# o3 Pro - Core.Today AI API

> Highest-effort version of o3. Thinks longer with more compute to deliver the most reliable answers on the hardest science, math, and coding problems.

- **Provider**: OpenAI
- **Model ID**: o3-pro
- **Category**: LLM
- **Credits**: 93 per 1K tokens (avg)
- **Speed**: Slow
- **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**: 37,160 credits ($24.77)
- **Output Tokens**: 148,640 credits ($99.09)

## Features
- Highest-effort o3 reasoning
- 200K context window
- 100K max output tokens
- Vision capabilities
- Function calling support
- Most reliable answers on hardest problems

## Use Cases
- High-stakes scientific analysis
- Hardest mathematical proofs
- Critical code review and verification
- Complex strategic decisions

## 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-pro) - Model identifier

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

## Examples

### High-Stakes Verification
Most reliable reasoning with o3 Pro
```json
{
  "model": "o3-pro",
  "messages": [
    {
      "role": "user",
      "content": "Verify whether this cryptographic key-exchange protocol is vulnerable to man-in-the-middle attacks. Enumerate every assumption and attack vector."
    }
  ],
  "max_completion_tokens": 16000
}
```

## 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
- Responses can take several minutes - it thinks much longer than o3
- Reserve for problems where reliability matters most - o3 is ~10x cheaper
- Budget generous max_completion_tokens - reasoning tokens count toward the limit

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