Grok Imagine

xAI’s Grok Imagine Video 1.5: quick clips with sound at 480p and 720p, 1 to 15 seconds, from a prompt, a start image, or up to 3 reference images.

Prices

A clip costs its length times the rate: a 5 second 480p clip is $0.355. It’s charged only when the video is delivered.

What it takes

• A prompt of up to 8,000 characters.
• A first_frame, or up to 3 reference_images, not both.
• Lengths from 1 to 15 seconds, in whole seconds.
• 16:9, 9:16, 1:1, 4:3 and 3:4. From a first frame, the video takes the image’s shape.
• Sound comes at no extra cost; set generate_audio to false for a silent clip.
• 480p and 720p.

Example

{
  "model": "grok-imagine-video-1.5",
  "reference_images": [
    "https://example.com/beekeeper.jpg",
    "https://example.com/honey-jar.jpg"
  ],
  "prompt": "The beekeeper from the first image holds up the honey jar from the second image and smiles.",
  "seconds": 5,
  "resolution": "720p",
  "aspect_ratio": "16:9"
}

Prompting

• Describe the shot and the motion: who moves, how, and what the camera does.
• With reference images, say who or what from each image appears and what they do.
• For clips you’ll score yourself, set generate_audio to false: the price is the same.

Good to know

• Short clips are usually ready in under a minute.
• There’s no end frame, negative prompt or seed, and no 1080p yet.
• Prompts or images that may break the content rules can be declined (content_policy); declined videos are free.
• Videos are kept for 30 days; download the ones you want to keep.

Full API details: Video generation. Try it in the dashboard’s Playground, which shows the code for each video.