AI News · New apps ·
Opera launches WebAI standard to run AI models locally in the browser
Opera introduced WebAI, a web standard that lets users run AI models directly in the browser rather than in the cloud. It supports open-weight models such as Google's Gemma and, on Macs, Apple's on-device foundation model, and is available as an opt-in early preview in Opera One.
Key points
- WebAI runs AI models inside the browser, with Opera One offering an opt-in early preview.
- It supports open-weight models such as Gemma, plus Apple's on-device foundation model on Macs.
- Opera GX and Opera Neon will get the same features soon, the company said.
What happened: Opera has introduced WebAI, a new web standard that lets people run AI models inside the browser instead of relying on cloud services, TechCrunch reported. The feature is available now as an early preview in Opera One, the company's flagship browser, and users must opt in. Opera said Opera GX, its browser for gamers and streamers, and Opera Neon, which uses AI agents to carry out tasks, will get the same features soon.
The details: Opera said WebAI is not tied to any one model and is built to support a wide range of open-weight systems. It cited Google's Gemma as an example, and on Macs WebAI also supports Apple's on-device foundation model. The standard grew out of earlier Opera work to bring locally run models into its browsers. "Developers can add AI features without running AI infrastructure or paying for every request," the company said. Opera also said users do not need AI subscriptions and that information handled by local AI stays on the device.
Who it affects: Web developers could build AI features into sites without paying for each request, and users could avoid sending personal data to a company's servers. TechCrunch noted that open-weight models are typically free to download but still carry some restrictions and are not the same as open-source software.
What to watch: Local models put more demand on a user's computer, and Opera said performance depends on the device's hardware. Whether other browser makers will adopt the standard was not reported.
Our take
Browser-level local AI could let teams add AI features without cloud inference costs or sending data to outside servers, at the cost of device performance.