more capacity, contact support with the expected request volume, concurrent work, and audio duration.