Skip to Content
Platform.Ontology

WebNN (neural network API)

Runs machine learning models on the device's NPU, GPU or CPU.

Works without askingOn-device AIComputeWeb browsersWhile you use it

In one line

Can run AI models on your device's chips, but only in Chrome and Edge testing

Runs machine learning models on the device's NPU, GPU or CPU.

Lets a page run AI locally. Reveals hardware class through speed and supported ops.

What it can and can't do

What the user does: Nothing. It happens when a page in the trial loads an AI feature

It can

  • Run AI models on your device's AI chip, graphics chip or main chip
  • Tell your hardware class from speed and supported steps
  • Keep the work on your device

It cannot

  • Work for most visitors, since it is only an origin trial
  • Work in Firefox, Safari or on iPhone
  • Work on Samsung Internet
  • Skip browser limits that guard your device

How it differs between platforms: Only Chrome and Edge, in a testing trial. Not in Firefox, Safari or on phones.

Browser support

BrowserStatusFirst versionNote
ChromeBehind a flag112Behind flag.
EdgeBehind a flag112Behind flag.
FirefoxNot supportedNot availableNone
SafariNot supportedNot availableNone
Safari on iPhoneNot supportedNot availableNone
Chrome on AndroidBehind a flag112Behind flag.
Samsung InternetNot supportedNot availableNone

How a site asks for it

APInavigator.ml.createContext(); builder.build(); context.dispatch()
Browser compat keysapi.Navigator.ml
How access is grantedorigin-trial
What the user seesOrigin trial in Chrome and Edge
Needs a secure context (HTTPS)Yes
Needs a user gestureYes
How long it lastsPer origin
How to take it backSite settings
Inside an iframeSame as top level; cross-origin iframes need a permissions policy where listed

Typical flow

  1. Call the API
  2. Browser applies its access rules
  3. Page receives the result

Data you get

What comes back: Runs machine learning models on the device's NPU, GPU or CPU.
Shape: object
How often: on demand

FieldTypeUnitRangePrecision
deviceTypeenumNonecpu, gpu, npuNot listed
powerPreferenceenumNonedefault, high-performance, low-powerNot listed

Technical limits

  • Flag only in BCD (112)
  • Android excluded from trial

The story

What it is

A page can run AI models using your device's AI chip, graphics chip or processor.

For you

You never see a prompt. Features like background blur, noise removal and photo effects run faster and use less battery. Everything stays on your device.

For makers

Makers use it to run image, audio and language models locally with chip speed. It cuts server costs and keeps data private. It is in testing, so it is not widely available.

Where you see it

TypeExampleApps
videoA video call blurs your background and cancels noise using the AI chip, with low battery use.Google Meet, Microsoft Teams
gamesA browser game uses a model to upscale graphics or run smart opponents on the device.None named
creativeA web photo editor removes a background in a second using the AI chip.None named
accessibilityA captions tool turns speech to text live on your device.None named
securityA site detects faces for login on the device, with no photo upload.None named
shoppingA virtual try on page runs a body or face model locally.None named
developerA developer ships one model that picks the fastest chip on each device.None named
educationA study tool reads handwriting from a photo offline.None named

Risks

  • In testing
  • Device details leak

What the platform says

Good uses and abuse

Legitimate uses

  • Local ML inference

Known abuse

  • Hardware fingerprint

Scores

ScoreValueMeaning
Sensitivity1 of 5How revealing the data is
Utility3 of 5How useful it is to honest apps
Friction3 of 5How much the user has to do
Fingerprint bits3Rough identifying entropy, when known

History

  • 2026-01, Chrome: W3C Candidate Recommendation updated 22 Jan 2026
  • 2026-02, Chrome 146: Origin trial begins (paused after release blockers; window M147 to M149)

Sources

How well checked: Based on official documentation.

On this page