# Gemini 2.5 Flash - Core.Today AI API

> Google's fast and efficient model with built-in thinking capabilities. Great balance of speed, reasoning, and cost for high-volume applications.

- **Provider**: Google
- **Model ID**: gemini-2.5-flash
- **Category**: LLM
- **Credits**: 1 per 1K tokens (avg)
- **Speed**: Fast
- **Quality**: High

## Model Specifications
- **Context Window**: 1.0M tokens
- **Max Output**: 66K tokens
- **Training Cutoff**: 2025-01
- **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**: 557 credits ($0.37)
- **Output Tokens**: 4,645 credits ($3.10)

## Features
- 1,048,576 token context window
- 65,536 max output tokens
- Multimodal input: text, image, video, audio
- Built-in thinking mode
- Function calling, structured outputs, code execution
- Search grounding, caching, Batch API
- Cost-effective

## Use Cases
- Complex math problems
- Multi-step reasoning
- Scientific analysis
- Debugging complex code
- High-volume applications

## 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, and audio inputs.

### Optional
- **temperature**: float (default: 1.0) - Sampling temperature (0-2).
- **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

### Complex Problem
Solve with step-by-step reasoning
```json
{
  "model": "gemini-2.5-flash",
  "messages": [
    {
      "role": "user",
      "content": "A train leaves station A at 9 AM traveling at 60 mph. Another train leaves station B (300 miles away) at 10 AM traveling toward A at 80 mph. When and where will they meet?"
    }
  ],
  "max_tokens": 4000
}
```

## 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 for problems requiring step-by-step reasoning
- Most cost-effective Gemini model with thinking
- Supports OpenAI SDK format for easy migration
- Great for high-volume applications

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