Rate Limits
Rate limits are enforced at the account level and vary by plan. Limits apply to both requests per minute (RPM) and tokens per minute (TPM).
Plan | Requests / min | Tokens / min |
Free | 10 | 40,000 |
Pro | 100 | 400,000 |
Enterprise | Custom | Custom |
How limits are enforced
When you exceed a rate limit, the API returns a 429 Too Many Requests response. The response headers include Retry-After, which tells you how many seconds to wait before retrying.
Handling rate limit errors
We recommend implementing exponential backoff in your request logic. Most official Crucible SDKs handle this automatically. If you're making raw HTTP requests, build in a retry loop that respects the Retry-After header.
Increasing limits
Pro plan limits are sufficient for most production workloads. If your application requires higher throughput, contact us at limits@crucible.dev to discuss an Enterprise plan with custom rate limits and SLA guarantees.