Skip to main content
POST
Use this endpoint to create a Vidu Q3 text-to-video or image-to-video task. The API returns a task ID immediately, so store the returned id and poll the task until it reaches a terminal status. POST /v1/videos uses multipart/form-data. Send scalar controls as form fields and reference images as input_reference file fields.

​
Choose an input mode

To confirm a Vidu model ID that is available to your API key, use List available models.

​
Use reference images

For image-to-video, upload one reference image through the input_reference multipart field. The file can be up to 20 MB. The image guides the composition and appearance of the generated video. Use the prompt to describe motion, camera behavior, and details that the video should preserve.

​
Set duration and size

Set size to one of the WxH values below.

​
Task flow

1

Create the task

Send the multipart form request and store the returned id.
2

Poll the task

Call Retrieve a Vidu video until status is completed, failed, or error.
3

Download the result

When the task is completed, call Retrieve Vidu video content to download the MP4 file.

Authorizations

​
Authorization
string
header
required

Bearer authentication. Use your CometAPI API key.

Body

multipart/form-data
​
model
string
required

Vidu Q3 model ID for this route. Choose an available model from the Models page.

Example:

"viduq3-turbo"

​
prompt
string
required

Text prompt that describes the video to generate. For image-to-video, describe the motion and camera behavior that should animate the reference image.

Example:

"An astronaut walks through soft blue fog with a slow cinematic camera move."

​
seconds
string

Requested clip duration in seconds. Use an integer from 1 through 16. Default is 5.

Example:

"1"

​
size
string

Supported WxH size values: 960x528, 1280x720, 1920x1080. Default is 1280x720.

​
input_reference
file

One reference image file for image-to-video. Omit this field for text-to-video. The file can be up to 20 MB. The image guides the composition and appearance of the generated video.

Response

Task created. Store the returned id and poll GET /v1/videos/{task_id}.

​
id
string
required

Task ID. Use this value with retrieve and content endpoints.

Example:

"task_example"

​
object
string
required

Object type. Video tasks return video.

Example:

"video"

​
model
string
required

Model ID used for the task.

Example:

"viduq3-turbo"

​
status
enum<string>
required

Task lifecycle status. Poll until the value is completed, failed, or error.

Available options:
queued,
in_progress,
completed,
failed,
error
Example:

"queued"

​
progress
integer
required

Task progress as a coarse percentage.

Required range: 0 <= x <= 100
Example:

0

​
created_at
integer
required

Task creation time as a Unix timestamp in seconds.

Example:

1779938152

​
task_id
string

Compatibility alias for id when present.

Example:

"task_example"

​
completed_at
integer

Task completion time as a Unix timestamp in seconds. This field appears on completed tasks.

Example:

1779938219

​
video_url
string

Temporary video delivery URL. This field appears on completed tasks.

Example:

"<temporary-video-url>"

​
error
object

Failure details. This field appears when the task fails.

Last modified on August 12, 2026