# BiRefNet V2 Background Removal API

> Entfernt Hintergründe und führt Matting bis zu 2304 px durch, optional mit Maskenausgabe.

BiRefNet V2 trennt das Motiv mit mehreren Modellvarianten (light, heavy, matting, portrait, dynamic) vom Hintergrund und unterstützt Betriebsauflösungen bis 2304x2304. Gibt den Freisteller und optional die Maske als PNG, WebP oder GIF zurück.

- Model id: `birefnet/v2`
- Made by: BiRefNet
- Category: Background Removal
- Output: image
- Estimated price per run: $0.002 / run (cheapest run $0.002 (2 API credits))
- Run: `POST https://api.doitong.com/v1/run/birefnet/v2`
- Quote: `POST https://api.doitong.com/v1/quote/birefnet/v2`
- Docs page: https://doitong.com/de/developers/models/birefnet/v2

## Pricing

Price: **$0.002 / run**. Estimated from the typical cost of one run. The quote is exactly what the run charges.

The full example input below costs $0.002 = 2 API credits (1 request × 2 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.com/v1/quote/birefnet/v2` 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 |
|---|---|---|---|---|---|---|
| `model` |  | enum (string) | no | `General Use (Light)` | `General Use (Light)`, `General Use (Light 2K)`, `General Use (Heavy)`, `Matting`, `Portrait`, `General Use (Dynamic)` | Auswahl des Modells zur Hintergrundentfernung: 'General Use (Light)' verweist auf BiRefNet, das ursprüngliche Modell des BiRefNet-Repositorys, und wird für die meisten Anwendungsfälle empfohlen. 'General Use (Light 2K)' verweist auf BiRefNet_lite-2K und verwendet dieses ursprüngliche, mit 2K-Bildern trainierte Modell. 'General Use (Heavy)' verweist auf BiRefNet_lite und bietet höhere Genauigkeit bei langsamerer Verarbeitung. 'Matting' verweist auf BiRefNet-matting und wurde speziell für Bild-Matting trainiert. 'Portrait' verweist auf BiRefNet-portrait und wurde speziell mit Porträtbildern trainiert. 'General Use (Dynamic)' verweist auf BiRefNet_dynamic und unterstützt variable Auflösungen von 256x256 bis 2304x2304. |
| `operating_resolution` |  | enum (string) | no | `1024x1024` | `1024x1024`, `2048x2048`, `2304x2304` | Arbeitsauflösung; '2304x2304' ist auf das Modell 'General Use (Dynamic)' beschränkt. Bei hochauflösenden Eingabebildern verbessern höhere Einstellungen die Ausgabequalität. |
| `output_mask` |  | boolean | no | `false` |  | Steuert, ob die Maske zur Hintergrundentfernung in der Ausgabe enthalten ist. |
| `refine_foreground` |  | boolean | no | `true` |  | Steuert die Vordergrundverfeinerung auf Grundlage der geschätzten Maske. |
| `image_url` | `image` | string (image URL) | yes |  |  | URL des Bildes, dessen Hintergrund entfernt wird. |
| `output_format` |  | enum (string) | no | `png` | `webp`, `png`, `gif` | Format des resultierenden Bildes. |
| `mask_only` |  | boolean | no | `false` |  | Umschalter für die Ausgabe ausschließlich der Maske: `True` überspringt die Vordergrundverfeinerung, lässt das Bild unverändert und gibt nur seine Segmentierungsmaske zurück. Wenn nur eine Maske benötigt wird, vermeidet dies zusätzliche Berechnungen und reduziert die übertragenen Daten. |

File parameters (`image`) 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_sneaker_ad.jpg"
}
```

A fuller example:

```json
{
  "image": "https://content.doitong.com/images/showcase/v3/gen_sneaker_ad.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.com/v1/run/birefnet/v2?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "image": "https://content.doitong.com/images/showcase/v3/gen_sneaker_ad.jpg"
  }'

# 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/birefnet/v2?wait=20", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "image": "https://content.doitong.com/images/showcase/v3/gen_sneaker_ad.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.com/v1"
headers = {"Authorization": "Bearer " + os.environ["DOITONG_API_KEY"]}

payload = {
    "image": "https://content.doitong.com/images/showcase/v3/gen_sneaker_ad.jpg",
}

# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/birefnet/v2", 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": "birefnet/v2",
      "input": {
        "image": "https://content.doitong.com/images/showcase/v3/gen_sneaker_ad.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": "birefnet/v2",
  "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": 2,
    "usd": "0.002",
    "charged": 2,
    "refunded": 0
  },
  "input": {
    "image": "https://content.doitong.com/images/showcase/v3/gen_sneaker_ad.jpg"
  },
  "output": {
    "image": {
      "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
    },
    "mask_image": {
      "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
    }
  },
  "outputs": [
    {
      "type": "image",
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
      "content_type": "image/jpeg",
      "file_size": 1843200,
      "width": 1024,
      "height": 768,
      "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 |
|---|---|---|
| `image` | object {url, content_type, file_name, file_size, width, height} | Bild nach der Hintergrundentfernung oder die Segmentierungsmaske, wenn `mask_only` auf `True` gesetzt ist. |
| `mask_image` | object {url, content_type, file_name, file_size, width, height} \| null | Bei der Hintergrundentfernung angewendete Maske. |

## Related models

- [Birefnet Background Removal](https://doitong.com/developers/models/birefnet.md) (`birefnet`): $0.002 / run
- [Bria RMBG 2.0](https://doitong.com/developers/models/bria/background/remove.md) (`bria/background/remove`): from $0.018 / request
- [Birefnet](https://doitong.com/developers/models/birefnet/v2/video.md) (`birefnet/v2/video`): $0.000575 / second of processing time
- [ben-v2-image](https://doitong.com/developers/models/ben/v2/image.md) (`ben/v2/image`): $0.102 / run
- [Ben-Video-Bg-Rm](https://doitong.com/developers/models/ben/v2/video.md) (`ben/v2/video`): $0.001 / megapixel of input video
- [Bria Guided Remove Background](https://doitong.com/developers/models/bria/guided-remove-background.md) (`bria/guided-remove-background`): $0.03 / image
- [Bria's VRMBG 3.0](https://doitong.com/developers/models/bria/video/background-removal/v3.md) (`bria/video/background-removal/v3`): $0.05 / second of input video
- [Feynobg Background Remover](https://doitong.com/developers/models/feynobg.md) (`feynobg`): $0.001 / request

## Links

- HTML page: https://doitong.com/developers/models/birefnet/v2
- 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=birefnet/v2
- Errors: https://doitong.com/developers/docs/errors
- Model details as JSON: https://api.doitong.com/v1/models/birefnet/v2