# GPT Audio - Core.Today AI API

> Full-size multimodal model with native audio input/output via chat completions. Handles speech in and speech out with strong general intelligence behind it.

- **Provider**: OpenAI
- **Model ID**: gpt-audio
- **Category**: LLM
- **Credits**: 12 per 1K tokens (avg)
- **Speed**: Medium
- **Quality**: Ultra

## 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**: 4,645 credits ($3.10)
- **Output Tokens**: 18,580 credits ($12.39)

## Features
- Native audio input/output
- Full-size model quality for voice
- Speech in / speech out via chat completions
- Text + audio combined
- Audio tokens billed at separate audio rates upstream

## Use Cases
- High-quality 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 the audio model
```json
{
  "model": "gpt-audio",
  "messages": [
    {
      "role": "user",
      "content": "Summarize the main techniques used in professional podcast audio mastering."
    }
  ],
  "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
- Works with the OpenAI SDK - set base_url to https://ai.api.core.today/llm/openai/v1
- Full-size sibling of GPT Audio Mini - use it when voice quality and intelligence matter most
- Listed rates cover text tokens - audio tokens are billed at separate audio rates upstream
- Supports both text and audio modalities in the same conversation

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