# Kling 4.0 Reference to Video API

> 生成 3-30 秒视频，保持最多 10 张参考图像、5 个参考视频和 7 个元素的外观

根据文本 `prompt` 以及参考图像、参考视频和角色或对象元素创建视频，这些元素在提示词中以 @Image1、@Video1 或 @Element1 的形式引用。时长为 3 到 30 秒（默认 5），输出分辨率为 720p 或 1080p，宽高比可选 auto、16:9、9:16、1:1 或 21:9。使用 `multi_prompt` 可为每个镜头提供提示词，此时总时长为各镜头时长之和。上限为 10 张图像、5 个时长为 3-30s 的视频和 7 个元素，其中最多 3 个元素可以携带语音。

- Model id: `kling/v4/reference-to-video`
- Made by: Kling
- Category: Reference to Video
- Output: video
- Price per second of your output video: from $0.157 / second of output video (cheapest run $0.157 (157 API credits))
- Run: `POST https://api.doitong.com/v1/run/kling/v4/reference-to-video`
- Quote: `POST https://api.doitong.com/v1/quote/kling/v4/reference-to-video`
- Docs page: https://doitong.com/zh/developers/models/kling/v4/reference-to-video

## Pricing

Price: **from $0.157 / second of output video** (the lowest tier; the quote prices your exact input). Price per second of your output 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.

Price by tier:

- 720p: $0.157 / second of output video
- 1080p: $0.235 / second of output video

The full example input below costs $1.175 = 1175 API credits (5 s output video × $0.235 (1080p)).

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/v4/reference-to-video` 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 |
|---|---|---|---|---|---|---|
| `prompt` |  | string \| null | no |  | ≤ 2500 characters | 满足必须提供 `prompt` 或 `multi_prompt` 要求的生成指令。要引用提供的输入，请使用 @Image1、@Video1、@Element1 等。 |
| `multi_prompt` |  | array of object {prompt, duration} \| null | no |  | ≥ 1 items | 逐镜头生成指令，每个提示词定义一个镜头，其时长计入视频总时长。 |
| `multi_prompt[].prompt` |  | string | yes |  | 1 – 512 characters | 当前镜头的文本指令。 |
| `multi_prompt[].duration` |  | integer | no | `5` | 1 – 30 | 单个镜头的时长，以秒为单位。 |
| `duration` |  | integer | no | `5` | 3 – 30 | 视频时长（秒），范围为 3 到 30。 |
| `start_image_url` | `image` | string (image URL) \| null | no |  |  | 可选的首帧图像，会计入图像参考数量限制。文件大小最大为 30.0 MB；宽度和高度都必须达到 300 px，宽高比介于 0.40 和 2.50 之间。 |
| `image_urls` | `images` | array of image URL \| null | no |  | ≤ 10 items | 使用 @Image1、@Image2 等引用的图像参考，最多 10 张。每个文件大小限制为 30.0 MB，两个维度都至少为 300 px，宽高比必须介于 0.40 和 2.50 之间。 |
| `video_urls` | `videos` | array of video URL \| null | no |  | ≤ 5 items | 最多 5 个参考视频，使用 @Video1、@Video2 等引用；每个视频时长为 3–30 秒（最多 30.05 秒），与元素视频合计不得超过 30 秒。每个文件不得超过 300 MB，宽度和高度均为 700 px 至 4553 px。宽高比必须为 0.40–2.50，帧率为 23.9–60.05 FPS。 |
| `elements` |  | array of object {frontal_image_url, reference_image_urls, video_url, voice_id} \| null | no |  | ≤ 7 items | 最多 7 个角色或对象，其中最多 3 个可包含 `voice_id`，最多 3 个可使用视频。使用 @Element1、@Element2 等引用这些元素。 |
| `elements[].frontal_image_url` |  | string (image URL) \| null | no |  |  | 展示元素主要视角的正面图像。文件大小最大为 30.0 MB；两个维度都必须至少为 300 px，宽高比必须介于 0.40 和 2.50 之间。 |
| `elements[].reference_image_urls` |  | array of image URL \| null | no |  | ≤ 3 items | 展示元素不同角度的补充图像，提供 1 到 3 个视角。每个文件最大为 30.0 MB，两个维度都必须至少为 300 px，宽高比必须介于 0.40 和 2.50 之间。 |
| `elements[].video_url` |  | string (video URL) \| null | no |  |  | 替代图像的元素视频表示，时长为 3–30 秒（最多 30.05 秒）。文件不得超过 300 MB；宽度和高度都必须在 700–4553 px 之间。支持的宽高比为 0.40–2.50，帧率为 23.9–60.05 FPS。 |
| `elements[].voice_id` |  | string \| null | no |  |  | 分配给元素的语音。 |
| `resolution` |  | enum (string) | no | `1080p` | `720p`, `1080p` | 输出的分辨率。 |
| `aspect_ratio` |  | enum (string) | no | `16:9` | `auto`, `16:9`, `9:16`, `1:1`, `21:9` | 视频比例，可显式选择，或选择 'auto' 根据参考内容推导。 |

File parameters (`image`, `images`, `videos`) 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
{}
```

A fuller example:

```json
{
  "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
}
```

## 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/v4/reference-to-video?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"
  }'

# 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/v4/reference-to-video?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"
  }),
});
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 = {
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
}

# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/kling/v4/reference-to-video", 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/v4/reference-to-video",
      "input": {
        "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
      },
      "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/v4/reference-to-video",
  "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": 1175,
    "usd": "1.175",
    "charged": 1175,
    "refunded": 0
  },
  "input": {
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
  },
  "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} | 模型生成的视频。 |

## Related models

- [Kling 4.0 Text to Video](https://doitong.com/developers/models/kling/v4/text-to-video.md) (`kling/v4/text-to-video`): from $0.157 / second of output video
- [Seedance 2.0 Fast Reference to Video](https://doitong.com/developers/models/bytedance/seedance-2.0/fast/reference-to-video.md) (`bytedance/seedance-2.0/fast/reference-to-video`): from $0.113 / second
- [Seedance 2.0 Reference to Video](https://doitong.com/developers/models/bytedance/seedance-2.0/reference-to-video.md) (`bytedance/seedance-2.0/reference-to-video`): from $0.141 / second
- [Wan 3.0 Reference to Video](https://doitong.com/developers/models/alibaba/wan-3.0/reference-to-video.md) (`alibaba/wan-3.0/reference-to-video`): from $0.05 / second
- [Kling O1 Reference Image to Video \[Pro\]](https://doitong.com/developers/models/kling-video/o1/reference-to-video.md) (`kling-video/o1/reference-to-video`): $0.112 / second
- [Kling O1 Reference Image to Video \[Standard\]](https://doitong.com/developers/models/kling-video/o1/standard/reference-to-video.md) (`kling-video/o1/standard/reference-to-video`): $0.084 / 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/v4/reference-to-video
- 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/v4/reference-to-video
- Errors: https://doitong.com/developers/docs/errors
- Model details as JSON: https://api.doitong.com/v1/models/kling/v4/reference-to-video