Rate limits and run limits
Requests per minute, runs in progress, input sizes and steps per run.
- How does the per-key rate limit work?Each key allows 10, 30, 60 or 120 requests per minute. Responses show X-RateLimit-Limit and Remaining; 429 adds Retry-After.Reference
- How often should I poll a run?Every 2 seconds or more. Faster polling eats your per-key rate limit; streaming avoids polling entirely.FAQ
- I get 413 too_large. Which limit did I hit?input over 20,000 characters, metadata over 2 KB or a body over 64 KB answers 413 too_large. Check each.Troubleshooting
- I get 429 too_many_runs. What does it mean?Your account already has 5 runs queued or running. Wait for one to finish or cancel one, then start the next.Troubleshooting
- My run stopped before finishing a big task. Did it hit the step limit?Runs take up to 150 steps. Split very large jobs into smaller runs that continue from a Cloud Repo.Troubleshooting
- What are the Agent API's limits?Every Agent API limit in one table: input, metadata, body size, steps, runs in progress, stream length, rate limits and keys.Reference
- Why can I only run 5 runs at once?The limit of 5 runs queued or running per account keeps the service fair and costs predictable. Queue the rest in your code.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.