# GPT Image 2.5 Edit API

> Bearbeitet oder kombiniert bis zu 16 Referenzbilder mit OpenAIs Bildmodell, optional mit Maske und Transparenz.

Bearbeitungsmodus von GPT Image 2.5: Beschreiben Sie die Änderung und übergeben Sie bis zu 16 Referenzbilder, optional mit einer Maske, die den Malbereich des Modells begrenzt. Unterstützt transparente Hintergründe, fünf Qualitätsstufen und bis zu zehn Ergebnisse pro Anfrage.

- Model id: `openai/gpt-image-2.5/flare/edit`
- Made by: OpenAI
- Category: Image Editing
- Output: image
- Estimated price per run: from $0.12 / image (cheapest run $0.12 (120 API credits))
- Run: `POST https://api.doitong.com/v1/run/openai/gpt-image-2.5/flare/edit`
- Quote: `POST https://api.doitong.com/v1/quote/openai/gpt-image-2.5/flare/edit`
- Docs page: https://doitong.com/de/developers/models/openai/gpt-image-2.5/flare/edit

## Pricing

Price: **from $0.12 / image** (the lowest tier; the quote prices your exact input). Estimated from the typical cost of one run, per output (`num_images`). The quote is exactly what the run charges.

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

- When `quality` = xhigh: base price × 1.8
- When `quality` = max: base price × 3

The full example input below costs $0.12 = 120 API credits (1 image × 120 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/openai/gpt-image-2.5/flare/edit` 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 |
|---|---|---|---|---|---|---|
| `prompt` |  | string | yes |  | 1 – 32000 characters | Zur Bildgenerierung verwendeter Prompt. |
| `image_urls` | `images` | array of image URL | yes |  | ≤ 16 items | Referenzbild-URLs für die Generierung, begrenzt auf 16 Bilder. |
| `mask_url` | `mask` | string (image URL) \| null | no |  |  | URL eines Maskenbilds, das den während der Generierung zu bearbeitenden Bereich identifiziert. |
| `image_size` |  | object {width, height} \| enum (string) | no | `auto` | `square_hd`, `square`, `portrait_4_3`, `portrait_16_9`, `landscape_4_3`, `landscape_16_9`, `auto` | Ausgabedimensionen, bei 'auto' aus den bereitgestellten Bildern abgeleitet. |
| `background` |  | enum (string) | no | `auto` | `auto`, `transparent`, `opaque` | Hintergrund des resultierenden Bildes. |
| `quality` |  | enum (string) | no | `high` | `auto`, `low`, `medium`, `high`, `xhigh`, `max` | Auswahl der Bildqualität; bei 'auto' überlässt das Modell die Entscheidung. Höhere Einstellungen liefern mehr Details, verursachen jedoch höhere Latenz und größeren Token-Verbrauch. |
| `num_images` | `num_outputs` | integer | no | `1` | 1 – 10 | Anzahl der zu erzeugenden Bilder. |
| `output_format` |  | enum (string) | no | `png` | `jpeg`, `png`, `webp` | Dateiformat der Ausgabebilder. |
| `output_compression` |  | integer \| null | no |  | 0 – 100 | Kompressionseinstellung, nur für 'jpeg' oder 'webp' in output_format verfügbar; zulässiger Bereich 0–100. |

File parameters (`images`, `mask`) 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
{
  "prompt": "Same sneaker, but on a snowy mountain trail in daylight",
  "images": [
    "https://content.doitong.com/images/showcase/v3/gen_sneaker_ad.jpg"
  ]
}
```

A fuller example:

```json
{
  "prompt": "Same sneaker, but on a snowy mountain trail in daylight",
  "images": [
    "https://content.doitong.com/images/showcase/v3/gen_sneaker_ad.jpg"
  ],
  "quality": "medium"
}
```

## 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/openai/gpt-image-2.5/flare/edit?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "Same sneaker, but on a snowy mountain trail in daylight",
    "images": [
      "https://content.doitong.com/images/showcase/v3/gen_sneaker_ad.jpg"
    ],
    "quality": "medium"
  }'

# 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/openai/gpt-image-2.5/flare/edit?wait=20", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "prompt": "Same sneaker, but on a snowy mountain trail in daylight",
    "images": [
      "https://content.doitong.com/images/showcase/v3/gen_sneaker_ad.jpg"
    ],
    "quality": "medium"
  }),
});
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 = {
    "prompt": "Same sneaker, but on a snowy mountain trail in daylight",
    "images": [
        "https://content.doitong.com/images/showcase/v3/gen_sneaker_ad.jpg",
    ],
    "quality": "medium",
}

# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/openai/gpt-image-2.5/flare/edit", 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": "openai/gpt-image-2.5/flare/edit",
      "input": {
        "prompt": "Same sneaker, but on a snowy mountain trail in daylight",
        "images": [
          "https://content.doitong.com/images/showcase/v3/gen_sneaker_ad.jpg"
        ],
        "quality": "medium"
      },
      "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": "openai/gpt-image-2.5/flare/edit",
  "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": 120,
    "usd": "0.12",
    "charged": 120,
    "refunded": 0
  },
  "input": {
    "prompt": "Same sneaker, but on a snowy mountain trail in daylight",
    "images": [
      "https://content.doitong.com/images/showcase/v3/gen_sneaker_ad.jpg"
    ],
    "quality": "medium"
  },
  "output": {
    "images": [
      {
        "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 |
|---|---|---|
| `images` | array of object {url, content_type, file_name, file_size, width, height} | Vom Modell erzeugte Bilder. |

## Related models

- [GPT Image 2.5 Sunburst Text to Image](https://doitong.com/developers/models/openai/gpt-image-2.5/sunburst/text-to-image.md) (`openai/gpt-image-2.5/sunburst/text-to-image`): $0.054 / image
- [GPT Image 2.5 Text to Image](https://doitong.com/developers/models/openai/gpt-image-2.5/flare/text-to-image.md) (`openai/gpt-image-2.5/flare/text-to-image`): from $0.008 / image
- [GPT Image 2.5 Sunburst Edit](https://doitong.com/developers/models/openai/gpt-image-2.5/sunburst/edit.md) (`openai/gpt-image-2.5/sunburst/edit`): $0.128 / image
- [FLUX.1 Kontext \[pro\]](https://doitong.com/developers/models/flux-pro/kontext.md) (`flux-pro/kontext`): $0.04 / 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
- [Seedream 5.0 Pro Edit](https://doitong.com/developers/models/bytedance/seedream/v5/pro/edit.md) (`bytedance/seedream/v5/pro/edit`): from $0.0675 / run of output image

## Links

- HTML page: https://doitong.com/developers/models/openai/gpt-image-2.5/flare/edit
- 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=openai/gpt-image-2.5/flare/edit
- Errors: https://doitong.com/developers/docs/errors
- Model details as JSON: https://api.doitong.com/v1/models/openai/gpt-image-2.5/flare/edit