# Sam 3 · Video RLE API

> 支援遮罩 URL 種子與影格索引控制的影片分割，且偵測門檻下限更低

使用文字 `prompt`、點或框提示，或在 `frame_index` 套用 `mask_url` 的初始遮罩，透過 SAM 3 分割影片。`detection_threshold` 範圍為 0.01 到 1；文字提示失效時，0.2 到 0.3 等較低值可能有所幫助。可透過 `boundingbox_zip` 回傳逐幀邊界框 zip。

- Model id: `sam-3/video-rle`
- Made by: Meta
- Category: Video to Video
- Output: video
- Price per 16 frames of your input video: $0.005 / 16 frames of input video (cheapest run $0.005 (5 API credits))
- Run: `POST https://api.doitong.ru/v1/run/sam-3/video-rle`
- Quote: `POST https://api.doitong.ru/v1/quote/sam-3/video-rle`
- Docs page: https://doitong.com/zh-TW/developers/models/sam-3/video-rle

## Pricing

Price: **$0.005 / 16 frames of input video**. Price per 16 frames 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 $0.095 = 95 API credits (19 × 16 frames input video × $0.005).

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/sam-3/video-rle` 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 |
|---|---|---|---|---|---|---|
| `video_url` | `video` | string (video URL) | yes |  |  | 用於分割的影片 URL。 |
| `mask_url` | `mask` | string (image URL) \| null | no |  |  | 初始套用的遮罩 URL。 |
| `prompt` |  | string | no | `` |  | 支援透過逗號分隔描述追蹤多個物件的分割提示詞，例如 'person, cloth'。 |
| `point_prompts` |  | array of object {x, y, label, object_id, frame_index} | no | `[]` |  | 指定影格索引的點提示詞清單。 |
| `point_prompts[].x` |  | integer \| null | no |  |  | 提示詞在 X 軸上的位置。 |
| `point_prompts[].y` |  | integer \| null | no |  |  | 提示詞在 Y 軸上的位置。 |
| `point_prompts[].label` |  | enum (integer) \| null | no |  | `0`, `1` | 前景或背景標籤：1 表示前景；0 表示背景。 |
| `point_prompts[].object_id` |  | integer \| null | no |  |  | 將用於細化單一物件的提示詞分組之選用識別碼。如果也提供文字作為提示詞，此識別碼會決定這些點要細化哪個偵測到的物件。 |
| `point_prompts[].frame_index` |  | integer \| null | no |  |  | 識別互動影格的索引。 |
| `box_prompts` |  | array of object {x_min, y_min, x_max, y_max, object_id, frame_index} | no | `[]` |  | 框提示詞清單，每個項目可選擇包含 frame_index。 |
| `box_prompts[].x_min` |  | integer \| null | no |  |  | 框的最小 x 座標。 |
| `box_prompts[].y_min` |  | integer \| null | no |  |  | 框的最小 y 座標。 |
| `box_prompts[].x_max` |  | integer \| null | no |  |  | 框的最大 X 座標。 |
| `box_prompts[].y_max` |  | integer \| null | no |  |  | 框的最大 Y 座標。 |
| `box_prompts[].object_id` |  | integer \| null | no |  |  | 將用於細化單一物件的框分組之選用識別碼。 |
| `box_prompts[].frame_index` |  | integer \| null | no |  |  | 識別互動影格的索引。 |
| `apply_mask` |  | boolean | no | `false` |  | 是否對影片套用遮罩。 |
| `boundingbox_zip` |  | boolean | no | `false` |  | 是否回傳包含每個影格邊界框疊加圖的 ZIP 封存檔。 |
| `detection_threshold` |  | number | no | `0.5` | 0.01 – 1 | 偵測信心門檻；現有物件預設為 0.5，新物件預設為 0.7。在 0.0–1.0 範圍內，較小的值會以精確度換取更多偵測結果；文字提示詞失效時可嘗試 0.2–0.3。 |
| `frame_index` |  | integer | no | `0` |  | 提供 mask_url 時，用於初始互動的影格索引。 |

File parameters (`video`, `mask`) 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
{
  "video": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4"
}
```

A fuller example:

```json
{
  "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/sam-3/video-rle?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "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/sam-3/video-rle?wait=20", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "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 = {
    "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/sam-3/video-rle", 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": "sam-3/video-rle",
      "input": {
        "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": "sam-3/video-rle",
  "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": 95,
    "usd": "0.095",
    "charged": 95,
    "refunded": 0
  },
  "input": {
    "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
    },
    "boundingbox_frames_zip": {
      "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} | 由分割產生的影片。 |
| `boundingbox_frames_zip` | object {url, content_type, file_name, file_size} \| null | 每個影格的邊界框疊加圖 ZIP 封存檔。 |

## Related models

- [Sam 3 · Image RLE](https://doitong.com/developers/models/sam-3/image-rle.md) (`sam-3/image-rle`): $0.005 / run
- [Segment Anything Model 3](https://doitong.com/developers/models/sam-3/image.md) (`sam-3/image`): $0.005 / run
- [Sam 3 · Video](https://doitong.com/developers/models/sam-3/video.md) (`sam-3/video`): $0.005 / 16 frames of input video
- [Sam 3 · 3D Body](https://doitong.com/developers/models/sam-3/3d-body.md) (`sam-3/3d-body`): $0.02 / run
- [Sam 3 · 3D Objects](https://doitong.com/developers/models/sam-3/3d-objects.md) (`sam-3/3d-objects`): $0.02 / run
- [Sam 3 · 3D Align](https://doitong.com/developers/models/sam-3/3d-align.md) (`sam-3/3d-align`): $0.02 / run
- [Sam 3 · Image · Embed](https://doitong.com/developers/models/sam-3/image/embed.md) (`sam-3/image/embed`): $0.005 / run
- [Sam 3 1 · Video](https://doitong.com/developers/models/sam-3-1/video.md) (`sam-3-1/video`): $0.01 / 16 frames of input video

## Links

- HTML page: https://doitong.com/developers/models/sam-3/video-rle
- 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=sam-3/video-rle
- Errors: https://doitong.com/developers/docs/errors
- Model details as JSON: https://api.doitong.ru/v1/models/sam-3/video-rle