WebInfer

Back to Providers
Chrome AI (Gemini Nano) logo

Chrome AI (Gemini Nano)

On-device AI with Chrome built-in Gemini Nano model

Free
Local & Self-Hosted
Local

Configure Chrome AI (Gemini Nano)

Enable Chrome AI (Gemini Nano) in Settings

Go to Settings
About Chrome AI (Gemini Nano)

Use Google's Gemini Nano model running directly in Chrome via the W3C Prompt API. Zero latency, completely private, and free. All inference happens on-device with no network requests. Public stable on web pages in Chrome 148+ (May 2026); available on extension stable since Chrome 138. Tool calling is exposed through the page's WebMCP registrations (navigator.modelContext) where supported.

Key Features
  • Runs entirely on-device in Chrome
  • Zero network latency
  • Completely free to use
  • Privacy-preserving - data never leaves device
  • Streaming support
  • System prompt support
  • Multimodal input (text + image + audio, Early Preview)
  • Tool calling via WebMCP (navigator.modelContext)
  • No API keys required
Capabilities
chat
streaming
local
browser
on-device
private
tool-calls
webmcp
multimodal
Configuration Schema
Required and optional fields for configuring this provider

No configuration required. This provider works out of the box.

CLI Usage
For users running the daemon server locally or a self-hosted gateway

Add provider:

npx webinfer provider add chrome-ai

Test connection:

npx webinfer provider test chrome-ai
Programmatic Usage
Use Chrome AI (Gemini Nano) in your code with WebInfer

Basic usage:

import { generateText } from "webinfer"

// WebInfer automatically routes to the best available provider
const result = await generateText({
  prompt: "Write a haiku about programming"
})

console.log(result.text)

Specify Chrome AI (Gemini Nano) explicitly:

import { generateText } from "webinfer"

const result = await generateText({
  prompt: "Write a haiku about programming",
  provider: "chrome-ai",
  model: "gemini-nano"
})

console.log(result.text)
console.log("Provider:", result.provider)
console.log("Model:", result.model)

Streaming:

import { streamText } from "webinfer"

const { textStream } = await streamText({
  prompt: "Write a story about AI",
  provider: "chrome-ai"
})

for await (const chunk of textStream) {
  process.stdout.write(chunk)
}
Available Models
Default model: gemini-nano

Gemini Nano

Google Gemini Nano - compact on-device model optimized for Chrome

4K context
Free
gemini-nano
Pricing
Free
Completely free. All computation happens on-device in Chrome.
Resources
Chrome AI (Gemini Nano) WebsiteConfigure in Settings