> ## Documentation Index
> Fetch the complete documentation index at: https://docs.varg.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Wan 2.5

> Budget-friendly video generation with strong character motion and audio support

## Overview

Wan 2.5 (by Alibaba) is a cost-effective video model with good motion quality, especially for character animation. It supports text-to-video, image-to-video, and optional audio input.

| Model ID          | Quality  | Credits | \~Cost |
| ----------------- | -------- | ------- | ------ |
| `wan-2.5`         | Standard | 80      | \$0.80 |
| `wan-2.5-preview` | Preview  | 60      | \$0.60 |

## Quick start

<CodeGroup>
  ```typescript SDK theme={null}
  import { createVarg } from "vargai/ai"

  const varg = createVarg({ apiKey: process.env.VARG_API_KEY! })

  const result = await varg.videoModel("wan-2.5").generate({
    prompt: "a cartoon character dancing energetically in a colorful studio",
    duration: 5,
    aspectRatio: "16:9",
  })

  console.log(result.video.url)
  ```

  ```bash cURL theme={null}
  curl -X POST https://api.varg.ai/v1/video \
    -H "Authorization: Bearer $VARG_API_KEY" \
    -H "Content-Type: application/json" \
    -d '{
      "model": "wan-2.5",
      "prompt": "a cartoon character dancing energetically in a colorful studio",
      "duration": 5,
      "aspect_ratio": "16:9"
    }'
  ```
</CodeGroup>

## Capabilities

### Text-to-video

```typescript theme={null}
const result = await varg.videoModel("wan-2.5").generate({
  prompt: "a woman walking through a busy market, vibrant colors, cinematic",
  duration: 8,
})
```

### Image-to-video

```bash cURL theme={null}
curl -X POST https://api.varg.ai/v1/video \
  -H "Authorization: Bearer $VARG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "wan-2.5",
    "prompt": "the character starts walking forward slowly",
    "duration": 5,
    "files": [{ "url": "https://example.com/character.jpg" }]
  }'
```

## Parameters

<ResponseField name="prompt" type="string" required>
  Text description of the video to generate.
</ResponseField>

<ResponseField name="duration" type="string" default="5">
  Video duration in seconds. Range: 3-10 seconds.
</ResponseField>

<ResponseField name="aspect_ratio" type="string" default="16:9">
  Output aspect ratio.
</ResponseField>

<ResponseField name="files" type="array">
  Array of `{ url: string }` objects for image-to-video.
</ResponseField>

<ResponseField name="provider_options" type="object">
  Pass-through options. Supports `resolution` (default `"480p"`), `negative_prompt`, and `audio_url` for audio-driven generation.
</ResponseField>

## Pricing

| Model             | Credits | USD    |
| ----------------- | ------- | ------ |
| `wan-2.5`         | 80      | \$0.80 |
| `wan-2.5-preview` | 60      | \$0.60 |

One of the most affordable video models available.

## Tips

* **Best value for character animation.** Wan handles human and cartoon motion well at a fraction of Kling/Seedance cost.
* **Preview variant** is good for quick iteration at even lower cost.
* **Combine with Soul** for consistent character generation — use Soul to create the character image, then Wan to animate.
* **Audio input** can drive motion — provide an `audio_url` in provider options for music-driven animation.

## Related models

<CardGroup cols={2}>
  <Card title="Kling V3" icon="film" href="/models/video/kling-v3">
    Higher quality, more expensive. Best for hero content.
  </Card>

  <Card title="Minimax" icon="minimize" href="/models/video/minimax">
    Similar price point, different motion characteristics.
  </Card>

  <Card title="LTX" icon="bolt" href="/models/video/ltx">
    Even cheaper at 50 credits. Fastest generation.
  </Card>
</CardGroup>