Gemini API makes Computer Use GA and changes a storage default

Google's October 26 to 30 Gemini API changelog records two developer-facing changes: Computer Use reached general availability on October 30, and a new-project storage default changed on October 26. The default change applies only to new paid-tier projects using the Generate Content API; existing projects keep their current setting. (https://ai.google.dev/gemini-api/docs/changelog)

Computer Use reaches general availability

On October 30, Google marked the Gemini API Computer Use tool generally available across the Interactions API and Generate Content API. The Computer Use documentation describes models using a tool to interact with a browser or desktop environment. Check the current model and API documentation for supported environments and implementation requirements before enabling it in an application. (https://ai.google.dev/gemini-api/docs/changelog; https://ai.google.dev/gemini-api/docs/computer-use)

New paid-tier projects store Generate Content requests by default

Starting October 26, new paid-tier projects using generateContent, streamGenerateContent, or batchGenerateContent default to store=true. Google says this aligns the Generate Content API with the Interactions API. Existing projects keep their current setting. (https://ai.google.dev/gemini-api/docs/changelog)

Developers who do not want requests stored can set store=false on individual requests or turn off Generate Content API logging in the Logs and Datasets dashboard settings. Review project creation and deployment defaults when creating a new paid-tier project; do not assume an existing project's behavior changed. (https://ai.google.dev/gemini-api/docs/changelog)

Sources

• Google AI for Developers, Gemini API changelog: https://ai.google.dev/gemini-api/docs/changelog
• Google AI for Developers, Computer Use: https://ai.google.dev/gemini-api/docs/computer-use