Welcome to the next era of the web with AI. See how AI can make it easier for developers to build powerful experiences on the web.
Get started Join the preview program

Gemini Nano in Chrome

Reimagine what's possible with Gemini Nano in Chrome.
We're bringing Gemini Nano, the most efficient model of the Gemini ecosystem, to Chrome.
Client-side AI brings powerful models to users, while protecting data privacy and improving latency.
Learn the requirements to start building features and applications with built-in AI.
Review the APIs and their availability status to use with Gemini Nano in Chrome.

Built-in AI APIs

Join the origin trials and start using these APIs in production.
Get started
Live translate text in the browser using local AI models. Now, users can contribute in their first language.
Identify the language used in any given text with the Language Detector API.
Generate different types of summaries in varied lengths and formats, such as sentences, paragraphs, bullet point lists, and more.
Discover the infinite possibilities of the Prompt API in Chrome Extensions.

Build with AI

Solve for your use case.
Use server-side generative AI to evaluate reviews. Inference occurs on a server.
Explore on-device AI solutions to help users write insightful reviews.
Empower global customer support with the Translator API.
Help your applications launch faster by caching the model on-device.
This guide introduces best practices for session management with the language model.
Enhance the browsing experience with browser customization and control over web content. Build next-level extensions with AI.

Best practices

Help your applications launch faster by caching the the model on-device.
Understand what streaming is and how it works with AI and LLMs.
Use these frontend best practices to display streamed responses from Gemini.
Use a special Chrome-internal page to see debugging details on prompts to Gemini Nano.

AI and Gemini Nano news

Introducing command and commandfor

Updated March 7, 2025

Learn about the new capabilities for declarative behavior on buttons.

Use scheduler.yield() to break up long tasks

Updated March 6, 2025

scheduler.yield() is a new API for ergonomically splitting up long tasks and getting prioritized continuation of execution.

Delaying the shipping of CSS @function from Chrome 136 to 139

Updated March 6, 2025

The Chrome team responds to concerns from the community.

Developer productivity

Chat with Gemini in DevTools. Conversations you start from this panel have context about technical details of the page you're inspecting.
Use the AI assistance panel to understand a website's overall layout, specific element styles and to get AI-generated fixes for CSS bugs.
Check out five ways to make styling your page easier, from understanding layouts to fixing airplanes.
Use the Console to view and debug the results of on-device AI.

Built-in AI Challenge winners

Find inspiration for built-in AI with the winners of the Built-in AI Challenge.
All winners
A dynamic, lightweight search bar that lets you create, modify, and delete prompts for daily small tasks.
Get inspired
Adapt web content to support users with reading disabilities, ADHD, and dyslexia.
Get inspired
Adding AI assistance to the WordPress block editor.
Get inspired

WebGPU

Support your AI efforts with WebGPU, a web graphics API that offers access to more advanced GPU features.
Disover the latest updates to WebGPU in Chrome.
Read the doc
Discover WebGPU in Chrome and get first-class support for general computations on the GPU.
Read the doc
Learn how to access the GPU with WebGPU.
Read the doc
Learn how to test client-side, browser-based AI models in true browser environments.
Read the doc
Learn why WebGPU may be inoperable or not working as expected in Chrome, and how to fix it..
Read the doc
Find the API reference on MDN.
Visit MDN

WebAssembly

Enable high-performance applications on web pages with Chrome
Learn about improvements to WebAssembly for tasks commonly used in AI inference.
Read the doc
Learn about the TensorFlow.js Wasm backend WASM backend and how it uses the XNNPACK library for optimized implementation of neural network operators.
Read the doc
Learn how to deploy the ONNX Runtime Web in a production environment and which WebAssembly binary file(s) to include in the application.
Read the doc

Introducing web AI

web.dev
Understand the basics and definitions of the various emerging technologies, often referred to as AI.
Read the doc
web.dev
As web practitioners, it's critical that we build new technology thoughtfully and responsibly.
Read the doc
web.dev
Discover techniques to use client-side AI, which offers benefits such as low latency, reduced server-side costs, increased user privacy, and more.
Read the doc