How do I run a big batch without hitting rate limits?

For thousands of requests:

• Use a dedicated key with a high limit (60 or 120 rpm) so the batch doesn't affect live traffic.
• Pace it: at 120 rpm, send about 2 requests per second.
• Queue and retry: on 429 or 5xx, put the item back with a delay.
• Check credits first: estimate cost (tokens × price) and top up so the batch doesn't stop at 402 out_of_credits halfway.
• Use Flash unless the task really needs more depth.

There's no separate batch endpoint; the batch is just many normal requests.

Good to know#

• Retry only 429 and 5xx errors, with backoff; honour Retry-After when it's sent. Which errors to retry
• Keep keys on your server, never in a browser or mobile app. Why
• Every response has an X-Request-Id; log it so a request can be found later. Why log it

Still need help?#

• General support: support@clatterlabs.com or team@clatterlabs.xyz
• Infrastructure questions, or permanent deletion of your data (your whole account or one service): infrastructure@clatterlabs.xyz

We usually reply within the first hour, and always within 24 hours. A full support team is with you.