What do the links at the top mean?

A link takes you to another page. The links at the top give you these choices:

  • Start here — follow the four short lessons from the beginning.
  • Everyday uses — find small, practical jobs you could try with AI.
  • AI tools — meet examples of outside AI apps and learn how to choose one.
  • Explore more — find news, detailed activities, and the separate children’s area.
Google

Gemini API storage defaults: check new paid-tier projects

Google changes request logging for new paid-tier projects. Existing settings stay in place; check the project, client, and retention controls before sending real information.

Sources checked 2026-10-26. Access and availability can change.

What changed

Google’s October 26 release notes say new paid-tier Gemini API projects now store Generate Content requests by default. This matters to developers and experienced technicians building applications that send prompts. Existing projects retain their current setting. The announcement provides a date, not a verified first-publication hour. [1]

The affected methods are generateContent, streamGenerateContent, and batchGenerateContent. New projects now default to store=true, matching the existing Interactions API behavior. This is an API-project configuration change, not an announcement about consumer Gemini chat history. [1]

Check the controls and retention

To disable this logging, use store=false for an individual request or turn off Generate Content API logging in the project’s AI Studio Logs and Datasets settings. The request property overrides the project default. Check Google’s minimum SDK versions before relying on the flag; the documentation lists different requirements by language. [1][2]

Logs have a 55-day default window, after which they expire and are marked for deletion. Shorter project windows can be configured. Logs saved into a dataset do not expire under that log-retention rule. A scheduled expiry is not a promise of immediate erasure. [2]

Saving logs and choosing to share datasets with Google for Gemini improvement are separate controls. The guide also excludes some models, agents, and input types from logging support; read its current limitations for your workload. [2]

Our take

Treat a new project as a fresh configuration review, even when reusing familiar application code. Record the project default, inspect the client version and any explicit request setting, and decide which information is appropriate to submit. Keep that decision separate from whether a dataset should be shared.

A storage switch alone does not establish an application’s complete data handling or a universal no-retention guarantee. We have not inspected a paid account, sent a test request, or tested an SDK. Follow the current documentation and your organization’s requirements.

Sources & further reading

Open the source to check the original wording and current availability.

This is a source-linked briefing, not a hands-on product review. Provider claims and outside evaluations are identified in the text.

Hey, I’m Patch.

Your little guide to this website.

Ask about an AI word or find your next small adventure.

New here? Try “Help me get started.”

Prepared explanations + site search. No live model. Your question stays in this browser. How Patch works.