# o3 - Core.Today AI API

> OpenAI's frontier reasoning model. Uses extended chain-of-thought to solve complex problems in science, coding, and math with high accuracy at a competitive price.

- **Provider**: OpenAI
- **Model ID**: o3
- **Category**: LLM
- **Credits**: 9 per 1K tokens (avg)
- **Speed**: Medium
- **Quality**: Ultra

## Model Specifications
- **Context Window**: 200K tokens
- **Max Output**: 100K tokens
- **Training Cutoff**: 2024-06
- **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**: 3,716 credits ($2.48)
- **Output Tokens**: 14,864 credits ($9.91)
- **Cached Tokens**: 929 credits ($0.62)

## Features
- Frontier chain-of-thought reasoning
- 200K context window
- 100K max output tokens
- Vision capabilities
- Function calling support
- Discounted cached input tokens

## Use Cases
- Scientific research
- Complex mathematics
- Advanced code generation and debugging
- Multi-step agentic reasoning
- Strategic planning

## 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
- **model**: string (default: o3) - Model identifier

### Optional
- **max_completion_tokens**: integer - Maximum tokens for completion (includes reasoning tokens)
- **reasoning_effort**: string (default: medium) - Reasoning effort level: low, medium, high
  Options: low, medium, high

## Examples

### Complex Math
Solve advanced math problems with o3
```json
{
  "model": "o3",
  "messages": [
    {
      "role": "user",
      "content": "Find all integer solutions to x^2 + y^2 = z^2 where x, y, z are consecutive terms of an arithmetic progression. Show your reasoning."
    }
  ],
  "reasoning_effort": "high"
}
```

### Code Debugging
Deep debugging with step-by-step reasoning
```json
{
  "model": "o3",
  "messages": [
    {
      "role": "user",
      "content": "This async Python function deadlocks intermittently under load. Walk through the possible interleavings and find the bug: [code snippet]"
    }
  ],
  "max_completion_tokens": 8000
}
```

## 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
- Use max_completion_tokens instead of max_tokens - temperature is not supported
- Use reasoning_effort='high' for the most complex problems
- Cached input tokens are billed at a steep discount - reuse long system prompts
- For maximum reliability on the hardest tasks, consider o3-pro

## Documentation
https://platform.openai.com/docs/models/o3