Skip to main content
POST
Create Video

Create Video

The Jimeng unified video entry uses POST /v1/video/create, and the request body is JSON. Unlike Jimeng video generation in OpenAI format, this API uses fields such as images, aspect_ratio, size, and duration.
  • The route entry is POST /v1/video/create.
  • Reference images are passed in as a list of URLs through the images array; for text-to-video, you can pass an empty array.
  • A common model example is jimeng-video-3.0; use the model actually available in the current channel.
  • After a successful submission, the task id and status are returned, and the result is polled later via Query Task.

Supported Models

  • jimeng-video-3.0
  • jimeng-video-2.0

Method and Path

Request Example

Response Example

Authentication

Body

model
string
required
Model name, for example jimeng-video-3.0.
prompt
string
required
Prompt. The text description for video generation, supporting both Chinese and English.
images
array<string>
required
List of image URLs. Pass [] for text-to-video, 1 image for first-frame-to-video, or 2 images for first-and-last-frame-to-video. Supports image URLs, with image formats including png, jpeg, jpg, and webp.
aspect_ratio
string
required
Aspect ratio. Available values include 16:9, 4:3, 1:1, 3:4, 9:16, and 21:9.
size
string
required
Video size. Available values include 720P and 1080P.

Response

created_at
string
Creation time (ISO 8601 format).
status
string
Task status. Common values include processing, failed, and completed.
task_id
string
Task ID, passed as the id parameter in subsequent queries.