# VGGT-1B API

> 根据最多 48 张图像或一个视频重建 3D 场景，返回深度图、相机姿态和点云

根据多个视角估计几何结构。在 `image_urls` 中提供最多 48 张图像，也可以选择添加按每 `frame_sampling_rate` 帧采样的视频 `video_url`。返回每帧深度图、相机外参和内参、原始预测文件，以及带相机视锥的 GLB 点云。`confidence_percentile` 和 `max_points` 控制点云密度。

- Model id: `vggt-1b`
- Made by: Meta
- Category: Vision
- Output: json
- Charged by usage (up to $1.755 per run, typical $0.04; the rest of the hold is refunded): $0.000975 / second of processing time (cheapest run $0.04 (40 API credits))
- Run: `POST https://api.doitong.ru/v1/run/vggt-1b`
- Quote: `POST https://api.doitong.ru/v1/quote/vggt-1b`
- Docs page: https://doitong.com/zh/developers/models/vggt-1b

## Pricing

Price: **$0.000975 / second of processing time**. Charged by actual usage at $0.000975 / second of processing time: up to $1.755 per run (the quote gives the maximum for your input), the rest is refunded automatically after the run. A typical run costs $0.04.

The full example input below holds up to $1.755 = 1755 API credits (up to 1800 s of processing time × $0.000975) when it starts; a typical run costs $0.04 (40 API credits).

Prices are the upstream price in USD, paid from the API balance in API credits (1000 API credits = 1 USD). This model is charged by usage: `POST https://api.doitong.ru/v1/quote/vggt-1b` with the same JSON body returns the most the run can cost for that input (`credits`, debited when the run starts); after the run you pay the usage the model reports and the rest is refunded automatically. An input whose maximum would exceed the per-run limit is refused with 422. 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_urls` | `images` | array of image URL | no |  | ≤ 48 items | 重建源图像；每张图像都会填充为正方形，并调整大小使最长边为 518 像素。支持 JPEG、PNG、WEBP 以及 Pillow 可解码的其他图像格式。 |
| `video_url` | `video` | string (video URL) \| null | no |  |  | 可选源视频，其采样帧会接在组合输入中的 image_urls 之后。采样使用每隔 `frame_sampling_rate` 帧取一帧，并始终包含第一帧和最后一帧。 |
| `frame_sampling_rate` |  | integer | no | `24` | 1 – 1,000 | 仅当通过 `video_url` 提供视频时应用帧间隔；否则不起作用。无论间隔如何，首尾帧都会保留，中间每隔 n 帧采样一帧。 |
| `alpha_blend_onto` |  | enum (string) | no | `white` | `keep`, `white`, `black`, `mean` | Alpha 通道处理有四种选择：'keep' 会移除 alpha，但不改变原始像素值；'mean' 会使用 ImageNet 平均 RGB 进行合成。对于纯色背景，请选择 'white' 或 'black'，以使用相应颜色进行合成。 |
| `export_prediction_data` |  | boolean | no | `true` |  | 将原始预测结果导出为每帧单独的 JSON 文件。每个文件包含深度及其置信度、掩码和编码后的相机位姿。 |
| `export_depth_maps` |  | boolean | no | `true` |  | 导出深度栅格，将 `depth_range` 线性映射到像素值 0–65535。每帧都会生成一个独立的 16 位灰度 PNG。 |
| `export_point_cloud` |  | boolean | no | `true` |  | 以 GLB 格式导出融合后的彩色点云，并在场景中用单独的圆锥网格表示估算的相机。 |
| `array_encoding` |  | enum (string) | no | `base64` | `base64`, `list` | 预测 JSON 文件的数组存储格式，其中 'list' 比 'base64' 占用更多空间。嵌套 JSON 列表请选择 'list'；包含 {data, shape, dtype} 的对象请选择 'base64'。 |
| `exclude_keys` |  | array of enum (string) | no |  |  | 从每个预测 JSON 文件中排除的键。 |
| `confidence_percentile` |  | number | no | `50` | 0 – 100 | 用于点云构建的基于置信度的过滤百分比：0 表示禁用过滤，其他值表示从置信度最低的点开始排除相应百分比的点。 |
| `max_points` |  | integer | no | `250000` | 1,000 – 5,000,000 | GLB 点数上限，默认值为 250,000。为降低序列化和上传延迟，当点云超过此预算时，会写入均匀下采样后的点。 |
| `enable_safety_checker` |  | boolean | no | `true` |  | 输入图像和视频的安全检查开关。 |

File parameters (`images`, `video`) 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
{}
```

## 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/vggt-1b?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{}'

# 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/vggt-1b?wait=20", {
  method: "POST",
  headers,
  body: JSON.stringify({}),
});
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 = {}

# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/vggt-1b", 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": "vggt-1b",
      "input": {},
      "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": "vggt-1b",
  "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": 1755,
    "usd": "1.755",
    "charged": 1755,
    "refunded": 0
  },
  "input": {},
  "output": {
    "point_cloud": {
      "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
    },
    "depth_maps": [
      {
        "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,
        "width": 1024,
        "height": 768
      }
    ],
    "prediction_data": [
      {
        "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
      }
    ],
    "num_frames": 1,
    "depth_range": [
      1.0
    ],
    "extrinsics": [
      [
        [
          1.0
        ]
      ]
    ],
    "intrinsics": [
      [
        [
          1.0
        ]
      ]
    ],
    "timings": {}
  },
  "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 |
|---|---|---|
| `point_cloud` | object {url, content_type, file_name, file_size} \| null | 当 `export_point_cloud` 为 true 时返回的点云导出结果；其 GLB 场景将融合后的点云与相机圆锥组合在一起。 |
| `depth_maps` | array of object {url, content_type, file_name, file_size, width, height} | 当 `export_depth_maps` 为 true 时可用的深度图导出结果。条目遵循源帧序列，每帧表示为 16 位灰度 PNG 栅格。 |
| `prediction_data` | array of object {url, content_type, file_name, file_size} | 原始预测导出结果：当 `export_prediction_data` 为 true 时，每帧都有自己的 JSON 文件，并且文件遵循帧序列。 |
| `num_frames` | integer | 重建的总帧数，包括图像和从视频中采样的帧。 |
| `depth_range` | array of number | 用于 `depth_maps` 量化的深度边界 [min, max]。按 min + pixel * (max - min) / 65535 恢复深度。 |
| `extrinsics` | array of array of array of number | 每帧的相机到世界外部矩阵，大小为 3x4；OpenCV 坐标轴中 x 轴向右、y 轴向下、z 轴向前。 |
| `intrinsics` | array of array of array of number | 每帧的针孔内参矩阵，大小为 3x3，以模型 518x518 帧的像素坐标表示。 |
| `timings` | object | 每个阶段经过的实际时间，单位为秒。 |

## Related models

- [Sam 3 · Image · Embed](https://doitong.com/developers/models/sam-3/image/embed.md) (`sam-3/image/embed`): $0.005 / run
- [Bagel · Understand](https://doitong.com/developers/models/bagel/understand.md) (`bagel/understand`): $0.05 / request
- [Bria Ad Delayer](https://doitong.com/developers/models/bria/ad-delayer.md) (`bria/ad-delayer`): $0.30 / request
- [Florence 2 Large Caption](https://doitong.com/developers/models/florence-2-large/caption.md) (`florence-2-large/caption`): $0.003 / run
- [Florence 2 Large Detailed Caption](https://doitong.com/developers/models/florence-2-large/detailed-caption.md) (`florence-2-large/detailed-caption`): $0.004 / run
- [Florence 2 Large OCR](https://doitong.com/developers/models/florence-2-large/ocr.md) (`florence-2-large/ocr`): $0.003 / run
- [Florence 2 Large Region To Category](https://doitong.com/developers/models/florence-2-large/region-to-category.md) (`florence-2-large/region-to-category`): $0.003 / run
- [Florence-2 Large · More Detailed Caption](https://doitong.com/developers/models/florence-2-large/more-detailed-caption.md) (`florence-2-large/more-detailed-caption`): $0.004 / run

## Links

- HTML page: https://doitong.com/developers/models/vggt-1b
- 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=vggt-1b
- Errors: https://doitong.com/developers/docs/errors
- Model details as JSON: https://api.doitong.ru/v1/models/vggt-1b