Kling Video O1
kling-video-o1Unified multi-modal model supporting text-only, image, video, or combined inputs.
Pricing
Includes our margin. Charged per request from your balance.
Per second by mode
- Text to video, Image to video, Reference to video image
- $0.12
- Video edit, Reference to video video
- $0.18
- Default duration
- 5 s
Duration billing: the larger of the requested duration and the output seconds submitted upstream; Standard text-to-video and image-to-video without an end frame run 5 or 10 seconds
Video edit billing: verified source-video seconds, rounded up and clamped to 3-10, and at least the requested duration
Details
- Provider
- Kling
- Added
- Dec 1, 2025
Options
Parameters this model accepts.
| Parameter | Values | Default |
|---|---|---|
modeHow to process video input: Edit modifies the video, Reference uses it as style guidance for new generation | Auto-detect, Edit Video, Reference to Video Default | auto |
durationVideo duration in seconds | 5 seconds, 10 seconds Default | 5 |
aspect_ratioVideo aspect ratio | 16:9 (Landscape), 9:16 (Portrait), 1:1 (Square) Default | 16:9 |
keep_original_soundPreserve original audio when using video input | Yes, No Default | true |