# Gemini 2.0 Flash - Core.Today AI API

> Google's fastest and most capable model. Features a massive 1M token context window, native multimodal support, and real-time capabilities.

- **Provider**: Google
- **Model ID**: gemini-2.0-flash
- **Category**: LLM
- **Credits**: 1 per 1K tokens (avg)
- **Speed**: Fast
- **Quality**: High

## Model Specifications
- **Context Window**: 1.0M tokens
- **Max Output**: 8K tokens
- **Training Cutoff**: August 2024
- **Supported Formats**: text, json, markdown
- **Compatible SDK**: OpenAI, Google

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

### Token Pricing (per 1M tokens)
- **Input Tokens**: 186 credits ($0.12)
- **Output Tokens**: 743 credits ($0.50)

## Features
- 1,048,576 token context window
- 8,192 max output tokens
- Native multimodal (text, image, audio, video)
- Real-time streaming
- Code execution, search grounding, caching, Batch API
- Grounding with Google Search
- Deprecated — migrate to Gemini 3 Flash or 2.5 Flash

## Use Cases
- Large document processing
- Multi-file code analysis
- Real-time applications
- Video understanding
- Long conversation memory
- Research assistance

## 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 supported)

### Optional
- **temperature**: float (default: 1.0) - Sampling temperature (0-2)
- **max_tokens**: integer - Maximum output tokens. Max: 8,192. Context window (input + output): 1,048,576 tokens.
- **stream**: boolean (default: false) - Enable streaming

## Examples

### Long Document Analysis
Analyze documents up to 1M tokens
```json
{
  "model": "gemini-2.0-flash",
  "messages": [
    {
      "role": "system",
      "content": "You are a document analyst. Provide comprehensive analysis."
    },
    {
      "role": "user",
      "content": "Analyze this entire codebase and identify potential security vulnerabilities: [code files]"
    }
  ],
  "max_tokens": 4000
}
```

### Video Understanding
Analyze video content
```json
{
  "model": "gemini-2.0-flash",
  "messages": [
    {
      "role": "user",
      "content": "Describe what's happening in this video and identify key moments."
    }
  ]
}
```

## 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
- Deprecated — migrate to Gemini 3 Flash or Gemini 2.5 Flash
- Max output tokens: 8,192 — much lower than 2.5/3.x Flash (65,536)
- Context window 1,048,576 tokens (input + output)
- Use for tasks requiring very long context
- Supports OpenAI SDK format for easy migration
- Can process video and audio natively

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