Gemini Model serving Cost Optimization Benchmarks Agent runtime infrastructure Sandboxing

Gemini 3.6 Flash

Google's workhorse Flash model for better coding, knowledge work, and multimodal performance with improved token efficiency.

Visit site

Gemini 3.6 Flash is a stable Gemini model release optimized for agentic workflows, coding, knowledge work, spatial reasoning, and multimodal understanding. It accepts text, image, video, audio, and PDF inputs and outputs text, with a 1,048,576-token input context window and 65,536-token output limit.

Pricing

Model profile · Current snapshot

Input / 1M

$1.50

Output / 1M

$7.50

Blended / 1M

$3.00

Output TPS

231

TTFT (s)

15.5

Model Intelligence

Context window

1,048,576 tokens

Arena ranking

Benchmarkable

Yes

Model level

release

Intelligence Index

50.1

Coding Index

69.2

GPQA

0.93

HLE

0.38

SciCode

0.53

LCR

0.7

Recent stories

2 linked stories

releaseSECONDARY2026-07-28

Gemini API adds token budget caps for Managed Agents

Google added token budget caps and other controls for Managed Agents in the Gemini API. The release also adds sandbox hooks, cron triggers, model configuration, free-tier support, and Gemini 3.6 Flash defaults.

releasePRIMARY2026-07-21

Google ships Gemini 3.6 Flash and 3.5 Flash-Lite to serving platforms

Gemini 3.6 Flash and 3.5 Flash-Lite went live on OpenRouter, Venice, Hyperbrowser, and Google surfaces. Early benchmarks show lower token use and cost, but mixed document and coding results.