Wan 3.0 API

Complete API reference for Wan 3.0 video generation models by Alibaba.

Model Variants

This API supports four model variants:

Quick Comparison

Shared Endpoint

All Wan 3.0 variants use the video task endpoint:

POST /api/v1/video/task

Shared Parameters

Required

Optional

Wan 3.0 Text to Video

Set model_name to "wan-3.0-text-to-video" and provide the shared required parameters.

Example Request

javascriptCopy
const response = await fetch('https://api.flaq.ai/api/v1/video/task', {
  method: 'POST',
  headers: {
    'Authorization': 'Bearer YOUR_API_KEY',
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
    model_name: 'wan-3.0-text-to-video',
    prompt: 'A cinematic tracking shot follows a cyclist through a rain-soaked neon city at night',
    duration: 8,
    resolution: '1080p',
    aspect_ratio: '16:9',
    sound: true,
    seed: 42
  })
});

const { data } = await response.json();
const taskId = data.task_id;

Wan 3.0 Image to Video

Required Image Inputs

Both images must use JPEG, JPG, PNG without an alpha channel, BMP, or WEBP. Each image side must be from 240 to 8000 pixels.

Example Request

javascriptCopy
{
  model_name: 'wan-3.0-image-to-video',
  prompt: 'The camera glides forward as daylight gradually shifts into a warm evening glow',
  image_url: 'https://example.com/start-frame.jpg',
  image_end_url: 'https://example.com/end-frame.jpg',
  duration: 8,
  resolution: '1080p',
  aspect_ratio: '16:9',
  sound: true,
  seed: 42
}

Wan 3.0 Video Edit

Required Video Input

The source video duration plus the requested output duration must not exceed 30 seconds.

Example Request

javascriptCopy
{
  model_name: 'wan-3.0-video-edit',
  prompt: 'Turn the daytime scene into a rainy evening while preserving the subject and camera movement',
  video_url: 'https://example.com/source-video.mp4',
  duration: 10,
  resolution: '1080p',
  aspect_ratio: '16:9',
  sound: true,
  seed: 42
}

Wan 3.0 Reference to Video

Reference inputs are optional and may be combined, except files and links, which cannot be submitted together.

Optional Reference Inputs

Example Request

javascriptCopy
{
  model_name: 'wan-3.0-reference-to-video',
  prompt: 'Use the references to create a cinematic product launch with coordinated motion and sound',
  duration: 12,
  resolution: '1080p',
  aspect_ratio: '16:9',
  sound: true,
  images: ['https://example.com/product-reference.jpg'],
  videos: ['https://example.com/motion-reference.mp4'],
  audios: ['https://example.com/sound-reference.mp3'],
  links: ['https://example.com/public-creative-brief'],
  seed: 42
}

To use a reference file instead of a webpage, omit links and pass a single URL in files.

Response Format

Initial Response

All models return a task_id for polling:

jsonCopy
{
  "code": 0,
  "message": "success",
  "data": {
    "task_id": "{task_id}",
    "response_url": "https://api.flaq.ai/api/v1/video/{task_id}",
    "task_status": "submitted"
  }
}

Polling Response

Poll GET /api/v1/video/{taskId} to check status:

jsonCopy
{
  "code": 0,
  "message": "success",
  "data": {
    "task_id": "{task_id}",
    "response_url": "https://api.flaq.ai/api/v1/video/{task_id}",
    "task_status": "succeed",
    "task_status_msg": null,
    "task_result": {
      "videos": [
        {
          "url": "https://example.com/generated-video.mp4"
        }
      ]
    }
  }
}

Status Values

• submitted: Task accepted and waiting to be processed
• processing: Video generation in progress
• succeed: Video generation completed
• failed: Video generation failed

Best Practices

1. Prompt Direction: Describe subjects, actions, camera movement, pacing, environment, and sound intent clearly.
2. Image Inputs: Use start, end, and reference images that match the requested aspect ratio. PNG images must not contain an alpha channel.
3. Video Edit Timing: Check the source duration before choosing the requested output duration so their total remains within 30 seconds.
4. Reference Limits: Validate the count, format, dimensions, and combined duration of every reference collection before submission.
5. Files and Links: Submit either one reference file or one public webpage link, never both in the same request.