Grok Imagine Video
by xAI
xAI's fast video model with native audio.
Grok Imagine Video turns prompts and stills into punchy, sound-backed clips with a distinctive cinematic grade. Quick, inexpensive and fun to iterate with.
More details
Grok Imagine Video by xAI is a fast-speed AI video generation model. Grok Imagine Video turns prompts and stills into punchy, sound-backed clips with a distinctive cinematic grade. Quick, inexpensive and fun to iterate with. Key capabilities include text-to-video, image-to-video, native audio generation, clips of 6 seconds, output up to 720p, 1 aspect ratios.
Grok Imagine Video is priced from $0.05 per second of generated video (up to $0.06 per second at the highest resolution) — a 6-second 720p clip costs about $0.36. You can generate videos with Grok Imagine Video on idapt.app alongside 200+ AI models in one workspace.
Pricing
Cost per second
from $0.05
Price range
$0.05 – $0.06
Varies by resolution & audio
| Resolution | Audio | Per second | Per 5s clip |
|---|---|---|---|
| 480p | Included | $0.05 | $0.24 |
| 720p | Included | $0.06 | $0.30 |
Capabilities
Speed
Fast: Usually under a minute
Generation modes
Text to video, Image to video
Clip length
6s
Aspect Ratios
16:9
Audio output
Native audio
Resolutions
480p, 720p
How to generate videos
In chat
Use Grok Imagine Video to make a 6-second video of a sunset over the oceanAPI
POST /api/v1/videos/generations
{"prompt": "A sunset over the ocean", "model": "grok-imagine-video"}CLI
idapt video generate --model grok-imagine-video --prompt "A sunset over the ocean"Video generation runs in the background. Poll the returned operation until the clip is ready.
