Skip to content

An editorial team and a community building with AI

← All articles

News · Google · 2 min read

Event date: · Published:

Google made the Gemini API Computer Use tool generally available across the Interactions and GenerateContent APIs

On October 30, 2026, Google made the Computer Use tool generally available across the Interactions and GenerateContent APIs. It supported browser, mobile and desktop environments and offered configurable safety policies.

Archive entry: this covers an event from October 30, 2026, and we published it on November 8, 2026. The details come from sources dated at the time and may have changed since.

On October 30, 2026, Google made the Computer Use tool in the Gemini API generally available across the Interactions and GenerateContent APIs, according to the Gemini API changelog entry for October 30, 2026. Google described the tool as supporting browser, mobile and desktop environments and offering configurable safety policies.

What changed

  • Computer use ran in browser, mobile and desktop environments.
  • An intent field explained the reason for each action the model proposed.
  • Safety policies were configurable, and scanning of screenshots for prompt injection was available as an opt-in.
  • The supported models were gemini-4-argon, gemini-3.8-flash (the recommended one), gemini-3.5-flash-lite and gemini-3-flash-preview.
  • The developer's own code, not the model, carried out the actions the model proposed.

What it meant for builders

Computer-use agents built on Gemini could go to production. Builders choosing a model had four supported options and a recommended one, gemini-3.8-flash, and the tool was generally available on both the Interactions API and the GenerateContent API.

On the safety side, the intent field explained each proposed action, safety policies were configurable and screenshot scanning for prompt injection was opt-in. The developer's own code still carried out every action the model proposed.

Documentation

A second source for this entry was the Computer use documentation in Google AI Studio.


Sources

Written with AI assistance, strictly from the sources listed above. Before it went live, automated checks verified its dates, sources and every language edition.

Google made the Gemini API Computer Use tool generally available across the Interactions and GenerateContent APIs | vibecoding.inc