whatmodel.sh / video / Kling O1 Pro
Kling O1 Pro
↗ share
+ contribute
Kling O1 Pro is a closed-weights video model from Kuaishou (Kling AI).
$ how it compares
The video models ranked either side of Kling O1 Pro, out of 139 with a score, then more from Kuaishou (Kling AI).
| # | model | score | where | ||
|---|---|---|---|---|---|
| 42 | 56±2 | api $0.080/sec +local | |||
| 43 | 56±2 | api $0.052/sec | |||
| 44 | 56±2 | api $0.11/sec | |||
| 45 | 55±7 | api $0.025/sec | |||
| 46 | 55±2 | api $0.020/sec | |||
| more from Kuaishou (Kling AI) | |||||
| 22 | 68±4 | api $0.084/sec | |||
| 31 | 64±4 | api $0.11/sec | |||
| 34 | 59±2 | api $0.070/sec | |||
$ what it's good at
text to video▆▄▃▄▆▅█▃▂▂▂▄ #25 of 68 * · 81% of its score · 1 test
Beats Seedance 1.0 Pro here, though they rank higher overall. Trails Hailuo 2.3, P-Video here, though they rank lower overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| LMArena video | 1204.6 ✎ | ▂▂▃▆█▆·▆▅▁▂▇ beats 14/41 | 81% |
video editing▄··█··▄··█▄█ #9 of 9 * · 17% of its score · 1 test
| test | result | vs the others in its run | counts |
|---|---|---|---|
| Arena video edit | 1197.3 ✎ | █··█··▄··█▄█ beats 1/9 | 17% |
$ where to run it
Through an API
api · Replicate · $0.11/sec · replicate.com ↗ · price sourceUSD per second of output video on Replicate's official kwaivgi/kling-o1 model, pro mode without video input. Other variants: std $0.084/s, std with video input $0.126/s, pro with video input (e.g. video editing) $0.168/s. Replicate does not state the output resolution per mode. Product: Replicate model API. API model: kwaivgi/kling-o1. Settings: mode=pro (the default), text prompt, no reference or edit video. Price basis: published per-second-of-output list rate. Kling's own developer pricing page lists no Kling O1 video price. Currency: USD. Not a Kling direct tariff. Replicate official model page, observed 2026-09-26.
$ how the score was worked out · LMArena leaderboard dataset 98%
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 | 98% | |
| prior · pull toward the middle | 2% | |
| weighted average | = 55.5 |
$ 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