Google Opens Gemini Notebooks to Free Users with 50-Source Limit
Google has expanded its Notebooks feature in the Gemini app to free users, allowing them to organize chats and files with up to 50 sources per notebook. The feature, which integrates with NotebookLM, was previously available only to Google AI subscribers.
Google Opens Gemini Notebooks to Free Users with 50-Source Limit
Google has expanded access to Notebooks in its Gemini app to free users, implementing a tiered system based on subscription level. Free users can now create notebooks with up to 50 sources, while paid tiers receive higher limits.
Tier-Based Source Limits
The feature follows a clear capacity structure:
- Free users: 50 sources per notebook
- AI Plus subscribers: 100 sources per notebook
- Pro subscribers: 300 sources per notebook
- Ultra subscribers: 600 sources per notebook
Notebooks appear in a new dedicated section within the Gemini app's side panel at gemini.google.com, positioned above Gems and Chats.
Technical Capabilities
Notebooks function as organizational hubs where users can consolidate conversations and files into dedicated projects. The system integrates directly with NotebookLM, enabling users to generate Video Overviews, Infographics, and other Studio outputs.
When processing queries, Gemini considers all chats within a notebook for context, though users can disable this "notebook memory" feature. The interface displays sources above the prompt box and lists related chats below. Users retain access to the full Gemini Tools suite and web search functionality.
Any conversation in the Gemini app can be added to a notebook through the three-dot overflow menu. Notebooks support custom instructions for controlling response tone and format.
Availability Timeline
The feature rolled out to Google AI subscribers earlier in April 2026 before expanding to free users. Desktop web access is currently live at gemini.google.com, but mobile and Mac applications do not yet support Notebooks. According to Google, full platform availability will occur over the "coming weeks."
What This Means
Google is positioning Notebooks as cross-product knowledge bases that will integrate throughout its ecosystem. The tiered approach creates a clear upgrade path while still providing meaningful functionality to free users. The 50-source limit for free accounts is substantial enough for personal use cases while reserving higher capacities for professional workflows. The staggered rollout across platforms suggests Google is testing stability before broader deployment.
Related Articles
Google launches Gemini Spark AI agent for Ultra subscribers in US with automated task execution
Google has launched Gemini Spark, a 24/7 AI agent for Google AI Ultra subscribers in the US. The service automates tasks across Google Workspace apps with remote browser control, supporting up to 15 concurrent tasks with compute-based usage limits.
Microsoft strips color from Copilot interface in pursuit of 'intelligence that feels present but not imposing'
Microsoft has rolled out a visual overhaul for Copilot in Microsoft 365, replacing the colorful interface with a predominantly black-and-white, text-forward design. The redesign, aimed at making the AI assistant feel "present but not imposing," includes a new adaptive prompt surface and consistent side panel placement across Word, PowerPoint, and Excel.
OpenAI GPT-5.5 and GPT-5.4 Launch on Amazon Bedrock at Parity Pricing
OpenAI's GPT-5.5 and GPT-5.4 models are now generally available on Amazon Bedrock, with pricing matching OpenAI's first-party rates. Codex, OpenAI's coding agent used by 5 million developers weekly, is also available with pay-per-token pricing and no seat licenses.
AWS adds Policy Engine and Lambda interceptors to Bedrock AgentCore gateway for agent security controls
Amazon Web Services launched Policy Engine and Lambda interceptors for Bedrock AgentCore gateway, enabling enterprises to control which tools AI agents can access and validate requests dynamically. The Policy Engine uses Cedar declarative policy language for deterministic access decisions, while Lambda interceptors run custom code before or after each tool call for validation, token exchange, and response filtering.
Comments
Loading...