wan2.7-i2v

wan2.7-i2v Unified Endpoint Guide

1. This page documents parameters for the platform unified endpoint /v1/videos.
2. If you want to call Wan models with native parameters, see: Aliyun Format (Videos).

Basic Info

Item	Description
Model Name	wan2.7-i2v
Model ID	wan2.7-i2v
Model Type	Image-to-video
Base URL	https://api-platform.ope.ai
Create Task	POST /v1/videos
Query Task	GET /v1/videos/{task_id}
Download Result	GET /v1/videos/{task_id}/content

Authentication:

• Authorization: Bearer YOUR_API_KEY

You can prepare these env vars in your shell:

BASE_URL="https://api-platform.ope.ai"
API_KEY="YOUR_API_KEY"

For pricing, see: Model Pricing.

1. Unified Endpoint to Aliyun Mapping

wan2.7-i2v uses the unified video endpoint POST /v1/videos. The gateway maps this request to Aliyun video-synthesis async protocol.

Unified field	Upstream Aliyun field	Notes
model	model	Use wan2.7-i2v
prompt	input.prompt	Text prompt
First image_url.url in input_reference.content	input.media[0].url	Auto-mapped as first frame
-	input.media[0].type	Gateway sets this to first_frame
size	parameters.size	Example: 1280x720
seconds	parameters.duration	String seconds are converted to integer
generate_audio	parameters.audio	Optional
seed	parameters.seed	Optional

Notes:

• For wan2.7-i2v, the unified endpoint currently consumes the first image_url as first-frame reference.
• resolution + ratio is a Seedance-only capability (Volcengine/Gravitex), not for Aliyun video channels.
• Top-level content is not supported; use input_reference.content.

2. Create Task (POST /v1/videos)

2.1 Recommended Request Body

{
  "model": "wan2.7-i2v",
  "prompt": "The character in the image takes two steps forward, with a slight camera push-in and cinematic lighting.",
  "size": "1280x720",
  "seconds": "5",
  "generate_audio": false,
  "input_reference": {
    "content": [
      {
        "type": "image_url",
        "role": "first_frame",
        "image_url": {
          "url": "https://example.com/first-frame.png"
        }
      }
    ]
  }
}

2.2 cURL Example

curl --request POST "$BASE_URL/v1/videos" \
  --header "Authorization: Bearer $API_KEY" \
  --header "Content-Type: application/json" \
  --data '{
    "model": "wan2.7-i2v",
    "prompt": "The character in the image takes two steps forward, with a slight camera push-in and cinematic lighting.",
    "size": "1280x720",
    "seconds": "5",
    "generate_audio": false,
    "input_reference": {
      "content": [
        {
          "type": "image_url",
          "role": "first_frame",
          "image_url": {
            "url": "https://example.com/first-frame.png"
          }
        }
      ]
    }
  }'

Typical response:

{
  "id": "0385dc79-5ff8-4d82-bcb6-xxxxxx",
  "object": "video",
  "status": "QUEUED",
  "created_at": 1780021218,
  "model": "wan2.7-i2v",
  "prompt": "The character in the image takes two steps forward, with a slight camera push-in and cinematic lighting.",
  "size": "1280x720",
  "seconds": "5"
}

id is the task_id used by query and download APIs.

3. Query Task (GET /v1/videos/{task_id})

curl --request GET "$BASE_URL/v1/videos/TASK_ID_HERE" \
  --header "Authorization: Bearer $API_KEY"

Typical response:

{
  "id": "0385dc79-5ff8-4d82-bcb6-xxxxxx",
  "status": "IN_PROGRESS",
  "model": "wan2.7-i2v",
  "created_at": 1780021218,
  "object": "video",
  "prompt": "The character in the image takes two steps forward, with a slight camera push-in and cinematic lighting.",
  "size": "1280x720"
}

Common statuses:

• QUEUED
• IN_PROGRESS
• SUCCESS
• FAILURE

4. Download Result (GET /v1/videos/{task_id}/content)

After task status becomes SUCCESS, call the content endpoint to download binary video stream:

curl --request GET "$BASE_URL/v1/videos/TASK_ID_HERE/content" \
  --header "Authorization: Bearer $API_KEY" \
  --output output.mp4

If the task is not finished, the endpoint returns an error.

5. Minimal Integration Flow

1. Create task with one first-frame image (POST /v1/videos)
2. Poll task status (GET /v1/videos/{task_id})
3. Download binary video after success (GET /v1/videos/{task_id}/content)

6. Official References

• Bailian console API doc (wan2.7-i2v): https://bailian.console.alibabacloud.com/cn-beijing?tab=api#/api/?type=model&url=3025059
• Aliyun help center (I2V general API): https://help.aliyun.com/zh/model-studio/image-to-video-general-api-reference