# GPT-4o Mini - Core.Today AI API

> Cost-effective, fast model with strong performance. Best for high-volume tasks where speed and cost matter more than absolute capability.

- **Provider**: OpenAI
- **Model ID**: gpt-4o-mini
- **Category**: LLM
- **Credits**: 1 per 1K tokens (avg)
- **Speed**: Fast
- **Quality**: High

## Model Specifications
- **Context Window**: 128K tokens
- **Max Output**: 16K tokens
- **Training Cutoff**: 2023-10
- **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**: 279 credits ($0.19)
- **Output Tokens**: 1,115 credits ($0.74)
- **Cached Tokens**: 139.35 credits ($0.09)

## Features
- 128K context window
- 16K max output tokens
- Vision capabilities
- Function calling support
- Extremely cost-effective
- Fast response times

## Use Cases
- High-volume chatbots
- Simple classification tasks
- Content summarization
- Data extraction
- Batch processing
- Development and testing

## 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
- **temperature**: float (default: 1.0) - Sampling temperature (0-2)
- **max_tokens**: integer - Maximum response tokens
- **stream**: boolean (default: false) - Enable streaming

## Examples

### Classification
Classify customer feedback
```json
{
  "model": "gpt-4o-mini",
  "messages": [
    {
      "role": "system",
      "content": "Classify the sentiment of the following text as positive, negative, or neutral. Respond with only the classification."
    },
    {
      "role": "user",
      "content": "The product arrived on time and works great!"
    }
  ],
  "temperature": 0
}
```

### Summarization
Summarize long text
```json
{
  "model": "gpt-4o-mini",
  "messages": [
    {
      "role": "user",
      "content": "Summarize this article in 3 bullet points: [article text here]"
    }
  ],
  "max_tokens": 500
}
```

## 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 choice for high-volume, cost-sensitive applications
- Use for simple tasks before upgrading to GPT-4o
- Great for prototyping and testing
- Same API as GPT-4o for easy switching

## Documentation
https://platform.openai.com/docs/models/gpt-4o-mini