Gemini Computer Use tool
Google's Gemini API tool for agents that operate user interfaces, now generally available in the Interactions and GenerateContent APIs.
This entry is marked for review. Check the original sources before relying on its details.
Overview
Google's Gemini API release notes list the Computer Use tool as generally available on October 30, 2026, across both the Interactions API and the GenerateContent API. It is billed as regular tokens at model pricing on the paid tier and unavailable on the free tier. Gemini 3.8 Flash is the recommended model; Gemini 4 Argon, Gemini 3.5 Flash-Lite and Gemini 3 Flash Preview are also listed. The first preview came in October 2025, and the standalone Gemini 2.5 Computer Use model was shut down on July 28, 2026.
This is a sourced directory entry. Features and capabilities are reported in the linked sources; this entry does not document independent Aymorphic testing.
Key features
- Generally available in the Interactions API and GenerateContent API
- Recommended model: Gemini 3.8 Flash
- Also supported: Gemini 4 Argon, Gemini 3.5 Flash-Lite, Gemini 3 Flash Preview
- Charged as regular tokens at model pricing; not on the free tier
- Replaces the retired standalone Gemini 2.5 Computer Use model
Use cases
- Browser automation agents that click, type and scroll
- UI testing and form filling where no API exists
Pricing
Regular token pricing for the chosen Gemini model on the paid tier; not available on the free tier.
Pricing reflects the source record and may change. Confirm current terms with the provider.
Dates and sources
- Released
- 30 Oct 2026
- Record updated
- 7 Nov 2026
- Record last checked
- 7 Nov 2026