Grok Imagine Video 1.5

Grok Imagine Video 1.5 is xAI’s video generation model. Use grok-imagine-video-1.5 for text-to-video or image-to-video with 1–7 reference images, at 480p or 720p, from 6 to 15 seconds. type is optional. When omitted, a request without image_urls runs as text-to-video and a request with images runs as image-to-video.

Request parameters

Parameter	Required	Accepted values
`prompt`	Yes	Non-blank text
`type`	No	`text-to-video` or `image-to-video`; inferred from `image_urls` when omitted
`image_urls`	For `image-to-video`	1–7 public HTTP(S) URLs. Base64 and data URIs are rejected. Not allowed for `text-to-video`
`aspect_ratio`	No	`16:9` (default), `9:16`, `1:1`, `3:2`, `2:3`. With reference images, the output follows the reference image’s ratio
`resolution`	No	`480p` or `720p` (default), lowercase
`duration`	No	Integer seconds from `6` to `15`, default `6`

Each request produces one video.

{
  "prompt": "Bring the scene to life with natural motion and drifting clouds",
  "type": "image-to-video",
  "image_urls": ["https://example.com/start.png"],
  "aspect_ratio": "16:9",
  "resolution": "720p",
  "duration": 10
}

Submit to POST /api/v1/task/submit/grok-imagine-video-1.5. Save the returned data.task_id and poll /api/v1/task/status.

Pricing

Grok Imagine Video 1.5 is billed per second by resolution. Reference images are not billed.

Resolution	Credits per second
480p	20
720p	37

Example: the default 6-second 720p video costs 37 × 6 = 222 credits. /pricing remains the current source of truth.

See the Grok Imagine Video 1.5 API reference for the machine-readable Schema.

Getting started

Agent integrations

Video Generation

Image Generation

Audio Generation

Grok Imagine Video 1.5