# Wan 3.0 - Core.Today AI API

> 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**: Alibaba
- **Model ID**: alibaba/wan-3
- **Category**: Video Generation
- **Credits**: 2330 per 5s 1080p video — billed per second (480p 116/s, 720p 233/s, 1080p 465/s)
- **Speed**: Medium
- **Quality**: High

## Features
- Text-to-video and image-to-video in one model
- Long clips — 2 to 30 seconds in a single generation
- Three resolutions: 480p, 720p, 1080p
- Adaptive aspect ratio — the model picks the best framing, or set one of five ratios explicitly
- Automatic prompt expansion for short prompts, seed support for reproducibility

## Use Cases
- Long-form (up to 30s) narrative clips without stitching
- Animating a first-frame image into a guided video
- Cost-efficient 480p drafts before a 1080p final render
- Vertical (9:16) short-form content for social media
- Cinematic b-roll from a text description

## API Endpoint

Base URL: https://api.core.today/v1
Create Prediction: POST /predictions
Get Status: GET /predictions/{job_id}

## Authentication
Header: X-API-Key: YOUR_API_KEY

## Input Parameters

### Required
- **prompt**: string - Text prompt for video generation

### Optional
- **image**: string - Optional first-frame image to animate (jpg/png/bmp/webp, ≤10MB). When provided, the video is generated from this image guided by the prompt
- **resolution**: string (default: 1080p) - Output resolution. 480p bills 116 credits/sec, 720p 233/sec, 1080p 465/sec
  Options: 480p, 720p, 1080p
- **aspect_ratio**: string (default: adaptive) - 'adaptive' lets the model choose the best ratio for the prompt. Ignored when an image is provided (the image's ratio is used)
  Options: adaptive, 16:9, 9:16, 1:1, 4:3, 3:4
- **duration**: integer (default: 5) - Video duration in seconds (2-30). Billed per second of output
- **negative_prompt**: string - Content that should not appear in the video
- **enable_prompt_expansion**: boolean (default: true) - Automatically expand and optimize the prompt. Improves quality for short prompts but increases latency
- **seed**: integer - Random seed for reproducible generation (0-2147483647)

## Examples

### Cinematic Text-to-Video
Generate a stylized video from a text prompt alone
```json
{
  "model": "alibaba/wan-3",
  "input": {
    "prompt": "a turtle swimming through a library, 35mm film",
    "duration": 5,
    "resolution": "1080p",
    "aspect_ratio": "adaptive"
  }
}
```

### Image-to-Video Animation
Animate a first-frame image guided by the prompt
```json
{
  "model": "alibaba/wan-3",
  "input": {
    "prompt": "The camera slowly pulls back as gentle snow begins to fall",
    "image": "https://example.com/first-frame.jpg",
    "duration": 8,
    "resolution": "720p"
  }
}
```

## Response Format
```json
{
  "job_id": "abc123",
  "status": "pending | processing | completed | failed",
  "result": "URL or data (when completed)"
}
```

## Usage Flow
1. POST /predictions with model and input -> receive job_id
2. GET /predictions/{job_id} -> poll until status is completed or failed
3. Result contains output URL(s)

## Tips
- Billing is per second of output — a 30s clip costs 6x a 5s one, so draft short and extend only when the motion works
- Iterate at 480p (a quarter of the 1080p rate), then re-render the final at 1080p
- Leave aspect_ratio on 'adaptive' for text-to-video unless you need a fixed frame; it is ignored with an input image anyway
- enable_prompt_expansion helps short prompts but adds latency — turn it off for long, detailed prompts you have already refined
- Use the seed parameter to reproduce a result while tweaking the prompt

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