# Kling O3 Reference Video to Video [Pro] API

> O3-Modell im Pro-Tarif, das anhand der Bewegung und des Kamerastils eines Referenzvideos neue Aufnahmen erstellt

Nimmt ein Referenzvideo (`video_url`, .mp4/.mov, 3-15 s, 720-3840px, maximal 200MB) und einen Prompt und erzeugt einen anhand der Referenz gesteuerten neuen Clip. Die Ausgabe-`duration` kann 3 bis 15 Sekunden betragen, `aspect_ratio` ist auto, 16:9, 9:16 oder 1:1. Referenzbilder und `elements` können insgesamt bis zu 4 hinzugefügt werden, und `keep_audio` steuert den Originalton.

- Model id: `kling-video/o3/pro/video-to-video/reference`
- Made by: Kling
- Category: Video to Video
- Output: video
- Price: $0.168 / second (3 s ≈ $0.504) (cheapest run $0.504 (504 API credits))
- Run: `POST https://api.doitong.ru/v1/run/kling-video/o3/pro/video-to-video/reference`
- Quote: `POST https://api.doitong.ru/v1/quote/kling-video/o3/pro/video-to-video/reference`
- Docs page: https://doitong.com/de/developers/models/kling-video/o3/pro/video-to-video/reference

## Pricing

Price: **$0.168 / second (3 s ≈ $0.504)**. Billed per second of output (`duration`, default 15).

The full example input below costs $2.52 = 2520 API credits (15 s × 168 API credits).

Prices are the upstream price in USD, paid from the API balance in API credits (1000 API credits = 1 USD). `POST https://api.doitong.ru/v1/quote/kling-video/o3/pro/video-to-video/reference` 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` |  | Sicherheitsprüfungen können nur mit einer Kontoberechtigung deaktiviert werden; Anfragen ohne Berechtigung werden immer geprüft. |
| `prompt` |  | string | yes |  | ≤ 2500 characters | Textanweisungen zur Videogenerierung. Verwende @Video1, um auf das Referenzvideo zu verweisen. |
| `video_url` | `video` | string (video URL) | yes |  |  | URL zu einem Referenzvideo im Format .mp4 oder .mov mit höchstens 200MB. Beide Abmessungen müssen zwischen 720px und 3840px liegen, die Bildrate zwischen 23.0–60.0 FPS und die Dauer zwischen 3–15 Sekunden (höchstens 15.05 Sekunden). |
| `image_urls` | `images` | array of image URL \| null | no |  |  | Bilder als Stil- oder Erscheinungsreferenzen, die im Prompt mit @Image1, @Image2 usw. angesprochen werden. Bei Videoeingabe dürfen Elemente und Referenzbilder zusammen höchstens 4 Einträge umfassen. Jede Datei ist auf 50 MB begrenzt; Breite und Höhe müssen jeweils mindestens 300 px betragen und das Seitenverhältnis muss zwischen 0.40 und 2.50 liegen. |
| `keep_audio` |  | boolean | no | `true` |  | Steuert, ob das ursprüngliche Audio des Referenzvideos beibehalten wird. |
| `elements` |  | array of object {frontal_image_url, reference_image_urls} \| null | no |  |  | Figuren oder Objekte, die aufgenommen und im Prompt mit @Element1 und @Element2 angesprochen werden. |
| `elements[].frontal_image_url` |  | string (image URL) \| null | no |  |  | Frontalbild mit der Hauptansicht des Elements. Die Dateigröße darf 50 MB nicht überschreiten; Breite und Höhe müssen jeweils mindestens 300px betragen, das Seitenverhältnis muss zwischen 0.40 und 2.50 liegen. |
| `elements[].reference_image_urls` |  | array of image URL \| null | no |  |  | Stelle 1–3 zusätzliche Referenzbilder aus verschiedenen Winkeln bereit. Jedes Bild muss ein Seitenverhältnis zwischen 0.40 und 2.50 haben, in beiden Abmessungen mindestens 300px messen und höchstens 50.0MB groß sein. |
| `shot_type` |  | string | no | `customize` |  | Modus zur Generierung von Videos mit mehreren Einstellungen. |
| `aspect_ratio` |  | enum (string) | no | `auto` | `auto`, `16:9`, `9:16`, `1:1` | Verhältnis von Breite zu Höhe. |
| `duration` |  | enum (string) \| null | no |  | `3`, `4`, `5`, `6`, `7`, `8`, `9`, `10`, `11`, `12`, `13`, `14`, `15` | Videolänge, gemessen in Sekunden; der Bereich des Referenzvideos beträgt 3–15s. |

File parameters (`video`, `images`) 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
{
  "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
  "video": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4"
}
```

A fuller example:

```json
{
  "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
  "video_url": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4"
}
```

## 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.ru/v1/run/kling-video/o3/pro/video-to-video/reference?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
    "video_url": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4"
  }'

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

### JavaScript

```javascript
const API = "https://api.doitong.ru/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/o3/pro/video-to-video/reference?wait=20", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
    "video_url": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4"
  }),
});
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.ru/v1"
headers = {"Authorization": "Bearer " + os.environ["DOITONG_API_KEY"]}

payload = {
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
    "video_url": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4",
}

# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/kling-video/o3/pro/video-to-video/reference", 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.ru/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/o3/pro/video-to-video/reference",
      "input": {
        "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
        "video_url": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4"
      },
      "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/o3/pro/video-to-video/reference",
  "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": 2520,
    "usd": "2.52",
    "charged": 2520,
    "refunded": 0
  },
  "input": {
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
    "video_url": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4"
  },
  "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.ru/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t",
    "cancel": "https://api.doitong.ru/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t/cancel"
  }
}
```

### Output fields (`output`)

| Field | Type | Description |
|---|---|---|
| `video` | object {url, content_type, file_name, file_size} | Vom Modell erzeugtes Video. |

## Related models

- [Kling O3 Text to Video \[Pro\]](https://doitong.com/developers/models/kling-video/o3/pro/text-to-video.md) (`kling-video/o3/pro/text-to-video`): from $0.112 / second
- [Kling O3 Text to Video \[Standard\]](https://doitong.com/developers/models/kling-video/o3/standard/text-to-video.md) (`kling-video/o3/standard/text-to-video`): from $0.084 / second
- [Kling Video · O3 · 4k · Text to Video](https://doitong.com/developers/models/kling-video/o3/4k/text-to-video.md) (`kling-video/o3/4k/text-to-video`): $0.42 / second
- [Kling O3 Image to Video · Pro](https://doitong.com/developers/models/kling-video/o3/pro/image-to-video.md) (`kling-video/o3/pro/image-to-video`): from $0.112 / second
- [Kling O3 Image to Video · Standard](https://doitong.com/developers/models/kling-video/o3/standard/image-to-video.md) (`kling-video/o3/standard/image-to-video`): from $0.084 / second
- [Kling Video · O3 · 4k · Image to Video](https://doitong.com/developers/models/kling-video/o3/4k/image-to-video.md) (`kling-video/o3/4k/image-to-video`): $0.42 / second
- [Kling O3 Reference to Video \[Pro\]](https://doitong.com/developers/models/kling-video/o3/pro/reference-to-video.md) (`kling-video/o3/pro/reference-to-video`): from $0.112 / second
- [Kling O3 Reference to Video \[Standard\]](https://doitong.com/developers/models/kling-video/o3/standard/reference-to-video.md) (`kling-video/o3/standard/reference-to-video`): from $0.084 / second

## Links

- HTML page: https://doitong.com/developers/models/kling-video/o3/pro/video-to-video/reference
- 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/o3/pro/video-to-video/reference
- Errors: https://doitong.com/developers/docs/errors
- Model details as JSON: https://api.doitong.ru/v1/models/kling-video/o3/pro/video-to-video/reference