Skip to main content
POST

​
Grok Imagine Video 1.5

Create 1–15 second videos from text, a single first-frame image, or up to seven reference images.
After submission, use the returned task_id with the video status endpoint, or provide callback_url to receive the completed result.

​
Generation modes

  • Text to video: omit both image fields. Supports 480p, 720p, and 1080p.
  • Image to video: provide exactly one URL in image_urls. Supports 480p, 720p, and 1080p.
  • Reference to video: provide 1–7 URLs in reference_image_urls and refer to them as <IMAGE_0>, <IMAGE_1>, and so on. Supports 480p and 720p.
image_urls and reference_image_urls cannot be used together. aspect_ratio is available for text and reference modes, but not first-frame image-to-video.

​
Parameters

  • prompt (required): up to 4,096 characters.
  • resolution: 480p, 720p, or 1080p. Default: 720p.
  • duration: integer from 1 to 15. Default: 6 for text/image mode and 8 for reference mode.
  • aspect_ratio: 16:9, 4:3, 3:2, 1:1, 2:3, 3:4, or 9:16. Default: 16:9 where supported.
  • callback_url: optional HTTPS completion webhook.

​
Billing

Video output is billed per second by resolution: 14.5 credits at 480p, 25 credits at 720p, and 45 credits at 1080p. Each submitted input or reference image adds 2 credits.
Use public HTTPS image URLs or upload images through the playground before submitting.

Authorizations

​
Authorization
string
header
required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Body

application/json
​
model
enum<string>
required
Available options:
grok-imagine-video-1.5
​
input
object
required

Omit image fields for text-to-video. image_urls and reference_image_urls are mutually exclusive. Reference mode does not support 1080p; first-frame image mode does not support aspect_ratio.

​
callback_url
string<uri>

Response

200 - application/json

Task submitted successfully

​
code
integer
Example:

200

​
message
string
​
data
object