whatmodel.sh / video / Wan 3.0 Prime
Wan 3.0 Prime
↗ share
+ contribute
Wan 3.0 Prime is a closed-weights video model from Alibaba, released August 2026. Licence: proprietary.
Catalogue identity notes
Alibaba's speed-optimised Wan 3.0 SKU, a separate Model Studio model ID (wan3.0-video-prime) with its own price, released 2026-08-20. Alibaba: 'Wan3.0-Video-Prime is the high-speed version of the Wan3.0 video generation model, with capabilities aligned with the Wan3.0-Video standard version.' Kept separate from wan-3-0 (wan3.0-video) in the same way as other speed tiers (veo-3-1-fast). The WROP paper (arXiv:2609.28654v1) ran 'Wan 3.0 Prime' through the FAL API in reference-to-video mode.
Model information sources
$ how it compares
The video models ranked either side of Wan 3.0 Prime, out of 139 with a score, then more from Alibaba.
| # | model | score | where | ||
|---|---|---|---|---|---|
| 1 |  Gemini Omni 1.1 Flash | 81±2 | api $0.10/sec | ||
| 2 | Wan 3.0 Prime | 80±7 | api $0.14/sec | ||
| 3 | Gemini Omni Flash | 80±2 | api $0.10/sec | ||
| 4 | Wan 3.0 | 79±2 | api $0.10/sec | ||
| 5 |  Dreamina Seedance 2.0 | 79±1 | api $0.30/sec | ||
| more from Alibaba | |||||
| 9 | HappyHorse 1.1 | 76±3 | api $0.14/sec | ||
| 14 | Wan 2.2 I2V Flash | 75±4 | api $0.036/sec | ||
| 16 | Wan 2.2 I2V Plus | 71±5 | api $0.10/sec | ||
$ what it's good at
other tests1 not in a task · 81% of its score
| test | result | vs the others in its run | counts |
|---|---|---|---|
| WROP object-permanence exam (human Elo) | 1723.6 ✎ | ▄····██···▄█ beats 6/7 | 81% |
$ where to run it
Through an API
api · Alibaba Cloud Model Studio · $0.14/sec · www.alibabacloud.com ↗ · price sourceUSD per second of video, 720P, International deployment (Singapore) list price. Product: Model Studio Wan 3.0 video generation. API model: wan3.0-video-prime (not wan3.0-video, $0.1/s at 720P). Settings: resolution=720P. Price basis: published list price; no discount shown for this model. Pricing rule on the page: input and output videos are both billed by duration (billable duration = input + output), so video-to-video costs more. 480P $0.068/s, 1080P $0.28/s; Global deployments list $0.127199/s at 720P. Free quota (30 s, Singapore only) excluded. Currency: USD. Alibaba Cloud Model Studio pricing page, observed 2026-10-09.
$ how the score was worked out · Training Object Permanence in… 81%
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 |
|---|---|---|
 Training Object Permanence in World Models (WROP exam; arXiv:2609.28654v1) | 1 | 81% |
| prior · pull toward the middle | 19% | |
| weighted average | = 79.7 |
$ 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