Google has made the Computer Use tool generally available through the Gemini API's Interactions and GenerateContent APIs. The October 30, 2026, Gemini API changelog says Google released Computer Use to general availability across both APIs.
Computer Use is a model tool for browser, mobile and desktop interaction. The model receives a screen image and proposes a UI operation — a click, scroll or keystroke — and the client application executes the operation in a target environment and sends back the next screen. For builders, the model response is a proposal, not a completed interaction.
Existing preview integrations require no migration because Google reports no breaking changes. The GA release preserves the preview's multi-environment design, and Google describes use cases such as filling forms, testing web applications and researching product information across websites.
Four models support the tool, with Gemini 3.8 Flash recommended by Google and Gemini 4 Argon for more complex tasks. For Gemini 4 and Gemini 3.x models, Google says an intent field can explain why the model selected an action. Google still cautions that Computer Use can make mistakes and encounter security vulnerabilities.
Computer Use carries no separate tool fee. Google bills its requests at each model's standard token rates on the paid tier, with no free-tier access. The pricing page lists Gemini 3.8 Flash, the recommended model, at $0.75 per million input tokens and $3.75 per million output tokens through December 31, 2026.
General availability makes the tool available through two APIs, but it does not eliminate the application layer between a model proposal and a changed screen. The release establishes availability, not performance or adoption, and independent reliability figures for complex workflows have not been published.
