# Gemini 3 Flash - Core.Today AI API

> Google's most advanced reasoning model with state-of-the-art multimodal understanding, PhD-level reasoning, and leading coding performance.

- **Provider**: Google
- **Model ID**: gemini-3-flash
- **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**: 929 credits ($0.62)
- **Output Tokens**: 5,574 credits ($3.72)

## Features
- PhD-level reasoning ability
- 1,048,576 token context window
- 65,536 max output tokens
- Multimodal input: text, image, video, audio, PDF
- Thinking, structured outputs, function calling
- Search grounding, code execution, caching, Batch API
- Breakthrough mathematics capabilities

## Use Cases
- Complex reasoning tasks
- Research and analysis
- Code generation and review
- Multimodal content understanding
- Scientific 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)

### Optional
- **temperature**: float (default: 1) - Sampling temperature (0-2)
- **top_p**: float (default: 0.95) - Nucleus sampling parameter
- **max_tokens**: integer - Maximum output tokens. Max: 65,536. Context window (input + output): 1,048,576 tokens.

## Examples

### Advanced Reasoning
Solve a complex multi-step reasoning problem
```json
{
  "model": "gemini-3-flash",
  "messages": [
    {
      "role": "user",
      "content": "A researcher has 5 compounds. Compound A reacts with B to form C. C reacts with D only in the presence of a catalyst E. If only 3g of E is available and each reaction consumes 1g of catalyst, what is the maximum yield of the final product if we start with 10g each of A, B, and D?"
    }
  ],
  "max_tokens": 4096,
  "temperature": 0.5
}
```

### Code Review
Review and improve code with expert-level analysis
```json
{
  "model": "gemini-3-flash",
  "messages": [
    {
      "role": "system",
      "content": "You are a senior software engineer. Provide detailed code review with severity levels and concrete fixes."
    },
    {
      "role": "user",
      "content": "Review this Python function for performance issues and security vulnerabilities, and suggest improvements."
    }
  ],
  "max_tokens": 2000,
  "temperature": 0.3
}
```

## 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)
- Use thinking_level 'high' for complex math, logic, and multi-step reasoning
- Lower temperature (0.2-0.5) for factual, analytical, and coding tasks
- Leverage the 1M context window for processing entire codebases or long documents
- Combine vision and text inputs for diagram analysis or document understanding

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