# VGGT-1B API

> Genskaber en 3D-scene ud fra op til 48 billeder eller en video og returnerer dybdekort, kamerapositioner og en punktsky

Estimerer geometri ud fra flere visninger. Angiv op til 48 billeder i `image_urls`, og tilføj eventuelt en `video_url`, der samples for hver `frame_sampling_rate` frames. Returnerer dybdekort pr. frame, kameraets extrinsics og intrinsics, rå prædiktionsfiler samt en GLB-punktsky med kamerakegler. `confidence_percentile` og `max_points` styrer punktskyens tæthed.

- 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.com/v1/run/vggt-1b`
- Quote: `POST https://api.doitong.com/v1/quote/vggt-1b`
- Docs page: https://doitong.com/da/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.com/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 | Kildebilleder til rekonstruktion, hvert med polstring til et kvadrat og ændret størrelse til en længste dimension på 518 pixels. JPEG, PNG, WEBP og alle yderligere billedformater, som Pillow kan afkode, accepteres. |
| `video_url` | `video` | string (video URL) \| null | no |  |  | Valgfri kildevideo, hvis samplede frames følger image_urls i det kombinerede input. Sampling bruger hvert `frame_sampling_rate`-te frame og inkluderer altid det første og sidste frame. |
| `frame_sampling_rate` |  | integer | no | `24` | 1 – 1,000 | Frame-interval, der kun anvendes, når en video leveres via `video_url`; ellers har det ingen effekt. Begge grænseframes bevares uanset intervallet, mens hvert n-te frame samples imellem dem. |
| `alpha_blend_onto` |  | enum (string) | no | `white` | `keep`, `white`, `black`, `mean` | Behandling af alfakanalen har fire valgmuligheder: 'keep' fjerner alfa uden at ændre de oprindelige pixelværdier; 'mean' komponerer mod ImageNet-gennemsnittet for RGB. Vælg 'white' eller 'black' for at komponere mod den tilsvarende farve. |
| `export_prediction_data` |  | boolean | no | `true` |  | Eksportér rå forudsigelser som separate JSON-filer for individuelle frames. Hver fil indeholder dybde og dens konfidens, en maske samt den kodede kamerapose. |
| `export_depth_maps` |  | boolean | no | `true` |  | Eksportér dybderastere med en lineær mapping af `depth_range` til pixelværdierne 0–65535. Hvert frame får en separat gråtone-PNG med 16-bit præcision. |
| `export_point_cloud` |  | boolean | no | `true` |  | Eksportér den fusionerede farvede punktsky i GLB-format, hvor estimerede kameraer repræsenteres af individuelle keglenet i scenen. |
| `array_encoding` |  | enum (string) | no | `base64` | `base64`, `list` | Array-lagringsformat for forudsigelses-JSON-filer, hvor 'list' bruger langt mere plads end 'base64'. Vælg 'list' til indlejrede JSON-lister eller 'base64' til objekter, der indeholder {data, shape, dtype}. |
| `exclude_keys` |  | array of enum (string) | no |  |  | Nøgler, der udelades fra alle forudsigelses-JSON-filer. |
| `confidence_percentile` |  | number | no | `50` | 0 – 100 | Konfidensbaseret filtreringsprocent til konstruktion af punktskyen: 0 deaktiverer filtrering, mens andre værdier udelader den angivne procentdel af punkterne, begyndende med de mindst konfidente. |
| `max_points` |  | integer | no | `250000` | 1,000 – 5,000,000 | Maksimalt antal punkter i GLB, som standard 250,000. For at reducere serialiserings- og uploadforsinkelse skrives et jævnt subsamplet udvalg, når skyen overskrider dette budget. |
| `enable_safety_checker` |  | boolean | no | `true` |  | Sikkerhedstjek for inputbilleder og video. |

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.com/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.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/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.com/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.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": "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.com/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t",
    "cancel": "https://api.doitong.com/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t/cancel"
  }
}
```

### Output fields (`output`)

| Field | Type | Description |
|---|---|---|
| `point_cloud` | object {url, content_type, file_name, file_size} \| null | Punktskyeksport, der returneres, når `export_point_cloud` er true; dens GLB-scene kombinerer den fusionerede sky med kamerakegler. |
| `depth_maps` | array of object {url, content_type, file_name, file_size, width, height} | Dybdekorteksport, der er tilgængelig, når `export_depth_maps` er true. Elementerne følger kildeframesekvensen, hvor hvert frame repræsenteres af en 16-bit gråtone-PNG-raster. |
| `prediction_data` | array of object {url, content_type, file_name, file_size} | Rå forudsigelseseksport: når `export_prediction_data` er true, har hvert frame sin egen JSON-fil, og filerne følger framesekvensen. |
| `num_frames` | integer | Det samlede antal rekonstruerede frames, inklusive billeder og frames samplet fra video. |
| `depth_range` | array of number | Dybdegrænser [min, max], der bruges til kvantisering af `depth_maps`. Gendan dybden som min + pixel * (max - min) / 65535. |
| `extrinsics` | array of array of array of number | Ekstrinsiske kamera-fra-verden-matricer på 3x4 for hvert frame; OpenCV-akser peger mod højre langs x, ned langs y og fremad langs z. |
| `intrinsics` | array of array of array of number | Pinhole-intrinsiske matricer på 3x3 for hvert frame, udtrykt i pixelkoordinaterne for modellens 518x518-frame. |
| `timings` | object | Forløbet væg-ur-tid for hvert trin, i sekund. |

## 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.com/v1/models/vggt-1b