# GPT-5 Pro - Core.Today AI API

> OpenAI's maximum-capability GPT-5 tier. Uses more compute to think longer and deliver the most reliable answers on the hardest reasoning, coding, and analysis tasks.

- **Provider**: OpenAI
- **Model ID**: gpt-5-pro
- **Category**: LLM
- **Credits**: 125 per 1K tokens (avg)
- **Speed**: Slow
- **Quality**: Ultra

## Model Specifications
- **Context Window**: 400K tokens
- **Max Output**: 272K tokens
- **Training Cutoff**: 2025-03
- **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**: 27,870 credits ($18.58)
- **Output Tokens**: 222,960 credits ($149)

## Features
- Maximum-capability GPT-5 tier
- 400K context window
- 272K max output tokens
- Extended thinking for hardest problems
- Native vision (text + image)
- Function calling & JSON mode

## Use Cases
- Hardest multi-step reasoning problems
- High-stakes code review and architecture
- Scientific and mathematical analysis
- Complex agentic workflows
- Long-document synthesis at maximum quality

## 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-5-pro) - Model identifier

### Optional
- **max_completion_tokens**: integer - Maximum tokens in response (includes internal reasoning tokens). Note: use max_completion_tokens, not max_tokens
- **reasoning_effort**: string - Reasoning effort level: low, medium, or high
  Options: low, medium, high
- **stream**: boolean (default: false) - Enable Server-Sent Events streaming

## Examples

### Hardest Reasoning
Maximum-effort analysis with GPT-5 Pro
```json
{
  "model": "gpt-5-pro",
  "messages": [
    {
      "role": "user",
      "content": "Design a distributed consensus protocol tolerant to Byzantine faults for a 7-node cluster, prove its safety properties, and provide pseudocode."
    }
  ],
  "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
- Reserve for the hardest problems - standard GPT-5 is far cheaper for routine tasks
- Responses take longer due to extended internal thinking
- Budget generous max_completion_tokens - reasoning tokens count toward the limit

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