Run headless Chrome on Cloudflare's global network for browser automation, web scraping, and content generation.
Run web browsers on Cloudflare's global network — scrape websites, render pages, and automate web tasks from the edge.
Cloudflare Browser Rendering enables developers to programmatically control and interact with headless browser instances running on Cloudflare's global edge network. This service went viral with 9.2M views on X for its revolutionary approach to browser automation at scale, offering instant access to thousands of browsers with minimal cold-start times.
The service provides multiple integration methods: a simple REST API for stateless tasks like screenshots, PDFs, and scraping, and Workers Bindings for full browser automation using Puppeteer, Playwright, or Stagehand. The REST API includes specialized endpoints for markdown conversion, structured data extraction, and web crawling — making it particularly powerful for AI agents that need to interact with web content.
Key differentiators include global distribution (browsers run close to users for better performance), massive scale (thousands of concurrent browser sessions), and AI-powered features like natural language data extraction through the JSON endpoint. The /crawl endpoint that gained viral attention provides intelligent web crawling with automatic content discovery and extraction.
For AI agent workflows, Browser Rendering excels at tasks requiring visual understanding of web pages, complex user interactions, or large-scale data collection. Unlike traditional scraping tools, it can handle modern SPAs, execute complex user flows, and capture visual content. The integration with Stagehand enables AI agents to control browsers using natural language instructions rather than CSS selectors.
The service supports session management for reusing browser contexts across requests, reducing overhead for multi-step workflows. Pricing is based on browser time used, with a generous free tier. The global edge deployment means consistent performance worldwide, making it ideal for applications serving international users.
Limitations include the inherent cost of browser automation compared to simple HTTP requests, potential complexity in debugging browser-based workflows, and dependency on Cloudflare's infrastructure. However, for applications requiring true browser interaction or visual content understanding, it offers unmatched scale and performance.
Was this helpful?
Cloudflare Browser Rendering revolutionizes web scraping and browser automation with global scale and edge performance. The viral /crawl endpoint and AI-powered extraction make it a game-changer for data-intensive applications.
Nine stateless endpoints — /content, /screenshot, /pdf, /markdown, /snapshot, /scrape, /json, /links, and /crawl — handle the most common browser tasks via a single HTTP request with no Worker deployment required. Each is purpose-built (e.g., /markdown for clean LLM-ready text, /json for AI extraction), making them ideal building blocks for agent and RAG pipelines.
Native support for the Model Context Protocol via Playwright MCP, plus Stagehand, lets LLM agents drive browsers using natural language intent rather than CSS selectors. This dramatically improves resilience when target sites change layout and is one of the more agent-native browser stacks available in 2026.
Browsers spin up across Cloudflare's global network of 330+ cities, opening sessions close to target users for lower latency and better availability. The pool scales to thousands of concurrent browsers with low cold-start time, suitable for high-volume screenshot, scraping, and testing workloads.
Browser sessions can be persisted across requests using Durable Objects, eliminating repeated cold-start overhead for multi-step agent flows or stateful crawls. This both improves performance and meaningfully reduces cost on browser-time billing for long-running workflows.
Connect to Cloudflare-managed browsers via raw Chrome DevTools Protocol over WebSocket from local machines, CI/CD runners, or external servers — no Worker deployment required. This makes it usable as a drop-in replacement for self-hosted browser farms in existing test suites and scraping infrastructure.
$0/month
Pay-as-you-go on browser time
Ready to get started with Cloudflare Browser Rendering?
View Pricing Options →Cloudflare Browser Rendering works with these platforms and services:
We believe in transparent reviews. Here's what Cloudflare Browser Rendering doesn't handle well:
Weekly insights on the latest AI tools, features, and trends delivered to your inbox.
In April 2026, Cloudflare rebranded Browser Rendering to 'Browser Run' and introduced several Beta features: Live View for visual session debugging, Human in the Loop for inserting manual approval steps into automated flows, Session recording for replay and audit, WebMCP for LLM-driven browser control via the Model Context Protocol, custom fonts support, and the /crawl Quick Action for asynchronous multi-page extraction. Stagehand integration also moved into Beta, enabling intent-based element selection for AI agents.
Search & Discovery
Cloud-hosted headless browser infrastructure built for AI agents, with stealth mode, session recording, and Playwright/Puppeteer compatibility. Free tier includes 1 browser hour; paid plans from $39/month.
AI Memory & Search
The Web Data API for AI that transforms websites into LLM-ready markdown and structured data, providing comprehensive web scraping, crawling, and extraction capabilities specifically designed for AI applications, RAG pipelines, and LLM agent workflows.
Search & Discovery
ScrapingBee: Web scraping API with rendering, proxies, and anti-bot tools. - Enhanced AI-powered platform providing advanced capabilities for modern development and business workflows. Features comprehensive tooling, integrations, and scalable architecture designed for professional teams and enterprise environments.
Browser Agents
Browser Use Desktop is an open-source desktop application that gives AI agents direct, reliable access to a Chromium browser for web automation, data extraction, form filling, and multi-step internet tasks. Built on the Browser Use Python framework (16,000+ GitHub stars as of early 2026), it packages the agent-browser bridge into a standalone app with a visual interface for monitoring agent activity in real time. Unlike headless-only automation libraries, Browser Use Desktop renders pages visually so operators can watch, pause, and debug agent sessions. It supports integration with LLM providers including OpenAI, Anthropic Claude, and local models through LangChain, enabling developers to pair any large language model with autonomous browser control.
No reviews yet. Be the first to share your experience!
Get started with Cloudflare Browser Rendering and see if it's the right fit for your needs.
Get Started →Take our 60-second quiz to get personalized tool recommendations
Find Your Perfect AI Stack →Explore 20 ready-to-deploy AI agent templates for sales, support, dev, research, and operations.
Browse Agent Templates →