Sign in
generations

Poll a generation

Changed on

Retrieves the current status of an asynchronous generation, and its results once complete. Use the generation_id returned by any /v2 endpoint that runs asynchronously: every video and tool endpoint, and any image endpoint called with async or a webhook_url.

While the generation is pending or has failed, the response contains only generation_id, status, and created (plus failure_reason once failed). Once status is completed, the response includes response_type and data. Each data item carries an object_type that identifies its shape, so image and video results can be told apart. usage_cost_usd_micros reports the amount billed when the request uses variable usage-based pricing.

Polling is rate limited per organization; a 429 response carries a Retry-After header with the number of seconds to wait.

get/v2/generations/{generation_id}

Request

  • Base URL: (relative, and it does not resolve against the document’s source URL)
  • URL: /v2/generations/{generation_id}
  • Auth: one of:
    • API key in header Api-Key
    • HTTP bearer

Path parameters

generation_idstring required

URL-safe base64 ID of the generation, as returned when the request was accepted.

Response

Generation status retrieved successfully.

generation_idstring required

URL-safe base64 ID of the generation.

status'pending' | 'completed' | 'failed' required

Current status of the generation. pending: still in progress; the response contains only generation_id, status, and created. completed: finished successfully; the response includes response_type and data, and may include usage_cost_usd_micros when the request uses variable usage-based pricing. failed: generation did not succeed; the response contains only generation_id, status, and created.

createdstring date-time required

The time the generation was created.

response_type'url'

Present when status is completed; always "url" for this shape.

usage_cost_usd_microsinteger

The total variable usage-based cost charged for the completed request, in millionths of a US dollar. Present only when status is completed and the request uses variable usage-based pricing; omitted otherwise.

failure_reasonstring

A short machine-readable reason the generation failed, for example content_policy_violation. Present only when status is failed.

Example response

{
  "generation_id": "bzue-VZtSlSMAneIbfCo2A",
  "status": "completed",
  "created": "2000-01-23T04:56:07+00:00",
  "response_type": "url",
  "data": [
    {
      "prompt": "prompt",
      "resolution": "2048x2048",
      "seed": 12345,
      "is_image_safe": true,
      "url": "https://ideogram.ai/api/images/ephemeral/xtdZiqPwRxqY1Y7NExFmzB.png?exp=1743867804&sig=e13e12677633f646d8531a153d20e2d3698dca9ee7661ee5ba4f3b64e7ec3f89"
    }
  ]
}

Changes

  • 604baa9fe41cRevision changes
    • ○

      added the optional property /// to the response with the status

  • 919a744eb885Revision changes
    • ▲

      added to the / response property oneOf list for the response status

    • ○

      added layerized_design.generation discriminator mapping keys to the / response property for the response status