Opera Introduces WebAI Standard to Run AI Models Locally in the Browser
Reported by TechCrunch, 9to5Mac, Crypto Briefing and 7 more outlets10 sources ↓
Opera introduced WebAI, a standard for running different AI models in the browser without cloud processing. It is available as an opt-in early preview in Opera One.
Key points
- Opera One users can opt in to run AI models locally through WebAI
- Available models include Google’s Gemma and, on Macs, Apple’s on-device foundation model
- Opera says Opera GX and Opera Neon will get the feature later
- Model performance depends on the user’s device hardware
Sources
- TechCrunchRead ↗Opera introduces a new web standard to let users deploy AI locally in their browser
- 9to5MacRead ↗Opera One now lets Mac users run Apple’s foundation model directly in the browser
- Crypto BriefingRead ↗Opera unveils WebAI standard to run AI models locally in the browser
- Unite.AIRead ↗Opera Launches WebAI, Bringing Local AI Models to Its Browsers
- Tech TimesRead ↗Opera WebAI Delivers Vendor-Neutral Browser AI Standard Without Chrome Content Policy
Details
WebAI is a proposed web standard that allows websites and browser extensions to access models running locally through the browser. Opera says its implementation is not tied to a specific model and supports tasks including text generation, content classification and identifying relationships between information.
The preview is available in Opera One, and users can control which websites access local models, according to 9to5Mac. Opera says local processing keeps information handled by the model on the user’s device and requires no AI subscription. TechCrunch reports that running models locally can place greater demands on a computer, with performance depending on its hardware.
Written from coverage as of
Stocks in this story
Change since open: 20 Nov to 21 Nov 2026
Last refresh