Gemini 3.8 Flash

Google calls this its most intelligent Flash model, aimed at long software-engineering tasks, autonomous agents and enterprise workflows. It is the newest stable text model in the Gemini API; the Pro line (Gemini 3.1 Pro) is still a preview.

When to choose it

• Mixed inputs in one request: text, images, video, audio and PDFs.
• High-volume analysis where cost matters more than the last bit of quality.
• Answers grounded in Google Search or Google Maps, or you already build on Google Cloud.

Specs (from Google, 2026-09-25)

API ID	gemini-3.8-flash
Input limit	1,048,576 tokens
Output limit	65,536 tokens
Inputs	Text, image, video, audio, PDF
Thinking	Low, medium, high
Price (paid tier)	$0.75 per million input tokens, $3.75 per million output, through December 31, 2026

Before you choose

The price is an introductory rate: from January 1, 2027 it doubles to $1.50 input and $7.50 output. Budget for that if you are building something that will run past year end. Computer use is still in preview for this model.