Rate limits
Rate limits are applied per model and per user. Exceeding a limit returns 429 Too Many Requests with a Retry-After header telling you how many seconds to wait before retrying.
Response headers
Every response carries the current rate-limit budget for the endpoint:
| Header | Meaning |
|---|---|
x-ratelimit-limit | The maximum for the current window |
x-ratelimit-remaining | How much of the current window is left |
x-ratelimit-reset | Seconds until the window resets |
Handling 429
- Read
Retry-Afterand back off for that duration - Do not retry the same input in a tight loop — you will burn through the reset window
- Do exponential backoff for retries beyond
Retry-After
Current limits
Per-model rate-limit numbers are set per account. The current values for your account are available in the console under Usage & Costs. Contact your Advania Solutions Architect if you need them raised.