Opera Launches WebAI Standard to Run AI Models Locally in the Browser
Opera’s WebAI preview runs AI tasks locally, keeping user data off third-party servers and removing per-request cloud costs for developers. Opt-in access is available in Opera One, with support for Google’s Gemma and Apple’s Mac foundation model.
Opera announced in October 2026 a new web standard called WebAI that allows users to run AI models directly in its browser, without sending data to the cloud.
WebAI is designed to work with a range of open-weight AI models. Opera cited Google’s Gemma as one example and noted that on Macs, WebAI also supports Apple’s on-device foundation model. The company said the standard is not tied to any single model and is built to support a broad set of open-weight AI systems.
The feature is currently available as an early preview in Opera’s flagship Opera One browser. Opera GX, its browser aimed at gamers and streamers, and Opera Neon, which uses AI agents to perform tasks, are expected to receive the same capability soon. Users must opt in to access the feature.
Opera said WebAI enables text generation, content classification, and relational understanding of information — all processed on the user’s device. “Developers can add AI features without running AI infrastructure or paying for every request,” the company said. “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.”
Privacy is a central motivation behind the standard. Because processing happens locally rather than on a company’s server, users avoid sending personal information to third parties — a concern that has grown as AI assistants gain access to more personal data. Opera has positioned digital privacy as a core selling point for several years.
There are trade-offs, however. Running AI models locally places greater demand on a user’s hardware, which may affect performance. Opera acknowledged that results will vary depending on the device.
Open-weight models, which underpin WebAI, are generally free to download and use, and their model weights are publicly available, giving developers flexibility to customize them — though some restrictions still apply, unlike fully open-source software.