v1

latestOpenAPI 3.1.02026-07-2661513.6 KB

Create video task

Create an asynchronous text-to-video or image-to-video task. Use JSON when there are no reference images and multipart/form-data when reference images are present.

post/videos

Request body

modelstring required

Video model ID.

promptstring required

Text instruction for the video.

secondsstring required

Requested duration. Must be listed in the selected model's capabilities.supported_seconds.

sizestring

Requested output size. Must be listed in the selected model's capabilities.supported_sizes when provided.

Example request

{
  "model": "gemini-veo31",
  "prompt": "Waves crashing on rocks, cinematic slow motion",
  "seconds": "6",
  "size": "1280x720"
}

Response

Queued video task

idstring required

Video task ID.

status'queued' | 'in_progress' | 'completed' | 'failed' required

Video task status.

Example response

{
  "id": "video_task_id",
  "status": "queued"
}