Released 2026-07-21

Gemini 3.6 Flash Guide

Google's Flash workhorse update: stronger coding and multimodal work at $1.50 input / $7.50 output per 1M tokens (Paid tier, thinking tokens included in output).

#gemini-3.6-flash #$1.50 / $7.50 #1,048,576 context #July 21, 2026

Release status

Gemini 3.6 Flash is generally available as model id gemini-3.6-flash. The same July 21 announcement also shipped 3.5 Flash-Lite and 3.5 Flash Cyber as separate models — do not mix their specs with 3.6 Flash.

At a glance

Model id

gemini-3.6-flash

API price (Paid)

$1.50 in / $7.50 out per 1M tokens

Context

1,048,576 input / 65,536 output

Knowledge cutoff

2026-03 (vendor model card)

Capabilities called out for builders

From Google model docs: caching, code execution, function calling, thinking, computer use (preview), and related agent tooling.

Caching supported

Code execution supported

Function calling supported

Thinking supported

Computer use (preview)

Multimodal inputs (text, image, video, audio, PDF) with text output

Efficiency note (with source)

Google reports about 17% fewer output tokens than 3.5 Flash on the Artificial Analysis Index. That is a vendor-cited efficiency claim, not a full quality ranking across all coding tasks.

Cost triangle (price only)

Short-context list rates for routing conversations. Different models have different strengths — this section compares dollars, not win rates.

GPT-5.6 Luna

$0.20 / $1.20 per 1M tokens after the 2026-07-30 cut. Often the cheapest high-volume execution tier in this set.

Gemini 3.6 Flash

$1.50 / $7.50 per 1M tokens (Paid tier; output includes thinking tokens).

Claude Sonnet 5 (intro)

$2 / $10 per 1M tokens, now confirmed as the standard rate. Strong agentic coding default for many Claude Code users.

Sources

Google blog Introducing Gemini 3.6 Flash, 3.5 Flash-Lite, and 3.5 Flash Cyber (2026-07-21); ai.google.dev models/gemini-3.6-flash and pricing pages.

FAQ

What is the Gemini 3.6 Flash API price?

On the Gemini Developer API Paid tier, Google lists $1.50 per million input tokens and $7.50 per million output tokens, with output including thinking tokens.

Is Gemini 3.6 Flash the same as 3.5 Flash-Lite?

No. 3.6 Flash is the workhorse update. 3.5 Flash-Lite and 3.5 Flash Cyber shipped the same day as separate models with different roles.

What context window does gemini-3.6-flash have?

Google documents 1,048,576 input tokens and 65,536 output tokens for gemini-3.6-flash.

Can I use Gemini models through QCode?

QCode's /models catalog lists gemini-3.6-flash. This model has had no calls on the platform recently — availability is governed by the live /models list and your own actual calls; this page makes no availability guarantee.

Create a QCode account

Plans from ¥60 / $8.57. One key across Claude, GPT, and Gemini models.

Create account Browse models View pricing