# GPT-4.5: AI model fact sheet

- **Provider:** openai
- **Released:** 2025-02-27
- **Context window:** 128,000 tokens
- **Parameters:** Not disclosed
- **API pricing:** $75.00 / 1M input, $150.00 / 1M output
- **OpenRouter ID:** openai/gpt-4.5-preview
- **Capabilities:** conversation, reasoning, code-generation, analysis, summarization

GPT-4.5 is a step forward in scaling up pre-training and post-training. With broader knowledge, improved intent understanding, and greater 'EQ', it excels at natural conversations, writing, programming, and practical problem solving with reduced hallucinations. GPT-4.5 achieved 62.5% accuracy on SimpleQA and a 37.1% hallucination rate, significantly outperforming GPT-4o and other models.

## Benchmarks

| Benchmark | Score |
| --- | --- |
| MMLU | 90.8% |
| MATH | 87.1% |
| GPQA | 69.5% |
| SimpleQA | 62.5% |
| SWE-bench Verified | 28.0% |

Source: real side-by-side outputs, pricing and specs at https://rival.tips/models/gpt-4.5