Using Veo Extend in your workflow

Sorceress brings Google models into a shared API catalog. Select this model explicitly, check its supported inputs, and keep your API key on your server. Model capabilities differ; the schema and options on this page describe this entry rather than every model from the same brand.

Explore motion and scene concepts.
Automate video generation with a saved job that your application can track.

Pricing and availability

Sorceress pricing is awaiting activation. The reference catalog lists 30 credits per video lite, 60 fast, 250 quality; that reference is not a Sorceress quote. This entry cannot currently be invoked through Sorceress.

Inputs and supported options

{
  "type": "object",
  "required": [
    "task_id",
    "prompt"
  ],
  "properties": {
    "model": {
      "enum": [
        "fast",
        "quality",
        "lite"
      ],
      "type": "string",
      "title": "Model",
      "default": "fast",
      "description": "Extension tier: \"fast\" (default), \"quality\" or \"lite\". Billed per extension at the chosen tier."
    },
    "seeds": {
      "type": "integer",
      "title": "Seeds",
      "maximum": 99999,
      "minimum": 10000,
      "description": "A random seed parameter that controls the randomness of the generated content. Range: 10000-99999. The same seed will generate similar video content, while different seeds will generate different video content. If not specified, the system will automatically assign a random seed."
    },
    "prompt": {
      "type": "string",
      "title": "Prompt",
      "description": "A text prompt describing the content of the extended video. It should detail how you want the video to be extended, including actions, scene changes, styles, etc."
    },
    "task_id": {
      "type": "string",
      "title": "Task ID",
      "description": "The task ID of the original video generation. Must be a valid task ID returned by the video generation API."
    },
    "watermark": {
      "type": "string",
      "title": "Watermark",
      "description": "Watermark text (optional). If provided, a watermark will be added to the generated video."
    }
  }
}

Completion, results and billing

Save the job identifier returned by asynchronous requests and poll the jobs endpoint until the job succeeds or fails. Do not resubmit a generation just because it is still processing. Chat returns a completed reply and usage details. A multi-step workflow can include separately billed successful steps even if a later step fails. Keep returned asset links with your project, and consult each action for its output format.

Coding agents can discover the current catalog and input requirements from the Sorceress agent instructions. Use a Sorceress key; provider credentials stay on the server.