Gemini 3.8 Flash

What Gemini 3.8 Flash is

Gemini 3.8 Flash is Google's current Flash-tier Gemini model, released on September 2, 2026 and described officially as 'our most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, and complex enterprise workflows—all with the speed and cost efficiency of Flash.' It carries a 1,048,576-token input limit and 65,536-token output limit, accepts text, image, video, audio, and PDF input, and supports caching, code execution, computer use (preview), file search, and function calling. It supersedes the previous-generation Gemini 3.7, 3.6, and 3.5 Flash models.

Key features

• Described by Google as 'our most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, and complex enterprise workflows—all with the speed and cost efficiency of Flash'
• Model code: gemini-3.8-flash
• 1,048,576-token input limit and 65,536-token output limit
• Accepts text, image, video, audio, and PDF input; returns text output
• Supports caching, code execution, computer use (preview), file search, and function calling
• Sits above the previous-generation Gemini 3.7 Flash, 3.6 Flash, and 3.5 Flash models in Google's lineup

Where it lives

Sources & media

• Gemini 3.8 Flash model card — specifications and limits · Google AI for Developers (official)
• Gemini API model list — all current and previous models · Google AI for Developers (official)
• Gemini Developer API pricing · Google AI for Developers (official)
• Gemini API release notes · Google AI for Developers (official)