# OpenAI o4-mini - Core.Today AI API

> Fast, cost-effective reasoning model optimized for coding and STEM tasks. Provides strong reasoning at a fraction of the cost of larger reasoning models.

- **Provider**: OpenAI
- **Model ID**: o4-mini
- **Category**: LLM
- **Credits**: 2 per 1K tokens (avg)
- **Speed**: Fast
- **Quality**: Ultra

## Model Specifications
- **Context Window**: 200K tokens
- **Max Output**: 100K tokens
- **Training Cutoff**: 2025-03
- **Supported Formats**: text, markdown, json
- **Compatible SDK**: OpenAI

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

### Token Pricing (per 1M tokens)
- **Input Tokens**: 2,044 credits ($1.36)
- **Output Tokens**: 8,175 credits ($5.45)

## Features
- Optimized for coding/STEM
- 200K context window
- 100K max output tokens
- Fast reasoning
- Cost-effective reasoning

## Use Cases
- Code generation and review
- Scientific calculations
- Technical problem solving
- Educational applications
- Competitive programming

## API Endpoint

Base URL: https://api.core.today
Endpoint: POST /llm/openai/v1/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

### Optional
- **max_completion_tokens**: integer - Maximum tokens for completion
- **reasoning_effort**: string - Reasoning depth level
  Options: minimal, low, medium, high

## Examples

### Code Review
Review and improve code
```json
{
  "model": "o4-mini",
  "messages": [
    {
      "role": "user",
      "content": "Review this code and suggest improvements:\n\ndef fib(n):\n    if n <= 1: return n\n    return fib(n-1) + fib(n-2)"
    }
  ],
  "max_completion_tokens": 16000,
  "reasoning_effort": "medium"
}
```

## 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
- Best for coding and STEM tasks
- Most cost-effective reasoning model
- Use reasoning_effort to balance speed vs depth
- Use max_completion_tokens instead of max_tokens

## Documentation
https://platform.openai.com/docs/models