Kuaishou
Kling 3.0 Turbo
Kling 3.0 Turbo — Kuaishou's fast text-to-video and image-to-video model at 720p and 1080p, on one OpenAI-compatible endpoint.
From $0.126 per second
Kling Motion Control API — Reference-Driven Motion Transfer
Drive a single reference image with a reference video and the Kling Motion Control API transfers the motion onto your subject. Two tiers, std or pro quality, billed per second of source footage.
Input
Required · guides motion, camera, style
Public URL · JPEG / PNG / WebP
MP4 / MOV · public URL · 3 to 30s
image · video
std · pro
Default yes
Default off
Estimated cost566 credits≈ $0.566
Result
Try one of these prompts
What you can build with this model
Real-world workflows and production use cases you can build and ship with this model.
Bring a still subject to life with a reference clip
Upload a subject image and a short motion video. The Kling Motion Control API maps the reference motion onto your subject and returns a clip that keeps the original identity while adopting the movement, rhythm, and timing of the reference.
Generate a clipReuse one performance across many subjects
Record a single reference performance once, then swap the reference image to apply the same choreography to different characters. Consistent motion, different subjects — useful for avatars, mascots, and recurring social formats.
Match the take to your shot direction
Pick image orientation to anchor the facing to your reference photo, or video orientation to follow the reference clip and allow up to 30 seconds. Set keep_original_sound to carry the reference soundtrack into the output.
Pricing
Credit-based — 1 credit = $0.001 USD. Pay only for completed generations.
| Category | Unit | Price |
|---|---|---|
| Kling v3 | ||
| Standard mode | 1 second | $0.114 114 credits |
| Pro mode | 1 second | $0.151 151 credits |
| Kling v2.6 | ||
| Standard mode | 1 second | $0.063 63 credits |
| Pro mode | 1 second | $0.101 101 credits |
Why reAPI
Reference image plus reference video
The Kling Motion Control API reads the subject from a reference image and the motion from a reference video, so the output keeps identity while adopting the reference movement. No keyframes, no rigging.
Two tiers, one request shape
Kling Motion Control ships two tiers: Kling v3 maximizes motion fidelity and subject consistency, while Kling v2.6 is the budget tier with the same parameters. Switch tiers by changing one string — the request body is identical.
Pay for the seconds you use
Kling Motion Control billing is per second of the source video, measured server-side from the actual clip length rather than a client estimate. Pick std or pro to trade cost for quality. Failed jobs refund automatically.
Kling Motion Control vs Runway Act-Two
Both transfer motion from a driving video onto a target subject. Kling Motion Control takes a reference image plus a reference video, supports image or video orientation, and bills per second across two tiers. Here is how the two compare on publicly documented behavior.
Capability
Kling Motion Control on reAPI
Runway Act-Two
Motion source
In Kling Motion Control, a reference video drives the motion; the subject comes from a single reference image.
A driving performance video animates a character image or generated character.
Subject input
One reference image fixes the subject's appearance and identity.
A character image or a generated character reference.
Orientation control
Kling Motion Control's character_orientation picks whether facing follows the reference image or the reference video.
Facing follows the driving performance; no separate orientation switch documented.
Source audio
keep_original_sound retains the reference video's soundtrack in the output.
Audio is tied to the driving performance video.
Clip length
Kling Motion Control runs up to 10s with image orientation or 30s with video orientation, set by the source clip.
Short performance clips; length follows the driving video.
Pricing model
Kling Motion Control bills per second of probed source footage; two tiers trade cost for fidelity, pay-as-you-go credits.
Credit-based pricing tied to plan and resolution.
Comparison reflects publicly documented behavior at the time of writing. Model behavior and pricing can change; check the pricing card above and the API docs for current values.
Ship the Kling Motion Control API in three steps
- step 01
Create an API key
Sign up and grab a key from the dashboard. Free credits cover your first Kling Motion Control API calls — no card required.
Open - step 02
Submit a motion task
POST to /api/v1/videos/generations with model = kling-v3-motion-control, an image_url, a video_url, character_orientation, and mode. The Kling Motion Control API returns a task ID immediately.
Open - step 03
Poll the result
GET /api/v1/tasks/:id until status is completed. Download the generated Kling Motion Control clip from output.video_urls[0] and ship it.
Open
Frequently asked questions
Common questions about this model.
The Kling Motion Control API is a reference-driven motion-transfer video model. You pass a reference image (the subject) and a reference video (the motion), and Kling Motion Control returns a clip of your subject performing the reference motion. An optional prompt refines camera, motion, and style.
Related models
Explore more models in the same category.
Kuaishou
Kling 3.0
Kling 3.0 — Kuaishou's multi-shot video model with native audio, image-to-video, and up to 4K, on one OpenAI-compatible endpoint.
From $0.077 per second
—
Music Video 1.0
One song plus reference images becomes a finished music video in a single API call.
From $0.050 per second
Alibaba
Wan 2.7 Video
Text, image, reference video and editing in one Wan 2.7 Video API call — per-second pricing, 720P or 1080P.
From $0.073 per second
start building
Ready to ship?
Try it in the playground or grab an API key to integrate now.