Google AI Studio News
Managed Agents: Free Tier, Budgets, Triggers
July 16, 2026
The Gemini API added new Managed Agents capabilities: free tier availability (use an API key from a project without billing and interactions run under free rate limits), budget guardrails via max_total_tokens (interactions stop safely as incomplete and can resume where they left off), and scheduled triggers that bind an agent, environment, prompt, and cron schedule into a persistent resource. Each scheduled run reuses the same sandbox, so files persist between runs.
View on X
Custom URLs for Deployed Apps
July 10, 2026
Google AI Studio introduced custom URLs: give your deployed apps a permanent, personalized home with a clean, memorable ai.studio domain. Because your apps deserve an identity.
View on X
Gemini Omni Flash in AI Studio
June 30, 2026
Gemini Omni Flash is here in Google AI Studio — a high-quality, cost-efficient model for video generation and conversational editing. Built for multimodal workflows, it lets you refine videos with natural language and simple prompting. Available now via AI Studio and the Gemini API.
View on X
Design Variations
June 26, 2026
Describing an aesthetic in a prompt can be tough — so Google AI Studio added a button for it. Design Variations instantly generates, explores, and applies new UI layouts with a single click.
View on X
250,000 Android Apps Built in One Week
May 27, 2026
Since launching the ability to build native Android apps in Google AI Studio, people have created more than 250,000 apps — likely >99% by people who had never built an Android app before. Android has over 3 billion active users. Anyone can now build for that audience, no coding required.
AI Studio Mobile — Build Your Ideas Anywhere
May 20, 2026
AI Studio mobile: build your ideas, wherever you are. Coming soon to an app store near you. ai.studio/mobile
View on X
Workspace, Android, and Cloud Run in AI Studio
May 20, 2026
What's new in AI Studio:
• Workspace integration — build with the Google ecosystem of apps (Docs, Sheets, Gmail, and more)
• Android apps — vibe code and test apps on your phone
• Publish your first two apps live on Cloud Run, no credit card required
View on X
One-Click Export to Antigravity
May 20, 2026
While Google AI Studio is the fastest path from prompt to app, as your team evolves moving to a local development platform helps you iterate faster. Developers can now export an AI Studio project and import it into Antigravity with one click.
View on X
Managed Agents on the Gemini API
May 20, 2026
Introducing Managed Agents on the Gemini API. In one API call, you get an agent that comes with a remote Linux environment hosted by Google, ready to scale. Define custom instructions, skills, and tools in Markdown.
View on X
Gemini 3.5 Flash Drops at I/O
May 20, 2026
via Google Gemini
It wouldn't be a Google I/O without new models. Say hello to Gemini 3.5 Flash — frontier performance for agents and coding, excelling at complex long-horizon tasks that deliver real-world utility. Now available via the Gemini API in Google AI Studio.
View on X
Multi-Step Interactions API
May 8, 2026
Google AI Studio's Gemini Interactions API now supports multi-step agentic workflows — each action (thinking, tool calls) is its own step, with mid-flight steering and async tool calls coming June 8, 2026.
Vibe Coding Update
May 6, 2026
Logan Kilpatrick shared the latest Vibe Coding improvements in Google AI Studio — faster iteration and cleaner generation for prompt-driven app building.
View on X
Nano Banana for App Images
May 6, 2026
Google AI Studio integrated Nano Banana for auto-generated app images, plus a redesigned visual edit tool.
View on X
Design Previews in Vibe Coding
April 15, 2026
Google AI Studio now shows custom design theme previews while your app is being built. Gemini generates multiple themes you can choose from in seconds — no more waiting with a blank screen.
https://x.com/OfficialLoganK/status/2044111467943964714
View on X
Gemini 3.1 Flash TTS
April 15, 2026
The next generation of expressive AI speech. Gemini 3.1 Flash TTS features improved quality and controllability with audio tags for adjusting vocal style and pacing. Supports 70+ languages with SynthID watermarking to identify AI-generated audio.