> ## Documentation Index
> Fetch the complete documentation index at: https://docs.haitoken.ai/llms.txt
> Use this file to discover all available pages before exploring further.
# Wan 2.7 Video Generation
> Video generation API compatible with the Alibaba Wan 2.7 protocol, supporting text-to-video, image-to-video, and video editing
This endpoint is fully compatible with the Alibaba Wan (DashScope) protocol, so you can reuse the parameter structure from the official documentation. The `X-DashScope-Async` header is not required because async semantics are built into the gateway. `model` must be a platform model identifier (e.g. `wan2.7-t2v` / `wan2.7-i2v` / `wan2.7-r2v` / `wan2.7-videoedit`), which the gateway rewrites to the channel model name after routing.
## Request structure
The request body consists of three parts:
* `model`: platform model identifier (required)
* `input`: input content, including `prompt` / `negative_prompt` / `audio_url` and the media element list `media` (first frame / last frame / reference image / reference video / video to edit; accepts public URLs or base64 data URIs, with `reference_voice` to specify the subject's voice timbre)
* `parameters`: generation parameters, including `resolution` / `ratio` / `duration` / `watermark` / `seed` / `prompt_extend` / `audio_setting`
`audio_setting` is only effective for video editing models: `auto` (default) lets the model decide whether to regenerate audio based on the prompt; `origin` forcibly keeps the original sound of the input video.
## Authentication
Include the `Authorization` header in the format `Bearer YOUR_API_KEY`.
## Supported Video Models
| Model Identifier | Model Type | Model Description |
| ---------------- | --------------- | ----------------------------------- |
| wan2.7-t2v | Text to Video | Based on text generation video |
| wan2.7-i2v | Image to Video | Based on image generation video |
| wan2.7-r2v | Reference Video | Based on reference generation video |
| wan2.7-videoedit | Video Edit | Edit input video |
## Quick example
```python Python theme={null}
import requests
url = "https://api.haitoken.ai/v1/alibaba/video/generations"
headers = {
"Authorization": "Bearer YOUR_API_KEY",
"Content-Type": "application/json"
}
data = {
"model": "wan2.7-t2v",
"input": {
"prompt": "A golden retriever runs along the beach at sunset, camera slowly tracking"
},
"parameters": {
"resolution": "720P",
"ratio": "16:9",
"duration": 5,
"watermark": False,
"prompt_extend": True
}
}
response = requests.post(url, json=data, headers=headers)
print(response.json())
```
```javascript Node.js theme={null}
const response = await fetch('https://api.haitoken.ai/v1/alibaba/video/generations', {
method: 'POST',
headers: {
'Authorization': 'Bearer YOUR_API_KEY',
'Content-Type': 'application/json'
},
body: JSON.stringify({
model: 'wan2.7-t2v',
input: {
prompt: 'A golden retriever runs along the beach at sunset, camera slowly tracking'
},
parameters: {
resolution: '720P',
ratio: '16:9',
duration: 5,
watermark: false,
prompt_extend: true
}
})
});
const data = await response.json();
console.log(data);
```
```curl cURL theme={null}
curl -X POST 'https://api.haitoken.ai/v1/alibaba/video/generations' \
-H 'Authorization: Bearer YOUR_API_KEY' \
-H 'Content-Type: application/json' \
-d '{
"model": "wan2.7-t2v",
"input": {
"prompt": "A golden retriever runs along the beach at sunset, camera slowly tracking"
},
"parameters": {
"resolution": "720P",
"ratio": "16:9",
"duration": 5,
"watermark": false,
"prompt_extend": true
}
}'
```
A successful creation returns the task ID:
```json theme={null}
{
"request_id": "8f3d2c1a-9b7e-4f5a-8c2d-1e6f0a9b3c5d",
"output": {
"task_id": "cgt-20260730120000-a1b2c3",
"task_status": "PENDING"
}
}
```
## Next steps
* See [Query Wan video task](/docs/en/api-reference/video/wan-status) to retrieve generation results
* See [Video generation](/docs/en/api-reference/video/generation) for the unified protocol
* See the [HappyHorse protocol](/docs/en/api-reference/video/happyHorse) for HappyHorse compatible parameters
* See the [model list](/docs/en/api-reference/models/list-models) for available video models
## OpenAPI
````yaml en/api-reference/video/wan/openapi.json POST /v1/alibaba/video/generations
openapi: 3.0.1
info:
title: Default Module
description: ''
version: 1.0.0
servers: []
security: []
tags: []
paths:
/v1/alibaba/video/generations:
post:
tags: []
summary: Create video generation task (Alibaba Wan compatible protocol)
description: >-
Body is identical to the official Wan API (no X-DashScope-Async header
required; async semantics are built into the gateway);
model must be a platform model identifier (rewritten to the channel
model name after routing).
parameters:
- name: Authorization
in: header
description: API Key token (Bearer sk-xxx)
required: true
example: 'Bearer '
schema:
type: string
- name: Content-Type
in: header
description: ''
example: application/json
schema:
type: string
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/AlibabaCreateTaskRequest'
description: ''
examples: {}
responses:
'200':
description: ''
content:
application/json:
schema:
$ref: '#/components/schemas/AlibabaCreateTaskResponse'
headers: {}
deprecated: false
security: []
components:
schemas:
AlibabaCreateTaskRequest:
type: object
properties:
model:
type: string
description: >-
Platform model identifier (e.g. wan2.7-t2v / wan2.7-i2v / wan2.7-r2v
/ wan2.7-videoedit),
rewritten to the channel model name by the gateway after routing
input:
$ref: '#/components/schemas/Input'
description: Input content (prompt and media elements)
parameters:
$ref: '#/components/schemas/Parameters'
description: Generation parameters
required:
- model
AlibabaCreateTaskResponse:
type: object
properties:
request_id:
type: string
description: Gateway request ID
output:
$ref: '#/components/schemas/TaskOutput'
description: Task output
Input:
type: object
properties:
negative_prompt:
type: string
description: Negative prompt
audio_url:
type: string
description: Audio URL (e.g. driving audio) or base64 data URI
prompt:
type: string
description: Text prompt
media:
type: array
items:
$ref: '#/components/schemas/MediaItem'
description: Media element
description: >-
Media element list (first frame / last frame / reference image /
reference video / video to edit)
Parameters:
type: object
properties:
audio_setting:
type: string
description: >-
Video sound setting (only effective for video editing models)
auto (default): the model intelligently decides based on the prompt.
If the prompt involves sound descriptions, audio may be regenerated;
otherwise the original sound of the input material may be kept.
origin: forcibly keeps the original sound of the input video without
regeneration.
prompt_extend:
type: boolean
description: Whether to enable intelligent prompt rewriting
resolution:
type: string
description: 'Resolution tier: 480P / 720P / 1080P'
ratio:
type: string
description: 'Aspect ratio: 16:9 / 9:16 / 1:1'
duration:
type: integer
description: Generation duration (seconds)
watermark:
type: boolean
description: Whether to include a watermark
seed:
type: integer
description: Random seed
format: int64
TaskOutput:
type: object
properties:
task_id:
type: string
description: Task ID
task_status:
type: string
description: 'Task status: PENDING'
MediaItem:
type: object
properties:
reference_voice:
type: string
description: >-
Audio URL. Used to specify the voice timbre of the subject in the
reference material (image/video)
type:
type: string
description: |-
Element type: first_frame / last_frame / reference_image /
reference_video / video (video to edit)
url:
type: string
description: >-
Media URL or base64 data URI (base64 is stored to OBS by the gateway
and replaced)
required:
- type
- url
````