# Gemini 3.5 Flash: AI model fact sheet

- **Provider:** google
- **Released:** 2026-05-19
- **Context window:** 1,048,576 tokens
- **API pricing:** $1.50 / 1M input, $9.00 / 1M output
- **OpenRouter ID:** google/gemini-3.5-flash
- **Capabilities:** conversation, reasoning, code-generation, analysis, tool-use, agentic-tool-use

Gemini 3.5 Flash is Google's high-efficiency multimodal model, bringing near-Pro level coding and reasoning at Flash-tier cost and speed. It is highly optimized for coding proficiency and parallel agentic execution loops, supporting text, image, video, audio, and PDF inputs. Defaults to medium thinking effort for faster and more cost-efficient responses, with full support for thinking levels (minimal, low, medium, high) for fine-grained cost/performance trade-offs.

Source: real side-by-side outputs, pricing and specs at https://rival.tips/models/gemini-3.5-flash