Overview
- Opera released an early preview of WebAI on Tuesday, October 27, 2026, making the feature available first in Opera One with rollouts to Opera GX and Opera Neon planned.
- WebAI is a model-agnostic browser API that lets websites and extensions run AI models on the user’s machine for tasks like text generation, content classification, and semantic search.
- At launch the system supports open-weight models such as Google’s Gemma and Apple’s on-device foundation model on Apple silicon Macs, with Opera providing a model manager and six example extensions to show developers what they can build.
- The feature is opt-in, disabled by default, and requires explicit permissions before sites or extensions can use local CPU or GPU resources so user data need not be sent to cloud servers.
- Local inference reduces developer cloud costs but raises hardware and performance trade-offs because WebAI currently targets Apple silicon Macs and 64-bit Windows Intel/AMD PCs and broader cross-browser adoption remains uncertain after Opera’s two years of on-device model work starting in 2024.