Tag: Tasks

  • Google Makes Gemini Tasks Free in Six Countries (2026)

    Google Makes Gemini Tasks Free in Six Countries (2026)

    Takeaway: On November 17, 2026, Google said Gemini Tasks is rolling out free of charge in the United States, Japan, Korea, Canada, Australia, and India, using Gemini 4 Hydrogen. Google’s Gemini Apps help page is more precise about who can use it: you must be 18 or older, signed in with a personal Google Account (not a work or school account), and have History on. In those six countries — the help page names South Korea rather than “Korea” — Tasks is available without a Google AI subscription. Everywhere else that Gemini Apps are supported, it requires Google AI Pro or Ultra, except in the European Economic Area, Nigeria, Switzerland, and the United Kingdom, where the help page says it is not available.

    This is a Gemini app feature, not a new model release. The dates, countries, and limits below come from Google’s November 17 blog post by Josh Woodward, vice president for Labs, the Gemini app, and AI Studio, and from the company’s Tasks help page. A help-page FAQ also answers “Where did Spark go?”: Google says it tested Spark in beta with subscribers since May and renamed it Task. Existing tasks and schedules, it says, are still in the sidebar. That rename is a different story from our coverage of Gemini Gems becoming read-only on November 17.

    How to start a task

    Google’s blog says to open Gemini, flip the home-screen toggle from Chat to Task, and tell Gemini what you need done. The help page’s computer instructions are similar: go to gemini.google.com, click Task below the text box, and describe the work. On a Mac, you can also use the Gemini app. The help page says Tasks currently work only in the Gemini mobile app, the Gemini app on Mac, and the Gemini web app at gemini.google.com.

    You can tell Gemini when to run a task, including around a specific time or after an event, and you can point it at an existing skill with @. The help page distinguishes a task (the goal), a schedule (when it should run), and a skill (reusable instructions). It also notes that schedules in tasks are not the same as schedules in Gemini chat.

    What Google says Tasks can do

    The help page’s examples include summarizing or archiving newsletters, building an urgent to-do list after a vacation, unsubscribing from email lists, watching flight and hotel prices within a budget, and packaging research with cited sources into downloadable files such as PDFs, documents, spreadsheets, and presentations. For website work such as shopping, booking travel, or making reservations, Gemini can use your local Chrome browser on desktop or a separate remote browser in the cloud. Chrome auto browse is currently desktop-only. The first time it needs to browse on a device, Chrome asks for permission; after that, Gemini asks for confirmation on each browsing task.

    Google lists several sources Tasks can use, including skills, schedules, custom connected apps, Contacts, Gemini Notebook, Google Pay and Google Wallet, Google Photos, Workspace apps (Calendar, Docs, Drive, Gmail, Keep, Sheets, Slides, and Tasks), Search services (Search, Finance, Flights, Hotels, and Maps), YouTube, several third-party apps, and Sign in with Google or Google Password Manager with your confirmation. The November 17 blog says Gemini already connects with more than 60 popular apps and that developers can apply to join the Connected Apps Platform. The help page does not publish a complete app-by-app roster.

    Calling, texting, email, and payments

    The blog also describes newer assistant behaviors. Woodward’s examples include Gemini calling businesses, sitting on hold, and adding an appointment to Google Calendar; signing into a utility portal with a new Google Password Manager integration; comparing products with Google’s Shopping Graph and checking out with a new Google Pay integration; adding items to an Instacart order by text, including from a photo, through a new RCS integration; and turning a batch of school emails forwarded to gemini@google.com into calendar events. Those are product illustrations from Google, not independent tests.

    Some of those channels are geographically limited in the official text. The blog’s how-to section says that, starting in the United States, you can forward emails to gemini@google.com or text Gemini after enabling “Text with Gemini” under Settings → Channels and verifying your phone number. A footnote says you must have a U.S. phone number with an eligible mobile carrier. Calling through Gemini is not currently available in Indiana, Louisiana, Minnesota, Montana, and Nebraska. Google says Gemini discloses that it is an AI when it calls, that businesses can opt out, and that Gemini will not give out payment or private account information unless you say so.

    On payments, the blog says Gemini now uses the Agent Payments Protocol (AP2). Google says it is working with American Express (coming soon), Mastercard, and Visa so purchases use digital tokens on supported cards, and that you still earn the card’s points, cash back, or purchase protections at checkout. You can set a hard spending cap. Receipts and tracking information, Google says, go to Google Wallet, “which is expanding to iOS starting today” — that is, November 17, 2026. The company also says it will later integrate the Universal Commerce Protocol (UCP) into Gemini; it does not give a date for that step.

    Limits, confirmation, and what Google still warns about

    You can have up to 15 tasks running at once. A schedule will not run if 15 tasks are already running. Usage is also capped by compute-based limits in Gemini Apps, which the help page says increase with higher Google AI subscriptions. How much of that budget a task uses depends on how many you assign and how complex they are. If you are close to a limit, Gemini lets you know.

    Google still describes Tasks as experimental and says Gemini can make mistakes or fail to finish. The blog says each task runs in a hardware-isolated virtual machine on Google Cloud’s Agent Compute Engine that is dedicated to your account and is not shared with other users. The help page tells people not to type sign-in information, payment details, or other sensitive information into the task thread; if a site needs those details, it says to take control of the browser and enter them on the page. Gemini is designed to ask for confirmation before actions such as sending messages, deleting data, sharing sensitive information, making purchases, completing financial transactions, submitting web forms, and signing in with Google or Password Manager. Even if you set an action to “Always allow,” Google says built-in checks still pause the assistant before it shares information such as health, financial, or government ID details.

    The help page also warns that agentic browsing can be misled by hidden instructions in a webpage, email, or file, and that Gemini may share information from your chat, Connected Apps, or Personal Intelligence with sites it visits to finish a task. Google documents several safeguards, including confirmation prompts, a “take control” handoff for steps such as entering a password or payment detail, and site-and-action restrictions. It also says those safeguards do not guarantee protection against every risk, and that you should supervise sensitive work and can stop a task or deny an action. If you deny an action, Gemini stops and does not try another way to complete it.

    What the official pages do not say

    Google does not publish a full list of which “advanced features” are limited to the United States beyond the how-to items it flags (email forwarding, texting, and the calling exceptions). It does not list every connected third-party app, name every eligible mobile carrier, or say when work and school accounts, or the EEA, Nigeria, Switzerland, and the United Kingdom, will get Tasks. The blog’s cost-saving and appointment-booking examples are Google’s own anecdotes, not independently verified results, and the company says some websites still force Gemini to hand the screen back so you can click the last button.

    Key facts

    ItemWhat Google says
    AnnouncementNovember 17, 2026 blog post; Tasks use Gemini 4 Hydrogen.
    Free without a Google AI subscriptionUnited States, Japan, South Korea, Canada, Australia, and India (help page wording).
    Paid availabilityGoogle AI Pro or Ultra in other supported Gemini Apps countries, except the EEA, Nigeria, Switzerland, and the United Kingdom.
    Who can use itAge 18 or over; personal Google Account; History on. Not available on work or school accounts for now.
    Where it runsGemini mobile app, Gemini app on Mac, and gemini.google.com.
    SparkHelp page: Spark beta since May was renamed Task; existing tasks and schedules remain in the sidebar.
    Concurrent tasksUp to 15 at a time; a schedule will not run at that cap.
    U.S. channels in the blog how-toForward email to gemini@google.com; text Gemini after verifying a U.S. number with an eligible carrier. Calling is unavailable in Indiana, Louisiana, Minnesota, Montana, and Nebraska.
    PaymentsAgent Payments Protocol (AP2); Amex coming soon, plus Mastercard and Visa; optional spending cap; receipts in Google Wallet, expanding to iOS as of November 17, 2026.

    FAQ

    Where is Gemini Tasks free?

    Google’s November 17 blog says the update is rolling out free of charge in the United States, Japan, Korea, Canada, Australia, and India. The help page lists the same six countries, using the name South Korea, and says no Google AI subscription is required there.

    Who can use Gemini Tasks?

    The help page says you must be 18 or older, signed in with a personal Google Account, and have History on. Work and school accounts are not eligible for now. Outside the six free countries, it requires Google AI Pro or Ultra where Gemini Apps are supported, except in the EEA, Nigeria, Switzerland, and the United Kingdom.

    Is Spark the same as Gemini Tasks?

    Google’s help FAQ says Spark was a beta tested with subscribers since May and was renamed Task. You use the Chat and Task toggle next to the prompt box, and Google says your existing tasks and schedules are still in the sidebar.

    How do I start a task in Gemini?

    Open Gemini and switch from Chat to Task — on the web, click Task below the text box at gemini.google.com — then describe what you want done. The help page says you can also tell Gemini when to run the task or attach a skill with @.

    Can I use Tasks with a work or school Google account?

    Not for now. The help page says the feature is not available if you sign in with a work or school Google Account. Google has not published a date for Workspace availability.

    Can Gemini Tasks call, text, or read forwarded email?

    The blog says those channels are starting in the United States: forward email to gemini@google.com, or set up “Text with Gemini” and verify a U.S. number on an eligible carrier. Calling through Gemini is not currently available in Indiana, Louisiana, Minnesota, Montana, and Nebraska. Google says Gemini identifies itself as an AI on calls and that businesses can opt out.

    How many Gemini Tasks can run at once?

    The help page says you can have up to 15 tasks running at a given time. You have to wait for some to finish before starting another, and a schedule will not run if 15 tasks are already running. Separate compute-based usage limits also apply and rise with higher Google AI subscriptions.

    Will Gemini buy something or sign in without asking?

    Google says Gemini is designed to ask for confirmation before purchases, financial transactions, sending communications, deleting data, submitting forms, and signing in with Google or Password Manager. The blog also says you can set a hard spending cap. You should still supervise those steps; Google’s help page says its safeguards do not cover every risk.