> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.empiriolabs.ai/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.empiriolabs.ai/_mcp/server.

# Wan 2.6

> Multimodal video generation model for cinematic, multi-shot stories with native audio-visual sync (lip-sync, dialogue, music, SFX).

![Wan 2.6](https://media.empiriolabs.ai/model-logos/wan.png)

[Alibaba Cloud](/providers/alibaba) · Video Generation

`POST /v1/videos/generations`

Multimodal video generation model for cinematic, multi-shot stories with native audio-visual sync (lip-sync, dialogue, music, SFX).

## At a glance

| Field               | Value                                         |
| ------------------- | --------------------------------------------- |
| Model id            | `wan-2-6`                                     |
| Model release date  | 2026-01-12                                    |
| Input modalities    | Text, Image, Video, Audio                     |
| Output modalities   | Video                                         |
| Context window      | -                                             |
| Weight precision    | -                                             |
| Region              | Singapore                                     |
| Features            | audio_sync, character_consistency, multi_shot |
| Native inference    | No                                            |
| New                 | No                                            |
| Supported endpoints | `POST /v1/videos/generations`                 |
| Alternate model ids | `alibaba/wan-2.6`, `wan-2.6`                  |

## Pricing

| Charge                 | Spec       | Rate      |
| ---------------------- | ---------- | --------- |
| Standard 720P          | per second | \$0.10    |
| Standard 1080P         | per second | \$0.15    |
| Flash 720P (audio)     | per second | \$0.050   |
| Flash 720P (no audio)  | per second | \$0.0250  |
| Flash 1080P (audio)    | per second | \$0.0750  |
| Flash 1080P (no audio) | per second | \$0.03750 |

## Example request

```bash
curl https://api.empiriolabs.ai/v1/videos/generations \
  -H 'Authorization: Bearer $EMPIRIOLABS_API_KEY' \
  -H 'Content-Type: application/json' \
  -d '{"model": "wan-2-6", "prompt": "sunrise over the ocean", "duration": 6}'
```

## Parameters

| Parameter         | Type    | Required | Default   | Description                                                                                                                                                                                      |
| ----------------- | ------- | -------- | --------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
| `prompt`          | string  | yes      | -         | Scene description.                                                                                                                                                                               |
| `mode`            | enum    | no       | `"auto"`  | auto picks the mode from your attachments. t2v: text-to-video. i2v: animate the attached image. r2v: reference-to-video, generated from reference images. · Allowed: `auto`, `t2v`, `i2v`, `r2v` |
| `resolution`      | enum    | no       | `"1080p"` | Output resolution. Larger = higher fidelity but slower / more expensive. · Allowed: `720p`, `1080p`                                                                                              |
| `duration`        | number  | no       | `5`       | Clip length in seconds: 5, 10 or 15. Reference-to-video is capped at 10. · Range: 5 – 15                                                                                                         |
| `aspect_ratio`    | enum    | no       | `"16:9"`  | Output aspect ratio for text-to-video and reference-to-video. Image-to-video follows the source image. · Allowed: `16:9`, `9:16`, `1:1`, `4:3`, `3:4`                                            |
| `shot_type`       | enum    | no       | `"multi"` | single: one continuous shot. multi: multi-shot narrative. · Allowed: `single`, `multi`                                                                                                           |
| `image`           | string  | no       | -         | Reference image URL. Required for i2v / r2v.                                                                                                                                                     |
| `negative_prompt` | string  | no       | `""`      | What to avoid.                                                                                                                                                                                   |
| `seed`            | number  | no       | -         | Reproducibility seed.                                                                                                                                                                            |
| `audio`           | boolean | no       | true      | Generate native audio with the video, in image-to-video and reference-to-video; text-to-video always has audio. With flash_mode, turning it off lowers the price.                                |
| `flash_mode`      | boolean | no       | false     | Faster generation at reduced cost. Applies to i2v and r2v only.                                                                                                                                  |
| `prompt_extend`   | boolean | no       | true      | Automatically expand and refine the prompt for better results.                                                                                                                                   |

## Notes

Generation can take 5+ minutes. Modes: t2v, i2v (image-to-video), r2v (reference-to-video). Flash Mode (i2v/r2v only), faster generation at reduced cost.

**Image inputs**

* Auto-resized: i2v 360-2000px, r2v 240-5000px
* HEIC/HEIF auto-converted

**Reference videos**

* MP4 or MOV
* 1-30s
* Max 100 MB
* r2v output capped at 10s

**Optional audio (t2v / i2v only)**

* 3-30s, max 15 MB, .mp3 or .wav
* Silently ignored in r2v (audio is extracted from the reference video instead)

**Uploaded media preprocessing**

* Reference and edit videos are normalized to provider-compatible MP4 when needed.
* Reference-video duration follows the mode limits shown above.

---

*Machine-readable schema:* `GET https://api.empiriolabs.ai/v1/models/wan-2-6`.