whatmodel.sh / video / Hailuo 01 (MiniMax video-01 / I2V-01)
Hailuo 01 (MiniMax video-01 / I2V-01)
↗ share
+ contribute
Hailuo 01 (MiniMax video-01 / I2V-01) is a closed-weights video model from MiniMax, released August 2024.
Model information sources
$ how it compares
The video models ranked either side of Hailuo 01 (MiniMax video-01 / I2V-01), out of 139 with a score, then more from MiniMax.
| # | model | score | where | ||
|---|---|---|---|---|---|
| 85 | 46±4 | local | |||
| 86 | 46±3 | local | |||
| 87 | 46±4 | api $0.083/sec | |||
| 88 | 45±5 | comparison only | |||
| 89 | 45±7 | comparison only | |||
| more from MiniMax | |||||
| 6 | 78±1 | api $0.13/sec +local | |||
| 10 | 76±4 | api $0.080/sec | |||
| 48 | 55±2 | api $0.047/sec | |||
$ what it's good at
text to video▆▄▃▄▆▅█▃▂▂▂▄ #40 of 68 * · 47% of its score · 1 test
Beats Wan 2.2 TI2V 5B here, though they rank higher overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| SkyReels-Bench T2V (human rating) | 60.0% ✎ | ▄····▄···█·▄ beats 3/4 | 47% |
image to video▁▂·▂▅█▅▄▅▆▃▄ #41 of 50 * · 47% of its score · 1 test
Beats HunyuanVideo 1.5, Wan 2.2 A14B, LTX-2 here, though they rank higher overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| SkyReels-Bench I2V (human rating) | 61.0% ✎ | ▄···▄······█ beats 1/3 | 47% |
$ where to run it
Through an API
api · fal.ai · $0.083/sec · fal.ai ↗ · price sourceUSD per second of 720p video, derived from fal's $0.50 per video for MiniMax Video 01 image-to-video, whose page states Resolution 1280x720 (720p), 25 fps, Video Duration 6 sec (÷ 6 = $0.083333). Product: fal partner API (MiniMax Hailuo AI Video 01). API model: fal-ai/minimax/video-01/image-to-video. Settings: 720p, 6 s, one video. Price basis: published per-video price ÷ the duration fal states. MiniMax's own pay-as-you-go page no longer lists video-01 (only Hailuo-02/2.3 as legacy). Currency: USD. Not a MiniMax direct tariff. fal.ai official model page, observed 2026-09-26.
$ how the score was worked out · SkyReels-V2: Infinite-length… 94%
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 |
|---|---|---|
| 2 | 94% | |
| prior · pull toward the middle | 6% | |
| weighted average | = 45.7 |
$ 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