Browser maker Opera announced a new web standard called WebAI that enables AI models to run directly inside the browser, without routing data or computation through cloud servers. The company says the standard is designed to work with a variety of models and is not tied to a single implementation.
Supported models and examples
Opera specifically names Google’s Gemma — an open-weight model that Google introduced about two years ago — as an example. On Macs, Opera says WebAI also supports Apple’s on-device foundation model. Despite these examples, Opera emphasizes that WebAI aims to support a wide range of open-weight AI systems rather than being limited to any particular model.
Availability and rollout
The new AI capabilities are available as an early preview in Opera One, the company’s flagship browser. Opera says Opera GX, its browser targeted at gamers and streamers, and Opera Neon, which uses AI agents to perform tasks, will receive the same functionality soon. According to Opera, users must opt in to enable the feature.
Why this matters: cost, customization and privacy
Open-weight models have several advantages: they are typically free to download and use, and their model weights are publicly available, allowing developers more freedom to customize behavior. While they are not necessarily fully open-source and may carry some restrictions, Opera says WebAI lets developers add AI features without running AI infrastructure or paying per request.
The company also highlights privacy benefits. Because processing happens on the user’s own device rather than on a company’s cloud servers, users can access AI features without sending personal data to external servers or subscribing to cloud-based AI services. Opera states: “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.”
Capabilities available in-browser
Opera says WebAI enables generating text, classifying content, and understanding relationships between pieces of information — all directly in the browser.
Trade-offs and limitations
Locally run models give users more control over their data but do not eliminate all privacy risks. Running models on-device places greater demand on a user’s computer and can affect system performance. Opera notes that model performance will depend on the device’s hardware capabilities.
Summary
WebAI is Opera’s step toward wider adoption of local AI processing in web browsers, aiming to reduce costs and increase user control over data. The feature is currently in early preview in Opera One, with plans to expand to other Opera browsers.
