Gemini 3.5 Flash-Lite

Language modelCard summarized

A low-latency, highly cost-effective subagent option designed for high-volume automation

Stable (GA)● Re-checked 12 Oct 2026 · 64 facts · 1 correction · 1 unconfirmedSource: Gemini 3.5 Flash-Lite Model Card (7 pp)

Use it via API

$206 /month

$4.13 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-3.5-flash-lite
Google Vertex AIgemini-3.5-flash-lite

Supports

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

Full feature support

Good for

Agentic workflows
Complex video reasoning
Coding tasks

Overview

Google · 01Flash-Lite

3.5 Flash-Lite

A low-latency, highly cost-effective subagent option designed for high-volume automation

Cost: $0.30 in
Context: 1M

Input / output: $0.30 / $2.50
Max output: 64K
Knows up to: March 2026
Released: 21 Jul 2026

An addition to the Gemini 3 series of natively multimodal reasoning models. It is cost-efficient and fast, built for high-volume, latency-sensitive tasks such as translation and classification, and also supports agentic workflows. p.2

gemini-3.5-flash-lite

Input / output per 1M: $0.30 / $2.50
Context window: 1M
Max output: 64K
Knows up to: March 2026
Reasoning: Dynamic, thinking_level minimal / 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 3.5 Flash-Lite Model Card. Every claim carries its source page.