# Wan 3.0

> Alibaba's Wan 3.0 generates video from a text prompt or a starting image, with cinematic motion and support for 480p, 720p, and 1080p output up to 30 seconds.

- **Provider**: replicate
- **Model ID**: alibaba/wan-3
- **Category**: video_generation
- **Credits**: 2330 per request
- **Pricing Type**: input_based

## API Endpoint

Base URL: https://api.core.today/v1

### Create Prediction
POST /predictions

### Get Status
GET /predictions/{job_id}

### Cancel
DELETE /predictions/{job_id}

## Authentication

Header: `X-API-Key: YOUR_API_KEY`

## Input Parameters

- `aspect_ratio` (string, optional): Aspect ratio of the generated video. 'adaptive' lets the model choose the best ratio for the prompt. Ignored when an image is provided (the input image's aspect ratio is used). (Default: `adaptive`; Options: `adaptive`, `16:9`, `9:16`, `1:1`, `4:3`, `3:4`)
- `duration` (integer, optional): Duration of the generated video in seconds (Default: `5`; Range: min: 2, max: 30)
- `image` (string, optional): Optional first-frame image to animate into a video (jpg/png/bmp/webp, ≤10MB). When provided, the video is generated from this image guided by the prompt.
- `resolution` (string, optional): Output video resolution (Default: `1080p`; Options: `480p`, `720p`, `1080p`)
- `negative_prompt` (string, optional): Negative prompt — describes content that should not appear in the video (Default: ``)
- `enable_prompt_expansion` (boolean, optional): Automatically expand and optimize the prompt for better results. Improves quality for short prompts but increases latency. (Default: `True`)
- `seed` (integer, optional): Random seed for reproducible generation. Range: 0-2147483647
- `prompt` (string, **required**): Text prompt for video generation. Up to 20000 characters (Alibaba Wan 3.0). Each Chinese character or letter counts as one; text beyond the limit is silently truncated upstream (not rejected), so the gateway rejects it up front instead.

## Example Request

```json
{
  "model": "alibaba/wan-3",
  "input": {
    "duration": 5,
    "aspect_ratio": "adaptive",
    "prompt": "a turtle swimming through a library, 35mm film",
    "resolution": "1080p"
  }
}
```

## Response Format

```json
{
  "job_id": "abc123",
  "status": "pending",
  "provider": "replicate",
  "model": "black-forest-labs/flux-schnell",
  "created_at": "2026-01-01T00:00:00Z",
  "result": null,
  "error": null
}
```

Status values: `pending`, `processing`, `completed`, `failed`, `cancelled`

## Usage Flow

1. POST /predictions with model and input → receive job_id
2. Poll GET /predictions/{job_id} until status is `completed` or `failed`
3. Result contains output URL(s) or data

## Output Type

url

## Tags

wan, alibaba, video-generation, text-to-video, image-to-video, long-form

## Documentation

https://replicate.com/alibaba/wan-3