Using Wan 2.6 Text To Video in your workflow

Sorceress brings Wan 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 70 credits per video 5 720p, 105 5 1080p, 140 10 720p, 210 10 1080p, 210 15 720p, 315 15 1080p; that reference is not a Sorceress quote. This entry cannot currently be invoked through Sorceress.

Inputs and supported options

{
  "type": "object",
  "required": [
    "prompt"
  ],
  "properties": {
    "prompt": {
      "type": "string",
      "title": "Prompt",
      "maxLength": 5000,
      "description": "Text prompts for video generation. Supports both Chinese and English, with a minimum of 1 characters and a maximum of 5,000 characters. (Max length: 5000 characters)"
    },
    "duration": {
      "enum": [
        "5",
        "10",
        "15"
      ],
      "type": "string",
      "title": "Duration",
      "default": "5",
      "description": "The duration of the generated video in seconds"
    },
    "resolution": {
      "enum": [
        "720p",
        "1080p"
      ],
      "type": "string",
      "title": "Resolution",
      "description": "Output resolution: 720p or 1080p. Set this field explicitly."
    },
    "multi_shots": {
      "type": "boolean",
      "title": "Multi shots",
      "default": false,
      "description": "The multi shots parameter controls the shot composition style during AI video generation, determining whether the generated video is a single continuous shot or multiple shots with transitions."
    },
    "nsfw_checker": {
      "type": "boolean",
      "title": "NSFW checker",
      "description": "Defaults to false. When false, no additional content filtering is applied and results are returned directly by the model."
    }
  }
}

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.