# Nano Banana 2 Edit API

> Schnelle, anweisungsbasierte Bearbeitung, die auch ein Video, einen Audioclip oder ein PDF als Kontext lesen kann.

Der Bearbeitungsmodus von Nano Banana 2: Übergeben Sie Bilder und beschreiben Sie die Änderung oder lassen Sie die Bilder weg und geben Sie ein Video, eine Audiodatei oder ein PDF (jeweils bis zu 15 MB) als Kontext zur Veranschaulichung an. Ausgabe von 0.5K bis 4K mit Seitenverhältnissen von 1:8 bis 8:1, optionaler Websuche und hohem Denkaufwand, bis zu vier Ergebnisse pro Anfrage.

- Model id: `nano-banana-2/edit`
- Made by: Google
- Category: Image Editing
- Output: image
- Price: from $0.06 / image (cheapest run $0.06 (60 API credits))
- Run: `POST https://api.doitong.com/v1/run/nano-banana-2/edit`
- Quote: `POST https://api.doitong.com/v1/quote/nano-banana-2/edit`
- Docs page: https://doitong.com/de/developers/models/nano-banana-2/edit

## Pricing

Price: **from $0.06 / image** (the lowest tier; the quote prices your exact input). Billed per generated image (`num_images`, default 1).

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

- When `enable_web_search` = true and `thinking_level` = high: by `resolution`, 0.5K: $0.077, 1K: $0.097, 2K: $0.137, 4K: $0.177 / image
- When `enable_web_search` = true: by `resolution`, 0.5K: $0.075, 1K: $0.095, 2K: $0.135, 4K: $0.175 / image
- When `thinking_level` = high: by `resolution`, 0.5K: $0.062, 1K: $0.082, 2K: $0.122, 4K: $0.162 / image

The full example input below costs $0.08 = 80 API credits (1 image × 80 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/nano-banana-2/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 |  | 3 – 50000 characters | Textanweisungen zum Bearbeiten eines Bildes. |
| `num_images` | `num_outputs` | integer | no | `1` | 1 – 4 | Für die Generierung angeforderte Bildanzahl. |
| `seed` |  | integer \| null | no |  |  | Seed-Wert zur Initialisierung der Zufallszahlengenerierung. |
| `aspect_ratio` |  | enum (string) \| null | no | `auto` | `auto`, `21:9`, `16:9`, `3:2`, `4:3`, `5:4`, `1:1`, `4:5`, `3:4`, `2:3`, `9:16`, `4:1`, `1:4`, `8:1`, `1:8` | Seitenverhältnis des Ausgabebilds einschließlich der extremen Optionen 4:1, 1:4, 8:1 und 1:8. |
| `output_format` |  | enum (string) | no | `png` | `jpeg`, `png`, `webp` | Dateiformat des resultierenden Bilds. |
| `safety_tolerance` |  | enum (string) | no | `4` | `1`, `2`, `3`, `4`, `5`, `6` | Stelle die Toleranz der Inhaltsmoderation zwischen der am wenigsten restriktiven Stufe 6 und der strengsten Stufe 1 ein, die den Großteil der Inhalte blockiert. |
| `image_urls` | `images` | array of image URL | no |  |  | Gib Quellbilder per URL für Bildbearbeitung oder Image-to-Image-Generierung an, sofern du nicht mindestens eine alternative Eingabe bereitstellst: `video_url`, `audio_url` oder `pdf_url`. |
| `system_prompt` |  | string | no | `` | ≤ 50000 characters | Optionale, anfrageweite Vorgaben für Persona und Ausgabestil, die Gemini als Systemanweisung oder OpenAI-kompatiblen Anbietern als Systemnachricht übermittelt werden. Bei leerem Wert wird für diese Anweisung nichts gesendet. |
| `resolution` |  | enum (string) | no | `1K` | `0.5K`, `1K`, `2K`, `4K` | Auflösung des Ausgabebilds. |
| `video_url` | `video` | string (video URL) \| null | no |  |  | Optionaler Videokontext als YouTube-URL oder http(s)/data-URL für eine Videodatei. YouTube-Links erreichen das Modell direkt ohne Download; Videodateien werden heruntergeladen und inline gesendet, vorbehaltlich einer Höchstgröße von 15 MB. |
| `audio_url` | `audio` | string (audio URL) \| null | no |  |  | Optionalen Audiokontext über eine http(s)- oder data-URL zu einer höchstens 15 MB großen Datei bereitstellen. Die Datei wird nach dem Download inline gesendet. |
| `pdf_url` |  | string \| null | no |  |  | Optionalen PDF-Kontext über eine http(s)- oder data-URL zu einem höchstens 15 MB großen Dokument bereitstellen. Das Dokument wird nach dem Download inline gesendet. |
| `limit_generations` |  | boolean | no | `true` |  | Experimentelle Generierungsgrenze, die bei Aktivierung die Qualität beeinflussen kann. Mit `True` wird jede Prompt-Runde auf 1 Generierung beschränkt, Bildanzahlanweisungen im Prompt überschrieben und vom Modell erzeugte Zwischenbilder ignoriert. |
| `enable_web_search` |  | boolean | no | `false` |  | Umschalter für die Websuche bei der Bildgenerierung, sodass das Modell aktuelle Online-Informationen in das Bild einbeziehen kann. |
| `thinking_level` |  | enum (string) \| null | no |  | `minimal`, `high` | Wähle 'minimal' oder 'high', um das Denken des Modells auf dieser Stufe zu aktivieren und seine Gedanken in die Generierung einzubeziehen; bleibt die Stufe nicht gesetzt, ist das Denken deaktiviert. |

File parameters (`images`, `video`, `audio`) 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": "Turn this night street scene into a sunny morning, keep the sneaker and the puddle reflections"
}
```

A fuller example:

```json
{
  "prompt": "Turn this night street scene into a sunny morning, keep the sneaker and the puddle reflections",
  "images": [
    "https://content.doitong.com/images/showcase/v3/gen_sneaker_ad.jpg"
  ],
  "resolution": "1K"
}
```

## 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/nano-banana-2/edit?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "Turn this night street scene into a sunny morning, keep the sneaker and the puddle reflections",
    "images": [
      "https://content.doitong.com/images/showcase/v3/gen_sneaker_ad.jpg"
    ],
    "resolution": "1K"
  }'

# 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/nano-banana-2/edit?wait=20", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "prompt": "Turn this night street scene into a sunny morning, keep the sneaker and the puddle reflections",
    "images": [
      "https://content.doitong.com/images/showcase/v3/gen_sneaker_ad.jpg"
    ],
    "resolution": "1K"
  }),
});
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": "Turn this night street scene into a sunny morning, keep the sneaker and the puddle reflections",
    "images": [
        "https://content.doitong.com/images/showcase/v3/gen_sneaker_ad.jpg",
    ],
    "resolution": "1K",
}

# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/nano-banana-2/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": "nano-banana-2/edit",
      "input": {
        "prompt": "Turn this night street scene into a sunny morning, keep the sneaker and the puddle reflections",
        "images": [
          "https://content.doitong.com/images/showcase/v3/gen_sneaker_ad.jpg"
        ],
        "resolution": "1K"
      },
      "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": "nano-banana-2/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": 80,
    "usd": "0.08",
    "charged": 80,
    "refunded": 0
  },
  "input": {
    "prompt": "Turn this night street scene into a sunny morning, keep the sneaker and the puddle reflections",
    "images": [
      "https://content.doitong.com/images/showcase/v3/gen_sneaker_ad.jpg"
    ],
    "resolution": "1K"
  },
  "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
      }
    ],
    "description": "string"
  },
  "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} | Aus der Bearbeitung resultierende Bilder. |
| `description` | string | Beschreibung zu den generierten Bildern. |

## Related models

- [Nano Banana 2](https://doitong.com/developers/models/nano-banana-2.md) (`nano-banana-2`): 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
- [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
- [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
- [Gemini 2.5 Flash Image · Edit](https://doitong.com/developers/models/gemini-25-flash-image/edit.md) (`gemini-25-flash-image/edit`): $0.0398 / image
- [Gemini 3 Pro Image Preview · Edit](https://doitong.com/developers/models/gemini-3-pro-image-preview/edit.md) (`gemini-3-pro-image-preview/edit`): from $0.15 / image

## Links

- HTML page: https://doitong.com/developers/models/nano-banana-2/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=nano-banana-2/edit
- Errors: https://doitong.com/developers/docs/errors
- Model details as JSON: https://api.doitong.com/v1/models/nano-banana-2/edit