# Nano Banana

> State of the art image editing model from Google Gemini 2.5.

## Overview

- **Endpoint**: `https://queue.modelrunner.run/google/nano-banana`
- **Model ID**: `google/nano-banana`
- **Category**: image-to-image
- **Kind**: inference
- **Tags**: image, text, image modifying, image editing, image generation, avatar

## Pricing

- **Price**: $0.039 per output

## Request Lifecycle

This model runs on the ModelRunner **asynchronous queue API** — a single POST does not return the output. Every call requires an `Authorization: Key $MODEL_RUNNER_KEY` header. Run three steps:

1. **Submit** — `POST https://queue.modelrunner.run/google/nano-banana` with a JSON body holding the input fields at the top level. The body may also include a reserved top-level `metadata` object — a flat string map (max 16 keys, key ≤64 / value ≤512 chars) stored on the request for your own tagging. It is never sent to the model; filter your request history with `GET https://queue.modelrunner.run/requests?metadata=<url-encoded JSON>` (exact key=value matches, AND-ed). The response carries request handles only (no output yet):

```json
{
  "status": "IN_QUEUE",
  "request_id": "<21-char id>",
  "status_url": "https://queue.modelrunner.run/google/nano-banana/requests/<request_id>/status",
  "response_url": "https://queue.modelrunner.run/google/nano-banana/requests/<request_id>",
  "cancel_url": "https://queue.modelrunner.run/google/nano-banana/requests/<request_id>/cancel"
}
```

2. **Poll status** — `GET <status_url>` until `status` is `COMPLETED`. Possible values are `IN_QUEUE`, `IN_PROGRESS`, `COMPLETED`, `FAILED`, `CANCELLED`. A `FAILED` request responds with HTTP 400 and an `error` field.

3. **Read result** — `GET <response_url>`. Returns the finished request, including the generated `output`:

```json
{ "id": "<request_id>", "status": "COMPLETED", "output": ..., "input": ... }
```

The JavaScript and Python SDKs below perform steps 2–3 for you. In any language without an SDK (Swift, Go, Kotlin, etc.) you must implement the polling loop and the final result fetch yourself — see the cURL example for the full flow.

### Input Schema

- **`prompt`** (`string`, _required_):
  The text prompt to generate an image from.

- **`image_urls`** (`array<string>`, _optional_):
  Optional URLs of images to use as input.

- **`num_outputs`** (`integer`, _optional_):
  The number of images to generate. Each generated image is billed.
  - Default: `1`
  - Range: `1` to `4`

- **`output_format`** (`output_format`, _optional_):
  The desired format for the output images.
  - Default: `"png"`
  - Options: `"jpg"`, `"png"`

### Output Schema

_No `Output` schema properties are available._

## Default Example

**Input**

```json
{
  "prompt": "A highly realistic aerial photograph showing a large balloon floating on the surface of the sea, perfectly shaped like the provided logo. The scene is captured from above, with the balloon centered in the frame. Gentle waves surround it, and the sunlight reflects softly off the water, emphasizing the logo’s shape and color.",
  "image_urls": [
    "https://media.modelrunner.ai/UY25DbajyBabWHTB"
  ],
  "num_outputs": 2,
  "output_format": "png"
}
```

**Output**

```json
[
  "https://media.modelrunner.ai/wlPZZguKeUWHJ6vCQPpE4.png",
  "https://media.modelrunner.ai/8S4Ekt10GAvpbtBmEne06.png"
]
```
## Usage Examples

### cURL

The queue API is asynchronous: submit the request, poll `status_url` until it is `COMPLETED`, then read the result from `response_url`. Requires `jq`.

```bash
# 1. Submit the request (returns request handles, not the output)
SUBMIT=$(curl --silent --request POST \
  --url https://queue.modelrunner.run/google/nano-banana \
  --header "Authorization: Key $MODEL_RUNNER_KEY" \
  --header "Content-Type: application/json" \
  --data '{
  "prompt": "A highly realistic aerial photograph showing a large balloon floating on the surface of the sea, perfectly shaped like the provided logo. The scene is captured from above, with the balloon centered in the frame. Gentle waves surround it, and the sunlight reflects softly off the water, emphasizing the logo’s shape and color.",
  "image_urls": [
    "https://media.modelrunner.ai/UY25DbajyBabWHTB"
  ],
  "num_outputs": 2,
  "output_format": "png"
}')

STATUS_URL=$(echo "$SUBMIT" | jq -r '.status_url')
RESPONSE_URL=$(echo "$SUBMIT" | jq -r '.response_url')

# 2. Poll until the request leaves the queue / in-progress state
while true; do
  STATUS=$(curl --silent --url "$STATUS_URL" \
    --header "Authorization: Key $MODEL_RUNNER_KEY" | jq -r '.status')
  echo "Status: $STATUS"
  case "$STATUS" in
    COMPLETED) break ;;
    FAILED|CANCELLED) echo "Request $STATUS"; exit 1 ;;
  esac
  sleep 1
done

# 3. Read the finished request, including the generated output
curl --silent --url "$RESPONSE_URL" \
  --header "Authorization: Key $MODEL_RUNNER_KEY"
```

### JavaScript

```javascript
import { modelrunner } from "@modelrunner/client";

const result = await modelrunner.subscribe("google/nano-banana", {
  input: {
  "prompt": "A highly realistic aerial photograph showing a large balloon floating on the surface of the sea, perfectly shaped like the provided logo. The scene is captured from above, with the balloon centered in the frame. Gentle waves surround it, and the sunlight reflects softly off the water, emphasizing the logo’s shape and color.",
  "image_urls": [
    "https://media.modelrunner.ai/UY25DbajyBabWHTB"
  ],
  "num_outputs": 2,
  "output_format": "png"
}
});

console.log(result.data);
```

### Python

```python
import asyncio
import modelrunner_ai

async def main():
    response = await modelrunner_ai.submit_async(
        "google/nano-banana",
        arguments={
  "prompt": "A highly realistic aerial photograph showing a large balloon floating on the surface of the sea, perfectly shaped like the provided logo. The scene is captured from above, with the balloon centered in the frame. Gentle waves surround it, and the sunlight reflects softly off the water, emphasizing the logo’s shape and color.",
  "image_urls": [
    "https://media.modelrunner.ai/UY25DbajyBabWHTB"
  ],
  "num_outputs": 2,
  "output_format": "png"
}
    )
    result = await response.get()
    print(result["output"])

asyncio.run(main())
```

## Additional Resources

- [Playground](https://modelrunner.ai/models/google/nano-banana)
- [OpenAPI Schema](https://modelrunner.ai/models/google/nano-banana/openapi.json)
- [LLM Instructions](https://modelrunner.ai/models/google/nano-banana/llms.txt)