Rate limits

Generation Rate Limit

We have a concurrency limit, which restricts the number of tasks that can be executed simultaneously.

Task Scope	Limit
text_to_model, image_to_model, multiview_to_model with model_version = P1-20260311	5
text_to_model, image_to_model, multiview_to_model with other model versions	10
refine_model	5
animate_model	10
animate_prerigcheck	10
animate_rig	10
animate_retarget	10
generate_multiview_image	1
edit_multiview_image	1
Other task types	10

Limits are calculated by concurrency group, not by each raw task type. For example, text_to_model and image_to_model with non-P1-20260311 model versions share the same concurrency bucket.

If you exceed the threshold, the API will return the error below.

{
  "code": 2000,
  "message": "You have exceeded the limit of generation",
  "suggestion": "Try again later. You can also check `Retry-After` header."
}

We recommend implementing an exponential backoff strategy in your code to handle these responses gracefully.

Upload Rate Limit

For uploading images, we offer a 10 qps limitation.