# GPT Audio Mini - Core.Today AI API

> Lightweight multimodal model with native audio input/output capabilities. Optimized for voice-based interactions and audio processing tasks.

- **Provider**: OpenAI
- **Model ID**: gpt-audio-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**: 2024-10
- **Supported Formats**: text, json, audio
- **Compatible SDK**: OpenAI

### Capabilities
- Function Calling
- Streaming
- JSON Mode
- System Prompt

### Token Pricing (per 1M tokens)
- **Input Tokens**: 1,115 credits ($0.74)
- **Output Tokens**: 4,459 credits ($2.97)

## Features
- Native audio input/output
- Voice-based interactions
- Cost-effective multimodal
- Fast response times
- Text + audio combined

## Use Cases
- Voice assistants
- Audio transcription and analysis
- Spoken language understanding
- Podcast and media processing
- Accessibility applications

## 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 (supports audio content)

### Optional
- **temperature**: float (default: 1.0) - Sampling temperature (0-2)
- **max_tokens**: integer - Maximum tokens in response

## Examples

### Audio Chat
Text-based interaction with audio model
```json
{
  "model": "gpt-audio-mini",
  "messages": [
    {
      "role": "user",
      "content": "Describe the key differences between spoken and written language."
    }
  ],
  "max_tokens": 1000
}
```

## 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
- Optimized for audio-related tasks
- Cost-effective for voice applications
- Supports both text and audio modalities
- Use for real-time voice interactions

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