Using Kling 2.1 Pro in your workflow

Sorceress brings Kling 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 50 credits per video 5, 100 10; that reference is not a Sorceress quote. This entry cannot currently be invoked through Sorceress.

Inputs and supported options

{
  "type": "object",
  "required": [
    "prompt",
    "image_url",
    "duration"
  ],
  "properties": {
    "prompt": {
      "type": "string",
      "title": "Prompt",
      "maxLength": 5000,
      "description": "Text prompt describing the video to generate (Max length: 5000 characters)"
    },
    "duration": {
      "enum": [
        "5",
        "10"
      ],
      "type": "string",
      "title": "Duration",
      "description": "Required. \"5\" or \"10\" (seconds)."
    },
    "cfg_scale": {
      "type": "number",
      "title": "CFG scale",
      "default": 0.5,
      "maximum": 1,
      "minimum": 0,
      "description": "The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt (Min: 0, Max: 1, Step: 0.1) (step: 0.1)"
    },
    "image_url": {
      "type": "string",
      "title": "Image URL",
      "format": "uri",
      "x-media": "image",
      "description": "URL of the image to be used for the video (Accepted types: image/jpeg, image/png; Max size: 10.0MB)"
    },
    "tail_image_url": {
      "type": "string",
      "title": "Tail image URL",
      "format": "uri",
      "x-media": "image",
      "description": "URL of the image to be used for the end of the video (Accepted types: image/jpeg, image/png; Max size: 10.0MB)"
    },
    "negative_prompt": {
      "type": "string",
      "title": "Negative prompt",
      "maxLength": 500,
      "description": "Terms to avoid in the generated video (Max length: 500 characters)"
    }
  }
}

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.