# Sam 3 · 3D Objects API

> 根据文本、点或框提示或掩码，从图像中重建选定的 3D 物体，并输出 splat

将照片中的物体转换为 3D 资产。可使用 `mask_urls`、文本 `prompt`、`point_prompts` 或 `box_prompts` 选择物体；多个框会生成独立物体。`detection_threshold` 接受 0.1 到 1，`export_textured_glb` 会烘焙纹理和 UV。输出包括 GLB、Gaussian splat 文件、多物体场景的逐物体文件、元数据和 zip 压缩包。

- Model id: `sam-3/3d-objects`
- Made by: Meta
- Category: Image to 3D
- Output: 3d
- Estimated price per run: $0.02 / run (cheapest run $0.02 (20 API credits))
- Run: `POST https://api.doitong.ru/v1/run/sam-3/3d-objects`
- Quote: `POST https://api.doitong.ru/v1/quote/sam-3/3d-objects`
- Docs page: https://doitong.com/zh/developers/models/sam-3/3d-objects

## Pricing

Price: **$0.02 / run**. Estimated from the typical cost of one run. The quote is exactly what the run charges.

The full example input below costs $0.02 = 20 API credits (1 request × 20 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/sam-3/3d-objects` 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 |
|---|---|---|---|---|---|---|
| `image_url` | `image` | string (image URL) | yes |  |  | 用于 3D 重建的图像 URL。 |
| `mask_urls` |  | array of image URL | no |  |  | 可选的逐对象掩码 URL 列表。没有掩码时，如果提供了提示词、point_prompts 或 box_prompts，自动分割会使用这些提示词；如果既未提供掩码也未提供分割提示词，则使用整个图像。 |
| `prompt` |  | string \| null | no | `car` |  | 掩码缺失时用于自动分割的文本，例如 'chair' 或 'lamp'。 |
| `point_prompts` |  | array of object {x, y, label, object_id} | no | `[]` |  | 掩码缺失时用于自动分割的基于点的提示词。 |
| `point_prompts[].x` |  | integer \| null | no |  |  | 提示词在 X 轴上的位置。 |
| `point_prompts[].y` |  | integer \| null | no |  |  | 提示词在 Y 轴上的位置。 |
| `point_prompts[].label` |  | enum (integer) \| null | no |  | `0`, `1` | 前景/背景标签：1 表示前景；0 表示背景。 |
| `point_prompts[].object_id` |  | integer \| null | no |  |  | 用于将细化同一对象的提示词分组的可选标识符。如果同时提供文本提示词，此标识符决定这些点细化哪个检测到的对象。 |
| `box_prompts` |  | array of object {x_min, y_min, x_max, y_max, object_id} | no | `[]` |  | 通过自动分割生成单独对象掩码的框提示词，用于 3D 重建；仅在未提供掩码时使用。可以提交多个框。 |
| `box_prompts[].x_min` |  | integer \| null | no |  |  | 框的最小 x 坐标。 |
| `box_prompts[].y_min` |  | integer \| null | no |  |  | 框的最小 y 坐标。 |
| `box_prompts[].x_max` |  | integer \| null | no |  |  | 框的最大 X 坐标。 |
| `box_prompts[].y_max` |  | integer \| null | no |  |  | 框的最大 Y 坐标。 |
| `box_prompts[].object_id` |  | integer \| null | no |  |  | 用于将细化同一对象的框分组的可选标识符。 |
| `seed` |  | integer \| null | no |  |  | 用于可复现随机生成的种子。 |
| `pointmap_url` |  | string \| null | no |  |  | 可选 URL，用于通过提供 NPY 或 NPZ 格式的外部 pointmap 或深度数据来改善 3D 重建中的深度估计。 |
| `detection_threshold` |  | number \| null | no |  | 0.1 – 1 | 检测置信度阈值；省略时使用模型默认值。范围为 0.1 到 1.0，较小的值会牺牲精确度以增加检测数量。 |
| `export_textured_glb` |  | boolean | no | `false` |  | GLB 导出选项：启用后会使用烘焙纹理和 UV 替换顶点颜色。 |

File parameters (`image`, `mask_urls`) 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
{
  "image": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg"
}
```

A fuller example:

```json
{
  "image_url": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg"
}
```

## 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-3/3d-objects?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "image_url": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg"
  }'

# 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-3/3d-objects?wait=20", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "image_url": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg"
  }),
});
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 = {
    "image_url": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg",
}

# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/sam-3/3d-objects", 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-3/3d-objects",
      "input": {
        "image_url": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg"
      },
      "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-3/3d-objects",
  "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": 20,
    "usd": "0.02",
    "charged": 20,
    "refunded": 0
  },
  "input": {
    "image_url": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg"
  },
  "output": {
    "gaussian_splat": {
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
      "content_type": "image/jpeg",
      "file_name": "0-output.jpeg",
      "file_size": 1843200
    },
    "model_glb": {
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
      "content_type": "image/jpeg",
      "file_name": "0-output.jpeg",
      "file_size": 1843200
    },
    "metadata": [
      {
        "object_index": 1,
        "scale": [
          []
        ],
        "rotation": [
          []
        ],
        "translation": [
          []
        ],
        "camera_pose": [
          []
        ]
      }
    ],
    "individual_splats": [
      {
        "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
        "content_type": "image/jpeg",
        "file_name": "0-output.jpeg",
        "file_size": 1843200
      }
    ],
    "individual_glbs": [
      {
        "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
        "content_type": "image/jpeg",
        "file_name": "0-output.jpeg",
        "file_size": 1843200
      }
    ],
    "artifacts_zip": {
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
      "content_type": "image/jpeg",
      "file_name": "0-output.jpeg",
      "file_size": 1843200
    }
  },
  "outputs": [
    {
      "type": "file",
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
      "content_type": "image/jpeg",
      "file_size": 1843200,
      "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 |
|---|---|---|
| `gaussian_splat` | object {url, content_type, file_name, file_size} | 包含多个对象时的组合场景 splat，否则为单个 splat；以 .ply 格式的 Gaussian splat 文件提供。 |
| `model_glb` | object {url, content_type, file_name, file_size} | 保存为 GLB 的 3D 输出：多个对象会组装到一个场景中，其他结果包含一个网格。 |
| `metadata` | array of object {object_index, scale, rotation, translation, camera_pose} | 每个对象的元数据，包括旋转、位移和缩放。 |
| `individual_splats` | array of object {url, content_type, file_name, file_size} \| null | 每个对象单独的 Gaussian splat 文件，仅在包含多个对象的场景中可用。 |
| `individual_glbs` | array of object {url, content_type, file_name, file_size} \| null | 每个对象单独的 GLB 网格文件，仅在包含多个对象的场景中可用。 |
| `artifacts_zip` | object {url, content_type, file_name, file_size} \| null | 包含所有资源及元数据的 ZIP 存档。 |

## 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 · Video RLE](https://doitong.com/developers/models/sam-3/video-rle.md) (`sam-3/video-rle`): $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 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
- [Hi3D Image to 3D](https://doitong.com/developers/models/hitem3d/hi3d/image-to-3d.md) (`hitem3d/hi3d/image-to-3d`): $0.50 / run

## Links

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