# Wan models on AI Gateway

**Published:** February 19, 2026 | **Authors:** Walter Korman , Jeremy Philemon, Matt Lenhard, Sylvie Zhang, Jerilyn Zheng

---

Generate stylized videos and transform existing footage with Alibaba's Wan models, now available through AI Gateway. Try them out now via AI SDK 6 or by selecting the models in the AI Gateway playground.

Wan produces artistic videos with smooth motion and can use existing content to keep videos consistent:

- **Character Reference (R2V)**: Extract character appearance and voice from reference videos/images to generate new scenes
- **Flash Variants**: Faster generation times for quick iterations
- **Flexible Resolutions**: Support for 480p, 720p, and 1080p output

[Video: wan sample reel](//videos.ctfassets.net/e5382hct74si/4ipvthIIQ4ziT2NV5fmqSe/4b189183ebfe82790741f4516fea0cde/wan-sample-reel.mov)

## Two ways to get started

Video generation is in beta and currently available for Pro and Enterprise plans and paid AI Gateway users.

- **AI SDK 6**: Generate videos programmatically AI SDK 6's `generateVideo`.

```tsx
import { experimental_generateVideo as generateVideo } from 'ai';
const { videos } = await generateVideo({
  model: 'alibaba/wan-v2.6-t2v',
  prompt: 'Watercolor painting of a koi pond coming to life.',
});
```

- **Gateway Playground**: Experiment with video models with no code in the configurable [AI Gateway playground](https://vercel.com/ai-gateway/models/wan-v2.6-i2v) that's embedded in each model page. Compare providers, tweak prompts, and download results without writing code. To access, click any video gen model in the [model list](https://vercel.com/ai-gateway/models?capabilities=video-generation&providers=alibaba).

## Available Models

| Model | Type | Description |
| `alibaba/wan-v2.6-t2v` | Text-to-Video | Generate videos from text prompts |
| `alibaba/wan-v2.6-i2v` | Image-to-Video | Animate still images |
| `alibaba/wan-v2.6-i2v-flash` | Image-to-Video | Fast image animation |
| `alibaba/wan-v2.6-r2v` | Reference-to-Video | Character transfer from references |
| `alibaba/wan-v2.6-r2v-flash` | Reference-to-Video | Fast style transfer |
| `alibaba/wan-v2.5-t2v-preview` | Text-to-Video | Previous version |

## Simple: Text-to-Video with Audio

Generate a stylized video from a text description.

[Video: simple wan video](//videos.ctfassets.net/e5382hct74si/6C2WsmgeQrjYyhvSgukVen/28510e3b680a2713f16dedc54e13694e/changelog-tokyo-anime.mp4)

You can use detailed prompts and specify styles with the Wan models to achieve the desired output generation. The example here uses `alibaba/wan-v2.6-t2v`:

```tsx
import { experimental_generateVideo as generateVideo } from 'ai';
const { videos } = await generateVideo({
  model: 'alibaba/wan-v2.6-t2v',
  prompt:
   `Animated rainy Tokyo street at night, anime style,
    neon signs reflecting on wet pavement, people with umbrellas
    walking past, red and blue lights glowing through the rain.`,
  resolution: '1280x720',
  duration: 5,
});
```

## Advanced: Reference-to-Video

Generate new scenes using characters extracted from reference images or videos.

[Video: wan advanced example](//videos.ctfassets.net/e5382hct74si/62bWsqr9tfz4CIOj1clvUt/e33f5fa517b9de3d3917fad1da908aab/r2v-dogs-beach-muted.mp4)

In this example, 2 reference images of dogs are used to generate the final video.

![Group 3: shiba and yorkie](//images.ctfassets.net/e5382hct74si/KRBJC9VA8ygsEE7ynxTLv/40cb7dff7b10c285159c9daef98e0081/Group_3.png)

Using `alibaba/wan-v2.6-r2v-flash` here, you can instruct the model to utilize the people/characters within the prompt. Wan suggests using `character1`, `character2`, etc. in the prompt for multi-reference to video to get the best results.

```tsx
import { experimental_generateVideo as generateVideo } from 'ai';
const { videos } = await generateVideo({
  model: 'alibaba/wan-v2.6-r2v-flash',
  prompt:
   `character1 and character2 are playing together on the beach in San Francisco
    with the Golden Gate Bridge in the background, sunny day, waves crashing`,
  resolution: '1280x720',
  duration: 5,
  providerOptions: {
    alibaba: {
      referenceUrls: [shibaImage, yorkieImage],
    },
  },
});
```

## Learn More

For more examples and detailed configuration options for Wan models, check out the [Video Generation Documentation](https://vercel.com/docs/ai-gateway/capabilities/video-generation). You can also find simple getting started scripts with the [Video Generation Quick Start](https://vercel.com/docs/ai-gateway/getting-started/video).

---

📚 **More updates:** [View all changelog entries](/changelog/sitemap.md) | [Blog](/blog/sitemap.md)