Gemini-3-Flash-Preview is a language model released by Google, typically part of its Gemini series. This model is optimized over the base version of Gemini-3, focusing on faster response times and more efficient computational power, while maintaining strong language comprehension and generation capabilities.
Context & Pricing
Max context
1.0M tokens
Prompt:¥0.2500/1M tokens
Output:¥1.5000/1M tokens
Cache Hit:¥0.0250/1M tokens
Tags & Capabilities
Tags
No tags configured
15-Day Usage Statistics
Total tokens usage across all users
AI Coding Agents Usage (15 Days)
Top 10 AI coding agents using this model
gemini-3-flash-preview API Pricing, Context and Usage | Routin