Microsoft Edge Powers AI Web Apps for Developers

Microsoft Introduces AI APIs for Edge Browser

Microsoft is introducing new Application Programming Interfaces (APIs) for its Edge web browser. These APIs are designed to enable developers to integrate artificial intelligence capabilities directly into their web applications.

Leveraging Built-in AI Models

The unveiling of these AI APIs occurred at Build 2025. They function similarly to features found in Google Chrome, which also provides developers with access to “built-in AI” for enhancing web applications.

Microsoft’s initiative demonstrates a commitment to providing a competitive alternative, potentially attracting developers to the Edge platform.

Introducing Phi 4 Mini

The new APIs grant websites and Edge browser extensions access to Phi 4 mini, an AI model released by Microsoft in late February.

Phi 4 mini, containing approximately 3.8 billion parameters, is particularly adept at solving mathematical problems. This proficiency stems from its training on a dataset comprising both human-generated and synthetically created data.

Understanding Model Parameters

Generally, the number of parameters in a model correlates with its problem-solving abilities. Models with a higher parameter count typically exhibit superior performance compared to those with fewer parameters.

However, smaller models offer the benefit of increased efficiency, especially on devices with limited processing power, such as laptops and mobile phones.

Additional AI Capabilities

Edge is also incorporating additional AI APIs, including tools for writing assistance. These tools facilitate text generation, summarization, and editing.

Microsoft intends to release a translator API within a few months, providing AI-powered language translation services through the Edge browser.

Privacy and Security Considerations

“These experimental APIs are envisioned as potential web standards, ensuring compatibility across platforms, browsers, and various AI models,” Microsoft stated in a press release to TechCrunch.

For developers handling sensitive data or operating within regulated industries, these APIs offer the advantage of on-device processing, eliminating the need to transmit data to external cloud services, thus enhancing privacy and security.

Availability

Currently, all of the new AI APIs are available in the Edge Canary and Dev channels.

PDF Translation Feature

In a related development, Microsoft is integrating a translation tool for PDFs into Edge. This tool supports over 70 languages.

Users can open a PDF within Edge, select the “Translate” icon in the address bar, and generate a translated document in their desired language.

The PDF translation feature will be broadly available next month, with Canary users gaining access starting today.