whatmodel.sh / video / Veo 3.1 Fast
Veo 3.1 Fast
↗ share
+ contribute
Veo 3.1 Fast is a closed-weights video model from Google, released October 2025. Licence: proprietary.
$ how it compares
The video models ranked either side of Veo 3.1 Fast, out of 139 with a score, then more from Google.
| # | model | score | where | ||
|---|---|---|---|---|---|
| 19 | Veo 3.1 | 69±1 | api $0.40/sec | ||
| 20 |  Sora 2 Pro | 68±2 | comparison only | ||
| 21 | Veo 3.1 Fast | 68±1 | api $0.10/sec | ||
| 22 |  Kling 3.0 | 68±4 | api $0.084/sec | ||
| 23 |  Wan 2.7 | 68±2 | api $0.10/sec | ||
| more from Google | |||||
| 1 |  Gemini Omni 1.1 Flash | 81±2 | api $0.10/sec | ||
| 3 | Gemini Omni Flash | 80±2 | api $0.10/sec | ||
| 25 | Veo 3 Fast | 65±2 | comparison only | ||
$ what it's good at
text to video▆▄▃▄▆▅█▃▂▃▂▄ #11 of 68 · 38% of its score · 4 tests
Beats Grok Imagine Video here, though they rank higher overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| LMArena video | 1361.9 ✎ | ▂▂▃▆█▆·▆▅▁▂▇ beats 30/41 | 31% |
| WorldJen human preference (Bradley-Terry) | 1614.0 ✎ | █···██·█··██ beats 5/5 | 4.4% |
| Sci-VBench testmini (expert human rating) | 55.8% ✎ | ▅·▃█▃·▅▃▅▃▃▃ beats 10/14 | 2.7% |
| HumanScore (T2V) | 85.9% ✎ | ▂··▂··█▄▂··▆ beats 5/11 | 0.7% |
image to video▁▂·▂▅█▅▄▅▆▃▄ #15 of 50 · 61% of its score · 4 tests
Beats HappyHorse 1.1, Veo 3.1 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 |
|---|---|---|---|
| WorldReasonBench human Elo (image+text-to-video world-state prediction) | 1253.0 ✎ | ▃▃··█··▃▃▃·▃ beats 7/8 | 21% |
| Arena image-to-video | 1385.1 ✎ | ▁▁▁▁▄▇▃▆▃▃▄█ beats 27/40 | 20% |
| Rapidata physics realism (I2V, with reference) | 1068.0 ✎ | ▂··▂▂▆█▆▂▂▆▄ beats 7/19 | 12% |
| Target-Bench v2 (VGGT planning score, I2V) | 19.2% ✎ | ▃·▃···▃▃█·▃▃ beats 3/8 | 7.7% |
$ where to run it
Through an API
api · $0.10/sec · ai.google.dev ↗ · price sourceUSD per generated video second at 720p WITH audio on Gemini Developer API. Only successfully generated videos billed; other resolutions differ. Product: Gemini Developer API. API model: veo-3.1-fast-generate-preview. Settings: resolution=720p, audio=yes, tier=paid. Price basis: per second of successfully generated output. Currency: USD.
$ how the score was worked out · LMArena leaderboard dataset 51%, WorldReasonBench: Human-Align… 21%, Rapidata/world-model-physics… 12% and 4 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
$ 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