# Gemini 3 Pro Image Preview - Core.Today AI API

> Google's premium image generation model within the Gemini 3 Pro family. Generates high-quality images directly in chat with the highest fidelity among Gemini image models. Image output tokens are priced at 10x text output tokens.

- **Provider**: Google
- **Model ID**: gemini-3-pro-image-preview
- **Category**: LLM
- **Credits**: 500 per request
- **Speed**: Medium
- **Quality**: Ultra

## Model Specifications
- **Context Window**: 66K tokens
- **Max Output**: 33K tokens
- **Training Cutoff**: January 2025
- **Supported Formats**: text, json, markdown, image
- **Compatible SDK**: OpenAI, Google AI

### Capabilities
- Vision (image input)
- Streaming
- JSON Mode
- System Prompt
- Image Generation

### Token Pricing (per 1M tokens)
- **Input Tokens**: 3,716 credits ($2.48)
- **Output Tokens**: 22,296 credits ($14.86)
- **Image Output Tokens**: 222,960 credits ($149)
  Note: ~1,120 tokens per 1024px image

## Features
- Premium image generation quality
- 65,536 token context window
- 32,768 max output tokens
- Input modalities: image + text
- Output modalities: image + text
- 10x pricing for image vs text output tokens
- Structured outputs, thinking, search grounding, Batch API

## Use Cases
- High-fidelity image generation
- Creative design and illustration
- Image editing with natural language
- Visual storytelling
- Product visualization and mockups

## API Endpoint

Base URL: https://api.core.today
Endpoint: POST /llm/gemini/v1beta/openai/chat/completions

## Authentication
Header: Authorization: Bearer YOUR_API_KEY

Note: LLM endpoints use OpenAI-compatible format with Authorization Bearer token.

## Input Parameters

### Required
- **messages**: array - Array of message objects (OpenAI format)

### Optional
- **temperature**: float (default: 1) - Sampling temperature (0-2)
- **top_p**: float (default: 0.95) - Nucleus sampling parameter
- **max_tokens**: integer - Maximum output tokens (text + image combined). Max: 32,768. Context window (input + output): 65,536 tokens.
- **stream**: boolean (default: false) - Enable Server-Sent Events streaming

## Examples

### Text Chat
Standard text conversation using Pro capabilities
```json
{
  "model": "gemini-3-pro-image-preview",
  "messages": [
    {
      "role": "user",
      "content": "Explain the principles of color theory and how they apply to digital design."
    }
  ],
  "max_tokens": 2000,
  "temperature": 0.7
}
```

### Image Generation
Generate a high-quality image through natural language
```json
{
  "model": "gemini-3-pro-image-preview",
  "messages": [
    {
      "role": "user",
      "content": "Generate a photorealistic image of a futuristic city skyline at golden hour, with flying vehicles and vertical gardens on skyscrapers."
    }
  ],
  "max_tokens": 4096
}
```

## Response Format
```json
{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Response text here"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 100,
    "completion_tokens": 50,
    "total_tokens": 150
  }
}
```

## Tips
- Max output tokens: 32,768 (combined text + image output)
- Context window 65,536 tokens — much smaller than other Gemini 3 Pro models
- Image output tokens are priced at $120.00/M (~120,000 credits/M) — 10x text output
- Each 1024px image uses approximately 1,120 output tokens (~134 credits per image)
- Text-only responses use standard text output pricing ($12.00/M)
- Function calling, caching, code execution, Live API are NOT supported
- Best image quality among Gemini models — use for premium visual content

## Documentation
https://ai.google.dev/gemini-api/docs