# Gemini 2.5 Pro Experimental: AI model fact sheet

- **Provider:** google
- **Released:** 2025-03-25
- **Context window:** 1,000,000 tokens
- **Parameters:** Not disclosed
- **API pricing:** $1.00 / 1M input, $2.00 / 1M output
- **OpenRouter ID:** google/gemini-2.5-pro-preview-03-25
- **Capabilities:** conversation, reasoning, code-generation, analysis

Gemini 2.5 Pro Experimental is Google's advanced model with improved multimodal reasoning, long context understanding with 1 million tokens, and specialized video comprehension.

## Benchmarks

| Benchmark | Score |
| --- | --- |
| MMLU | 90.0% |
| MATH | 83.5% |
| SWE-bench Verified | 63.8% |

Source: real side-by-side outputs, pricing and specs at https://rival.tips/models/gemini-2.5-pro-exp