Codingby Google DeepMind

Gemini 3.6 Flash

Name: Gemini 3.6 Flash
Author: Google DeepMind

Free

Token-efficient multimodal model for coding, agents, and knowledge work

Gemini 3.6 Flash is Google DeepMind's latest Flash-tier model designed for speed and efficiency. It delivers 17% fewer output tokens than Gemini 3.5 Flash while improving quality across coding, knowledge work, and multimodal tasks. The model features a 1M token context window, supports text, image, video, and audio inputs, and includes computer use capabilities as a built-in tool for agentic workflows.

Who it's for

developersAI agentscoding assistantsdocument processorsknowledge workersmultimodal applications

Pricing · usage-based

checked today

Plan	Price	Includes
Pay-as-you-go API	Free	$1.50 per million input tokens · $7.50 per million output tokens · Supports prompt caching and batch processing for cost reduction

AI-researched pricing — verify on the official site before subscribing.

Use it for

— Building production AI agents with lower token costs
— Coding and code generation tasks
— Document analysis and knowledge extraction
— Agentic workflows requiring multi-step reasoning
— Multimodal content processing (text, image, video, audio)
— Real-time applications requiring low latency

Get the most out of it

01Use prompt caching to reduce costs by 30-80% on repeated contexts
02For high-throughput tasks, consider Gemini 3.5 Flash-Lite ($0.30/$2.50) as a lower-cost alternative
03Leverage the built-in computer use tool via the Gemini API for better agentic automation without custom implementations
04Monitor output token efficiency—3.6 Flash produces fewer tokens than 3.5 Flash for equivalent tasks, yielding savings beyond the price reduction
05Access through Google AI Studio, Vertex AI, or the Gemini API for immediate integration

Visit Gemini 3.6 Flash

Stacks featuring Gemini 3.6 Flash

For indie developer

Agile Code Development Stack

spiral-coderKimi K3Gemini 3.6 Flash

Optimize the coding workflow for faster product iterations and quality assurance.

How the workflow runs

01kimi-k3 — Utilize the large LLM for efficient coding assistance and complex problem-solving.
02spiral-coder — Plan, build, verify, and validate code according to specifications on local hardware.
03gemini-3-6-flash — Implement fast, multimodal coding solutions to assist in documentation and coding tasks efficiently.

This stack integrates advanced code generation with local autonomy and verification, enhancing both speed and reliability in software development.

Total (3 tools)Free

For small marketing team

Empowered Data Analysis Team

Copilot in Power BIGemini 3.6 FlashApple Intelligence

Utilize AI tools for insightful data visualization and analytics to drive marketing strategies.

How the workflow runs

01copilot-in-power-bi — Automate data analysis reports and visualization generation for team insights.
02gemini-3-6-flash — Enhance document processing and summarize findings for easier stakeholder presentations.
03apple-intelligence — Employ privacy-focused AI features to analyze user data while maintaining compliance.

Integrating data visualization with advanced AI assistance provides comprehensive insights for informed marketing decisions while respecting user privacy.

Total (3 tools)$260/mo

In the news

Was this useful?

Plan

Price

Includes

Pay-as-you-go API

Free

$1.50 per million input tokens · $7.50 per million output tokens · Supports prompt caching and batch processing for cost reduction

Get the most out of it

01Use prompt caching to reduce costs by 30-80% on repeated contexts

02For high-throughput tasks, consider Gemini 3.5 Flash-Lite ($0.30/$2.50) as a lower-cost alternative

03Leverage the built-in computer use tool via the Gemini API for better agentic automation without custom implementations

04Monitor output token efficiency—3.6 Flash produces fewer tokens than 3.5 Flash for equivalent tasks, yielding savings beyond the price reduction

05Access through Google AI Studio, Vertex AI, or the Gemini API for immediate integration

Stacks featuring Gemini 3.6 Flash

For indie developer

Agile Code Development Stack

spiral-coderKimi K3Gemini 3.6 Flash

Optimize the coding workflow for faster product iterations and quality assurance.

How the workflow runs

01kimi-k3 — Utilize the large LLM for efficient coding assistance and complex problem-solving.
02spiral-coder — Plan, build, verify, and validate code according to specifications on local hardware.
03gemini-3-6-flash — Implement fast, multimodal coding solutions to assist in documentation and coding tasks efficiently.

This stack integrates advanced code generation with local autonomy and verification, enhancing both speed and reliability in software development.

Total (3 tools)Free

For small marketing team

Empowered Data Analysis Team

Copilot in Power BIGemini 3.6 FlashApple Intelligence

Utilize AI tools for insightful data visualization and analytics to drive marketing strategies.

How the workflow runs

01copilot-in-power-bi — Automate data analysis reports and visualization generation for team insights.
02gemini-3-6-flash — Enhance document processing and summarize findings for easier stakeholder presentations.
03apple-intelligence — Employ privacy-focused AI features to analyze user data while maintaining compliance.

Integrating data visualization with advanced AI assistance provides comprehensive insights for informed marketing decisions while respecting user privacy.

Total (3 tools)$260/mo