Private AI
Native 4K Kling O3 model for text-to-video, image-to-video, and reference-to-video generation. Supports start/end frame control, up to 7 reference images, and 3-15 second durations.
Added Apr 23, 2026
Approx. Price
$2.10 per video
Model Type
both
Generation controls available for this model.
Output Format
Default Duration
5
13 duration options
Aspect Ratio
Default
16:9
Options (3)
Landscape (16:9), Portrait (9:16), Square (1:1)
Output aspect ratio
Duration
Default
5
Options (13)
3 seconds, 4 seconds, 5 seconds, 6 seconds +9 more
Video duration in seconds
Generate Audio
Default
No
Enable native audio generation
Human preference benchmarks sourced from Artificial Analysis.
Text to Video
#13 / 77
ELO
1215.0
Appearances
6,087
95% CI
-8/8
Image to Video
#17 / 71
ELO
1265.0
Appearances
5,537
95% CI
-9/9
Release Date 2026-02 · Matched as Kling 3.0 Omni 720p (Standard)
Artificial Analysis APILoading examples…