Rate limits
Each key can make a set number of requests per minute. Above that, you get 429 with Retry-After.
Il centro assistenza è scritto in inglese e in olandese. Stai leggendo la versione inglese.
The limit counts the requests of one key over the last 60 seconds. The default is 600 requests per minute. GET /v1/key shows the exact limit of your key, under rate_limit:
curl https://api.nexrouting.com/v1/key \
-H "Authorization: Bearer $NEXROUTING_API_KEY"Over the limit, the API answers 429 with the code rate_limit_exceeded and a Retry-After header with the number of seconds to wait.
A 429 can also mean that the model itself is busy at that moment. Then wait a few seconds and try again.
Handle it in your code
- Retry after the
Retry-Aftertime, with a longer pause after each failed try (exponential backoff). - Keep the number of requests you send per minute within your limit.
- Need a higher limit? Contact support.
Requests that get a 429 cost nothing. Limits on paying are separate: see Top-up limits.