Rate limits
Per-key requests per minute, headers and backing off.
- How do I get a higher rate limit?Create a key with a higher limit (up to 120 rpm), or split traffic across several keys.How-to
- How do I run a big batch without hitting rate limits?Queue requests, cap concurrency to your key's per-minute limit, honour Retry-After, and use a dedicated key.How-to
- How many requests can I send at the same time?No separate concurrency limit is documented for the Model API; the per-key requests-per-minute limit applies.FAQ
- How should my app back off on 429?Wait exactly Retry-After seconds, then retry; pace requests using X-RateLimit-Remaining to avoid 429s.How-to
- I get 429 even though I'm under my limit. Why?Check the code: rate_limited is the key's limit; team_daily_quota_reached or team_spend_limit_reached come from team settings.Troubleshooting
- Is the rate limit lower while I'm using the free credit?The docs tie rate limits to keys (10–120 rpm, chosen at creation), not to your credit or plan.FAQ
- Is the rate limit per key or per account?Per key. Each key has its own requests-per-minute limit.FAQ
- What are the Model API rate limits?Each key has its own limit: 10, 30 (default), 60 or 120 requests per minute. Over it answers 429 rate_limited.Reference
- Why don't I see X-RateLimit headers on some responses?Rate limit headers come on keyed responses. GET /v1/models doesn't need a key, so it may not carry them.FAQ
Still need help?
Tried the steps above and still stuck? Email us. We usually reply within the first hour, and always within 24 hours. A full support team is with you.
Infrastructure questions, or permanent deletion of your data
infrastructure@clatterlabs.xyzFor deleting your whole account or the data of one service.