Grok Imagine Video

Submit a JSON video generation task with .

POST /v1/videos

Available models

Headers

Name	Type	Required	Description
	string	Yes	Request authentication. Use a Bearer Token, for example: .
	string	Yes	Request content type. Must be set to .

Request body

Name	Type	Required	Description
	string	Yes	Model name. See Available models above.
	string	Yes	Video generation prompt. Max characters.
	string	No	Target duration in seconds. Minimum ; prefer a string, for example .
	string	No	Aspect ratio. Supports common presets ,,,,,,,,,,,,, and custom ratios.
	string	No	Output resolution. Supports and ; also accepts and .
	string	No	Single reference image as a data URI such as .
	array<string>	No	Multiple reference images. Array items use data URIs such as . Do not send at the same time when using multiple images.

Request example

Text-to-video

curl -X POST https://octopusx.ai/v1/videos \
  -H "Authorization: Bearer <token>" \
  -H "Content-Type: application/json" \
  -d '
{
  "model": "grok-imagine-video",
  "prompt": "A quiet city street at dawn, sunlight through leaves, camera slowly moving forward",
  "seconds": "8",
  "aspect_ratio": "16:9",
  "resolution": "720P"
}'

Image-to-video

curl -X POST https://octopusx.ai/v1/videos \
  -H "Authorization: Bearer <token>" \
  -H "Content-Type: application/json" \
  -d '
{
  "model": "grok-imagine-video",
  "prompt": "Let the person in the reference image turn naturally, keep a soft depth of field in the background",
  "seconds": "6",
  "aspect_ratio": "9:16",
  "resolution": "720P",
  "image": "data:image/png;base64,BASE64_IMAGE_DATA"
}'

Multi-image reference

curl -X POST https://octopusx.ai/v1/videos \
  -H "Authorization: Bearer <token>" \
  -H "Content-Type: application/json" \
  -d '
{
  "model": "grok-imagine-video",
  "prompt": "Use subject features from multiple images to generate a coherent product showcase video",
  "seconds": "10",
  "aspect_ratio": "16:9",
  "resolution": "720P",
  "images": [
    "data:image/png;base64,FIRST_IMAGE_BASE64",
    "data:image/png;base64,SECOND_IMAGE_BASE64"
  ]
}'

Response example

200

{
  "id": "video_abc123",
  "object": "video",
  "model": "grok-imagine-video",
  "status": "queued",
  "progress": 0,
  "created_at": 1735689600,
  "seconds": "6",
  "size": "720P",
  "video_url": ""
}

Response fields

Name	Type	Description
	string	Task ID. Use it to query the task later.
	string	Object type, usually .
	string	Model name actually submitted.
	string	Task status. Common values: ,,,,.
	integer	Task progress percentage.
	string	Video URL when the task completes. You can also download the result directly.

Related endpoints

• Grok video overview
• Video APIs overview
• Error codes