xAI · video
Grok Imagine
xAI's video model with native sound, up to 15 seconds at 720p.
Text to videoImage to videoNative audio
- Length
- 1 to 15 s
- Resolution
- 480p, 720p
- Aspect ratio
- 16:9, 9:16, 1:1, 4:3, 3:4, 3:2, 2:3
- References
- Up to 1 image file
About Grok Imagine
Grok Imagine is xAI's video model, priced at $0.13 per second. It runs as text to video and image to video, with native sound, from 1 second to 15 seconds, at 480p and 720p.
The price is per second and depends on the resolution: the default length costs $0.75 at 480p and $1.05 at 720p. Animating an image adds a small charge for the image. A typical generation takes about 2 min.
Good for
- Short clips with sound, with the length set to the second
- Animating a still image
- Posting in many shapes, from 16:9, 9:16, 1:1, 4:3, 3:4, 3:2 and 2:3
Getting good results
- The price is per second and the dial starts at 1 second: a short clip costs little, $0.75 at 480p for the default length.
- When you animate an image, the image sets the frame; the aspect ratio menu applies to text to video only.
- Iterate at 480p, then generate the final clip at 720p.
Grok Imagine questions
Does Grok Imagine make sound?
Yes, native audio with the video; there is no setting to turn it off.
How long can a clip be?
From 1 second to 15 seconds: $2.63 for the full length at 720p.