# GPT-4o - Core.Today AI API

> OpenAI's flagship multimodal model. Industry-leading performance in reasoning, coding, and creative tasks with native vision capabilities and structured output support.

- **Provider**: OpenAI
- **Model ID**: gpt-4o
- **Category**: LLM
- **Credits**: 3 per 1K tokens (avg)
- **Speed**: Fast
- **Quality**: Ultra

## 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**: 4,645 credits ($3.10)
- **Output Tokens**: 18,580 credits ($12.39)
- **Cached Tokens**: 2,322.5 credits ($1.55)

## Features
- Native multimodal (text + vision + audio)
- 128K context window
- 16K max output tokens
- Function calling & JSON mode
- Structured outputs
- Image understanding & analysis

## Use Cases
- Complex reasoning and analysis
- Code generation and debugging
- Content creation and editing
- Data extraction from documents/images
- Multi-step task automation
- Customer support chatbots

## 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-4o) - Model identifier

### Optional
- **temperature**: float (default: 1.0) - Sampling temperature (0-2). Lower = more focused, higher = more creative
- **max_tokens**: integer (default: 4096) - Maximum tokens in response (up to 16384)
- **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
- **top_p**: float (default: 1.0) - Nucleus sampling threshold (0-1)

## Examples

### Basic Chat
Simple conversation with the model
```json
{
  "model": "gpt-4o",
  "messages": [
    {
      "role": "system",
      "content": "You are a helpful assistant."
    },
    {
      "role": "user",
      "content": "Explain quantum computing in simple terms."
    }
  ],
  "temperature": 0.7,
  "max_tokens": 1000
}
```

### Code Generation
Generate Python code with explanation
```json
{
  "model": "gpt-4o",
  "messages": [
    {
      "role": "system",
      "content": "You are an expert Python developer. Write clean, well-documented code."
    },
    {
      "role": "user",
      "content": "Write a Python class for a binary search tree with insert, search, and delete methods."
    }
  ],
  "temperature": 0.3,
  "max_tokens": 2000
}
```

### JSON Mode
Get structured JSON output
```json
{
  "model": "gpt-4o",
  "messages": [
    {
      "role": "system",
      "content": "You are a data extraction assistant. Always respond with valid JSON."
    },
    {
      "role": "user",
      "content": "Extract the following info from this text: 'John Smith, 35 years old, software engineer at Google, living in San Francisco'. Return as JSON with fields: name, age, job, company, city"
    }
  ],
  "response_format": {
    "type": "json_object"
  },
  "max_tokens": 500
}
```

### Vision Analysis
Analyze images with GPT-4o
```json
{
  "model": "gpt-4o",
  "messages": [
    {
      "role": "user",
      "content": [
        {
          "type": "text",
          "text": "What's in this image? Describe it in detail."
        },
        {
          "type": "image_url",
          "image_url": {
            "url": "https://example.com/image.jpg"
          }
        }
      ]
    }
  ],
  "max_tokens": 1000
}
```

### Function Calling
Use tools/functions with the model
```json
{
  "model": "gpt-4o",
  "messages": [
    {
      "role": "user",
      "content": "What's the weather like in Seoul today?"
    }
  ],
  "tools": [
    {
      "type": "function",
      "function": {
        "name": "get_weather",
        "description": "Get current weather for a location",
        "parameters": {
          "type": "object",
          "properties": {
            "location": {
              "type": "string",
              "description": "City name"
            },
            "unit": {
              "type": "string",
              "enum": [
                "celsius",
                "fahrenheit"
              ]
            }
          },
          "required": [
            "location"
          ]
        }
      }
    }
  ]
}
```

## 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
- Use system messages to set behavior and constraints
- Lower temperature (0.1-0.3) for factual/coding tasks
- Higher temperature (0.7-1.0) for creative writing
- Enable JSON mode for structured data extraction
- Use function calling for tool integration
- Vision works with URLs or base64-encoded images
- Streaming reduces time-to-first-token significantly

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