xAI
Fastreleased January 2026Grok Imagine Video
Fast, affordable video with native audio
xAI's Grok Imagine creates lively clips from text or a photo, uses reference images for consistent subjects and edits existing videos with a simple instruction — with natively generated sound. One of the fastest models in the catalog.
- Very fast generation
- Native audio on every clip
- Reference images for consistency
- Edit a clip with a prompt
- Min. credits
- 50
- Typical time
- ~45s
- Max resolution
- 720p
Specs
Capabilities
- Modes
- Text to videoImage to videoReference to videoVideo to video
- Inputs
- TextPhotoVideo
Up to 7 reference images
- Aspect ratios
- 16:99:161:14:33:43:22:3
- Durations
- 5s10s15s
- Resolutions
- 480p720p
- Native audio
- Yes
Credits
Pricing
Credits per output. Free generations cover Standard quality.
| Setting | Quality | Credits |
|---|---|---|
| 480p · 5s | Draft | 50 |
| 720p · 5s | Standard | 50 |
| 480p · 10s | Standard | 100 |
| 720p · 10s | Standard | 100 |
| 480p · 15s | High | 150 |
| 720p · 15s | High | 150 |
