Gemini 3.5 Flash

Google

Google's GA Gemini 3.5 Flash — frontier performance for agentic and coding tasks. ~1M context, multimodal.

Text Generation API Latest Gemini Family v3.5

Documentation Back to Models

Parameters

params

Context Window

1.0M

tokens

Max Output

66K

tokens

Input Price

$1.5

per 1M tokens

Output Price

per 1M tokens

Gemini Family 13 models

The full Gemini line by generation — pricing and capabilities vary across the family.

3.5

3.5 Flash Current Latest

Agentic workflows, coding, multimodal, high-throughput

$1.5 / $9

in / out · 1M

May 2026

3.1

3.1 Flash-Lite

High-volume agentic tasks, translation, summarization, routing

Complex reasoning, code generation, agentic tasks

Most capable Google model

Reasoning, coding, multimodal

Fast multimodal, high volume

2.5

Lightweight classification, unlimited quota fallback for high-volume tasks

Fast document classification, balanced speed/quality for ingestion pipeline

High-quality classification, long-context analysis, strategic planning via Gemini CLI

2.0

Next-gen multimodal, agents

1.5

Long context, multimodal

Fast multimodal, cost-effective

GCP native, enterprise

$1.25 / $5

in / out · 1M

Capabilities

👁️

Vision

⚡

Function Calling

📋

JSON Mode

🌊

Streaming

💬

System Prompt

🖥️

Code Execution

🔍

Web Search

🔌

MCP Support

Extended Pricing

Input

$1.5/1M

Output

$9/1M

Cache Read

$0.15/1M

Details

Release Date: May 19, 2026
Knowledge Cutoff: -
Source: API
API Key Required: Yes
License: Proprietary
Model ID: gemini-3.5-flash

Last updated: May 27, 2026