# Nano Banana 2.1

> Google's latest fast image generation model — the high-efficiency counterpart to Nano Banana Pro. Builds on Nano Banana 2 with sharper output, better text rendering, conversational editing, multi-image fusion (up to 14 references), Google Search / Image Search grounding, and up to 4K output.

- **Provider**: replicate
- **Model ID**: google/nano-banana-2.1
- **Category**: image_generation
- **Credits**: from 79 for the default configuration — varies by input, see Pricing
- **Pricing Type**: input_based

## API Endpoint

Base URL: https://api.core.today/v1

### Create Prediction
POST /predictions

### Get Status
GET /predictions/{job_id}

### Cancel
DELETE /predictions/{job_id}

## Authentication

Header: `X-API-Key: YOUR_API_KEY`

## Input Parameters

- `prompt` (string, **required**): A text description of the image you want to generate
- `image_input` (array, optional): Input images to transform or use as reference (supports up to 14 images)
- `aspect_ratio` (string, optional): Aspect ratio of the generated image (Default: `match_input_image`; Options: `match_input_image`, `1:1`, `1:4`, `1:8`, `2:3`, `3:2`, `3:4`, `4:1`, `4:3`, `4:5`, `5:4`, `8:1`, `9:16`, `16:9`, `21:9`)
- `output_format` (string, optional): Format of the output image (Default: `jpg`; Options: `jpg`, `png`)
- `image_search` (boolean, optional): Use Google Image Search grounding to find web images as visual context for generation. When enabled, web search is also used automatically. (Default: `false`)
- `google_search` (boolean, optional): Use Google Web Search grounding to generate images based on real-time information (e.g. weather, sports scores, recent events). (Default: `false`)
- `resolution` (string, optional): Resolution of the generated image. Higher resolutions take longer to generate. (Default: `1K`; Options: `1K`, `2K`, `4K`)

## Example Request

```json
{
  "model": "google/nano-banana-2.1",
  "input": {
    "image_input": [],
    "aspect_ratio": "16:9",
    "output_format": "jpg",
    "prompt": "a photorealistic close-up of a ripe banana wearing tiny sunglasses on a beach, golden hour lighting",
    "resolution": "1K"
  }
}
```

## Response Format

```json
{
  "job_id": "abc123",
  "status": "pending",
  "provider": "replicate",
  "model": "google/nano-banana-2.1",
  "created_at": "2026-01-01T00:00:00Z",
  "result": null,
  "error": null,
  "credits_used": null
}
```

Status values: `pending`, `processing`, `completed`, `failed`, `cancelled`

When the job is `completed`, `result` holds the output URL(s) or data and `credits_used` the net credits charged. When it is `failed`, `error` and `error_code` say why and the charge is refunded.

## Usage Flow

1. POST /predictions with model and input → receive job_id
2. Poll GET /predictions/{job_id} until status is `completed` or `failed`
3. Result contains output URL(s) or data

## Pricing

Charged by input. Rules are checked top to bottom and the first match applies:

- When `resolution` = `1K`: 78.12 credits per request
- When `resolution` = `2K`: 117.18 credits per request
- When `resolution` = `4K`: 263.655 credits per request
- Otherwise: 78.12 credits per request

Default configuration: 79 credits.

These are list prices. The amount charged is rounded, and large charges are discounted progressively. `POST /predictions/estimate` with the same `model` and `input` returns the charge for that input without creating a job (an estimate when the price depends on the output).

## Output Type

url

## Tags

image-generation, text-to-image, image-editing, typography, multilingual, gemini, google, character-consistency, multi-image-fusion, conversational-editing, google-search, synthid

## Documentation

https://replicate.com/google/nano-banana-2.1