# Kling Video · v3 · Pro · Motion Control API

> Transferencia de movimiento del nivel Pro que aplica el movimiento de un personaje en un video de referencia a una imagen de personaje

Combina una imagen de personaje en `image_url` con movimientos de un video de referencia en `video_url`. `character_orientation` es obligatorio y determina si la orientación sigue la imagen o el video. Se admite un `prompt` opcional de hasta 2500 caracteres, `keep_original_sound` conserva el audio de referencia y se puede vincular un elemento facial mediante `elements` para ayudar a preservar la identidad.

- Model id: `kling-video/v3/pro/motion-control`
- Made by: Kling
- Category: Video to Video
- Output: video
- Price per second of your input video: $0.168 / second of input video (cheapest run $0.168 (168 API credits))
- Run: `POST https://api.doitong.com/v1/run/kling-video/v3/pro/motion-control`
- Quote: `POST https://api.doitong.com/v1/quote/kling-video/v3/pro/motion-control`
- Docs page: https://doitong.com/es/developers/models/kling-video/v3/pro/motion-control

## Pricing

Price: **$0.168 / second of input video**. Price per second of your input video: the input files are measured before the run (length, resolution, frame rate). The quote measures the same files and is exactly what the run charges.

The full example input below costs $1.68 = 1680 API credits (10 s input video × $0.168).

Prices are the upstream price in USD, paid from the API balance in API credits (1000 API credits = 1 USD). `POST https://api.doitong.com/v1/quote/kling-video/v3/pro/motion-control` with the same JSON body returns the exact price for that input; the quote is exactly what a run charges. Invalid input is never charged and failed or canceled requests are refunded automatically.

## Input parameters

Send either the canonical name or the native field name (not both). Canonical names are the same across models.

| Parameter | Canonical name | Type | Required | Default | Allowed values / range | Description |
|---|---|---|---|---|---|---|
| `enable_safety_checker` |  | boolean | no | `true` |  | Las comprobaciones de seguridad solo se pueden desactivar con autorización de la cuenta; las solicitudes sin autorización siempre se someten a comprobación. |
| `prompt` |  | string \| null | no |  | ≤ 2500 characters |  |
| `image_url` | `image` | string (image URL) | yes |  |  | URL de imagen de referencia para la generación del video, con un límite de tamaño de archivo de 10.0MB, un ancho y una altura de entre 340px y 3850px, y una proporción de 0.40 a 2.50. Esta imagen guía los personajes, fondos y otros elementos del video. Para los personajes, asegúrate de que las proporciones corporales sean claras, no haya oclusiones y la cobertura supere el 5% del área de la imagen. |
| `video_url` | `video` | string (video URL) | yes |  |  | URL que apunta al video cuyas acciones del personaje guían la salida; debe mostrar un personaje de estilo realista y sin obstrucciones, con la cabeza y el cuerpo completo o la parte superior del cuerpo visibles. La configuración character_orientation limita la duración a 10s para 'image' o 30s para 'video'. Límites del archivo: 100 MB como máximo, ancho y altura de entre 340px y 3850px, y duración de entre 3.0s y 30.05s. |
| `keep_original_sound` |  | boolean | no | `true` |  | Controla la conservación del sonido original del video de referencia. |
| `character_orientation` |  | enum (string) | yes |  | `image`, `video` | Fuente de orientación del personaje: 'image' coincide con la imagen de referencia y es mejor para seguir los movimientos de cámara, con un máximo de 10 segundos. Para movimientos complejos, 'video' es mejor: coincide con la orientación del video de referencia y permite hasta 30 segundos. |
| `elements` |  | array of object {frontal_image_url, reference_image_urls} \| null | no |  |  | Vinculación facial opcional para mejorar la conservación de la identidad en el video de salida, limitada a 1 elemento cargado. Usa @Element1 para hacer referencia a él en el prompt. La vinculación solo está disponible con character_orientation establecido en 'video'. |
| `elements[].frontal_image_url` |  | string (image URL) \| null | no |  |  | Imagen frontal que muestra la vista principal del elemento. El tamaño del archivo no debe superar 50 MB; el ancho y la altura deben ser de al menos 300px cada uno, con una proporción de entre 0.40 y 2.50. |
| `elements[].reference_image_urls` |  | array of image URL \| null | no |  |  | Proporciona entre 1–3 imágenes de referencia adicionales que muestren distintos ángulos. Cada imagen debe tener una proporción de entre 0.40 y 2.50, medir al menos 300px en ambas dimensiones y no superar 50.0MB. |

File parameters (`image`, `video`) take a public `https://` URL, a `data:` URI up to 10 MB, or the `file_url` of an upload from `POST /files`.

## Example input

Required parameters only:

```json
{
  "image": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg",
  "video": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4",
  "character_orientation": "image"
}
```

A fuller example:

```json
{
  "image_url": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg",
  "video_url": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4",
  "character_orientation": "image"
}
```

## Run it

Set `DOITONG_API_KEY` to a key from https://doitong.com/developers/dashboard#keys. `?wait=20` returns the finished request in the same call when it is ready within 20 seconds; otherwise poll `GET /requests/{id}` (it also accepts `?wait=`), or pass `webhook_url`.

### curl

```bash
# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://api.doitong.com/v1/run/kling-video/v3/pro/motion-control?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "image_url": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg",
    "video_url": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4",
    "character_orientation": "image"
  }'

# Still "queued" or "running"? Poll with the id from the response:
curl "https://api.doitong.com/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"
```

### JavaScript

```javascript
const API = "https://api.doitong.com/v1";
const headers = {
  "Authorization": "Bearer " + process.env.DOITONG_API_KEY,
  "Content-Type": "application/json",
};

// Run the model; wait up to 20 s for the finished result in the same call
let res = await fetch(API + "/run/kling-video/v3/pro/motion-control?wait=20", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "image_url": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg",
    "video_url": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4",
    "character_orientation": "image"
  }),
});
let request = await res.json();
if (!res.ok) throw new Error(request.error.code + ": " + request.error.message);

// Not finished yet: long-poll until it is
while (request.status === "queued" || request.status === "running") {
  res = await fetch(API + "/requests/" + request.id + "?wait=20", { headers });
  request = await res.json();
}
if (request.status !== "succeeded") throw new Error(JSON.stringify(request.error));
console.log(request.outputs.map((o) => o.url), request.cost.credits + " API credits ($" + request.cost.usd + ")");
```

### Python

```python
import os
import requests

API = "https://api.doitong.com/v1"
headers = {"Authorization": "Bearer " + os.environ["DOITONG_API_KEY"]}

payload = {
    "image_url": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg",
    "video_url": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4",
    "character_orientation": "image",
}

# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/kling-video/v3/pro/motion-control", params={"wait": 20}, json=payload, headers=headers)
request = r.json()
if not r.ok:
    raise RuntimeError(request["error"]["code"] + ": " + request["error"]["message"])

# Not finished yet: long-poll until it is
while request["status"] in ("queued", "running"):
    request = requests.get(API + "/requests/" + request["id"], params={"wait": 20}, headers=headers).json()
if request["status"] != "succeeded":
    raise RuntimeError(request["error"])
print([o["url"] for o in request["outputs"]], request["cost"]["credits"], "API credits", "$" + request["cost"]["usd"])
```

### MCP

The MCP server at `https://api.doitong.com/v1/mcp` exposes the tools `search_models`, `get_model`, `quote`, `run`, `get_request`, `cancel_request`, `list_requests`, `create_upload` and `get_account`. A `run` call for this model:

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "run",
    "arguments": {
      "model_id": "kling-video/v3/pro/motion-control",
      "input": {
        "image_url": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg",
        "video_url": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4",
        "character_orientation": "image"
      },
      "wait_seconds": 20
    }
  }
}
```

## Response

Every call returns a request object. `status` is one of `queued`, `running`, `succeeded`, `failed`, `canceled`. `outputs` lists the generated files with URLs on our storage (kept forever, or 7 days with `?storage=temporary`; `storage` says which); `output` is the model's own result object with the same URLs.

```json
{
  "id": "req_8k2m4q7x1z9c3v5b6n0p2r4t",
  "object": "request",
  "model": "kling-video/v3/pro/motion-control",
  "status": "succeeded",
  "created_at": "2026-10-20T12:00:00Z",
  "started_at": "2026-10-20T12:00:02Z",
  "completed_at": "2026-10-20T12:00:09Z",
  "queue_position": null,
  "cost": {
    "credits": 1680,
    "usd": "1.68",
    "charged": 1680,
    "refunded": 0
  },
  "input": {
    "image_url": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg",
    "video_url": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4",
    "character_orientation": "image"
  },
  "output": {
    "video": {
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.mp4",
      "content_type": "video/mp4",
      "file_name": "0-output.mp4",
      "file_size": 1843200
    }
  },
  "outputs": [
    {
      "type": "video",
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.mp4",
      "content_type": "video/mp4",
      "file_size": 1843200,
      "width": 1280,
      "height": 720,
      "duration": 5,
      "stored": true
    }
  ],
  "error": null,
  "metrics": {
    "inference_seconds": 6.8
  },
  "urls": {
    "self": "https://api.doitong.com/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t",
    "cancel": "https://api.doitong.com/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t/cancel"
  }
}
```

### Output fields (`output`)

| Field | Type | Description |
|---|---|---|
| `video` | object {url, content_type, file_name, file_size} | Video producido por el modelo. |

## Related models

- [Kling Video · v3 · Standard · Motion Control](https://doitong.com/developers/models/kling-video/v3/standard/motion-control.md) (`kling-video/v3/standard/motion-control`): $0.126 / second of input video
- [Kling O1 Edit Video \[Pro\]](https://doitong.com/developers/models/kling-video/o1/video-to-video/edit.md) (`kling-video/o1/video-to-video/edit`): $0.168 / second of input video
- [Kling O1 Edit Video \[Standard\]](https://doitong.com/developers/models/kling-video/o1/standard/video-to-video/edit.md) (`kling-video/o1/standard/video-to-video/edit`): $0.126 / second of input video
- [Kling O1 Reference Video to Video \[Pro\]](https://doitong.com/developers/models/kling-video/o1/video-to-video/reference.md) (`kling-video/o1/video-to-video/reference`): $0.168 / second
- [Kling O1 Reference Video to Video \[Standard\]](https://doitong.com/developers/models/kling-video/o1/standard/video-to-video/reference.md) (`kling-video/o1/standard/video-to-video/reference`): $0.126 / second
- [Kling O3 Edit Video \[Pro\]](https://doitong.com/developers/models/kling-video/o3/pro/video-to-video/edit.md) (`kling-video/o3/pro/video-to-video/edit`): $0.168 / second of input video
- [Kling O3 Edit Video \[Standard\]](https://doitong.com/developers/models/kling-video/o3/standard/video-to-video/edit.md) (`kling-video/o3/standard/video-to-video/edit`): $0.126 / second of input video
- [Kling O3 Reference Video to Video \[Pro\]](https://doitong.com/developers/models/kling-video/o3/pro/video-to-video/reference.md) (`kling-video/o3/pro/video-to-video/reference`): $0.168 / second

## Links

- HTML page: https://doitong.com/developers/models/kling-video/v3/pro/motion-control
- All models and guides for AI agents: https://doitong.com/developers/llms.txt
- OpenAPI 3.1 with this model's typed request body: https://doitong.com/developers/openapi.json?model=kling-video/v3/pro/motion-control
- Errors: https://doitong.com/developers/docs/errors
- Model details as JSON: https://api.doitong.com/v1/models/kling-video/v3/pro/motion-control