Grok Imagine Models

Overview

Vendor: Grok. grok-imagine creates video from text or an image prompt. grok-imagine-1-5 is an image-only model with a single 16-second, 720p configuration.

Supported modes

Model	Mode	Durations	Resolutions	Aspect ratios	Audio
`grok-imagine`	text-to-video, image-to-video	6s, 10s, 15s, 30s	480p, 720p	2:3, 3:2, 1:1, 9:16, 16:9	No
`grok-imagine-1-5`	image-to-video only	16s	720p	16:9, 9:16	No

Credit pricing

`grok-imagine`

The matrix is identical for text-to-video and image-to-video.

Resolution	6s	10s	15s	30s
480p	10	20	30	60
720p	20	30	45	90

`grok-imagine-1-5`

Resolution	16s
720p	20

All values are credits per generation.

cURL

curl -X POST https://vidrush-ai.com/api/v1/videos \
  -H "Authorization: Bearer $VIDRUSH_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "grok-imagine-1-5",
    "mode": "image-to-video",
    "prompt": "The camera slowly pushes toward the subject",
    "image_urls": ["https://example.com/source.jpg"],
    "options": {
      "duration": "16s",
      "resolution": "720p",
      "aspect_ratio": "16:9"
    }
  }'

CLI

vidrush generate -m grok-imagine-1-5 \
  -p "The camera slowly pushes toward the subject" \
  --mode image-to-video --image https://example.com/source.jpg \
  --duration 16s --resolution 720p --aspect-ratio 16:9 --wait

MCP

Ask the MCP client to call generate_video with grok-imagine-1-5, an image_urls array, and mode: "image-to-video".

Notes

grok-imagine-1-5 supports only image-to-video and requires an image input.
Do not send audio: true for either Grok model.

Grok Imagine Models

On this page