# Nano Banana 2.1 - Core.Today AI API

> 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, and real-time grounding while keeping Flash-family speed and cost. Features conversational editing, multi-image fusion with up to 14 reference images, Google Web / Image Search grounding, and resolutions up to 4K.

- **Provider**: Google
- **Model ID**: google/nano-banana-2.1
- **Category**: Image Generation
- **Credits**: 79 per image (1K), 120 for 2K, 260 for 4K
- **Speed**: Fast
- **Quality**: Ultra

## Features
- Sharper output and better text rendering than Nano Banana 2
- Accurate multilingual text in signage, posters, labels, and infographics
- Google Web Search and Image Search grounding for real-time context
- Up to 14 reference images for editing and multi-image fusion
- Up to 4K output resolution (1K, 2K, 4K)
- Extreme aspect ratios: 1:4, 4:1, 1:8, 8:1

## Use Cases
- Typography, logos, and branding with accurate multilingual text
- Infographics and posters that need clean, readable text
- Real-time data visualization using Google Search grounding
- Conversational image editing with reference images
- High-resolution content production up to 4K at Flash-level cost

## API Endpoint

Base URL: https://api.core.today/v1
Create Prediction: POST /predictions
Get Status: GET /predictions/{job_id}

## Authentication
Header: X-API-Key: YOUR_API_KEY

## Input Parameters

### Required
- **prompt**: string - A text description of the image you want to generate

### Optional
- **image_input**: array (default: []) - Input images to transform or use as reference (supports up to 14 images)
- **aspect_ratio**: string (default: match_input_image) - Aspect ratio of the generated 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
- **resolution**: string (default: 1K) - Resolution of the generated image. Higher resolutions take longer to generate.
  Options: 1K, 2K, 4K
- **google_search**: boolean (default: false) - Use Google Web Search grounding for real-time information (weather, sports scores, recent events)
- **image_search**: boolean (default: false) - Use Google Image Search grounding for visual context. Enabling this also enables web search.
- **output_format**: string (default: jpg) - Format of the output image
  Options: jpg, png

## Examples

### Text Rendering in a Scene
Render a brand name as hand-painted lettering on a storefront window
```json
{
  "model": "google/nano-banana-2.1",
  "input": {
    "prompt": "A vibrant storefront window display for a bakery called \"CORE.TODAY\", with the name spelled out in elegant hand-painted gold lettering on the glass, fresh pastries and banana bread artfully arranged inside, warm morning light, photorealistic, highly detailed",
    "aspect_ratio": "16:9",
    "resolution": "1K",
    "output_format": "jpg"
  }
}
```

### Photorealistic Close-up
Generate a playful photorealistic image with golden hour lighting
```json
{
  "model": "google/nano-banana-2.1",
  "input": {
    "prompt": "a photorealistic close-up of a ripe banana wearing tiny sunglasses on a beach, golden hour lighting",
    "aspect_ratio": "16:9",
    "resolution": "1K"
  }
}
```

## Response Format
```json
{
  "job_id": "abc123",
  "status": "pending | processing | completed | failed",
  "result": "URL or data (when completed)"
}
```

## Usage Flow
1. POST /predictions with model and input -> receive job_id
2. GET /predictions/{job_id} -> poll until status is completed or failed
3. Result contains output URL(s)

## Tips
- Cheapest way to get Nano Banana quality — 1K costs 79 credits, less than half of Nano Banana 2
- Text rendering is sharper than Nano Banana 2 — put exact wording in quotes for signage, posters, and labels
- Use google_search for real-time data (weather, sports, news); image_search adds web images as visual context
- Use 1K (79 credits) for drafts and 4K (260 credits) only for final production assets
- Set aspect_ratio to match_input_image when editing to keep the original framing
- Combine up to 14 reference images with a text prompt for style fusion and character consistency