Aliyun Video Generation

Create a video task using the Alibaba Cloud Model Studio / DashScope native format. This endpoint is only for Aliyun video channels and does not accept the OpenAI/Sora top-level prompt request body.

The current public Aliyun video models are wan2.7-i2v and wan2.6-i2v. The table below only lists official Alibaba Cloud Model Studio / DashScope request-body fields that clients should send.

For the official API reference, see: Bailian API Console (wan2.7-i2v).

Try It

POST/aliyun/v1/videos/generationshttps://api-platform.ope.ai

Endpoints

Endpoint	Auth	Purpose
POST /aliyun/v1/videos/generations	Authorization: Bearer <api-key>	Create an Aliyun video task
GET /aliyun/v1/tasks/{task_id}	Authorization: Bearer <api-key>	Query Aliyun video task status
GET /aliyun/v1/videos/{task_id}/content	Authorization: Bearer <api-key>	Download the Aliyun video result

Models And Input Rules

Model	Required input	Main parameters	Notes
wan2.7-i2v	input.media	parameters.resolution parameters.duration parameters.prompt_extend parameters.watermark parameters.seed	Official newer image-to-video protocol; reference materials go in the media array
wan2.6-i2v	input.img_url	parameters.resolution parameters.duration parameters.prompt_extend parameters.shot_type parameters.watermark parameters.seed	Official first-frame image-to-video protocol

Request Body（application/json）

Field	Type	Required	Description
model	string	Yes	Aliyun video model ID, for example wan2.7-i2v or wan2.6-i2v
input	object	Yes	Video input
input.prompt	string	No	Text prompt; recommended
input.negative_prompt	string	No	Negative prompt
input.media	array	Conditional	Official multimodal input for wan2.7-i2v; each item contains type and url
input.img_url	string	Conditional	First-frame image URL for wan2.6-i2v
input.audio_url	string	No	Audio URL for wan2.6-i2v audio-driving scenarios
parameters	object	No	Video processing parameters
parameters.resolution	string	No	Resolution tier, for example 720P or 1080P
parameters.duration	integer	No	Duration in seconds; default and valid values are model-specific
parameters.prompt_extend	boolean	No	Whether to enable prompt rewriting
parameters.shot_type	string	No	Shot type for wan2.6-i2v
parameters.watermark	boolean	No	Whether to add a watermark
parameters.seed	integer	No	Random seed

For wan2.7-i2v, use official input.media[].type values: first_frame, last_frame, driving_audio, and first_clip. Each media item must include a reachable url.

Request Examples

wan2.7-i2v

curl -X POST "https://api-platform.ope.ai/aliyun/v1/videos/generations" \
  -H "Authorization: Bearer $OPEAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "wan2.7-i2v",
    "input": {
      "prompt": "A kitten running on grass with a cinematic camera move.",
      "media": [
        {
          "type": "first_frame",
          "url": "https://example.com/first-frame.png"
        }
      ]
    },
    "parameters": {
      "resolution": "720P",
      "duration": 5,
      "prompt_extend": true,
      "watermark": false
    }
  }'

wan2.6-i2v

curl -X POST "https://api-platform.ope.ai/aliyun/v1/videos/generations" \
  -H "Authorization: Bearer $OPEAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "wan2.6-i2v",
    "input": {
      "prompt": "Make the person in the image turn slowly with natural wind in the background.",
      "img_url": "https://example.com/first-frame.png"
    },
    "parameters": {
      "resolution": "720P",
      "duration": 5,
      "prompt_extend": true
    }
  }'

Response Example

Successful creation returns an Aliyun task structure. Save output.task_id for status polling and content download.

{
  "output": {
    "task_status": "PENDING",
    "task_id": "0385dc79-5ff8-4d82-bcb6-xxxxxx"
  },
  "request_id": "4909100c-7b5a-9f92-bfe5-xxxxxx"
}

Error Example

{
  "error": {
    "message": "only aliyun channel is supported on /aliyun/v1/videos/generations",
    "type": "invalid_request_error",
    "param": null,
    "code": "invalid_request_error"
  }
}