Gemini Can Now Make Calls, Pay Bills and Shop, Free in Six Countries With Gemini 4 Hydrogen

Google announced on 17 November 2026 that the Gemini app can now hand off errands such as calling businesses, analyzing utility bills and shopping with a spending cap. The update is free in six countries and runs on the new Gemini 4 Hydrogen model.

Christopher Ort
By Christopher Ort · 3 min read
Share
A smartphone on a kitchen counter beside a notebook, coffee and envelopes.
Image: AI-generated, i10X
On this page
  1. Quick Take
  2. In plain English
  3. What happened
  4. Background
  5. How it works
  6. Why it matters
  7. What's still open
  8. Sources
  9. i10x Perspective

Google has added a Task mode to the Gemini app that can make phone calls, analyze bills, book appointments and complete purchases on a user’s behalf. Josh Woodward, Vice President of Labs, Gemini app and AI Studio, announced it on 17 November 2026. The update rolls out free of charge in the U.S., Japan, Korea, Canada, Australia and India, using the new Gemini 4 Hydrogen model.

i10X Quick Take

Quick Take

  1. What: a Chat-to-Task toggle on the Gemini home screen lets users hand off errands such as calling dealerships, analyzing a utility bill or adding groceries to an order.
  2. Availability: free in six countries; a set of advanced features starts in the U.S. first.
  3. Payments: purchases use the Agent Payments Protocol (AP2), with Mastercard and Visa supported, American Express “coming soon,” and a hard spending cap users can set upfront.
  4. Channels: users can also forward emails to gemini@google.com or text Gemini on Android or iOS.
  5. Safety: each task runs in a hardware-isolated virtual machine on Google Cloud’s Agent Compute Engine, and Gemini is designed to ask before clicking “Buy.”

In plain English

Instead of chatting with Gemini and doing the follow-up yourself, you now describe a job and Gemini does it: it can phone a garage, read your past bills in email, compare chargers, or add items to a grocery order. It can use your Google data if you connect it, and it pauses to ask before important steps. Google says the aim is to save people time and money.

What happened

Woodward described using Task mode to ask Gemini to call two dealerships about a car service. Gemini found them on Google Maps, called both at once, disclosed that it is an AI, and added a Friday morning appointment to his calendar. In another example, it analyzed past billing statements in email and traced a surprise $389 electric bill to a heat pump running at peak pricing. Calling is not currently available in Indiana, Louisiana, Minnesota, Montana and Nebraska.

Background

Google has been building up Gemini’s ability to act for users, including a feature that lets Gemini place calls to businesses. See our earlier coverage of Google’s Call for Me feature in Gemini. The new update connects those pieces with payments, email, texting and a sandboxed runtime.

How it works

Google says Gemini connects to more than 60 apps and that developers can apply to its Connected Apps Platform. For shopping it uses Google’s Shopping Graph and Google Pay, and receipts land in Google Wallet, which is expanding to iOS. Google also said it plans to integrate the Universal Commerce Protocol (UCP) next. Security layers include prompt-injection filters and Google Safe Browsing to limit which links Gemini can open, and users can set “Always allow” for routine steps.

Why it matters

For consumers, a free assistant that completes errands lowers the bar for using agents day to day.

For merchants and websites, Google says bots were blocked by default for decades and that it is partnering with sites and security providers on open, verifiable standards.

For rival assistants, Google is leaning on the data already in its ecosystem, stating that this sensitive data “already lives at Google securely.”

What’s still open

  • How often tasks fail or stop short, as Google says it has not “eliminated all of them” and asks for thumbs-down feedback.
  • When the advanced features reach countries beyond the U.S.
  • How businesses will respond to AI callers and the opt-out Google says they have.

Sources

  • Google, “Put Gemini to work for you,” Josh Woodward, 17 November 2026

i10x Perspective

The launch is written by a Google executive, so the examples are best read as best cases. The notable design choices are the spending cap, the confirmation before purchase and the isolated VM per user, which show agent safety is becoming part of the product. More in our Browsers & Assistants section, on the Gemini product page and on the Google company page.

Christopher Ort

Christopher Ort

Christopher Ort handles SEO, AI agent workflows and PR & partnerships at i10x.ai, the all-in-one AI workspace built by i10X Global Pte. Ltd. in Singapore. He is a graduate of Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU). He is the author of “The Style Penalty”, a study published on SSRN that analyses 1,576 evaluation decisions by four frontier AI models to show how AI-written CVs fare in automated hiring screens; the research has been covered by heise online and t3n.

Timeline

What happened before

  1. Release

    Gemini 4 Argon

    1.05M context · $2 / $10 per 1M tokens

    Google's most capable model for complex coding, agentic, math and science tasks.

    ai.google.dev (source, opens in a new tab)
  2. Release

    Gemini 3.8 Flash

    1.05M context · $0.75 / $3.75 per 1M tokens

    ai.google.dev (source, opens in a new tab)
  3. Release

    Gemini 3.7 Flash

    1.05M context · $0.75 / $3.75 per 1M tokens · Deprecated 8 Oct 2026 (API routes to Gemini 3.8 Flash)

    ai.google.dev (source, opens in a new tab)
  4. Release

    Gemini 3.6 Flash & 3.5 Flash-Lite

    1.05M context · $0.75 / $3.75 per 1M tokens

    ai.google.dev (source, opens in a new tab)
  5. Release

    Gemini 3.5 Flash

    1.05M context · $1.5 / $9 per 1M tokens · Deprecated 8 Oct 2026 (API routes to Gemini 3.6 Flash)

    Launched at I/O 2026 as the first Gemini 3.5 model; Google later dropped the planned 3.5 Pro.

    blog.google (source, opens in a new tab)
Full Gemini timeline ›

Editor's picks

  1. Genesys Launches Standalone AI Agents and Arena, With Pricing Based on How Hard Each Task Is
  2. Seedance 2.5 4K Reaches Developers: 10-Bit Video up to 30 Seconds With 480p Draft Mode
  3. Perplexity Computer Adds Multiagent Mode, Where Up to 16 Agents on Rival Models Check Each Other
  4. Gemini Can Now Make Calls, Pay Bills and Shop, Free in Six Countries With Gemini 4 Hydrogen
  5. Hinton on Firing Line: AI Is Making ‘Alien Beings’ and Self-Regulation Is ‘Absurd’