Private AI
Kling 3.0 Standard delivers high-quality text-to-video and image-to-video with smooth motion, cinematic visuals, and strong prompt adherence. Upload an image to switch to image-to-video, with optional native audio.
Added Feb 4, 2026
Approx. Price
$0.252 per video
Model Type
both
Generation controls available for this model.
Output Format
Default Duration
5
13 duration options
Aspect Ratio (T2V)
Default
16:9
Options (3)
Landscape (16:9), Portrait (9:16), Square (1:1)
Applies to text-to-video
Audio
Default
No
Generate sound with the video
CFG Scale
Default
0.5
Higher values follow the prompt more strictly
Duration
Default
5
Options (13)
3 seconds, 4 seconds, 5 seconds, 6 seconds +9 more
3 to 15 seconds
Element List (JSON)
Optional JSON array for the element_list field. Create reusable element IDs with Kling Elements.
Human preference benchmarks sourced from Artificial Analysis.
Text to Video
#20 / 86
ELO
1214.0
Appearances
6,639
95% CI
-8/8
Image to Video
#21 / 79
ELO
1264.0
Appearances
6,272
95% CI
-9/9
Release Date 2026-02 · Matched as Kling 3.0 720p (Standard)
Artificial Analysis APIMulti Prompt (JSON)
Optional JSON array for the multi_prompt field, useful for multi-shot or complex compositions.