Opera Launches WebAI Standard to Run Local AI Models in Browsers

Browser maker Opera has introduced WebAI, a new web standard that allows users and web developers to run artificial intelligence models locally inside the browser without transmitting personal data to cloud servers or paying per-request API fees, according to TechCrunch.

Available now as an opt-in early preview in Opera’s flagship Opera One browser, WebAI will also roll out soon to Opera GX—the company’s browser for gamers and streamers—and Opera Neon, its agentic browser.

Support for Google Gemma, Apple On-Device Models, and Open-Weight Systems

Opera designed WebAI to be model-agnostic across open-weight AI systems, citing Google’s open-weight Gemma family as well as support on macOS for Apple’s on-device foundation model. Using WebAI, web applications can generate text, classify content, and analyze relationships between pieces of information directly on the client device.

“Developers can add AI features without running AI infrastructure or paying for every request,” Opera said in its announcement. “Users don’t need AI subscriptions, the information the local AI handles stays on their own device, and they stay in control of the AI on their computer.” Opera noted that because inference runs entirely on local hardware, model speed and performance depend on the user’s computer specifications.