Video

Kling 3.0 Motion Control API

Kling 3.0 Motion Control transfers the motion from a reference video onto the character in a reference image, so one video generation call reanimates any character with the exact actions of your driving clip. Upload a character image and a motion video, pick Standard or Pro, and the Kling 3.0 Motion Control API returns a new clip through async jobs and webhooks. It runs on Apiframe with no separate Kling AI account to manage.

Get API key Read the docs

~150s
Avg. generation: 5 credits/s
From

Video · made with Kling 3.0

Cinematic push-in on a barista pouring rust-colored latte art into a white Ember Coffee cup, steam, warm tungsten, gentle cafe sound.

Playground

Try Kling 3.0 Motion Control right here.

model: kling-3.0-motion-control

Prompt

Mode

Character orientation

Media inputs

Character image Reference video

Advanced settings

Keep original sound Keep the reference video’s original audio track.

Estimated cost 5–8 credits per second Generate in Studio

Output Example · Kling 3.0

Cinematic push-in on a barista pouring rust-colored latte art into a white Ember Coffee cup, steam, warm tungsten, gentle cafe sound.

Pricing

Simple per-second pricing.

5–8 credits per second of output ≈ $0.05–$0.08

The rate depends on the resolution and options you pick.

You only pay for successful generations. Failed jobs are refunded automatically.
One credit balance across every model on Apiframe, no per-model plans.
Start with free credits. No subscription required.
Volume discounts on larger plans.

See plans and credit packs

Specs

At a glance.

Provider Kuaishou

Model ID kling-3.0-motion-control

Image input Supported

Avg. time ~150s

Quickstart

How to call the Kling 3.0 Motion Control API.

Send one POST /v2/videos/generate request with your API key. The call returns a jobId you can poll, or pass a webhook_url and the result is pushed to you the moment it's ready.

Swap kling-3.0-motion-control for any other model and nothing else changes.

Get API key Read the docs

generate.js

const response = await fetch("https://api.apiframe.ai/v2/videos/generate", {
  method: "POST",
  headers: {
    "X-API-Key": "afk_your_api_key_here",
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "prompt": "a cinematic sunrise over a futuristic cityscape, smooth camera push-in",
    "model": "kling-3.0-motion-control",
    "klingParams": {
      "image": "https://example.com/input.jpg",
      "video": "https://example.com/input.jpg",
      "mode": "pro",
      "character_orientation": "image"
    }
  }),
});
const { jobId } = await response.json();
console.log(jobId);

import requests

response = requests.post(
    "https://api.apiframe.ai/v2/videos/generate",
    headers={
        "X-API-Key": "afk_your_api_key_here",
        "Content-Type": "application/json",
    },
    json={
        "prompt": "a cinematic sunrise over a futuristic cityscape, smooth camera push-in",
        "model": "kling-3.0-motion-control",
        "klingParams": {
            "image": "https://example.com/input.jpg",
            "video": "https://example.com/input.jpg",
            "mode": "pro",
            "character_orientation": "image"
        }
    },
)
print(response.json())  # { "jobId": "...", "status": "QUEUED" }

curl -X POST https://api.apiframe.ai/v2/videos/generate \
  -H "X-API-Key: afk_your_api_key_here" \
  -H "Content-Type: application/json" \
  -d '{
        "prompt": "a cinematic sunrise over a futuristic cityscape, smooth camera push-in",
        "model": "kling-3.0-motion-control",
        "klingParams": {
            "image": "https://example.com/input.jpg",
            "video": "https://example.com/input.jpg",
            "mode": "pro",
            "character_orientation": "image"
        }
    }'

let job;
do {
  await new Promise((r) => setTimeout(r, 2000));
  job = await fetch("https://api.apiframe.ai/v2/jobs/JOB_ID", {
    headers: { "X-API-Key": "afk_your_api_key_here" },
  }).then((r) => r.json());
} while (job.status !== "COMPLETED" && job.status !== "FAILED");
console.log(job.result);

import requests, time

while True:
    job = requests.get(
        "https://api.apiframe.ai/v2/jobs/JOB_ID",
        headers={"X-API-Key": "afk_your_api_key_here"},
    ).json()
    if job["status"] in ("COMPLETED", "FAILED"):
        break
    time.sleep(2)
print(job["result"])

curl https://api.apiframe.ai/v2/jobs/JOB_ID \
  -H "X-API-Key: afk_your_api_key_here"

Input schema

Every field Kling 3.0 Motion Control accepts, with types and defaults. The full reference lives in the docs.

Field	Type	Description
prompt required	string	Text description of what to generate.
model required	string	The model identifier for this endpoint. Default:"kling-3.0-motion-control" · "kling-3.0-motion-control"
klingParams.image	string (URL)	Reference image the generated character is based on.
klingParams.video	string (URL)	Motion reference clip (3–30s). The character mirrors its actions.
klingParams.mode	string	Mode Default:"pro" · "std", "pro"
klingParams.character_orientation	string	Whether the character faces as in the image or follows the video. Default:"image" · "image", "video"
klingParams.keep_original_sound	boolean	Keep the reference video’s original audio track. Default:true

The Kling flagship

Kling 3.0 Motion Control is one of 6 Kling video models on Apiframe. The full editorial page (showcase, comparison, and use cases) lives on the flagship.

Flagship from 11 cr/s Kling 3.0

Multi-shot video with pro-grade 4K modes.

Explore Kling 3.0 All video models

Kling 3.0 Motion Control questions

What teams ask before shipping with Kling 3.0 Motion Control. Everything else lives in the docs.

What is Kling 3.0 Motion Control?

Kling 3.0 Motion Control is a Kuaishou Kling model that transfers motion from a reference video onto a character image. You provide a character image and a motion reference clip, and the model generates a new video where your character performs the actions from the reference video with improved consistency and quality.

How do I call the Kling 3.0 Motion Control API?

Get an api key, then send a POST request to the video generation endpoint with model set to kling-3.0-motion-control and klingParams containing an image URL and a video URL. The request returns a task id; poll it or use a webhook to fetch the generated video. Apiframe gives you Kling video behind one AI API and key.

What inputs are required?

Both a reference image and a reference video are required. The image supplies the character and scene; the video supplies the motion. You can optionally set mode (std or pro), character_orientation (image or video), and keep_original_sound.

How long can the reference video be?

When character_orientation is "image", the reference video can be up to 10 seconds. When it is "video", the clip can be up to 30 seconds. The reference video should be 3 seconds or longer. Requests outside that range are rejected before any credits are charged.

How is Kling 3.0 Motion Control priced?

Pricing is per second of the reference video: 5 credits per second in Standard (std) mode and 8 credits per second in Pro (pro) mode. The billed duration is measured from the reference clip you upload, so a 5-second Pro request costs 40 credits.

What is the difference between Standard and Pro mode?

Standard mode renders at 720p and is the cost-effective option; Pro mode renders at 1080p for higher quality. Pick the tier per request to balance cost and fidelity.