Skip to main content
Rate limits depend on the account, subscription, and selected model. View the limits assigned to your account in Higgsfield Cloud. The primary generation limit is concurrency: the number of requests that may be queued or processing at the same time. Some models can also have model-specific limits.

​
When concurrency is reached

The API currently returns 400 Bad Request with a message similar to:
Wait for an existing request to reach a terminal status before submitting more work.

​
Client recommendations

  • Limit generation submissions with a worker pool or semaphore.
  • Track each accepted request_id until it becomes terminal.
  • Use backoff and jitter instead of retrying in a tight loop.
  • Keep polling traffic separate from generation submission concurrency.
  • Contact support before a planned traffic increase if you need higher limits.
The API does not currently publish standard rate-limit response headers or Retry-After. Treat the limits shown in your dashboard as the authoritative values for your account.