# Nano Banana 2 API

> Google's fast Gemini image model, from quick 0.5K drafts to 4K, with extreme aspect ratios and web grounding.

A quicker, cheaper sibling of Nano Banana Pro that still handles text in images and multi-object scenes well. Output runs from 0.5K previews to 4K, with aspect ratios from 1:8 to 8:1 for banners and vertical stories. Optional web search grounds the picture in current facts, and an optional high thinking level plans complex layouts before drawing. Up to four images per request.

- Model id: `nano-banana-2`
- Made by: Google
- Category: Text to Image
- 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`
- Quote: `POST https://api.doitong.com/v1/quote/nano-banana-2`
- Docs page: https://doitong.com/developers/models/nano-banana-2

## 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` 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 | Text instructions used to generate an image. |
| `num_images` | `num_outputs` | integer | no | `1` | 1 – 4 | Image count requested for generation. |
| `seed` |  | integer \| null | no |  |  | Seed value that initializes random-number generation. |
| `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` | Choose the generated image's aspect ratio explicitly, including extreme options 4:1, 1:4, 8:1, 1:8, or select "auto" for a prompt-based choice by the model. |
| `output_format` |  | enum (string) | no | `png` | `jpeg`, `png`, `webp` | File format for the resulting image. |
| `safety_tolerance` |  | enum (string) | no | `4` | `1`, `2`, `3`, `4`, `5`, `6` | Set content-moderation tolerance between the least restrictive level, 6, and the strictest level, 1, which blocks most content. |
| `system_prompt` |  | string | no | `` | ≤ 50000 characters | Optional request-wide persona and output-style guidance, delivered to Gemini as a system instruction or to OpenAI-compatible providers as a system message. Nothing is sent for this instruction when the value is blank. |
| `resolution` |  | enum (string) | no | `1K` | `0.5K`, `1K`, `2K`, `4K` | Resolution for the output image. |
| `limit_generations` |  | boolean | no | `true` |  | Experimental generation cap that may affect quality when enabled. With `True`, each prompting round is restricted to 1 generation, overriding image-count instructions in the prompt and ignoring model-generated intermediate images. |
| `enable_web_search` |  | boolean | no | `false` |  | Web search toggle for image generation, allowing the model to incorporate up-to-date information found online into the image. |
| `thinking_level` |  | enum (string) \| null | no |  | `minimal`, `high` | Select 'minimal' or 'high' to activate model thinking at that level and include its thoughts in the generation; leaving the level unset keeps thinking disabled. |

## Example input

Required parameters only:

```json
{
  "prompt": "A cozy bookshop window at night with a hand-painted sign reading \"Open Late\", warm light, rain on the glass"
}
```

A fuller example:

```json
{
  "prompt": "A cozy bookshop window at night with a hand-painted sign reading \"Open Late\", warm light, rain on the glass",
  "aspect_ratio": "4:5",
  "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?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "A cozy bookshop window at night with a hand-painted sign reading \"Open Late\", warm light, rain on the glass",
    "aspect_ratio": "4:5",
    "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?wait=20", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "prompt": "A cozy bookshop window at night with a hand-painted sign reading \"Open Late\", warm light, rain on the glass",
    "aspect_ratio": "4:5",
    "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": "A cozy bookshop window at night with a hand-painted sign reading \"Open Late\", warm light, rain on the glass",
    "aspect_ratio": "4:5",
    "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", 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",
      "input": {
        "prompt": "A cozy bookshop window at night with a hand-painted sign reading \"Open Late\", warm light, rain on the glass",
        "aspect_ratio": "4:5",
        "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",
  "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": "A cozy bookshop window at night with a hand-painted sign reading \"Open Late\", warm light, rain on the glass",
    "aspect_ratio": "4:5",
    "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} | Images produced by the model. |
| `description` | string | Description accompanying the generated images. |

## Related models

- [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](https://doitong.com/developers/models/nano-banana-pro.md) (`nano-banana-pro`): from $0.15 / image
- [FLUX.1 \[dev\]](https://doitong.com/developers/models/flux/dev.md) (`flux/dev`): $0.025 / megapixel
- [FLUX.1 \[schnell\]](https://doitong.com/developers/models/flux/schnell.md) (`flux/schnell`): $0.003 / megapixel
- [FLUX.2 \[dev\]](https://doitong.com/developers/models/flux-2.md) (`flux-2`): $0.012 / megapixel
- [FLUX.2 \[pro\]](https://doitong.com/developers/models/flux-2-pro.md) (`flux-2-pro`): $0.015 / megapixel of output 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
- [Ideogram V4.5](https://doitong.com/developers/models/ideogram/v4.5.md) (`ideogram/v4.5`): from $0.03 / image

## Links

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