# Wan v2.6 Reference to Video API

> Tạo video, giữ lại chủ thể từ 1 đến 3 video tham chiếu, được trích dẫn là @Video1 đến @Video3

Tạo đoạn video có các chủ thể (người, động vật hoặc vật thể) lấy từ 1 đến 3 video trong `video_urls`, mỗi video tối thiểu 16 FPS. Lời nhắc tham chiếu chúng bằng @Video1, @Video2 và @Video3, đồng thời có thể mô tả các cảnh theo thời gian. `aspect_ratio` có năm lựa chọn, `resolution` là 720p hoặc 1080p và `duration` là 5 hoặc 10 giây.

- Model id: `wan/v2.6/reference-to-video`
- Made by: Alibaba
- Category: Reference to Video
- Output: video
- Price: from $0.10 / second (5 s ≈ $0.50) (cheapest run $0.50 (500 API credits))
- Run: `POST https://api.doitong.com/v1/run/wan/v2.6/reference-to-video`
- Quote: `POST https://api.doitong.com/v1/quote/wan/v2.6/reference-to-video`
- Docs page: https://doitong.com/vi/developers/models/wan/v2.6/reference-to-video

## Pricing

Price: **from $0.10 / second (5 s ≈ $0.50)** (the lowest tier; the quote prices your exact input). Billed per second of output (`duration`, default 10).

Price rules (the first rule that matches the input wins; a parameter you leave out counts as its default):

- When `resolution` = 1080p: $0.15 (150 API credits) / second

The full example input below costs $0.75 = 750 API credits (5 s × 150 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.com/v1/quote/wan/v2.6/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 | yes |  | ≥ 1 characters | Lời nhắc tối đa 1500 ký tự, trong đó các chủ thể video được xác định bằng @Video1, @Video2, @Video3; chủ thể có thể là người, động vật hoặc vật thể. Lời nhắc nhiều cảnh dùng dạng: '[0-3s] Shot 1. [3-6s] Shot 2.' |
| `video_urls` | `videos` | array of video URL | yes |  |  | Cung cấp 1–3 video tham chiếu để duy trì chủ thể nhất quán, gồm người, động vật hoặc vật thể, và xác định chúng trong lời nhắc bằng @Video1, @Video2, @Video3. Mỗi video phải có ít nhất 16 FPS, dài 2 đến 30 giây và không lớn hơn 100 MB. |
| `aspect_ratio` |  | enum (string) | no | `16:9` | `16:9`, `9:16`, `1:1`, `4:3`, `3:4` | Tỷ lệ khung hình của video đầu ra. |
| `resolution` |  | enum (string) | no | `1080p` | `720p`, `1080p` | Mức độ phân giải cho đầu ra video; R2V chấp nhận 720p hoặc 1080p nhưng không chấp nhận 480p. |
| `duration` |  | enum (string) | no | `5` | `5`, `10` | Đặt thời lượng video được tạo, tính bằng giây. Với R2V, chọn 5 hoặc 10 giây; không hỗ trợ 15 giây. |
| `negative_prompt` |  | string \| null | no | `` |  | Lời nhắc phủ định chỉ định nội dung không mong muốn, tối đa 500 ký tự. |
| `enable_prompt_expansion` |  | boolean | no | `true` |  | Kiểm soát việc LLM có viết lại lời nhắc hay không. |
| `multi_shots` |  | boolean | no | `true` |  | Kiểm soát phân đoạn cảnh, chỉ khả dụng khi enable_prompt_expansion được đặt thành True. Mặc định true dùng phân đoạn thông minh để xây dựng mạch truyện nhất quán giữa các cảnh; false giữ video thành một cảnh liên tục. |
| `seed` |  | integer \| null | no |  |  | Seed giúp quá trình tạo sinh có thể tái lập. Đặt thành None sẽ chọn seed ngẫu nhiên. |
| `enable_safety_checker` |  | boolean | no | `true` |  | Công tắc kiểm tra an toàn, trong đó trạng thái tắt yêu cầu ủy quyền tài khoản. Nếu không có ủy quyền, mọi yêu cầu đều được kiểm tra bất kể cài đặt; true bật trình kiểm tra. |

File parameters (`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
{
  "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
  "videos": [
    "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_urls": [
    "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.com/v1/run/wan/v2.6/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",
    "video_urls": [
      "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.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/wan/v2.6/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",
    "video_urls": [
      "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.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",
    "video_urls": [
        "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/wan/v2.6/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": "wan/v2.6/reference-to-video",
      "input": {
        "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
        "video_urls": [
          "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": "wan/v2.6/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": 750,
    "usd": "0.75",
    "charged": 750,
    "refunded": 0
  },
  "input": {
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
    "video_urls": [
      "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,
      "width": 1024,
      "height": 768,
      "fps": 1.0,
      "duration": 5,
      "num_frames": 1
    },
    "seed": 42,
    "actual_prompt": "Dance battle between Character1 and Character2, cinematic lighting, dynamic camera movement."
  },
  "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, width, height, fps, duration, num_frames} | Tệp video kết quả. |
| `seed` | integer | Giá trị seed dùng trong quá trình tạo sinh. |
| `actual_prompt` | string \| null | Lời nhắc thực sự được sử dụng khi bật tính năng viết lại. |

## Related models

- [Wan v2.6 Text to Image](https://doitong.com/developers/models/wan/v2.6/text-to-image.md) (`wan/v2.6/text-to-image`): $0.03 / image
- [Wan v2.6 Image to Image](https://doitong.com/developers/models/wan/v2.6/image-to-image.md) (`wan/v2.6/image-to-image`): $0.03 / image
- [Wan v2.6 Text to Video](https://doitong.com/developers/models/wan/v2.6/text-to-video.md) (`wan/v2.6/text-to-video`): from $0.10 / second
- [Wan v2.6 Image to Video](https://doitong.com/developers/models/wan/v2.6/image-to-video.md) (`wan/v2.6/image-to-video`): from $0.10 / second
- [Alibaba V2.6 · Reference to Video · Flash](https://doitong.com/developers/models/wan/v2.6/reference-to-video/flash.md) (`wan/v2.6/reference-to-video/flash`): from $0.05 / second of output video
- [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
- [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

## Links

- HTML page: https://doitong.com/developers/models/wan/v2.6/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=wan/v2.6/reference-to-video
- Errors: https://doitong.com/developers/docs/errors
- Model details as JSON: https://api.doitong.com/v1/models/wan/v2.6/reference-to-video