Gemini 3.8 Flash

Language modelCard summarized

Our most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, and complex enterprise workflows

Stable (GA)● Re-checked 12 Oct 2026 · 68 facts · 1 correction · 1 unconfirmedSource: Gemini 3.8 Flash Model Card (8 pp)

Use it via API

$882 /month

$17.64 per 1K requests

RAG over docs: 12K in · 600 out · 50K requests/mo · 30% cached · change

Code example Compare

Where to call it

Gemini APIgemini-3.8-flash
Google Vertex AIgemini-3.8-flash

Supports

Structured outputs
Reasoning control
Tool calling
Prompt caching
Batch API
Image input
PDF input

Full feature support

Good for

Cost-effective scaling of general-purpose, production-ready agents
Software engineering
Agent tasks

Overview

Google · 03Flash

Gemini 3.8 Flash

Our most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, and complex enterprise workflows

Cost: $1.50 in
Context: 1M

Input / output: $1.50 / $7.50
Max output: 64K
Knows up to: March 2026
Released: 2 Sep 2026

The next iteration in the Gemini 3 family, building on Gemini 3.7 Flash, with gains in software engineering and agentic knowledge work. It keeps customizable effort levels to trade off quality, cost and latency. p.2

gemini-3.8-flash

Input / output per 1M: $1.50 / $7.50
Context window: 1M
Max output: 64K
Knows up to: March 2026
Reasoning: Dynamic, thinking_level low / medium / high
Weights: Closed

About this card. A model card is the maker's own account of a model: what it's for, how it was trained and tested, and where it falls short. This page condenses Google DeepMind's Gemini 3.8 Flash Model Card. Every claim carries its source page.