xAI · Text to video

Grok Imagine

Grok Imagine Video creates short audiovisual clips from a scene prompt or an image starting point. It is useful for animated illustrations, expressive social clips and product-motion concepts where a subject and camera need to come to life together. Describe the desired action, visual style and sound clearly, or begin with a well-composed still to anchor the subject’s appearance and the opening framing of the scene.

Generation mode

Text to video

Credit cost

10–210 credits

Observed generation time

Not enough public data

Release date

Dec 1, 2025

Current credit pricing

Duration	Configuration	Credits
1 seconds	480p	10
1 seconds	720p	14
2 seconds	480p	20
2 seconds	720p	28
3 seconds	480p	30
3 seconds	720p	42
4 seconds	480p	40
4 seconds	720p	56
5 seconds	480p	50
5 seconds	720p	70
6 seconds	480p	60
6 seconds	720p	84
7 seconds	480p	70
7 seconds	720p	98
8 seconds	480p	80
8 seconds	720p	112
9 seconds	480p	90
9 seconds	720p	126
10 seconds	480p	100
10 seconds	720p	140
11 seconds	480p	110
11 seconds	720p	154
12 seconds	480p	120
12 seconds	720p	168
13 seconds	480p	130
13 seconds	720p	182
14 seconds	480p	140
14 seconds	720p	196
15 seconds	480p	150
15 seconds	720p	210

Availability and credit rows come from Flowctory's active production catalog. Observed time is shown only after at least five completed generations and is not a controlled benchmark. Model availability, limits, and costs can change.

Use model