Using Wan 2.5 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 60 credits per video 5 720p, 100 5 1080p, 120 10 720p, 200 10 1080p; that reference is not a Sorceress quote. This entry cannot currently be invoked through Sorceress.

Inputs and supported options

{
  "type": "object",
  "required": [
    "prompt",
    "duration",
    "resolution"
  ],
  "properties": {
    "seed": {
      "type": "integer",
      "title": "Seed",
      "description": "Random seed for reproducibility. If omitted, a random seed is chosen."
    },
    "prompt": {
      "type": "string",
      "title": "Prompt",
      "maxLength": 800,
      "description": "The text prompt for video generation. Supports Chinese and English. Maximum length: 800 characters."
    },
    "duration": {
      "enum": [
        "5",
        "10"
      ],
      "type": "string",
      "title": "Duration",
      "description": "The duration of the generated video in seconds. `5`: 5 seconds `10`: 10 seconds"
    },
    "resolution": {
      "enum": [
        "720p",
        "1080p"
      ],
      "type": "string",
      "title": "Resolution",
      "description": "Required. 720p or 1080p."
    },
    "aspect_ratio": {
      "enum": [
        "16:9",
        "9:16",
        "1:1"
      ],
      "type": "string",
      "title": "Aspect ratio",
      "description": "The aspect ratio of the generated video. `16:9`: Landscape `9:16`: Portrait `1:1`: Square"
    },
    "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."
    },
    "negative_prompt": {
      "type": "string",
      "title": "Negative prompt",
      "maxLength": 500,
      "description": "Negative prompt used to describe content to avoid. Maximum length: 500 characters."
    },
    "enable_prompt_expansion": {
      "type": "boolean",
      "title": "Enable prompt expansion",
      "description": "Whether to enable prompt rewriting using LLM. Improves results for short prompts but increases processing time. Boolean value: `true` / `false`"
    }
  }
}

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.