curl --request POST \
--url https://api.poyo.ai/api/generate/submit \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"model": "pixverse-v6-max",
"input": {
"prompt": "A blue glass marble rolls across a clean white table in warm morning light",
"duration": 5,
"resolution": "540p",
"aspect_ratio": "16:9"
}
}
'{
"code": 200,
"data": {
"task_id": "task-unified-1792190000-example",
"status": "not_started",
"created_time": "2026-10-28T10:30:00"
}
}{
"code": 400,
"error": {
"message": "Invalid request parameters",
"type": "invalid_request_error"
}
}{
"code": 400,
"error": {
"message": "Invalid request parameters",
"type": "invalid_request_error"
}
}PixVerse
PixVerse V6 Max
Generate a 1–15 second video from text or one image, with optional native audio, at 360p to 1080p.
POST
/
api
/
generate
/
submit
curl --request POST \
--url https://api.poyo.ai/api/generate/submit \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"model": "pixverse-v6-max",
"input": {
"prompt": "A blue glass marble rolls across a clean white table in warm morning light",
"duration": 5,
"resolution": "540p",
"aspect_ratio": "16:9"
}
}
'{
"code": 200,
"data": {
"task_id": "task-unified-1792190000-example",
"status": "not_started",
"created_time": "2026-10-28T10:30:00"
}
}{
"code": 400,
"error": {
"message": "Invalid request parameters",
"type": "invalid_request_error"
}
}{
"code": 400,
"error": {
"message": "Invalid request parameters",
"type": "invalid_request_error"
}
}- After submission, a
task_idwill be returned. If you provided acallback_url, when the task status becomesfinishedorfailed, a POST request will be sent to thecallback_url. - Regardless of whether
callback_urlis provided, you can retrieve the response result through the unified Query Task Status endpoint.
Models
- pixverse-v6-max — Text-to-video and single-image-to-video generation
Features
- Generate videos from 1 to 15 seconds.
- Create a clip from text, or animate exactly one image.
- Choose 360p, 540p, 720p, or 1080p output.
- Optionally generate a native audio track.
Input modes
- Text-to-video: Omit
image_urls.promptis required.aspect_ratioselects the frame. - Image-to-video: Provide exactly one URL in
image_urls.promptis optional. The output follows the image, so do not sendaspect_ratio.
Required parameters
prompt(string): Required for text-to-video. Must contain 1–5,000 characters and cannot be blank.image_urls(array of strings): Required for image-to-video. Must contain exactly one public image URL.
Optional parameters
prompt(string): Optional for image-to-video, with a maximum of 2,048 characters. Cannot be blank when provided.duration(integer): Output length from 1 to 15 seconds. Defaults to5.resolution(string):360p,540p,720p, or1080p. Defaults to540p.aspect_ratio(string):16:9,9:16,4:3,3:4,1:1,2:3,3:2, or21:9. Defaults to16:9. Text-to-video only.audio(boolean): Generate a native audio track. Defaults tofalse.
Examples
The request examples show a text-to-video clip with an explicit frame, and an image animation that omitsaspect_ratio. Both use the pixverse-v6-max model ID.
Notes
- Put all generation parameters inside
input. - Image-to-video accepts one JPEG, PNG, or WebP image over a public HTTP or HTTPS URL.
- Do not send two or more images, a first and last frame, or a source video.
- Pixel dimensions follow the model’s native output for the selected resolution.
Authorizations
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
Body
application/json
Public model identifier.
Available options:
pixverse-v6-max Text-to-video requires prompt and omits image_urls. Image-to-video requires exactly one image_urls item and does not accept aspect_ratio.
Show child attributes
Show child attributes
Optional webhook URL for task completion or failure notifications. Use a publicly accessible HTTP or HTTPS URL.