whatmodel.sh / video / Kling 2.1 Master
Kling 2.1 Master
↗ share
+ contribute
Kling 2.1 Master is a closed-weights video model from Kuaishou (Kling AI), released May 2025.
Model information sources
$ how it compares
The video models ranked either side of Kling 2.1 Master, out of 139 with a score, then more from Kuaishou (Kling AI).
| # | model | score | where | ||
|---|---|---|---|---|---|
| 54 |  Vidu Q2 Pro | 53±3 | comparison only | ||
| 55 |  HunyuanVideo 1.5 (I2V) | 53±2 | api $0.075/sec +local | ||
| 56 | Kling 2.1 Master | 53±2 | api $0.28/sec | ||
| 57 |  Kandinsky 5.0 Pro | 52±2 | api $0.040/sec +local | ||
| 58 |  HY-OmniWeaving | 52±4 | comparison only | ||
| more from Kuaishou (Kling AI) | |||||
| 22 | Kling 3.0 | 68±4 | api $0.084/sec | ||
| 31 | Kling O3 Pro | 64±4 | api $0.11/sec | ||
| 34 | Kling 2.6 Pro | 59±2 | api $0.070/sec | ||
$ what it's good at
text to video▆▄▃▄▆▅█▃▂▂▂▄ #32 of 68 * · 59% of its score · 1 test
Trails PixVerse 5.5, Cosmos3-Nano, HunyuanVideo 1.5 here, though they rank lower overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| LMArena video | 1162.9 ✎ | ▂▂▃▆█▆·▆▅▁▂▇ beats 8/41 | 59% |
image to video▁▂·▂▅█▅▄▅▆▃▄ #36 of 50 * · 39% of its score · 1 test
Beats Seedance 1.5 Pro, Kling 2.1 Standard, HunyuanVideo 1.5 (I2V) here, though they rank higher overall. Trails Cosmos3-Nano here, though they rank lower overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| Arena image-to-video | 1235.0 ✎ | ▁▁▁▁▄▇▃▆▃▂▄█ beats 12/40 | 39% |
$ where to run it
Through an API
api · Replicate · $0.28/sec · replicate.com ↗ · price sourceUSD per second of output video, 1080p: Replicate's official kwaivgi/kling-v2.1-master ('Generate 1080p 5s and 10s videos from text or an image') is billed $0.28 per second of output video. Product: Replicate model API. API model: kwaivgi/kling-v2.1-master. Settings: 1080p, text-to-video or image-to-video. Price basis: published per-second-of-output list rate. Flag: fal lists its Kling 2.1 Master endpoints as deprecated and Kling's own developer pricing page no longer prices 2.1; the Replicate model is online. Currency: USD. Not a Kling direct tariff. Replicate official model page, observed 2026-09-26.
$ how the score was worked out · LMArena leaderboard dataset 99%
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 | 2 | 99% |
| prior · pull toward the middle | 1% | |
| weighted average | = 52.5 |
$ 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