---
title: Wan2.5-Preview | Runware Docs
url: https://runware.ai/docs/models/alibaba-wan2-5-preview
description: Wan2.5-Preview AI Text to Video with Native Audio
---
# Wan2.5-Preview

![Wan2.5-Preview](https://assets.runware.ai/covers/alibaba-wan2-5-preview.jpg)

Wan2.5-Preview is Alibaba’s multimodal video model in research preview. It supports text to video and image to video with native audio generation for clips around 10 seconds. It offers strong prompt adherence, smooth motion, and multilingual audio for narrative scenes.

- **Status**: live
- **ID**: `runware:201@1`
- Try in Playground
- **Creator**: Alibaba
- **Release Date**: September 28, 2025
- **Capabilities**: Text to Video, Image to Video, Audio to Video, Checkpoint, Audio

## Pricing

$0.0946 from, per second · ~1m 59s per request

**Rates** (per second)

- 720p: `$0.0946`
- 1080p: `$0.148`

**4 example generations**

- [text-to-video](https://runware.ai/docs/models/alibaba-wan2-5-preview/examples#example-harbor-pilot-safety-bulletin) · 720p · 5s · audio: `$0.454` (~1m 49s)
- [audio-driven](https://runware.ai/docs/models/alibaba-wan2-5-preview/examples#example-couture-apiary-protective-suit-reel) · 832×1088 · 5s: `$0.454` (~2m 8s)
- [text-to-video](https://runware.ai/docs/models/alibaba-wan2-5-preview/examples#example-florist-shears-social-video-ad) · 720p · 5s · audio: `$0.454` (~1m 49s)
- [first-frame](https://runware.ai/docs/models/alibaba-wan2-5-preview/examples#example-fossil-preparation-tour-reel) · 1080p · 10s · audio: `$1.36` (~3m 9s)

times vary, measured end to end · [How pricing works](https://runware.ai/docs/models-api/pricing)

## Compatibility & Validation

Either provide `inputs.frameImages`, or specify `width/height`.

---

`inputs.audio` cannot be used with `providerSettings.alibaba.audio`.

---

`resolution` cannot be used with `width/height`.

---

When `resolution` is provided, `inputs.frameImages` is required.

---

`width` and `height` must be used together.

---

The following dimension combinations are supported:

| Configuration | Dimensions |
| --- | --- |
| `480p (16:9)` | `832x480` |
| `480p (9:16)` | `480x832` |
| `480p (1:1)` | `624x624` |
| `720p (16:9)` | `1280x720` |
| `720p (9:16)` | `720x1280` |
| `720p (1:1)` | `960x960` |
| `720p (17:13)` | `1088x832` |
| `720p (13:17)` | `832x1088` |
| `1080p (16:9)` | `1920x1080` |
| `1080p (9:16)` | `1080x1920` |
| `1080p (1:1)` | `1440x1440` |
| `1080p (17:13)` | `1632x1248` |
| `1080p (13:17)` | `1248x1632` |

## Request Parameters

**API Options**

Platform-level options for task execution and delivery.

### [taskType](https://runware.ai/docs/models/alibaba-wan2-5-preview#request-tasktype)

- **Type**: `string`
- **Required**: true
- **Value**: `videoInference`

Identifier for the type of task being performed.

### [taskUUID](https://runware.ai/docs/models/alibaba-wan2-5-preview#request-taskuuid)

- **Type**: `string`
- **Required**: true
- **Format**: `UUID v4`

UUID v4 identifier for tracking tasks and matching async responses. Must be unique per task.

### [outputType](https://runware.ai/docs/models/alibaba-wan2-5-preview#request-outputtype)

- **Type**: `string`
- **Default**: `URL`

Video output type.

**Allowed values**: `URL`

### [outputFormat](https://runware.ai/docs/models/alibaba-wan2-5-preview#request-outputformat)

- **Type**: `string`
- **Default**: `MP4`

Specifies the file format of the generated output. The available values depend on the task type and the specific model's capabilities.

- \`MP4\`: Widely supported video container (H.264), recommended for general use.
- \`WEBM\`: Optimized for web delivery.
- \`MOV\`: QuickTime format, common in professional workflows (Apple ecosystem).

**Allowed values**: `MP4` `WEBM` `MOV`

### [outputQuality](https://runware.ai/docs/models/alibaba-wan2-5-preview#request-outputquality)

- **Type**: `integer`
- **Min**: `20`
- **Max**: `99`
- **Default**: `95`

Compression quality of the output. Higher values preserve quality but increase file size.

### [webhookURL](https://runware.ai/docs/models/alibaba-wan2-5-preview#request-webhookurl)

- **Type**: `string`
- **Format**: `uri`

Webhook URL that receives JSON responses via HTTP POST when generation tasks complete. For batch requests with multiple results, each completed item triggers a separate webhook call as it becomes available.

**Learn more** (1 resource):

- [Webhooks](https://runware.ai/docs/models-api/webhooks) (platform)

### [deliveryMethod](https://runware.ai/docs/models/alibaba-wan2-5-preview#request-deliverymethod)

- **Type**: `string`
- **Default**: `async`

Determines how the API delivers task results.

**Allowed values**:

- `sync` Returns results directly in the API response. Over HTTP, a task still running after 120 seconds continues as an async task and comes back with status 'processing'. Poll for its results using getResponse.
- `async` Returns an immediate acknowledgment with the task UUID. Poll for results using getResponse.

**Learn more** (1 resource):

- [Task Polling](https://runware.ai/docs/models-api/task-polling) (platform)

### [uploadEndpoint](https://runware.ai/docs/models/alibaba-wan2-5-preview#request-uploadendpoint)

- **Type**: `string`
- **Format**: `uri`

Specifies a URL where the generated content will be automatically uploaded using the HTTP PUT method. The raw binary data of the media file is sent directly as the request body. For secure uploads to cloud storage, use presigned URLs that include temporary authentication credentials.

**Common use cases:**

- **Cloud storage**: Upload directly to S3 buckets, Google Cloud Storage, or Azure Blob Storage using presigned URLs.
- **CDN integration**: Upload to content delivery networks for immediate distribution.

```text
// S3 presigned URL for secure upload
https://your-bucket.s3.amazonaws.com/generated/content.mp4?X-Amz-Signature=abc123&X-Amz-Expires=3600

// Google Cloud Storage presigned URL
https://storage.googleapis.com/your-bucket/content.jpg?X-Goog-Signature=xyz789

// Custom storage endpoint
https://storage.example.com/uploads/generated-image.jpg
```

The content data will be sent as the request body to the specified URL when generation is complete.

### [safety](https://runware.ai/docs/models/alibaba-wan2-5-preview#request-safety)

- **Path**: `safety.checkContent`
- **Type**: `object (2 properties)`

Content safety checking configuration for video generation.

#### [checkContent](https://runware.ai/docs/models/alibaba-wan2-5-preview#request-safety-checkcontent)

- **Path**: `safety.checkContent`
- **Type**: `boolean`

Enable or disable content safety checking. Increases total generation time and adds a small charge on top of the generation cost.

#### [mode](https://runware.ai/docs/models/alibaba-wan2-5-preview#request-safety-mode)

- **Path**: `safety.mode`
- **Type**: `string`
- **Default**: `fast`

Safety checking mode for video generation.

**Allowed values**:

- `fast` Checks key frames.
- `full` Checks all frames.

### [ttl](https://runware.ai/docs/models/alibaba-wan2-5-preview#request-ttl)

- **Type**: `integer`
- **Min**: `60`

Time-to-live (TTL) in seconds for generated content. Only applies when `outputType` is `URL`.

### [includeCost](https://runware.ai/docs/models/alibaba-wan2-5-preview#request-includecost)

- **Type**: `boolean`

Include task cost in the response.

### [numberResults](https://runware.ai/docs/models/alibaba-wan2-5-preview#request-numberresults)

- **Type**: `integer`
- **Min**: `1`
- **Max**: `4`
- **Default**: `1`

Number of results to generate. Each result uses a different seed, producing variations of the same parameters.

**Inputs**

Input resources for the task (images, audio, etc). These must be nested inside the \`inputs\` object.

### [frameImages](https://runware.ai/docs/models/alibaba-wan2-5-preview#request-inputs-frameimages)

- **Path**: `inputs.frameImages`
- **Type**: `array of strings or objects`
- **Min items**: `items: 1`

An array of frame-specific image inputs to guide video generation. Each item can be either a plain image input (UUID, URL, Data URI, or Base64) or an object that pairs an image with a target position in the video.

The `frameImages` parameter allows you to constrain specific frames within the video sequence, ensuring that particular visual content appears at designated points. Position can be specified using `frame` (named positions or frame indices) or `timestamp` (seconds), depending on model support. This is different from `referenceImages`, which provide overall visual guidance without constraining specific timeline positions.

When the `frame` parameter is omitted, automatic distribution rules apply:

- **1 image**: Used as the first frame.

**Examples**:

**Shorthand format:** When you don't need to specify a frame position, you can pass a plain image input directly.

```json
"frameImages": [
  "aac49721-1964-481a-ae78-8a4e29b91402"
]
```

**Object format:** When you need to specify a position, use an object with `image` and either `frame` or `timestamp` (model-dependent).

```json
"frameImages": [
  {
    "image": "aac49721-1964-481a-ae78-8a4e29b91402",
    "frame": "first"
  }
]
```

**Format 1: string[]**:

- **Type**: `string`

Image input (UUID, URL, Data URI, or Base64).

**Format 2: object[]**:

#### [image](https://runware.ai/docs/models/alibaba-wan2-5-preview#request-inputs-frameimages-format-2-image)

- **Path**: `inputs.frameImages.image`
- **Type**: `string`
- **Required**: true

Image input (UUID, URL, Data URI, or Base64).

#### [frame](https://runware.ai/docs/models/alibaba-wan2-5-preview#request-inputs-frameimages-format-2-frame)

- **Path**: `inputs.frameImages.frame`
- **Type**: `object`

Target frame position for the image. This model only supports the first frame.

**Allowed values**:

- `first` First frame of the video.
- `0` Frame index 0 (first frame).

### [audio](https://runware.ai/docs/models/alibaba-wan2-5-preview#request-inputs-audio)

- **Path**: `inputs.audio`
- **Type**: `string`

Audio input (UUID or URL).

**Core Parameters**

Primary parameters that define the task output.

### [model](https://runware.ai/docs/models/alibaba-wan2-5-preview#request-model)

- **Type**: `string`
- **Required**: true
- **Value**: `runware:201@1`

Send `auto` instead of an AIR identifier to have the model router choose the model for this task. The rest of the request is unchanged, every value you send is kept, and only the parameters you leave out are filled in. See [Model Router](https://runware.ai/docs/models-api/model-router).

**Learn more** (3 resources):

- [Text To Image: Model Selection](https://runware.ai/docs/learn/text-to-image#model-selection) (learn)
- [Image Inpainting: Model Specialized Inpainting Models](https://runware.ai/docs/learn/image-inpainting#model-specialized-inpainting-models) (learn)
- [Image Outpainting: Other Critical Parameters](https://runware.ai/docs/learn/image-outpainting#other-critical-parameters) (learn)

### [positivePrompt](https://runware.ai/docs/models/alibaba-wan2-5-preview#request-positiveprompt)

- **Type**: `string`
- **Required**: true
- **Min**: `1`
- **Max**: `2000`

Text prompt describing elements to include in the generated output.

**Learn more** (1 resource):

- [Prompts](https://runware.ai/docs/learn/prompts) (learn)

### [negativePrompt](https://runware.ai/docs/models/alibaba-wan2-5-preview#request-negativeprompt)

- **Type**: `string`
- **Min**: `1`
- **Max**: `500`

Prompt to guide what to exclude from generation. Ignored when guidance is disabled (CFGScale ≤ 1).

**Learn more** (1 resource):

- [Prompts: Negative Prompts](https://runware.ai/docs/learn/prompts#negative-prompts) (learn)

### [width](https://runware.ai/docs/models/alibaba-wan2-5-preview#request-width)

- **Type**: `integer`
- **Required**: conditional — Required when inputs.frameImages is not provided
- **Paired with**: height

Width of the generated media in pixels.

**Learn more** (2 resources):

- [Dimensions](https://runware.ai/docs/learn/dimensions) (learn)
- [Image Outpainting: Dimensions Critical For Outpainting](https://runware.ai/docs/learn/image-outpainting#dimensions-critical-for-outpainting) (learn)

### [height](https://runware.ai/docs/models/alibaba-wan2-5-preview#request-height)

- **Type**: `integer`
- **Required**: conditional — Required when inputs.frameImages is not provided
- **Paired with**: width

Height of the generated media in pixels.

**Learn more** (2 resources):

- [Dimensions](https://runware.ai/docs/learn/dimensions) (learn)
- [Image Outpainting: Dimensions Critical For Outpainting](https://runware.ai/docs/learn/image-outpainting#dimensions-critical-for-outpainting) (learn)

### [resolution](https://runware.ai/docs/models/alibaba-wan2-5-preview#request-resolution)

- **Type**: `string`

Resolution preset for the output. When used with input media, automatically matches the aspect ratio from the input.

**Allowed values**: `480p` `720p` `1080p`

### [duration](https://runware.ai/docs/models/alibaba-wan2-5-preview#request-duration)

- **Type**: `integer`
- **Default**: `5`

Length of the generated video in seconds. The total number of frames produced is determined by duration multiplied by the model's frame rate (fps).

**Allowed values**: `5` `10`

### [seed](https://runware.ai/docs/models/alibaba-wan2-5-preview#request-seed)

- **Type**: `integer`
- **Min**: `0`
- **Max**: `2147483647`

Random seed for reproducible generation. When not provided, a random seed is generated in the unsigned 32-bit range.

**Provider Settings**

Parameters specific to this model provider. These must be nested inside the \`providerSettings.alibaba\` object.

### [audio](https://runware.ai/docs/models/alibaba-wan2-5-preview#request-providersettings-alibaba-audio)

- **Path**: `providerSettings.alibaba.audio`
- **Type**: `boolean`
- **Default**: `true`

Generate native audio aligned with visual content.

### [promptExtend](https://runware.ai/docs/models/alibaba-wan2-5-preview#request-providersettings-alibaba-promptextend)

- **Path**: `providerSettings.alibaba.promptExtend`
- **Type**: `boolean`
- **Default**: `true`

Enable LLM-based prompt rewriting to expand and clarify inputs. Affects reproducibility.

## Response Parameters

### [taskType](https://runware.ai/docs/models/alibaba-wan2-5-preview#response-tasktype)

- **Type**: `string`
- **Required**: true
- **Value**: `videoInference`

Identifier for the type of task this response belongs to.

### [taskUUID](https://runware.ai/docs/models/alibaba-wan2-5-preview#response-taskuuid)

- **Type**: `string`
- **Required**: true
- **Format**: `UUID v4`

UUID v4 identifier echoed from the original request, used to match async responses to their tasks.

### [videoUUID](https://runware.ai/docs/models/alibaba-wan2-5-preview#response-videouuid)

- **Type**: `string`
- **Required**: true
- **Format**: `UUID v4`

UUID of the output video.

### [videoURL](https://runware.ai/docs/models/alibaba-wan2-5-preview#response-videourl)

- **Type**: `string`
- **Format**: `uri`

URL of the output video.

### [videoBase64Data](https://runware.ai/docs/models/alibaba-wan2-5-preview#response-videobase64data)

- **Type**: `string`

Base64-encoded video data.

### [videoDataURI](https://runware.ai/docs/models/alibaba-wan2-5-preview#response-videodatauri)

- **Type**: `string`
- **Format**: `uri`

Data URI of the output video.

### [seed](https://runware.ai/docs/models/alibaba-wan2-5-preview#response-seed)

- **Type**: `integer`

The seed used for generation. If none was provided, shows the randomly generated seed.

### [NSFWContent](https://runware.ai/docs/models/alibaba-wan2-5-preview#response-nsfwcontent)

- **Type**: `boolean`

Flag indicating if NSFW content was detected.

### [cost](https://runware.ai/docs/models/alibaba-wan2-5-preview#response-cost)

- **Type**: `float`

Task cost in USD. Present when `includeCost` is set to `true` in the request.

## Examples

### text-to-video (text-to-video)

[Watch video](https://assets.runware.ai/examples/alibaba-wan2-5-preview/0eef37b1-948b-4bc2-8ea4-67fa7e6a955a.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "64957a3d-45b9-4fcf-ae1d-287258e2f050",
  "model": "runware:201@1",
  "positivePrompt": "A polished five-second talking-head safety bulletin filmed inside the wheelhouse of a working harbor tug at dawn. Chest-up medium close-up of an experienced female harbor pilot in a navy uniform and bright orange flotation vest, facing the camera with calm authority. She speaks clearly with precise synchronized lip movement: “Crosswinds peak at noon—secure deck loads before leaving the inner harbor.” Through rain-speckled windows behind her, steel-blue water heaves, container cranes slide past, and a deckhand briefly crosses the background. One windshield wiper sweeps across the glass as the vessel rolls gently, creating subtle natural body movement and shifting reflections. Cool overcast daylight, warm instrument glow on her face, crisp broadcast-documentary realism, stable landscape composition, shallow depth of field. Native synchronized audio: clear female voice, low diesel-engine vibration, soft rain on glass, one wiper squeak, faint radio chatter, and a distant foghorn. No captions, logos, interface elements, or music.",
  "negativePrompt": "Poor lip sync, slurred speech, distorted face, extra people in foreground, exaggerated camera shake, subtitles, captions, logos, watermarks, interface graphics, background music.",
  "width": 1280,
  "height": 720,
  "duration": 5,
  "providerSettings": {
    "alibaba": {
      "audio": true,
      "promptExtend": true
    }
  }
}
```

---

### text-to-video (text-to-video)

[Watch video](https://assets.runware.ai/examples/alibaba-wan2-5-preview/30171759-6046-4d7d-9050-4d2055e7548f.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "ba2c5273-c0f5-43ef-81de-4ac425272fcb",
  "model": "runware:201@1",
  "positivePrompt": "A polished five-second landscape social media product ad for professional florist shears, styled like a kinetic sports commercial inside a bright commercial flower greenhouse. Bold palette of cobalt-blue shears, vermilion gardening gloves, chartreuse foliage, and golden morning sunlight. Open on an extreme macro side view as the sharp steel blades decisively snip through a thick sunflower stem; tiny fibers separate cleanly and yellow petals shake loose. The camera instantly tracks sideways with a skilled florist making three fast, precise cuts through colorful stems, gathering the flowers into one arm while leaves and petals sweep through the sunbeams in crisp slow motion. Finish on a low, tight hero angle as the shears snap shut beside the fresh bouquet, polished blades catching a clean flare. Photoreal commercial cinematography, energetic camera movement, shallow depth of field, tactile detail, premium tool advertising, natural hand motion, clear product visibility, no lettering or logos. Native synchronized audio: crisp metallic snips timed exactly to every cut, stems cracking softly, leaves rustling, petals brushing the workbench, subtle greenhouse birds and ventilation ambience, no dialogue.",
  "negativePrompt": "Text, captions, logos, watermarks, distorted hands, extra fingers, duplicate tools, warped blades, floating flowers, artificial neon lighting, nighttime, rain, fantasy elements, app interface, camera shake, muddy image, unrelated music",
  "width": 1280,
  "height": 720,
  "duration": 5,
  "providerSettings": {
    "alibaba": {
      "audio": true
    }
  }
}
```

---

### first-frame (first-frame)

[Watch video](https://assets.runware.ai/examples/alibaba-wan2-5-preview/0ae972d2-bac7-448b-9559-491ecef3b970.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "a618e197-a548-476c-815c-9fd372ed577c",
  "model": "runware:201@1",
  "positivePrompt": "The fossil preparator gently lowers the vibrating air scribe to the limestone and begins tracing the ammonite’s curved edge. Fine pale dust lifts into the warm task light while her gloved hand moves with precise, practiced control. The vertical camera makes a slow, steady push toward the specimen, transitioning from the preparator’s concentrated expression to an extreme macro view of stone grains breaking away. Tiny chips scatter across the bench in crisp slow motion. She switches to a soft brush and sweeps the dust aside, revealing the complete ridged ammonite spiral with a subtle mineral shimmer. Finish on the freshly uncovered fossil filling the frame as her brush exits cleanly. Premium museum documentary aesthetic, tactile macro detail, limestone cream and muted teal palette, realistic laboratory lighting, calm sense of discovery. Native audio: delicate air-scribe buzz, granular stone crackle, brush bristles and restrained modern percussion built from tool taps. A warm, articulate female voiceover says exactly: “Watch 180 million years come back into view. Book a behind-the-scenes fossil lab tour this weekend.”",
  "resolution": "1080p",
  "duration": 10,
  "providerSettings": {
    "alibaba": {
      "audio": true
    }
  },
  "inputs": {
    "frameImages": [
      "https://assets.runware.ai/assets/inputs/eac55d84-039f-4866-ae18-820da667b7c4.jpg"
    ]
  }
}
```

---

### audio-driven (audio-driven)

[Watch video](https://assets.runware.ai/examples/alibaba-wan2-5-preview/f343b131-2627-4bfe-8269-f352eca998a5.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "d20b73b9-84d1-4208-b433-2e14406cf0a4",
  "model": "runware:201@1",
  "positivePrompt": "A polished five-second portrait fashion showcase for a premium technical beekeeping suit, synchronized precisely to the supplied percussion. Set on a sunlit modern rooftop apiary styled like a clean Bauhaus set: chalk-white hive boxes, cobalt deck, marigold-yellow wall, cloudless pale-blue sky. The garment is sculptural pearl-white ripstop with cobalt seam tape, articulated elbows, tailored waist, reinforced gloves, and a translucent amber mesh hood. Opening metallic zipper sound: extreme macro of a gloved hand pulling the waterproof cobalt zipper upward. On the next two fabric snaps, sharp match cuts show the hood unfolding and its magnetic collar locking into place. On the brushed snare, reveal the beekeeper model in a confident half-turn as the amber veil catches sunlight and the jointed sleeves flex. A few calm bees drift safely outside the veil. On the final bass hit, settle into a full-body hero frame beside one matte-white hive, the complete silhouette centered and clearly readable. High-end outdoor workwear editorial, crisp hard sunlight, controlled shadows, tactile fabric detail, elegant purposeful movement, smooth stabilized camera, premium color grade, no text or logos.",
  "negativePrompt": "No captions, logos, labels, watermarks, extra limbs, exposed skin inside the veil, malformed hands, torn fabric, dirty suit, aggressive swarm, honey dripping, smoke clouds, fantasy elements, handheld shake, warped hive boxes, duplicate model, or cluttered background.",
  "width": 832,
  "height": 1088,
  "duration": 5,
  "inputs": {
    "audio": "https://assets.runware.ai/assets/inputs/f515bcf4-0133-4be4-b13e-c92f0e2a52b8.mp3"
  }
}
```