# GPT-5 Pro: AI model fact sheet

- **Provider:** openai
- **Released:** 2025-10-06
- **Context window:** 400,000 tokens
- **API pricing:** $15.00 / 1M input, $120.00 / 1M output
- **OpenRouter ID:** openai/gpt-5-pro
- **Capabilities:** conversation, reasoning, code-generation, analysis

GPT-5 Pro is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. Optimized for complex, high-stakes tasks that demand step-by-step reasoning, instruction following, and accuracy. Supports test-time routing controls and advanced prompt understanding, including intent cues like "think hard about this". Delivers reduced hallucination, lower sycophancy, and stronger performance across coding, writing, and health-related workloads.

## Benchmarks

| Benchmark | Score |
| --- | --- |
| GPQA Diamond | 88.4% |
| AIME 2025 | 100% |
| HMMT Feb 2025 | 100% |
| SWE-bench Verified | 74.9% |
| LiveCodeBench | 54.3% |
| Humanity's Last Exam | 42.0% |

Source: real side-by-side outputs, pricing and specs at https://rival.tips/models/gpt-5-pro