# Gemini 3.1 Pro Preview - Core.Today AI API

> Google's latest and most capable Gemini model in preview. Features dynamic pricing that adjusts based on context length, with enhanced pricing for inputs over 200K tokens.

- **Provider**: Google
- **Model ID**: gemini-3.1-pro-preview
- **Category**: LLM
- **Credits**: 500 per request
- **Speed**: Medium
- **Quality**: Ultra

## Model Specifications
- **Context Window**: 1.0M tokens
- **Max Output**: 66K tokens
- **Training Cutoff**: January 2025
- **Supported Formats**: text, json, markdown
- **Compatible SDK**: OpenAI, Google AI

### Capabilities
- Vision (image input)
- Function Calling
- Streaming
- JSON Mode
- System Prompt

### Token Pricing (per 1M tokens)
- **Input Tokens**: 3,716 credits ($2.48)
- **Output Tokens**: 22,296 credits ($14.86)

## Features
- Dynamic pricing (standard / long-context >200K)
- Advanced reasoning and analysis
- 1,048,576 token context window
- 65,536 max output tokens
- Multimodal input: text, image, audio, video, PDF
- Function calling, structured outputs, thinking, search grounding, code execution, caching, Batch API

## Use Cases
- Complex reasoning and research tasks
- Long document analysis and summarization
- Multimodal content understanding
- Advanced code generation and review
- Scientific and mathematical problem solving

## 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). Supports text, image, video, audio, and PDF inputs.

### Optional
- **temperature**: float (default: 1) - Sampling temperature (0-2). Lower values produce more deterministic outputs.
- **top_p**: float (default: 0.95) - Nucleus sampling parameter (0-1).
- **max_tokens**: integer - Maximum output tokens. Max: 65,536. Context window (input + output): 1,048,576 tokens.
- **stop**: string | array - Up to 4 sequences where the model stops generating.
- **response_format**: object - Output format constraint. Use `{ type: 'json_object' }` for structured JSON output.
- **presence_penalty**: float (default: 0) - Penalty (-2.0 to 2.0) for repeating tokens.
- **frequency_penalty**: float (default: 0) - Penalty (-2.0 to 2.0) by token frequency.
- **seed**: integer - Seed for deterministic sampling (best-effort).
- **stream**: boolean (default: false) - Enable Server-Sent Events streaming.

## Examples

### Research Analysis
In-depth analysis with Gemini 3.1 Pro
```json
{
  "model": "gemini-3.1-pro-preview",
  "messages": [
    {
      "role": "user",
      "content": "Analyze the current state of quantum error correction research and identify the most promising approaches for achieving fault-tolerant quantum computing by 2030."
    }
  ],
  "max_tokens": 4096,
  "temperature": 0.5
}
```

## 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: 65,536 — set max_tokens up to this limit
- Context window 1,048,576 tokens (input + output)
- Dynamic pricing: inputs >200K tokens use long-context pricing ($4.00/$18.00 per M)
- Keep inputs under 200K tokens when possible for standard pricing
- Excellent for research, analysis, and complex reasoning tasks
- Combine with vision inputs for document and diagram analysis

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