# Nano Banana Pro (Gemini 3 Pro Image) - Core.Today AI API

> Google's state-of-the-art image generation and editing model built on Gemini 3 Pro. Creates detailed visuals with legible text in multiple languages, connects to real-time information from Google Search, and provides professional-grade creative controls. Supports up to 14 reference images and resolutions up to 4K.

- **Provider**: Google
- **Model ID**: google/nano-banana-pro
- **Category**: Image Generation
- **Credits**: 350 per image (1K/2K), 700 credits for 4K
- **Speed**: Medium
- **Quality**: Ultra

## Features
- Gemini 3 Pro-powered generation with advanced reasoning
- Legible text rendering in multiple languages
- Google Search integration for real-time data visualization
- Up to 14 reference images for multi-image blending
- Up to 4K output resolution (1K, 2K, 4K)

## Use Cases
- Typography, logos, and branding with accurate text
- Multilingual marketing materials and localization
- Data-driven infographics and educational content
- Multi-image product mockups and lifestyle scenes
- Professional photo editing with creative controls

## 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, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9
- **resolution**: string (default: 2K) - Resolution of the generated image
  Options: 1K, 2K, 4K
- **output_format**: string (default: jpg) - Format of the output image
  Options: jpg, png
- **safety_filter_level**: string (default: block_only_high) - Safety filter strictness level
  Options: block_low_and_above, block_medium_and_above, block_only_high
- **allow_fallback_model**: boolean (default: false) - Fallback to another model (currently bytedance/seedream-5) if Nano Banana Pro is at capacity.

## Examples

### Location-based Image
Generate an image from GPS coordinates and time
```json
{
  "model": "google/nano-banana-pro",
  "input": {
    "prompt": "35.6586° N, 139.7454° E at 19:00",
    "resolution": "2K",
    "aspect_ratio": "4:3",
    "output_format": "png"
  }
}
```

### Multi-image Team Photo
Blend multiple reference images into a single composition
```json
{
  "model": "google/nano-banana-pro",
  "input": {
    "prompt": "an office team photo, everyone making a silly face",
    "resolution": "2K",
    "aspect_ratio": "4:3"
  }
}
```

## 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
- Excels at rendering accurate, legible text in images — ideal for posters, logos, and infographics
- Use Google Search-powered prompts (e.g., real-time weather, sports scores) for data-driven visuals
- Blend up to 14 reference images for complex compositions with consistent character appearance
- Use 2K resolution for most tasks; reserve 4K (1125 credits) for final production assets
- Consider using Nano Banana (117 credits) for quick drafts before final generation