whatmodel.sh / video / Grok Imagine Video 1.5
Grok Imagine Video 1.5
↗ share
+ contribute
Grok Imagine Video 1.5 is a closed-weights video model from xAI, released June 2026.
Model information sources
$ how it compares
The video models ranked either side of Grok Imagine Video 1.5, out of 139 with a score, then more from xAI.
| # | model | score | where | ||
|---|---|---|---|---|---|
| 10 |  MiniMax H3 Max | 76±4 | api $0.080/sec | ||
| 11 |  Muse Video | 76±2 | comparison only | ||
| 12 | Grok Imagine Video 1.5 | 75±2 | api $0.080/sec | ||
| 13 |  HiDream-O1-Video 1.0 | 75±3 | comparison only | ||
| 14 |  Wan 2.2 I2V Flash | 75±4 | api $0.036/sec | ||
| more from xAI | |||||
| 17 | Grok Imagine Video | 69±2 | api $0.050/sec | ||
$ what it's good at
image to video▁▂·▂▅█▅▄▅▆▃▄ #9 of 50 · 70% of its score · 3 tests
Beats HappyHorse 1.1 here, though they rank higher overall. Trails Wan 2.2 I2V Flash here, though they rank lower overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| Arena image-to-video | 1456.0 ✎ | ▁▁▁▁▄▇▃▆▃▂▄█ beats 33/40 | 44% |
| Rapidata physics realism (I2V, with reference) | 1143.0 ✎ | ▂··▂▂▆█▆▂▂▆▄ beats 12/19 | 25% |
| Rapidata camera movement (I2V) | 1039.3 ✎ | ▄···▄▄▄█··▄█ beats 4/8 | 1.2% |
other tests3 not in a task · 28% of its score
| test | result | vs the others in its run | counts |
|---|---|---|---|
| Rapidata relative camera movement (I2V, alignment Elo) | 1226.0 ✎ | █···▄▄██·█▄█ beats 8/12 | 16% |
| Rapidata image-to-video realism (overall Elo) | 1315.7 ✎ | ▂······▃▂▃▃█ beats 11/12 | 8.4% |
| Datapoint Video Bench (overall Elo) | 980.3 ✎ | ▃▃·▅·▃·▃··▃█ beats 3/9 | 3.8% |
$ where to run it
Through an API
api · $0.080/sec · docs.x.ai ↗ · price sourceUSD per second of output video. Product: xAI Imagine video API. API model: grok-imagine-video-1.5 (aliases grok-imagine-video-1.5-preview, grok-imagine-video-1.5-2026-05-30). Price basis: published flat output rate; no resolution tiers listed. Not grok-imagine-video ($0.050/s). Currency: USD. xAI models and pricing documentation, observed 2026-09-25.
$ how the score was worked out · LMArena leaderboard dataset 44%, Rapidata/world-model-physics… 25%, Rapidata/relative-camera-move… 16% and 3 more
Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works
| source | results | share of the score |
|---|---|---|
 LMArena leaderboard dataset | 1 | 44% |
 Rapidata/world-model-physics published dataset-card rankings | 1 | 25% |
| Rapidata/relative-camera-movement-human-preference-900k published dataset-card rankings | 1 | 16% |
| Rapidata/image-to-video-realism published dataset-card rankings | 1 | 8% |
| Datapoint Video Bench leaderboard (datapointai/text-to-video-human-preferences-326k dataset card) | 1 | 4% |
| Rapidata/camera-movement published dataset-card rankings | 1 | 1% |
| prior · pull toward the middle | 2% | |
| weighted average | = 75.2 |
$ improve this page
Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.
data updated · sources and licences · json