Submit Task (Jimeng Format)

Structurally identical to the official Jimeng API: both submit and query hit POST /jimeng/, distinguished by the Action query parameter:

Endpoint

POST /jimeng/?Action=CVSync2AsyncSubmitTask&Version=2022-08-31

Request Body

FieldTypeRequiredNotes
req_keystringYesModel identifier (differs between text-to-video and image-to-video, e.g. jimeng_vgfm_t2v_l20; per the Model Plaza)
promptstringYesVideo description
binary_data_base64string[]NoImage-to-video: array of Base64 images
image_urlsstring[]NoImage-to-video: array of image URLs
aspect_ratiostringNoAspect ratio

Request Examples

cURL
Python
Node.js
# Submit a text-to-video task
curl -X POST "https://api-model.shuntianchuang.cn/jimeng/?Action=CVSync2AsyncSubmitTask&Version=2022-08-31" \
  -H "Authorization: Bearer sk-your-token" \
  -H "Content-Type: application/json" \
  -d '{
    "req_key": "jimeng_vgfm_t2v_l20",
    "prompt": "An orange cat chasing butterflies on a lawn, cinematic shot"
  }'

Response Body

A successful submission likewise returns a task object; the id / task_id is used for querying.

Response Example

{
  "id": "task_xxxxxxxx",
  "object": "video",
  "task_id": "task_xxxxxxxx",
  "status": "queued",
  "progress": 0,
  "model": "jimeng_vgfm_t2v_l20",
  "created_at": 1769473000
}

For status query and download see Query & Download.