# Gemini 2.5 Flash Preview (thinking): AI model fact sheet

- **Provider:** google
- **Released:** 2025-04-17
- **Context window:** 1,048,576 tokens
- **Max output:** 66,000 tokens
- **API pricing:** $0.17 / 1M input, $3.50 / 1M output
- **OpenRouter ID:** google/gemini-2.5-flash-preview:thinking
- **Capabilities:** conversation, reasoning, code-generation, analysis

Gemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scientific tasks. It includes built-in "thinking" capabilities, enabling it to provide responses with greater accuracy and nuanced context handling.

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