curl --request POST \
--url https://api.poyo.ai/api/generate/submit \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"model": "grok-imagine-video-1.5",
"input": {
"prompt": "A cinematic city at sunrise",
"resolution": "1080p",
"duration": 6,
"aspect_ratio": "16:9"
}
}
'{
"code": 200,
"message": "<string>",
"data": {
"task_id": "<string>",
"status": "<string>",
"created_time": "2023-11-07T05:31:56Z"
}
}Grok (xAI)
Grok Imagine Video 1.5
The Grok Imagine Video 1.5 API generates 1–15 second videos from text or one first-frame image at up to 1080p, or from up to seven reference images at up to 720p.
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": "grok-imagine-video-1.5",
"input": {
"prompt": "A cinematic city at sunrise",
"resolution": "1080p",
"duration": 6,
"aspect_ratio": "16:9"
}
}
'{
"code": 200,
"message": "<string>",
"data": {
"task_id": "<string>",
"status": "<string>",
"created_time": "2023-11-07T05:31:56Z"
}
}- 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 result through the unified Query Task Status endpoint.
grok-imagine-video-1.5 for three generation modes with 1–15 second outputs:
- Text to video: omit both image fields. Supports 480p, 720p, and 1080p.
- Image to video: provide exactly one item in
image_urlsas the first frame. Supports 480p, 720p, and 1080p. - Reference to video: provide 1–7 items in
reference_image_urls. Reference them in the prompt as<IMAGE_0>,<IMAGE_1>, and so on. Supports 480p and 720p.
image_urls and reference_image_urls cannot be used together.
Parameters
- prompt (required): up to 4,096 characters.
- image_urls: exactly one first-frame image for image-to-video.
- reference_image_urls: 1–7 reference images for character, subject, or style consistency.
- resolution:
480p,720p, or1080p. Reference-to-video does not support1080p. Default:720p. - duration: integer from
1to15. Default:6for text/image mode and8for reference mode. - aspect_ratio:
16:9,4:3,3:2,1:1,2:3,3:4, or9:16. Available only for text and reference modes; default:16:9. - callback_url: optional completion webhook URL.
Authorizations
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
Body
application/json