Using PixVerse V6 Transition (First/Last Frame) in your workflow

Sorceress brings Pixverse 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 4 credits per second 360p without generate audio switch, 5.6 540p without generate audio switch, 5.6 360p with generate audio switch, 7.2 720p without generate audio switch, 7.2 540p with generate audio switch, 9.6 720p with generate audio switch, and 2 more; that reference is not a Sorceress quote. This entry cannot currently be invoked through Sorceress.

Inputs and supported options

{
  "type": "object",
  "required": [
    "prompt",
    "first_frame_image_url",
    "last_frame_image_url",
    "duration",
    "quality"
  ],
  "properties": {
    "seed": {
      "type": "integer",
      "title": "Seed",
      "maximum": 2147483647,
      "minimum": 0,
      "description": "Random seed, value range is 0–2147483647. Using the same parameters and seed helps improve result reproducibility."
    },
    "prompt": {
      "type": "string",
      "title": "Prompt",
      "maxLength": 5000,
      "minLength": 3,
      "description": "Generate prompt, cannot be empty, length is limited to 3-5000 characters."
    },
    "quality": {
      "enum": [
        "360p",
        "540p",
        "720p",
        "1080p"
      ],
      "type": "string",
      "title": "Quality",
      "description": "Required. Output video resolution. Supports 360p, 540p, 720p, and 1080p."
    },
    "duration": {
      "type": "integer",
      "title": "Duration",
      "maximum": 15,
      "minimum": 1,
      "description": "Required. Output video duration in seconds. PixVerse V6 supports 1–15 seconds."
    },
    "last_frame_image_url": {
      "type": "string",
      "title": "Last frame image URL",
      "format": "uri",
      "x-media": "image",
      "description": "Last frame image URL. Supports HTTP, HTTPS, and OSS addresses; supported image formats include JPG, JPEG, PNG, and WebP; the size of a single image file must not exceed 20 MB"
    },
    "first_frame_image_url": {
      "type": "string",
      "title": "First frame image URL",
      "format": "uri",
      "x-media": "image",
      "description": "First frame image URL. Supports HTTP, HTTPS, and OSS addresses; supported image formats include JPG, JPEG, PNG, and WebP; the size of a single image file must not exceed 20 MB"
    },
    "generate_audio_switch": {
      "type": "boolean",
      "title": "Generate audio switch",
      "default": false,
      "description": "Whether to generate audio synchronized with the video content."
    }
  }
}

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.