whatmodel.sh / video / Wan 2.1 I2V Turbo
Wan 2.1 I2V Turbo
↗ share
+ contribute
Wan 2.1 I2V Turbo is a closed-weights video model from Alibaba, released February 2025. Licence: proprietary.
Catalogue identity notes
Alibaba Cloud Model Studio API model wan2.1-i2v-turbo (formerly wanx2.1-i2v-turbo) (image-to-video; 480P or 720P, 3-5 s per the image-to-video API reference; released 2025-02-27); international release date from Model Studio's 'newly released models' page (https://www.alibabacloud.com/help/en/model-studio/newly-released-models, observed 2026-09-29). Commercial API tier; not assumed identical to any open Wan checkpoint. No price recorded (no approved price_source read for this tier).
$ how it compares
The video models ranked either side of Wan 2.1 I2V Turbo, out of 139 with a score, then more from Alibaba.
| # | model | score | where | ||
|---|---|---|---|---|---|
| 91 |  CogVideoX-5B | 44±2 | api price unknown +local | ||
| 92 |  Step-Video-TI2V | 44±7 | comparison only | ||
| 93 | Wan 2.1 I2V Turbo | 43±7 | api price unknown | ||
| 94 |  Ray 2 | 43±2 | comparison only | ||
| 95 |  Open-Sora 2.0 | 42±5 | local | ||
| more from Alibaba | |||||
| 2 | Wan 3.0 Prime | 80±7 | api $0.14/sec | ||
| 4 | Wan 3.0 | 79±2 | api $0.10/sec | ||
| 9 | HappyHorse 1.1 | 76±3 | api $0.14/sec | ||
$ what it's good at
image to video▁▂·▂▅█▅▄▅▆▃▄ #44 of 50 * · 79% of its score · 1 test
Beats Wan 2.2 A14B, LTX-2, HunyuanVideo-I2V here, though they rank higher overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| Target-Bench v2 (VGGT planning score, I2V) | 5.9% ✎ | ▃·▃···▃▃█·▃▃ beats 0/8 | 79% |
$ where to run it
Through an API
api · Alibaba Cloud Model Studio · price unknown · www.alibabacloud.com ↗
$ how the score was worked out · Target-Bench: Can Video World… 79%
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 |
|---|---|---|
 Target-Bench: Can Video World Models Achieve Mapless Path Planning with Semantic Targets? | 1 | 79% |
| prior · pull toward the middle | 21% | |
| weighted average | = 42.9 |
$ 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