Kling 3.0 Standard
kling-v30-stdKling 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.
Pricing
Includes our margin. Charged per request from your balance.
Per duration
- 3 s
- $0.28
- 4 s
- $0.37
- 5 s
- $0.46
- 6 s
- $0.55
- 7 s
- $0.65
- 8 s
- $0.74
- 9 s
- $0.83
- 10 s
- $0.92
- 11 s
- $1.02
- 12 s
- $1.11
- 13 s
- $1.20
- 14 s
- $1.29
- 15 s
- $1.39
- Audio multiplier
- ×1.5
Details
- Provider
- Kling
- Added
- Feb 4, 2026
Options
Parameters this model accepts.
| Parameter | Values | Default |
|---|---|---|
soundGenerate sound with the video | On or off Default | off |
duration3 to 15 seconds | 3–15 seconds Default | 5 |
cfg_scaleHigher values follow the prompt more strictly | 0 to 1 Default | 0.5 |
aspect_ratioApplies to text-to-video | Landscape (16:9), Portrait (9:16), Square (1:1) Default | 16:9 |
element_listOptional JSON array for the element_list field. Applies only with a start image. Create reusable element IDs with Kling Elements. | Text | — |
multi_promptOptional JSON array for the multi_prompt field, useful for multi-shot or complex compositions. | Text | — |