# ReconViaGen 0.5 API

> 多視角影像轉 3D 重建，從同一物件的 1 到 16 張照片輸出具紋理的 GLB 網格

根據 `image_urls` 建立 3D 模型，接受同一物件的 1 到 16 個視角；視角越多，重建效果越好。回傳包含 PBR 材質的 GLB 檔案。`resolution` 可為 512、1024 或 1536，`texture_size` 可為 1024、2048 或 4096，`decimation_target` 將網格頂點數設定為 5,000 到 2,000,000。`ss_source` 和 `multi_image_strategy` 選擇結構與視角的合併方式，並提供各階段的引導與取樣控制。

- Model id: `reconviagen-0.5`
- Made by: Open model
- Category: Image to 3D
- Output: 3d
- Price: from $0.25 / request (cheapest run $0.25 (250 API credits))
- Run: `POST https://api.doitong.ru/v1/run/reconviagen-0.5`
- Quote: `POST https://api.doitong.ru/v1/quote/reconviagen-0.5`
- Docs page: https://doitong.com/zh-TW/developers/models/reconviagen-0.5

## Pricing

Price: **from $0.25 / request** (the lowest tier; the quote prices your exact input). Billed once per request.

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

- When `resolution` = 1024: $0.30 (300 API credits) / request
- When `resolution` = 1536: $0.35 (350 API credits) / request

The full example input below costs $0.30 = 300 API credits (1 request × 300 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/reconviagen-0.5` 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 |
|---|---|---|---|---|---|---|
| `seed` |  | integer \| null | no |  |  | 用於可重現隨機生成的種子。 |
| `resolution` |  | enum (integer) | no | `1024` | `512`, `1024`, `1536` | 輸出解析度；提高解析度會增加細節，但需要更長時間。 |
| `ss_source` |  | enum (string) | no | `mesh` | `direct`, `mesh`, `mvtrellis2` | 用於建立稀疏結構的來源。選擇 'direct' 以取得最高速度，選擇 'mesh' 以取得最高品質，或選擇 'mvtrellis2' 使用 TRELLIS.2 進行多視角處理。 |
| `ss_guidance_strength` |  | number | no | `7.5` | 0 – 10 | 控制初始 3D 結構對輸入的保真度；此值提高時，可能增加雜訊以換取更接近的匹配。 |
| `ss_guidance_rescale` |  | number | no | `0.7` | 0 – 1 | 降低第 1 階段強引導造成的瑕疵。 |
| `ss_sampling_steps` |  | integer | no | `12` | 1 – 50 | 用於建立初始結構的去雜訊步驟數。 |
| `ss_rescale_t` |  | number | no | `5` | 1 – 6 | 生成結構時使用的雜訊排程銳利度。 |
| `slat_guidance_strength` |  | number | no | `7.5` | 0 – 10 | SLat 階段的引導強度；僅在 ss_source 設為 'mesh' 時套用。 |
| `slat_guidance_rescale` |  | number | no | `0.5` | 0 – 1 | SLat 階段的引導重新縮放；僅在 ss_source 設為 'mesh' 時套用。 |
| `slat_sampling_steps` |  | integer | no | `12` | 1 – 50 | SLat 階段的取樣步驟數；僅在 ss_source 設為 'mesh' 時套用。 |
| `slat_rescale_t` |  | number | no | `3` | 1 – 6 | SLat 階段的 Rescale T 設定；僅在 ss_source 設為 'mesh' 時套用。 |
| `shape_slat_guidance_strength` |  | number | no | `7.5` | 0 – 10 | 生成詳細幾何結構時對輸入的遵循程度。 |
| `shape_slat_guidance_rescale` |  | number | no | `0.5` | 0 – 1 | 降低形狀階段強引導造成的瑕疵。 |
| `shape_slat_sampling_steps` |  | integer | no | `12` | 1 – 50 | 用於細化形狀的去雜訊步驟數。 |
| `shape_slat_rescale_t` |  | number | no | `3` | 1 – 6 | 細化形狀時使用的雜訊排程銳利度。 |
| `tex_slat_guidance_strength` |  | number | no | `1` | 0 – 10 | 紋理對輸入顏色的遵循程度。 |
| `tex_slat_guidance_rescale` |  | number | no | `0` | 0 – 1 | 降低紋理階段強引導造成的瑕疵。 |
| `tex_slat_sampling_steps` |  | integer | no | `12` | 1 – 50 | 用於生成紋理的去噪步驟數。 |
| `tex_slat_rescale_t` |  | number | no | `3` | 1 – 6 | 生成紋理時使用的雜訊排程銳利度。 |
| `decimation_target` |  | integer | no | `500000` | 5,000 – 2,000,000 | 完成網格的所需頂點數。 |
| `texture_size` |  | enum (integer) | no | `2048` | `1024`, `2048`, `4096` | 網格烘焙紋理圖像所使用的解析度。 |
| `image_urls` | `images` | array of image URL | yes |  | 1 – 16 items | 提供用於 3D 重建的視角：單一視角即可，但額外視角可改善品質，且所有視角都必須呈現同一物件。 |
| `multi_image_strategy` |  | enum (string) | no | `adaptive_guidance_weight` | `average_right`, `weighted_average`, `sequential`, `average`, `adaptive_guidance_weight`, `fixed_guidance_rescale` | 多視角條件策略，僅適用於多張輸入圖像；大多數情況下，請選擇 'adaptive_guidance_weight' 以取得最佳結果。 |
| `enable_safety_checker` |  | boolean | no | `true` |  | 在呼叫端獲得授權的情況下，將此值設為 false 可放寬審核。 |

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

A fuller example:

```json
{
  "image_urls": [
    "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/reconviagen-0.5?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "image_urls": [
      "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/reconviagen-0.5?wait=20", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "image_urls": [
      "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_urls": [
        "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/reconviagen-0.5", 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": "reconviagen-0.5",
      "input": {
        "image_urls": [
          "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": "reconviagen-0.5",
  "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": 300,
    "usd": "0.30",
    "charged": 300,
    "refunded": 0
  },
  "input": {
    "image_urls": [
      "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg"
    ]
  },
  "output": {
    "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
    },
    "seed": 42
  },
  "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 |
|---|---|---|
| `model_glb` | object {url, content_type, file_name, file_size} | 包含具 PBR 材質之 3D 模型的生成 GLB。 |
| `seed` | integer | 生成期間套用的種子。 |

## Related models

- [Pixal3d](https://doitong.com/developers/models/pixal3d.md) (`pixal3d`): from $0.30 / request
- [Hi3D Image to 3D](https://doitong.com/developers/models/hitem3d/hi3d/image-to-3d.md) (`hitem3d/hi3d/image-to-3d`): $0.50 / run
- [Hi3D Image to 3D · v3.0](https://doitong.com/developers/models/hitem3d/hi3d/v3.0/image-to-3d.md) (`hitem3d/hi3d/v3.0/image-to-3d`): from $1.80 / run
- [Hi3D Multiview to 3D · Multi View to 3D](https://doitong.com/developers/models/hitem3d/hi3d/multi-view-to-3d.md) (`hitem3d/hi3d/multi-view-to-3d`): $0.50 / run
- [Hi3D Multiview to 3D · v3.0 · Multi View to 3D](https://doitong.com/developers/models/hitem3d/hi3d/v3.0/multi-view-to-3d.md) (`hitem3d/hi3d/v3.0/multi-view-to-3d`): from $1.80 / run
- [Hunyuan 3D Pro Image to 3D](https://doitong.com/developers/models/hunyuan-3d/v3.1/pro/image-to-3d.md) (`hunyuan-3d/v3.1/pro/image-to-3d`): $0.375 / run
- [Hunyuan 3D Rapid Image to 3D](https://doitong.com/developers/models/hunyuan-3d/v3.1/rapid/image-to-3d.md) (`hunyuan-3d/v3.1/rapid/image-to-3d`): from $0.225 / request
- [Hunyuan World · Image to World](https://doitong.com/developers/models/hunyuan_world/image-to-world.md) (`hunyuan_world/image-to-world`): $0.30 / request

## Links

- HTML page: https://doitong.com/developers/models/reconviagen-0.5
- 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=reconviagen-0.5
- Errors: https://doitong.com/developers/docs/errors
- Model details as JSON: https://api.doitong.ru/v1/models/reconviagen-0.5