# Browser Use Cloud > Browser Use Cloud has two products. **Browser Use Agents** accept a > natural-language goal and complete the web task. **Browser Infrastructure** > is hosted cloud browser infrastructure for AI agents, controlled through the > SDK, REST, or CDP. Auth uses > `X-Browser-Use-API-Key` (keys start with `bu_`). - Dashboard: https://cloud.browser-use.com - Create API key: https://cloud.browser-use.com/settings?tab=api-keys&new=1 - Docs: https://docs.browser-use.com - Developer overview: https://browser-use.com/developers.md — Choose between Browser Use Agents, Browser Infrastructure, and the Open Source Library, and select an interface for a new integration. - Pricing: https://browser-use.com/pricing.md — Current plans, credits, and usage rates. - Product map: https://browser-use.com/llms.txt — Canonical machine-readable routes for Browser Use products and documentation. - Open-source repo: https://github.com/browser-use/browser-use — The self-hosted Python library; its API differs from the Cloud SDK. The V2, V3, and V4 references remain available below. Use the developer overview to choose an interface for a new integration. **TypeScript V4 browser settings:** The generated `RunBrowserSettings` type currently requires `proxyCountryCode`; pass `"us"` to retain the default managed residential proxy, or `null` to disable the proxy. **Stopping standalone browsers:** Do not use `client.close()`, `browser.close()`, or a dropped CDP connection as the API V4 stop operation. Keep the browser session ID returned by `POST /api/v4/browsers`, then call `PATCH /api/v4/browsers/{id}` with `{"action":"stop"}`. See the pricing page for billing behavior. **Create and reuse a login profile:** Create one profile per end user, then pass its ID as top-level `profileId` when creating browsers, or as `browserSettings.profileId` on agent runs: ```bash profile=$(curl -sS https://api.browser-use.com/api/v4/profiles \ -H "X-Browser-Use-API-Key: $BROWSER_USE_API_KEY" \ -H "Content-Type: application/json" \ -d '{"name":"My user"}') export BROWSER_USE_PROFILE_ID=$(echo "$profile" | jq -r .id) curl -sS https://api.browser-use.com/api/v4/browsers \ -H "X-Browser-Use-API-Key: $BROWSER_USE_API_KEY" \ -H "Content-Type: application/json" \ -d "{\"profileId\":\"$BROWSER_USE_PROFILE_ID\",\"proxyCountryCode\":\"us\"}" ``` Log in once in that browser, stop it, then use the same profile ID to start the next browser already logged in. Full guide: https://docs.browser-use.com/cloud/guides/authentication **SDK typing:** Check the installed SDK types against the API reference. New schema fields and model IDs can reach REST before a generated SDK release. Before writing code, check if `browser-use-sdk` is already installed. If so, upgrade to the latest version. If not, install it: - Python: `pip install --upgrade browser-use-sdk` - TypeScript: `npm install browser-use-sdk@latest` Set API key (starts with `bu_`). If the user doesn't have one yet, they can create one in one click at https://cloud.browser-use.com/settings?tab=api-keys&new=1: ``` export BROWSER_USE_API_KEY=bu_your_key_here ``` ## Get Started - [Quick start](https://docs.browser-use.com/cloud/quickstart): Choose Browser Use Agents or hosted cloud browser infrastructure for AI agents. - [Choosing an Agent](https://docs.browser-use.com/cloud/choosing-an-agent): Compare measured Browser Use Cloud agent accuracy and speed. - [Prompt for Vibecoders](https://docs.browser-use.com/cloud/vibecoding): Complete Cloud SDK reference for AI coding agents. ## Browser Use Agents - [Run a task](https://docs.browser-use.com/cloud/agent/quickstart): Give a high-accuracy browser agent a goal and get the result. - [Models](https://docs.browser-use.com/cloud/agent/models): Choose a V4 model and configure its reasoning behavior. - [Thinking levels](https://docs.browser-use.com/cloud/agent/thinking-levels): Configure model reasoning depth across API V2, V3, and V4. - [Structured output](https://docs.browser-use.com/cloud/agent/structured-output): Ask for JSON and validate the V4 result in your application. - [Sessions](https://docs.browser-use.com/cloud/agent/sessions): Continue one conversation across multiple V4 runs. - [Workspaces & files](https://docs.browser-use.com/cloud/agent/workspaces): Persist files across V4 runs and conversations. - [Rerunnable scripts](https://docs.browser-use.com/cloud/agent/scripts): Save a Browser Use task as a rerunnable script for repeated live data extraction and self-healing runs. - [Human in the loop](https://docs.browser-use.com/cloud/agent/human-in-the-loop): Open the live browser, take over, then continue the same session. - [Observability](https://docs.browser-use.com/cloud/agent/observability): Poll ordered V4 events to monitor a run or build a custom UI. ## Browser Infrastructure - [Browser Infrastructure quickstart](https://docs.browser-use.com/cloud/browser/quickstart): Control hosted cloud browser infrastructure for AI agents through the SDK, REST, or CDP. - [Stealth](https://docs.browser-use.com/cloud/browser/stealth): Hardened Chromium and configurable proxy routing for cloud browser sessions. - [CAPTCHA handling](https://docs.browser-use.com/cloud/browser/captcha-handling): Cloud browsers solve supported CAPTCHA challenges automatically. - [Proxies](https://docs.browser-use.com/cloud/browser/proxies): Route API V4 agent runs through residential or custom proxies. - [Live preview & recording](https://docs.browser-use.com/cloud/browser/live-preview): Watch an API V4 run in real time or record its browser. - [Playwright, Puppeteer, Selenium](https://docs.browser-use.com/cloud/browser/playwright-puppeteer-selenium): Control a Browser Use cloud browser directly over CDP. ## Authentication - [Profiles](https://docs.browser-use.com/cloud/guides/authentication): Reuse cookies and browser state in API V4 runs. - [Sync local and cloud cookies](https://docs.browser-use.com/cloud/guides/profile-sync): Sync a local login, then use it in an API V4 run. - [2FA](https://docs.browser-use.com/cloud/guides/2fa): Handle two-factor authentication in API V4 runs. ## More - [FAQ](https://docs.browser-use.com/cloud/faq): Common questions and solutions. ## Integrations - [OpenClaw](https://docs.browser-use.com/cloud/tutorials/integrations/openclaw): Give OpenClaw agents browser automation with Browser Use — via CDP or the CLI skill. - [Hermes Agent](https://docs.browser-use.com/cloud/tutorials/integrations/hermes-agent): Give Hermes Agent cloud browser automation with Browser Use. ## Anthropic - [Claude Code](https://docs.browser-use.com/cloud/tutorials/integrations/claude-code): Give Claude Code cloud browser automation with Browser Use. - [Claude Managed Agents](https://docs.browser-use.com/cloud/tutorials/integrations/claude-managed-agents): Give Anthropic's Claude Managed Agents Browser Infrastructure through the Browser Use CLI. ## Tutorials - [Agent Sign Up for Browser Use](https://docs.browser-use.com/cloud/agent-signup): How the Browser Use agent challenge lets an AI agent create an account and API key. ## API v2 guides - [Agent (v2)](https://docs.browser-use.com/cloud/legacy/agent): V2 agent models and file handling. - [Public share links (v2)](https://docs.browser-use.com/cloud/legacy/public-share): Generate shareable URLs for agent sessions using the v2 API. - [Skills](https://docs.browser-use.com/cloud/legacy/skills): Turn any website into a deterministic API endpoint. Create once, call repeatedly. - [1Password & 2FA](https://docs.browser-use.com/cloud/guides/1password): Auto-fill passwords and TOTP codes from 1Password during agent tasks. - [Secrets](https://docs.browser-use.com/cloud/guides/secrets): Pass domain-scoped credentials to the agent securely. ## API v4 - [API Reference](https://docs.browser-use.com/cloud/api-v4-overview): Authenticate and start using the Browser Use API v4 for agents and direct browser control. - [API v4 OpenAPI specification](https://docs.browser-use.com/cloud/openapi/v4.json) ## API v3 - [API Reference](https://docs.browser-use.com/cloud/api-reference): Authenticate and start using the Browser Use REST API. - [API v3 OpenAPI specification](https://docs.browser-use.com/cloud/openapi/v3.json) ## V3 guides and tutorials - [MCP Server](https://docs.browser-use.com/cloud/guides/mcp-server): Run browser automation tasks from your AI coding assistant. Connect to Claude, Cursor, Windsurf, or any MCP client. - [Webhooks](https://docs.browser-use.com/cloud/guides/webhooks): Receive real-time notifications when tasks complete. Configure webhook endpoints for async task monitoring. - [x402 wallet payments](https://docs.browser-use.com/cloud/guides/x402): Pay for Browser Use Cloud with crypto (USDC on Base), without an API key. - [x402 agent wallets](https://docs.browser-use.com/cloud/guides/x402-agent-wallets): Pay for Browser Use Cloud from an agent-native wallet: AgentCash (local wallet, MCP) or Coinbase's Agentic Wallet (hosted wallet, CLI). - [n8n](https://docs.browser-use.com/cloud/tutorials/integrations/n8n): Use Browser Use as an HTTP node in n8n workflows. - [Chat UI](https://docs.browser-use.com/cloud/tutorials/chat-ui): Build a chat UI with live browser preview, follow-up tasks, recording, and task messages. - [Grow Therapy provider search](https://docs.browser-use.com/cloud/tutorials/grow-therapy-compare): Search Grow Therapy for therapists by location, insurance, and specialty — with cached reruns. ## API v2 - [API key](https://docs.browser-use.com/cloud/api-v2-overview): Set your API key to access the Browser Use v2 REST API. - [API v2 OpenAPI specification](https://docs.browser-use.com/cloud/openapi/v2.json)