Kling 4.0
kling-4.0Kling 4.0 by Kuaishou creates 3–30 second videos at 720p or 1080p with synchronized stereo audio. Generate from text or images, guide motion with ordered keyframes and image, video or audio references, edit existing footage, or append a new segment with an optional ending frame.
Pricing
Includes our margin. Charged per request from your balance.
- Minimum charge
- $0.57
Per second by resolution
- 720p
- $0.19
- 1080p
- $0.28
Video input per counted second by resolution
- 720p
- $0.11
- 1080p
- $0.17
- Available
- Yes
Video reference/edit: output seconds plus max(output seconds, combined input-video seconds capped at 30 and rounded up to the next whole second). Reference audio is not charged. Extension charges only new seconds. Input-video duration is verified before billing.
Details
- Provider
- Kling
- Added
- Oct 21, 2026
Options
Parameters this model accepts.
| Parameter | Values | Default |
|---|---|---|
mode | Text to video, Image to video, Reference to video, Edit video, Extend video Default | image-to-video |
duration | Follow source (edit only), 3 seconds, 4 seconds, 5 seconds, 6 seconds, 7 seconds, 8 seconds, 9 seconds, 10 seconds, 11 seconds, 12 seconds, 13 seconds, 14 seconds, 15 seconds, 16 seconds, 17 seconds, 18 seconds, 19 seconds, 20 seconds, 21 seconds, 22 seconds, 23 seconds, 24 seconds, 25 seconds, 26 seconds, 27 seconds, 28 seconds, 29 seconds, 30 seconds Default | 5 |
imageUrlRequired starting JPEG/PNG for image-to-video; optional first numbered image in reference mode. At most 30 MB. | Text | — |
videoUrlRequired source video in edit/extend mode. Extension returns the original plus new segment; only new seconds are charged. | Text | — |
keyframesOrdered middle JPEG/PNG frame URLs in image mode; start, end and middle frames share a 10-image limit. | Text | — |
resolution | 720p, 1080p Default | 1080p |
aspect_ratio | auto, 16:9, 9:16, 1:1, 21:9 Default | auto |
lastImageUrlOptional ending JPEG/PNG in image or extend mode. At most 30 MB. | Text | — |
reference_audiosReference mode: 5–30-second audio clips. All references share a 15-file limit. | Text | — |
reference_imagesReference/edit mode. Up to 10 images including the optional start frame. Prompt tags @Image1, @Image2. | Text | — |
reference_videosReference mode: up to 5 readable videos; at most 30 seconds combined are used. Billing requires verified whole-second input duration. | Text | — |
keep_original_sound | Default for mode, Keep original sound, Generate new sound Default | auto |