# GPT-5 Mini - Core.Today AI API

> Fast and efficient variant of GPT-5. Delivers strong performance across reasoning, coding, and creative tasks with a 1M token context window and 32K output tokens, at a fraction of the cost of GPT-5.

- **Provider**: OpenAI
- **Model ID**: gpt-5-mini
- **Category**: LLM
- **Credits**: 1 per 1K tokens (avg)
- **Speed**: Fast
- **Quality**: High

## Model Specifications
- **Context Window**: 1.0M tokens
- **Max Output**: 33K tokens
- **Training Cutoff**: 2025-03
- **Supported Formats**: text, json, markdown
- **Compatible SDK**: OpenAI

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

### Token Pricing (per 1M tokens)
- **Input Tokens**: 464 credits ($0.31)
- **Output Tokens**: 3,716 credits ($2.48)
- **Cached Tokens**: 46.45 credits ($0.03)

## Features
- 1M token context window
- 32K max output tokens
- Fast inference speed
- Native vision (text + image)
- Function calling & JSON mode
- Structured outputs
- Cost-effective GPT-5 performance

## Use Cases
- General-purpose chat and assistance
- Code generation and debugging
- Document summarization
- Content creation and editing
- Data extraction and classification
- API integration and automation

## 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 with role and content
- **model**: string (default: gpt-5-mini) - Model identifier

### Optional
- **max_completion_tokens**: integer (default: 4096) - Maximum tokens in response (up to 32768). Note: use max_completion_tokens, not max_tokens
- **reasoning_effort**: string (default: medium) - Reasoning effort level: low, medium, or high
- **stream**: boolean (default: false) - Enable Server-Sent Events streaming
- **response_format**: object - Format of response: { type: 'json_object' } for JSON mode
- **tools**: array - List of tools (functions) the model can call

## Examples

### Quick Chat
Efficient general-purpose conversation with GPT-5 Mini
```json
{
  "model": "gpt-5-mini",
  "messages": [
    {
      "role": "system",
      "content": "You are a helpful assistant. Be concise and clear."
    },
    {
      "role": "user",
      "content": "Explain the difference between REST and GraphQL APIs, including when to use each."
    }
  ],
  "max_completion_tokens": 2000
}
```

### Code Debugging
Debug code efficiently with GPT-5 Mini
```json
{
  "model": "gpt-5-mini",
  "messages": [
    {
      "role": "system",
      "content": "You are an expert debugger. Find and fix bugs in the provided code."
    },
    {
      "role": "user",
      "content": "This Python function should return the nth Fibonacci number but it's running too slowly for large n. Optimize it:\n\ndef fib(n):\n    if n <= 1:\n        return n\n    return fib(n-1) + fib(n-2)"
    }
  ],
  "max_completion_tokens": 2000
}
```

## 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 value for most everyday tasks — strong performance at low cost
- 5x cheaper than GPT-5 on input tokens, 5x cheaper on output tokens
- 1M context window same as GPT-5 for long document processing
- Ideal for high-volume applications where cost matters
- Use for chat, summarization, and code tasks
- Streaming recommended for responsive user experience

## Documentation
https://platform.openai.com/docs/models/gpt-5-mini