# Pixelcut Product Photo API

> Produktbild-Kompositioun: schneit den Artikel eraus a placéiert en op engem neie Canvas mat Hannergrond, Margen a Schied

Veraarbecht eng Produktfoto zu engem Bild am Katalogstil. Dir kënnt de Canvas mat `image_size`-Presets oder personaliséierten Dimensioune festleeën, e faarwegen, transparenten oder Bild-`background` wielen an de `margin` upassen. E generativt oder Drop-`shadow` an eng optional `watermark`-Iwwerlagerung si verfügbar. Den Output ass png oder jpeg; jpeg kann net mat engem transparenten Hannergrond benotzt ginn.

- Model id: `pixelcut/product-photo`
- Made by: Pixelcut
- Category: Image Editing
- Output: image
- Price: $0.024 / image (cheapest run $0.024 (24 API credits))
- Run: `POST https://api.doitong.com/v1/run/pixelcut/product-photo`
- Quote: `POST https://api.doitong.com/v1/quote/pixelcut/product-photo`
- Docs page: https://doitong.com/lb/developers/models/pixelcut/product-photo

## Pricing

Price: **$0.024 / image**. Billed per generated image.

The full example input below costs $0.024 = 24 API credits (1 image × 24 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/pixelcut/product-photo` 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 |  |  | URL vum Produktbild fir d'Beaarbechtung. |
| `image_size` |  | object {width, height} \| enum (string) \| null | no | `square_hd` | `square_hd`, `square`, `portrait_4_3`, `portrait_16_9`, `landscape_4_3`, `landscape_16_9` | Dimensioune vum Output-Canvas, als personaliséiert {width, height} oder als Preset: square_hd, square, portrait_4_3, portrait_16_9, landscape_4_3, landscape_16_9. De Standard ass square_hd (1024x1024). |
| `background` |  | object {mode, color, image_url, image_fit} | no |  |  | Hannergrond fir den Output: e Bild, Transparenz oder eng faarweg Fläch, déi standardméisseg wäiss ass. |
| `background.mode` |  | enum (string) | no | `Color` | `Transparent`, `Color`, `Image` | Hannergrondmodus: 'Color' benotzt `color`, standardméisseg wäiss; 'Transparent' produzéiert Transparenz a benotzt ëmmer PNG; 'Image' setzt d'Resultat iwwer `image_url` zesummen. |
| `background.color` |  | object {r, g, b} | no | `{"b":255,"g":255,"r":255}` |  | Eefaarweg Hannergrondfëllung fir de 'Color'-Modus, standardméisseg wäiss, iwwer R/G/B-Komponente vun 0 bis 255 spezifizéiert. |
| `background.color.r` |  | integer | yes |  | 0 – 255 |  |
| `background.color.g` |  | integer | yes |  | 0 – 255 |  |
| `background.color.b` |  | integer | yes |  | 0 – 255 |  |
| `background.image_url` |  | string (image URL) \| null | no |  |  | URL vum Hannergrondbild; am 'Image'-Modus obligatoresch. |
| `background.image_fit` |  | enum (string) | no | `Cover` | `Cover`, `Contain`, `Stretch` | Wielt, wéi d'Hannergrondbild an de Canvas gepasst gëtt. 'Contain' behält e passend Bild mat Letterboxing iwwer `color`; 'Stretch' benotzt Verzerrung fir d'Passung; 'Cover' fëllt de Canvas duerch Ofschneiden. |
| `margin` |  | object {all, left, right, top, bottom} | no |  |  | Plaz tëscht dem Produkt an de Canvasränner. Benotzt `all`, fir all Margen ze setzen, mat optionalen Iwwerschreiwunge fir eenzel Säiten; de Standard ass 20% pro Säit. |
| `margin.all` |  | string | no | `20%` |  | Gläichméisseg Margin op all Säit, als '%' vun der Canvasdimensioun vun 0 bis 49% oder a 'px' mat engem Minimum vun 0px spezifizéiert. |
| `margin.left` |  | string \| null | no |  |  | Lénks Margin, déi `all` op där Säit ersetzt. Akzeptéiert '%' vun 0 bis 49% oder 'px' ab 0px. |
| `margin.right` |  | string \| null | no |  |  | Riets Margin, déi `all` op där Säit ersetzt. Akzeptéiert '%' vun 0 bis 49% oder 'px' ab 0px. |
| `margin.top` |  | string \| null | no |  |  | Uewescht Margin, déi `all` op där Säit ersetzt. Akzeptéiert '%' vun 0 bis 49% oder 'px' ab 0px. |
| `margin.bottom` |  | string \| null | no |  |  | Ënnescht Margin, déi `all` op där Säit ersetzt. Akzeptéiert '%' vun 0 bis 49% oder 'px' ab 0px. |
| `shadow` |  | object {type, generative, drop} | no |  |  | Schattekonfiguratioun: wielt 'Generative' oder 'Drop' a konfiguréiert seng Astellungen. Net setzen, fir kee Schiet unzewenden. |
| `shadow.type` |  | enum (string) \| null | no |  | `Generative`, `Drop` | Optionalen Schietstil; wann net gesat, gëtt kee Schiet benotzt. Wielt 'Generative' fir AI-Synthes oder 'Drop' fir en deterministesche Schiet. |
| `shadow.generative` |  | object {opacity, light_source} | no |  |  | Astellunge fir den AI-generéierte Schiet, applizéiert wann den Typ 'Generative' ass. |
| `shadow.generative.opacity` |  | number | no | `0.2` | 0 – 1 | Opazitéit vum komplett zesummegesate Schiet, vun 0 bis 1. |
| `shadow.generative.light_source` |  | object {size, position} \| null | no |  |  | Explizit virtuell Liichtquell fir d'Schattesynthes, déi bei enger Liwwerung d'automatesch Schätzung vun der Liichtrichtung aus dem Bild ersetzt. |
| `shadow.drop` |  | object {color, horizontal, vertical, blur, opacity} | no |  |  | Astellunge fir den Drop-Schiet, applizéiert wann den Typ 'Drop' ass. |
| `shadow.drop.color` |  | object {r, g, b} | no | `{"b":0,"g":0,"r":0}` |  | RGB-Faarf vum Schiet; schwaarz ass de Standard. |
| `shadow.drop.horizontal` |  | number | no | `50` | -100 – 100 | Horizontal Verschibung vum Schiet, wou d'Maximum-Astellung 100 10% vun der Canvasbreet duerstellt. Wäerter leie vun -100 bis 100; negativ Astellunge verschiben no lénks, positiv no riets. |
| `shadow.drop.vertical` |  | number | no | `8` | -100 – 100 | Vertikal Verschibung vum Schiet, wou d'Maximum-Astellung 100 10% vun der Canvashéicht duerstellt. Wäerter leie vun -100 bis 100; negativ Astellunge verschiben no uewen, positiv no ënnen. |
| `shadow.drop.blur` |  | number | no | `24` | 0 – 100 | Schiet-Verwëscherung, mat maximaler Weichheet bei 100, wat engem Radius vu 5% vun der kuerzerer Canvasdimensioun entsprécht. De Beräich fänkt bei 0 un, wouduerch d'Ränner haart bleiwen. |
| `shadow.drop.opacity` |  | number | no | `0.25` | 0 – 1 | Opazitéit vum Schiet, vun 0 bis 1. |
| `watermark` |  | object {image_url, remove_background, position, scale, opacity, margin} \| null | no |  |  | Logo- oder Waasserzeechen-Iwwerlag, aktivéiert duerch d'Liwwerung vun engem Bild; wann et ewechgelooss gëtt, bleift den Output ouni Waasserzeechen, wéi standardméisseg. |
| `watermark.image_url` |  | string (image URL) \| null | no |  |  | URL vum Logo- oder Waasserzeechenbild. En eidele Wäert léisst den Output ouni Waasserzeechen. |
| `watermark.remove_background` |  | boolean | no | `false` |  | Ob den Hannergrond vum Waasserzeechen duerch Hannergrondentfernung ewechgeholl soll ginn, sou datt d'Iwwerlag en net enthält. |
| `watermark.position` |  | enum (string) | no | `bottom_right` | `top_left`, `top_right`, `bottom_left`, `bottom_right`, `center` | Plazéierung vum Waasserzeechen. |
| `watermark.scale` |  | number | no | `0.1` | 0.01 – 1 | Breet vum Waasserzeechen, als Brochdeel vun der Canvasbreet ausgedréckt. |
| `watermark.opacity` |  | number | no | `1` | 0 – 1 | Opazitéit vum Waasserzeechen, vun 0 bis 1. |
| `watermark.margin` |  | string | no | `3%` |  | Distanz no bannen vum Canvassrand, als '%' vum Canvas (0–49%) oder a 'px' ausgedréckt. |
| `output_format` |  | enum (string) \| null | no |  | `png`, `jpeg` | Kodéierung vum Output-Bild, gewielt aus PNG oder JPEG, woubäi JPEG bei transparenten Hannergrënn net verfügbar ass. Wann d'Auswiel ewechgelooss gëtt, bleift de Format vum Input erhale. |

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_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.com/v1/run/pixelcut/product-photo?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.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/pixelcut/product-photo?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.com/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/pixelcut/product-photo", 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": "pixelcut/product-photo",
      "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": "pixelcut/product-photo",
  "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": 24,
    "usd": "0.024",
    "charged": 24,
    "refunded": 0
  },
  "input": {
    "image_url": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.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
    }
  },
  "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} \| null | Produktfotografie, virbereet fir d'Benotzung an engem Katalog. |

## Related models

- [Pixelcut Looping Video](https://doitong.com/developers/models/pixelcut/looping-video.md) (`pixelcut/looping-video`): from $0.08 / second
- [Pixelcut Background Remover](https://doitong.com/developers/models/pixelcut/background-removal.md) (`pixelcut/background-removal`): $0.016 / image
- [Pixelcut Video Background Removal](https://doitong.com/developers/models/pixelcut/video-background-removal.md) (`pixelcut/video-background-removal`): $0.022 / 30 frames of input video
- [FLUX.1 Kontext \[pro\]](https://doitong.com/developers/models/flux-pro/kontext.md) (`flux-pro/kontext`): $0.04 / image
- [GPT Image 2.5 Edit](https://doitong.com/developers/models/openai/gpt-image-2.5/flare/edit.md) (`openai/gpt-image-2.5/flare/edit`): from $0.12 / image
- [Nano Banana 2 Edit](https://doitong.com/developers/models/nano-banana-2/edit.md) (`nano-banana-2/edit`): from $0.06 / image
- [Nano Banana Pro Edit](https://doitong.com/developers/models/nano-banana-pro/edit.md) (`nano-banana-pro/edit`): from $0.15 / image
- [Qwen Image 3 Edit](https://doitong.com/developers/models/alibaba/qwen-image-3/edit.md) (`alibaba/qwen-image-3/edit`): from $0.04 / image

## Links

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