# Seedance 2.0 Reference to Video API

> Directs a 4 to 15 second clip with sound from up to 9 images, 3 videos and 3 audio clips you reference by name.

ByteDance's multi-reference video model: upload characters, products, locations, a motion or camera reference and a voice or music clip, then call them in the prompt as @Image1, @Video1, @Audio1 and so on. It keeps identities consistent across cuts and generates synchronized audio. At least one image or video reference is required and all references together may not exceed 12 files. Output from 480p to 4K.

- Model id: `bytedance/seedance-2.0/reference-to-video`
- Made by: ByteDance
- Category: Reference to Video
- Output: video
- Price: from $0.141 / second (4 s ≈ $0.564) (cheapest run $0.564 (564 API credits))
- Run: `POST https://api.doitong.com/v1/run/bytedance/seedance-2.0/reference-to-video`
- Quote: `POST https://api.doitong.com/v1/quote/bytedance/seedance-2.0/reference-to-video`
- Docs page: https://doitong.com/developers/models/bytedance/seedance-2.0/reference-to-video

## Pricing

Price: **from $0.141 / second (4 s ≈ $0.564)** (the lowest tier; the quote prices your exact input). Billed per second of output (`duration`, default 15).

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

- When `video_urls` is set and `duration` ≤ 4: by `resolution`, 480p: $0.141, 720p: $0.304, 1080p: $0.682, 4k: $1.556 / second
- When `video_urls` is set and `duration` ≤ 5: by `resolution`, 480p: $0.141, 720p: $0.304, 1080p: $0.682, 4k: $1.556 / second
- When `video_urls` is set and `duration` ≤ 6: by `resolution`, 480p: $0.141, 720p: $0.304, 1080p: $0.682, 4k: $1.556 / second
- When `video_urls` is set and `duration` ≤ 7: by `resolution`, 480p: $0.141, 720p: $0.304, 1080p: $0.682, 4k: $1.556 / second
- When `video_urls` is set and `duration` ≤ 8: by `resolution`, 480p: $0.141, 720p: $0.304, 1080p: $0.682, 4k: $1.556 / second
- When `video_urls` is set and `duration` ≤ 9: by `resolution`, 480p: $0.141, 720p: $0.304, 1080p: $0.682, 4k: $1.556 / second
- When `video_urls` is set and `duration` ≤ 10: by `resolution`, 480p: $0.141, 720p: $0.304, 1080p: $0.682, 4k: $1.556 / second
- When `video_urls` is set and `duration` ≤ 11: by `resolution`, 480p: $0.141, 720p: $0.304, 1080p: $0.682, 4k: $1.556 / second
- When `video_urls` is set and `duration` ≤ 12: by `resolution`, 480p: $0.141, 720p: $0.304, 1080p: $0.682, 4k: $1.556 / second
- When `video_urls` is set and `duration` ≤ 13: by `resolution`, 480p: $0.141, 720p: $0.304, 1080p: $0.682, 4k: $1.556 / second
- When `video_urls` is set and `duration` ≤ 14: by `resolution`, 480p: $0.141, 720p: $0.304, 1080p: $0.682, 4k: $1.556 / second
- When `video_urls` is set: by `resolution`, 480p: $0.141, 720p: $0.304, 1080p: $0.682, 4k: $1.556 / second
- When `resolution` is 480p, 720p, 1080p, 4k: by `resolution`, 480p: $0.141, 720p: $0.304, 1080p: $0.682, 4k: $1.556 / second

The full example input below costs $1.52 = 1520 API credits (5 s × 304 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/bytedance/seedance-2.0/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 |  |  | Text prompt that guides video generation. |
| `image_urls` | `images` | array of image URL | no |  | ≤ 9 items | Image references for video guidance, limited to 9 images and subject to a 12-file maximum across all modalities. Each image may be at most 30 MB and must use JPEG, PNG, or WebP. Use @Image1, @Image2, and subsequent numbered labels to identify these references in the prompt. |
| `video_urls` | `videos` | array of video URL | no |  | ≤ 3 items | Video references for generation, supplied as MP4 or MOV files and identified in the prompt by @Video1, @Video2, and subsequent numbered labels. Each must have a resolution from approximately 480p (640x640) to approximately 720p (834x1112). The set is limited to 3 videos totaling less than 50 MB, with an aggregate duration from 2 to 15 seconds. |
| `audio_urls` | `audios` | array of audio URL | no |  | ≤ 3 items | Audio references for video guidance require at least one accompanying image or video reference. Supply MP3 or WAV files of at most 15 MB each, with no more than 3 files and an aggregate duration capped at 15 seconds. Identify them in the prompt using @Audio1, @Audio2, and subsequent numbered labels. |
| `resolution` |  | enum (string) | no | `720p` | `480p`, `720p`, `1080p`, `4k` | Output resolution: 480p prioritizes speed, 720p offers balance, 1080p delivers high quality, and 4k provides the highest quality. |
| `duration` |  | enum (string) | no | `auto` | `auto`, `4`, `5`, `6`, `7`, `8`, `9`, `10`, `11`, `12`, `13`, `14`, `15` | Video length selection: `auto` delegates the choice to the model using the prompt, while an explicit duration must be from 4 to 15 seconds. |
| `aspect_ratio` |  | enum (string) | no | `auto` | `auto`, `21:9`, `16:9`, `4:3`, `1:1`, `3:4`, `9:16` | Output aspect ratio: 16:9 gives landscape, 9:16 gives portrait/vertical, 1:1 gives square, and 21:9 gives cinematic ultrawide. Select `auto` for the model to choose the ratio. |
| `generate_audio` |  | boolean | no | `true` |  | Enable this to accompany the video with synchronized audio. Generated audio includes speech matched to lip movements, environmental ambience, and sound effects. |
| `bitrate_mode` |  | enum (string) | no | `standard` | `standard`, `high` | Choose the output encoding bitrate: 'standard' retains the default, whereas 'high' asks the model to improve encoding quality at the expense of a larger file. |
| `codec` |  | enum (string) | no | `auto` | `auto`, `H264`, `H265` | Video codec selection: `auto` leaves the default codec behavior unchanged, `H264` selects H.264, and `H265` selects H.265. |

File parameters (`images`, `videos`, `audios`) 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": "@Image1 The banana manager walks through the office and high-fives the carrot, upbeat comedy tone"
}
```

A fuller example:

```json
{
  "prompt": "@Image1 The banana manager walks through the office and high-fives the carrot, upbeat comedy tone",
  "images": [
    "https://content.doitong.com/images/gp/image_20260610003801_541d9719_316882.png"
  ],
  "resolution": "720p",
  "duration": 5
}
```

## 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/bytedance/seedance-2.0/reference-to-video?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "@Image1 The banana manager walks through the office and high-fives the carrot, upbeat comedy tone",
    "images": [
      "https://content.doitong.com/images/gp/image_20260610003801_541d9719_316882.png"
    ],
    "resolution": "720p",
    "duration": 5
  }'

# 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/bytedance/seedance-2.0/reference-to-video?wait=20", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "prompt": "@Image1 The banana manager walks through the office and high-fives the carrot, upbeat comedy tone",
    "images": [
      "https://content.doitong.com/images/gp/image_20260610003801_541d9719_316882.png"
    ],
    "resolution": "720p",
    "duration": 5
  }),
});
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": "@Image1 The banana manager walks through the office and high-fives the carrot, upbeat comedy tone",
    "images": [
        "https://content.doitong.com/images/gp/image_20260610003801_541d9719_316882.png",
    ],
    "resolution": "720p",
    "duration": 5,
}

# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/bytedance/seedance-2.0/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": "bytedance/seedance-2.0/reference-to-video",
      "input": {
        "prompt": "@Image1 The banana manager walks through the office and high-fives the carrot, upbeat comedy tone",
        "images": [
          "https://content.doitong.com/images/gp/image_20260610003801_541d9719_316882.png"
        ],
        "resolution": "720p",
        "duration": 5
      },
      "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": "bytedance/seedance-2.0/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": 1520,
    "usd": "1.52",
    "charged": 1520,
    "refunded": 0
  },
  "input": {
    "prompt": "@Image1 The banana manager walks through the office and high-fives the carrot, upbeat comedy tone",
    "images": [
      "https://content.doitong.com/images/gp/image_20260610003801_541d9719_316882.png"
    ],
    "resolution": "720p",
    "duration": 5
  },
  "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
    },
    "seed": 42
  },
  "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 file produced by generation. |
| `seed` | integer | Seed value applied during generation. |

## Related models

- [Seedance 2.0 Fast Text to Video](https://doitong.com/developers/models/bytedance/seedance-2.0/fast/text-to-video.md) (`bytedance/seedance-2.0/fast/text-to-video`): from $0.113 / second
- [Seedance 2.0 Mini Text to Video](https://doitong.com/developers/models/bytedance/seedance-2.0/mini/text-to-video.md) (`bytedance/seedance-2.0/mini/text-to-video`): from $0.0721 / second
- [Seedance 2.0 Text to Video](https://doitong.com/developers/models/bytedance/seedance-2.0/text-to-video.md) (`bytedance/seedance-2.0/text-to-video`): from $0.141 / second
- [Seedance 2.0 Fast Image to Video](https://doitong.com/developers/models/bytedance/seedance-2.0/fast/image-to-video.md) (`bytedance/seedance-2.0/fast/image-to-video`): from $0.113 / second
- [Seedance 2.0 Image to Video](https://doitong.com/developers/models/bytedance/seedance-2.0/image-to-video.md) (`bytedance/seedance-2.0/image-to-video`): from $0.141 / second
- [Seedance 2.0 Mini Image to Video](https://doitong.com/developers/models/bytedance/seedance-2.0/mini/image-to-video.md) (`bytedance/seedance-2.0/mini/image-to-video`): from $0.0721 / 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 Mini](https://doitong.com/developers/models/bytedance/seedance-2.0/mini/reference-to-video.md) (`bytedance/seedance-2.0/mini/reference-to-video`): $0.007 / 1000 tokens

## Links

- HTML page: https://doitong.com/developers/models/bytedance/seedance-2.0/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=bytedance/seedance-2.0/reference-to-video
- Errors: https://doitong.com/developers/docs/errors
- Model details as JSON: https://api.doitong.com/v1/models/bytedance/seedance-2.0/reference-to-video