Predictions

Get prediction status

Check the status of a prediction request. This is the second step in the asynchronous workflow.

When the prediction is completed successfully, the response will include download URLs for the generated content (images or videos).

Rate limit: 30,000 requests per minute.

get/v1/predictions/status/{id}

Request

  • Base URL: https://api.pruna.ai
  • URL: https://api.pruna.ai/v1/predictions/status/{id}
  • Auth: API key in header apikey

Path parameters

idstring required
Example:1knpbkf075rme0csjqr987hg4w

The prediction ID returned from the initial request

Response

Prediction status retrieved successfully

status'starting' | 'processing' | 'succeeded' | 'failed' | 'canceled' required

Current status of the prediction

generation_urlstring

URL to download the generated content (available when status is 'succeeded')

metadataobject

Model-defined metadata from the prediction (always present when status is 'succeeded'; empty object when the model emitted none)

messagestring

Status message

errorstring

Error details (available when status is 'failed')

Example response

{
  "status": "processing",
  "generation_url": "https://api.pruna.ai/v1/predictions/delivery/xezq/52UGYRrRfqViaKmvYsEnENTh0qLDAWHptQ8jOnEHu7XC6AtKA/output.mp4",
  "metadata": {
    "seed": 42
  },
  "message": "Generation in progress",
  "error": "Number of samples, -5, must be non-negative."
}

Changes

No recorded changes to this operation across all 1 revision of this API.