whatmodel.sh / video / Grok Imagine Video
Grok Imagine Video
↗ share
+ contribute
Grok Imagine Video is a closed-weights video model from xAI, released January 2026. Licence: proprietary.
$ how it compares
The video models ranked either side of Grok Imagine Video, out of 139 with a score, then more from xAI.
| # | model | score | where | ||
|---|---|---|---|---|---|
| 15 |  HappyHorse 1.0 | 73±2 | api $0.14/sec | ||
| 16 |  Wan 2.2 I2V Plus | 71±5 | api $0.10/sec | ||
| 17 | Grok Imagine Video | 69±2 | api $0.050/sec | ||
| 18 |  Kling 3.0 Pro | 69±2 | api $0.11/sec | ||
| 19 |  Veo 3.1 | 69±1 | api $0.40/sec | ||
| more from xAI | |||||
| 12 | Grok Imagine Video 1.5 | 75±2 | api $0.080/sec | ||
$ what it's good at
text to video▆▄▃▄▆▅█▃▂▃▂▄ #12 of 68 * · 42% of its score · 1 test
Trails Veo 3.1 Fast, Veo 3.1 here, though they rank lower overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| LMArena video | 1342.2 ✎ | ▂▂▃▆█▆·▆▅▁▂▇ beats 27/41 | 42% |
image to video▁▂·▂▅█▅▄▅▆▃▄ #11 of 50 · 48% of its score · 4 tests
Beats HappyHorse 1.1, HappyHorse 1.0, Wan 2.2 I2V Plus here, though they rank higher overall. Trails Kling 3.0 here, though they rank lower overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| Arena image-to-video | 1415.3 ✎ | ▁▁▁▁▄▇▃▆▃▂▄█ beats 29/40 | 28% |
| Rapidata physics realism (I2V, with reference) | 1118.0 ✎ | ▂··▂▂▆█▆▂▂▆▄ beats 10/19 | 16% |
| What-If World causal-intervention video generation (APEO paired average, Gemini 3.1 Pro judge) | 51.7% ✎ | █·▄····▄···█ beats 5/5 | 2.5% |
| Physics-IQ Verified (I2V, best-practice prompts) | 34.8% ✎ | ██···█··█·██ beats 5/5 | 1.9% |
video editing▄··█··▄··█▄█ #7 of 9 * · 8.5% of its score · 1 test
| test | result | vs the others in its run | counts |
|---|---|---|---|
| Arena video edit | 1257.8 ✎ | █··█··▄··█▄█ beats 3/9 | 8.5% |
$ where to run it
Through an API
api · $0.050/sec · docs.x.ai ↗ · price sourceUSD per second of output video for grok-imagine-video; flat published rate, no resolution tiers listed on the current page. Not video-1.5 ($0.080/s). Currency: USD. xAI models and pricing documentation, observed 2026-09-25.
$ how the score was worked out · LMArena leaderboard dataset 79%, Rapidata/world-model-physics… 16%, What-If World: A Causal Bench… 2% and 1 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 | 3 | 79% |
 Rapidata/world-model-physics published dataset-card rankings | 1 | 16% |
 What-If World: A Causal Benchmark for General World Models in Embodied Scenarios (arXiv:2605.27589v1), Table 2 | 1 | 2% |
| Physics-IQ Verified | 1 | 2% |
| prior · pull toward the middle | 1% | |
| weighted average | = 68.9 |
$ 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