Generate videos with audio from text or images using SpaceXAI Grok Imagine Video. Supports 6s or 10s duration, 480p/720p, and multiple aspect ratios. Content policy rejections may still incur SpaceXAI's $0.05 policy-violation fee, which we pass through.
Added Jan 29, 2026
Approx. Price
$0.300 per video
Model Type
both
Settings
Generation controls available for this model.
Output Format
Default Duration
6
2 duration options
Aspect Ratio
Default
16:9
Options (3)
Landscape (16:9), Square (1:1), Vertical (9:16)
Text-to-video supports multiple aspect ratios. Image-to-video uses the source image framing.
Duration
Default
6
Options (2)
6 seconds, 10 seconds
Length of the generated video in seconds
Resolution
Default
720p
Options (2)
480p, 720p
Output resolution
Benchmarks
Benchmarks
Human preference benchmarks sourced from Artificial Analysis.
Text to Video
#10 / 81
ELO
1222.0
Appearances
11,466
95% CI
-7/7
Image to Video
#7 / 75
ELO
1324.0
Appearances
9,896
95% CI
-8/8
Release Date 2026-01 · Matched as grok-imagine-video
Artificial Analysis APIExamples
Loading examples…
Related video models
Compare Grok Imagine Video with similar models from the same provider or model family.
Grok Imagine Video 1.5
xai/grok-imagine-video/v1.5/image-to-videoGrok Imagine Video 1.5 generates from text, a starting image, or reference images.
Grok Imagine Video Edit
grok-imagine-video-editEdit an existing video with SpaceXAI Grok Imagine. Requires a source video, supports 480p or 720p output, and bills per input-video second up to 8 seconds. Content policy rejections may still incur SpaceXAI's $0.05 policy-violation fee, which we pass through.
Grok Imagine Extend Video
grok-imagine-video-extendExtend an existing video with SpaceXAI Grok Imagine. Requires a source video, supports 2-10s extensions, and bills on both input-video seconds and generated output seconds. Content policy rejections may still incur SpaceXAI's $0.05 policy-violation fee, which we pass through.
Grok Imagine Reference to Video
grok-imagine-video-reference-to-videoGenerate video from one or more reference images with SpaceXAI Grok Imagine. Supports up to 7 reference images, 1-10s duration, and 480p/720p output. Content policy rejections may still incur SpaceXAI's $0.05 policy-violation fee, which we pass through.
MiniMax H3 Max Multi Angle
minimax/h3-max/multi-angle/image-to-videoAnimate a starting image with precise camera control: orbit around the subject, move closer, pull back, or rise above the scene. Choose a camera movement or supply custom keyframes. Supports 5–15 seconds at 480p, 768p, or refined 1080p.
InfiniteTalk
wavespeed-ai/infinitetalkAnimate one or two people from an image and audio tracks.