Skip to main content

​
Generation Rate Limits

Rate limits for model inference requests are based on your account tier:

​
Deployed Model Rate Limits

Models you deploy on the platform have a rate limit of 300 RPM per instance. If you need higher throughput, scale up the number of instances — total RPM equals the number of instances multiplied by 300.

​
Batch API Rate Limits

  • Batch file upload: 1 per minute
  • Batch processing rate limits are separate from generation rate limits. See the Batch API docs for details.

​
General API Rate Limits

The Catalyst gateway enforces a general rate limit of 100 requests per second per API key or IP address. This applies across all endpoints.

​
Increasing Your Limits

If you need higher rate limits, contact us or use the support chat to request a custom tier.