Opera introduces WebAI to run AI models locally in the browser

Opera introduces WebAI to run AI models locally in the browser

Ondřej Barták
Ondřej Barták
Entrepreneur and Programmer
27. 10. 2026
1 minutes reading · 4 views
Opera introduces WebAI to run AI models locally in the browser

Opera has introduced WebAI, a web standard that lets users run artificial intelligence models directly in the browser without relying on the cloud. The new features are available as an early preview in Opera One.

Text generation and model support

According to Opera, WebAI can generate text, classify content and recognize relationships between pieces of information in the browser. The company says the standard is not tied to a single model and is designed for a wide range of open-weight AI systems.

Opera cites Google’s Gemma as an example of a supported model. On Macs, WebAI also supports Apple’s on-device foundation model.

Availability and activation

The early preview is available in Opera One, but users must actively opt in to use the features, according to the company. Opera says the same features will soon come to Opera GX and Opera Neon.

Opera says developers can add AI features without running their own AI infrastructure or paying for every request, while users do not need an AI service subscription.

On-device data and performance demands

Opera says information processed by local AI stays on the user’s device rather than being sent to company servers. Running models locally also places greater demands on the computer, and the company notes that model performance depends on the device’s hardware.

Advertisement

Content created with help from UpTier.

SEO and GEO on autopilot. UpTier’s multi-agent systems write and optimize content for search engines and AI answers.

Discover UpTier ↗

Category:AI
Did you enjoy this article?
Discover more interesting posts on our blog
Back to blog

Related posts

Nvidia releases Nemotron 3.5 Transcribe for speech transcription in up to 40 languagesNvidia releases Nemotron 3.5 Transcribe for speech transcription in up to 40 languages
The free, open-weight model processes recorded audio. Nvidia says it can also translate and distinguish speakers.
1 min read
28. 10. 2026
Genie 4 creates interactive worlds with sound and lets users change scenes in real timeGenie 4 creates interactive worlds with sound and lets users change scenes in real time
Google DeepMind has made Genie 4 available to selected testers. The model generates sound and lets users change simulated environments with text prompts as they run.
2 min read
28. 10. 2026
SpaceX Borrowed $40 Billion for AI Chips, Musk Predicts Smaller Rivals Will FailSpaceX Borrowed $40 Billion for AI Chips, Musk Predicts Smaller Rivals Will Fail
SpaceX secured $40 billion for AI chips as Musk warns that hundreds of smaller neoclouds could collapse. Only firms with deeper pockets and steady revenues will survive.
5 min read
27. 10. 2026
Přihlaste se k odběru našeho newsletteru
Zůstaňte informováni o nejnovějších příspěvcích, exkluzivních nabídkách, a aktualizacích.
CodedTrip

Operated by CodedTrip LLC, USA.

YouTube
TikTok