Google AI assistant

How to use
Gemini.

Working across large source material and Google-oriented workflows, especially when the relevant documents and context already live in your Google account.

What it isgeneral AI assistant Workflows2 UpdatedJuly 2026

Gemini is a general AI assistant. Working across large source material and Google-oriented workflows, especially when the relevant documents and context already live in your Google account. This guide covers the whole path in one place: official access, a first session that produces something reviewable, the checks that make output trustworthy, and the permissions worth limiting before you connect real work.

Troiana principle

AI should make the work easier to inspect. If the workflow removes the source, the owner, or the review step, redesign the workflow.

01

Access & setup

Find, install, and sign in to Gemini

Get into the official Gemini experience with the right account and a setup you understand.

  1. 01

    Start at https://gemini.google.com/ and confirm the domain before entering account or payment information.

  2. 02

    Availability: A native Gemini app is documented for macOS; Gemini is also available on the web.

  3. 03

    Google documents the Mac app for Apple Silicon Macs running macOS 15 or later, with at least 8 GB of RAM and 200 MB of free space. Availability and advanced features can vary by account, plan, country, and rollout.

  4. 04

    Sign in with the account you intend to keep using, then review plan, data, notification, and permission settings.

  5. 05

    Run one low-risk test task before connecting sensitive files, repositories, or workspace data.

  • Use official download pages.
  • Review permissions during setup.
  • Keep installers and applications updated.
02

First session

Your first useful Gemini session

Learn the interaction loop using a small task with a clear outcome.

  1. 01

    Sign in at gemini.google.com or install the macOS app if it is available for your account and device.

  2. 02

    Give the task, intended reader, and output format before adding source material.

  3. 03

    Ask Gemini to separate supported facts, assumptions, and open questions.

  4. 04

    For a document or research task, inspect citations and source excerpts before sharing the output.

  • State the outcome before the background.
  • Provide the real source material.
  • Review the result before expanding the task.
03

Quality control

Check the quality of Gemini output

Turn a plausible draft into work you are willing to stand behind.

  1. 01

    Restate the original outcome and acceptance criteria before reviewing the response.

  2. 02

    Mark every factual claim, calculation, quotation, or figure that could materially affect the result.

  3. 03

    Check those items against the original source, a primary reference, or direct inspection.

  4. 04

    Ask the tool to list its assumptions and uncertainty, but never rely on self-review as the only check.

  5. 05

    Complete a human edit for relevance, tone, privacy, accessibility, and the exact delivery format.

  • Verify consequential claims independently.
  • Fluency is not accuracy; confident phrasing is not evidence.
  • Keep a record of sources and review decisions.
04

Privacy & permissions

Use Gemini safely

Use the platform productively without giving it unnecessary access or authority.

  1. 01

    Classify the task and its data before uploading or connecting anything.

  2. 02

    Review the product, account, organisation, retention, and training settings that apply to you.

  3. 03

    Grant the narrowest file, workspace, microphone, screen, or integration permissions needed.

  4. 04

    Remove secrets and personal or regulated information unless your approved policy explicitly permits it.

  5. 05

    Review the output and revoke permissions or disconnect sources that are no longer needed.

  • New Gemini features are frequently rolled out gradually. Confirm that a feature is available on your account before building a workflow around it.
  • Follow your organisation's approved-use policy.
  • Never treat fluent output as authorization to act.
05

Models & pricing

What Gemini costs, model by model.

Google's Gemini line splits into Pro for reasoning, Flash for balanced throughput, and Flash-Lite for the cheapest current-generation inference. Pro pricing steps up above a 200K-token prompt.

Gemini API models and token pricing
ModelRoleInputOutput
Gemini 3.1 Pro (≤200K)Reasoning and long-context work$2.00$12.00
Gemini 3.1 Pro (>200K)Above the long-context threshold$4.00$18.00
Gemini 3.5 Flash-LiteCheapest current generation$0.15$1.25
Gemini 2.5 Flash-LiteLegacy, lowest cost overall$0.10$0.40
Gemini Pro rates apply to prompts up to 200K tokens and step up above that threshold. The Batch API takes 50% off both directions. Published Flash-tier rates moved several times during 2026 and vary between references — confirm against Google's own pricing page before you budget.

Figures verified 2 September 2026 against Gemini API pricing ↗. Model pricing changes frequently — confirm before you budget.

Frontier and default-tier pricing across the three major providers
ProviderFrontier tierBalanced defaultLow-cost tier
OpenAIGPT-5.6 Sol — $5 / $30GPT-5.6 Terra — $2 / $12GPT-5.6 Luna — $0.20 / $1.20
AnthropicFable 5.1 — $10 / $50Sonnet 5 — $2 / $10Haiku 4.5 — $1 / $5
GoogleGemini 3.1 Pro — $2 / $12Gemini 3.1 Pro — $2 / $12Gemini 3.5 Flash-Lite — $0.15 / $1.25
Input / output USD per million tokens, standard context, before batch or caching discounts. Compare tiers by role rather than by name — vendors label their tiers differently.

Cross-provider comparison verified 2 September 2026. Sources: OpenAI API pricing ↗ · Claude platform pricing ↗ · Gemini API pricing ↗

06

Common questions

Gemini questions people actually ask.

Why did my Gemini bill exceed the quoted rate?

Two usual causes. First, Pro pricing steps up above a 200K-token prompt, so long-context requests bill at roughly double. Second, thinking tokens are billed as output on reasoning models, and they are invisible in your prompt — so a short answer can carry a long, billable reasoning trace behind it.

Which Gemini model is cheapest?

Gemini 2.5 Flash-Lite at $0.10 input / $0.40 output per million tokens, though it is a previous generation. Among current-generation models, Gemini 3.5 Flash-Lite is the cheapest at $0.15 / $1.25.

07

Core workflows

Step-by-step ways to use Gemini for the work it does best.

Each workflow is a separate guide with its own steps and review checkpoints.

08

Official references

Check the current product documentation.

Features, plan limits, availability, and data controls change. These official pages are the starting points used for this guide.

Explore the Troiana AI Hub →