# Prompteryx > Prompteryx is an AI platform where one chat does the work: it browses real websites for you, runs automations, researches with sources and makes websites, documents, images, video and music. Prompteryx is an AI workspace for delegating real work. A single chat picks the right AI model for each job, uses an AI browser agent that operates a real Chrome browser (your own through Prompteryx Desktop, or a cloud browser), connects to more than 3,000 apps, and can turn any task into a repeatable workflow on the Visual Studio canvas that runs on a schedule, by API or by webhook. Prompteryx is made by PROMPTERYX LIMITED, a company registered in England and Wales (company number 17472473). ## Key facts - One chat for everything, with Auto model selection across leading AI models - AI Browser Agent that uses a real Chrome browser to complete tasks on any website - Prompteryx Desktop (Windows) to run agents in your own Chrome with your own logins - Cloud browsers with residential proxies, session recording and automatic CAPTCHA solving - Visual Studio: a drag-and-drop workflow canvas with 80+ browser action nodes - Connect Hub: actions in 3,000+ apps such as Gmail, Google Sheets, Slack and Notion - Schedules, webhooks and a REST API to run any workflow automatically - Batch Prompter for running many prompts across AI platforms from a spreadsheet - Websites, documents, slide decks, images, video, voice and music made in the chat - Explore: a gallery of things people made with Prompteryx, with the recipe behind each one - Developer tools: REST API, TypeScript SDK, CLI and a hosted MCP server that Claude, ChatGPT, Cursor and VS Code connect to with OAuth; n8n, Make and Zapier connect through their HTTP, webhook and MCP apps - Pricing: A 7-day free trial, then monthly plans (Starter, Developer and Pro, with Enterprise on request). Each plan includes AI Credits, workflow executions and cloud-browser time; extra usage can be paid as you go from AI Credits. Current prices: https://www.prompteryx.ai/pricing ## Who it is for - Individuals and small teams who want routine browser work done for them - Operations, sales and marketing teams automating web tasks that have no API - Developers who need cloud browsers, an AI browser agent API, an MCP server or a TypeScript SDK - Creators who want websites, slide decks, images, video and music from one chat ## How it works 1. Describe what you want done in the chat. 2. Prompteryx chooses a model (or you pick one) and, when the task needs the web, an AI browser agent opens a real browser and does it, showing each step. 3. Save a successful run as a workflow and replay it without AI costs, on a schedule, or from your own code. ## Good to know - Prompteryx does not sell personal data or use it for third-party advertising (privacy policy: https://www.prompteryx.ai/privacy). - Actions involving money or security always ask you first when run by the personal agent. ## Plans and prices (from the live plan configuration) ### Free Trial (free for 7 days) Experience full functionality for 7 days - 1,500 workflow executions during the trial - 50 AI Credits for the trial - 10 cloud-browser minutes - 1 concurrent cloud browser - Residential proxy, paid from AI Credits (0.5 credits/MB) - Auto-CAPTCHA — 10 solves - REST API + webhooks (up to 10 API keys) - 7-day execution history - Email support ### Starter ($20 per month) Perfect for solo builders and creators - 3,000 workflow executions/month - 500 AI Credits/month - 100 cloud-browser hours/month - 2 concurrent cloud browsers - 100 MB residential proxy data/month, then 0.5 credits/MB - Auto-CAPTCHA — 100 solves/month - Connect Hub — 100 credits/month (3,000+ apps) - Session & video recording - Run invisible (background) mode - 5 concurrent automations - 5 scheduled workflows - Share up to 5 automations - REST API + webhooks (up to 10 API keys) - 90-day execution history - Optional pay-as-you-go usage credits, with your own monthly limit - Priority support ### Developer ($20 per month) Cloud-browser infrastructure: API, proxies, recordings - 3,000 workflow executions/month - 100 AI Credits/month - 200 cloud-browser hours/month - 25 concurrent cloud browsers - 1 GB residential proxy data/month, then 0.5 credits/MB - Auto-CAPTCHA — 100 solves/month - Session & video recording - Run invisible (background) mode - 5 concurrent automations - 5 scheduled workflows - REST API + webhooks (up to 10 API keys) - 30-day execution history - Optional pay-as-you-go usage credits, with your own monthly limit - Email support ### Pro ($45 per month) For businesses and power users - 12,000 workflow executions/month - 1,500 AI Credits/month - 250 cloud-browser hours/month - 5 concurrent cloud browsers - 250 MB residential proxy data/month, then 0.5 credits/MB - Auto-CAPTCHA — 500 solves/month - Connect Hub — 300 credits/month (3,000+ apps) - Session & video recording - Run invisible (background) mode - 10 concurrent automations - 15 scheduled workflows - Share up to 15 automations - REST API + webhooks (up to 10 API keys) - 365-day execution history - Optional pay-as-you-go usage credits, with your own monthly limit - Priority support ### Enterprise (custom pricing) For large organizations with custom needs - 12,000+ workflow executions/month - 1,500+ AI Credits included - 200,000+ max tokens per session - Rate limit: 2,000/hour - 2-year execution history - Visual Studio + AI Browser Agents - 10+ concurrent automations - 15+ scheduled workflows - Share 15+ automations - Dedicated support - Custom SLA (by contract) - White-label, dedicated cloud browser or isolated deployment - Security review pack + Data Processing Agreement ## Questions and answers ### What is Prompteryx? Prompteryx is an AI platform where one chat does the work: it browses real websites for you, runs automations, researches with sources and makes websites, documents, images, video and music. ### What can the Prompteryx AI browser agent do? It opens a real Chrome browser and completes tasks on websites the way a person would: searching, clicking, filling in forms, extracting data and downloading files. It can run in your own Chrome through Prompteryx Desktop, with your logins, or in a Prompteryx cloud browser. ### Do I need to code to use Prompteryx? No. You describe tasks in plain English in the chat, and workflows are built on a drag-and-drop canvas. Developers can also use the REST API, TypeScript SDK, CLI or MCP server. ### How much does Prompteryx cost? A 7-day free trial, then monthly plans (Starter, Developer and Pro, with Enterprise on request). Each plan includes AI Credits, workflow executions and cloud-browser time; extra usage can be paid as you go from AI Credits. Current prices are on https://www.prompteryx.ai/pricing. ### Who makes Prompteryx? Prompteryx is made by PROMPTERYX LIMITED, a company registered in England and Wales (company number 17472473). ## Key pages - [Home](https://www.prompteryx.ai/) - [Pricing](https://www.prompteryx.ai/pricing) - [Why Prompteryx](https://www.prompteryx.ai/why-prompteryx) - [Templates and examples](https://www.prompteryx.ai/templates) - [Use cases](https://www.prompteryx.ai/use-cases) - [Integrations](https://www.prompteryx.ai/integrations) - [Documentation](https://www.prompteryx.ai/docs) - [Download Prompteryx Desktop](https://www.prompteryx.ai/download) ## Products - [The Prompteryx app (one chat for everything)](https://www.prompteryx.ai/features/app) - [AI Browser Agent](https://www.prompteryx.ai/features/ai-browser-agent) - [Visual Studio workflow builder](https://www.prompteryx.ai/features/visual-studio) - [Cloud Browser](https://www.prompteryx.ai/features/cloud-browser) - [Batch Prompter](https://www.prompteryx.ai/features/batch-prompter) ## Comparisons - [Compare Prompteryx](https://www.prompteryx.ai/compare) - [Prompteryx vs Browserbase](https://www.prompteryx.ai/compare/vs-browserbase): Prompteryx and Browserbase both run cloud browsers for automation and AI agents. Compare browser-hours, billing, regions, SDKs, no-code building, your own Chrome and app connections. Facts checked 25 October 2026. - [Prompteryx vs n8n](https://www.prompteryx.ai/compare/vs-n8n): n8n is a popular workflow automation platform you can self-host. Prompteryx adds a built-in browser engine, AI browser agents, recordings of every run and your own Chrome. A fair comparison, checked 25 October 2026. - [Prompteryx vs Zapier](https://www.prompteryx.ai/compare/vs-zapier): Zapier connects 9,000+ apps through their APIs. Prompteryx automates the steps that have no API: websites, portals and forms, with an AI browser agent. A fair comparison, checked 25 October 2026. - [Prompteryx vs Manus](https://www.prompteryx.ai/compare/vs-manus): Manus runs general-purpose AI agents in the cloud and on your computer. Prompteryx combines AI browser agents with workflows you can edit step by step and replay without AI costs. A fair comparison, checked 25 October 2026. - [Prompteryx vs Claude](https://www.prompteryx.ai/compare/vs-claude): Claude is a leading AI assistant with Claude in Chrome, computer use, connectors and scheduled tasks. Prompteryx is an automation platform that can use Claude models. Compare browser agents, workflows, schedules and cloud browsers. Checked 25 October 2026. - [Prompteryx vs Perplexity Comet](https://www.prompteryx.ai/compare/vs-comet): Comet is Perplexity's free AI web browser with a built-in assistant. Prompteryx is an automation platform with AI browser agents, cloud browsers and workflows that replay without AI costs. A fair comparison, checked 25 October 2026. - [Prompteryx vs Axiom.ai](https://www.prompteryx.ai/compare/vs-axiom): Axiom.ai builds no-code browser bots in a Chrome extension, with cloud runs and a desktop app. Prompteryx adds an AI browser agent, a drag-and-drop canvas and 3,000+ app actions. A fair comparison, checked 25 October 2026. ## Company, trust and support - [Enterprise](https://www.prompteryx.ai/enterprise) - [Trust centre](https://www.prompteryx.ai/trust) - [Subprocessors](https://www.prompteryx.ai/trust/subprocessors) - [Security](https://www.prompteryx.ai/security) - [Support](https://www.prompteryx.ai/support) ## Legal - [Privacy policy](https://www.prompteryx.ai/privacy) - [Terms of service](https://www.prompteryx.ai/terms) - [Acceptable use policy](https://www.prompteryx.ai/acceptable-use) - [App builder terms](https://www.prompteryx.ai/legal/app-builder) - [Data processing agreement](https://www.prompteryx.ai/legal/dpa) - [Kimi model terms](https://www.prompteryx.ai/legal/kimi) - [Company details](https://www.prompteryx.ai/imprint) - [Delete your account](https://www.prompteryx.ai/delete-account) ## Use cases - [Web Scraping Without the Maintenance](https://www.prompteryx.ai/use-cases/web-scraping): Scrape data from any website with real browsers that handle JavaScript, logins and anti-bot checks. Build scrapers visually, schedule them, auto-fall-back when selectors break, and export straight to Google Sheets — with a full video recording of every run. - [Lead Generation & List Building](https://www.prompteryx.ai/use-cases/lead-generation): Automate lead generation by scraping business directories, search results and company sites into structured contact lists. Qualify leads with AI, schedule fresh pulls, and sync straight to Google Sheets, Airtable or your CRM. - [E-commerce & Product Data](https://www.prompteryx.ai/use-cases/ecommerce-data): Scrape product catalogs, prices, reviews and inventory from any online store with real browsers. Handle JavaScript, pagination and anti-bot checks, schedule fresh pulls, and export to Sheets, Airtable or your data warehouse. - [Job Board Aggregation](https://www.prompteryx.ai/use-cases/job-board-aggregation): Aggregate job listings, salaries and company info from multiple job boards into one structured, deduplicated feed. Schedule daily pulls and deliver a digest to Google Sheets, email or Slack — no code required. - [Form Filling & Data Entry](https://www.prompteryx.ai/use-cases/form-filling): Automate repetitive form filling and data entry across web portals. Pull rows from Google Sheets or Airtable, fill complex forms (dropdowns, checkboxes, uploads) in a real browser, and capture a video of every submission. - [Portal Logins & Report Downloads](https://www.prompteryx.ai/use-cases/report-downloads): Automate logging into web portals and downloading reports, invoices and statements on a schedule. Use your own local Chrome with existing logins, file downloads into Drive or email, and keep a video record of every run. - [Social Media Automation](https://www.prompteryx.ai/use-cases/social-media-automation): Automate social media posting, scheduling and monitoring through a real browser — no expensive or restricted APIs. Drive posts from a Google Sheets content calendar, use your own logged-in accounts, and record every action. - [AI Web Research Agent](https://www.prompteryx.ai/use-cases/web-research-agent): Give an AI browser agent a goal in plain English and it navigates, clicks, fills forms and extracts answers across the web. Pick Gemini, Claude or GPT, watch it live, record the run, and convert it into a reusable zero-cost workflow. - [Price & Competitor Monitoring](https://www.prompteryx.ai/use-cases/price-monitoring): Automatically monitor product and competitor prices across any website on a schedule. Get instant Slack or email alerts when prices drop or change, with per-second billing that makes frequent checks affordable and a video record of every run. - [End-to-End Testing & Uptime Monitoring](https://www.prompteryx.ai/use-cases/end-to-end-testing): Build end-to-end tests and synthetic monitors for your critical user journeys without code. Assert element states and values in a real browser, run on a schedule, alert on failure, and keep a video recording of every test run. - [Bin Day Reminders — a real product built on Prompteryx](https://www.prompteryx.ai/use-cases/bin-day-reminders): See how Bin Day Reminders — a live UK bin-collection reminder service — is built entirely on Prompteryx: scheduled AI browser scraping of 300+ council sites, automatic schedule parsing, and branded email automation, with no custom backend. ## Documentation - [Selectors guide](https://www.prompteryx.ai/docs/advanced/selectors): Master element selection for reliable automations - [Variables and expressions](https://www.prompteryx.ai/docs/advanced/variables): Pass data between nodes using variables and expressions - [AI Browser Agent commands](https://www.prompteryx.ai/docs/ai-browser/commands): Learn how to write effective prompts for the AI Browser Agent - [Get started with the AI Browser Agent](https://www.prompteryx.ai/docs/ai-browser/getting-started): Start your first AI-powered browser automation session - [AI Browser Agent overview](https://www.prompteryx.ai/docs/ai-browser/overview): Control browsers with natural language and automatically record actions for Visual Studio - [AI Browser Agent documentation](https://www.prompteryx.ai/docs/ai-browser): An AI browsing copilot with computer vision that runs on our Cloud Browser or in your own Chrome - [Run browser agents in parallel](https://www.prompteryx.ai/docs/ai-browser/parallel-agents): Run one task as several agents at once — split a batch for speed, or collaborate on a single shared page. - [Record AI Browser Agent runs](https://www.prompteryx.ai/docs/ai-browser/recording): Convert AI Browser sessions into reusable Visual Studio workflows - [AI Browser Agent settings](https://www.prompteryx.ai/docs/ai-browser/settings): What each setting does, when to use it, and what to watch out for. - [Structured output from the AI Browser Agent](https://www.prompteryx.ai/docs/ai-browser/structured-output): Get a run's result as JSON matching a schema you define — alongside the written answer - [AI Browser Agent tips and best practices](https://www.prompteryx.ai/docs/ai-browser/tips): Get the most out of the AI Browser Agent with these tips - [AI Browser Agent in the chat](https://www.prompteryx.ai/docs/app/browser-agent): Run the AI Browser Agent from the main chat: choose the cloud browser or your own Chrome, pick a model, watch it work, and read the outcome card with Try again and Try with another model. - [The app: Connectors](https://www.prompteryx.ai/docs/app/connectors): Connect the apps you use, such as Gmail, Google Sheets, Slack and Notion, so the chat can read and act in them for you. - [What you can make](https://www.prompteryx.ai/docs/app/create): One chat makes websites, games, images, video, music, voiceovers, sound effects, documents, slides, spreadsheets, PDFs and cited research. How to ask, what you get back, and how to keep, publish or share it. - [Prompteryx Desktop](https://www.prompteryx.ai/docs/app/desktop): Prompteryx Desktop runs automations in your own Chrome with your logins and free local minutes, and opens the Prompteryx app in its own window. - [Explore and publishing](https://www.prompteryx.ai/docs/app/explore): Explore is where people share what they make with Prompteryx. Browse websites, games, images, videos, music and browser tasks, see the prompt behind each one, make your own version, and share your own work. - [The app: Groups](https://www.prompteryx.ai/docs/app/groups): Group chats and direct messages where anyone can ask @Prompteryx to make something for everyone. - [Memory and Skills](https://www.prompteryx.ai/docs/app/memory-and-skills): What the Prompteryx assistant remembers about you and the switches that control it, the About you profile, incognito chats, and reusable Skills. - [Models and Auto](https://www.prompteryx.ai/docs/app/models): How the Prompteryx app chooses a model with Auto, how to pick a specific model for one message, and how to change your defaults. - [The Prompteryx app: documentation](https://www.prompteryx.ai/docs/app): The Prompteryx app is where everything starts: one chat that answers with any model, builds websites and games, makes images, video, music and documents, does research, runs the AI Browser Agent and builds workflows. - [Your personal agent (beta)](https://www.prompteryx.ai/docs/app/personal-agent): An agent with its own name that keeps working when you're not in the app: it briefs you, watches pages for you, and asks before it acts. - [The app: Phone app](https://www.prompteryx.ai/docs/app/phone): Prompteryx on Android: your chats, Groups, Studio and your agent, with notifications. - [Plans, credits and top-ups](https://www.prompteryx.ai/docs/app/plans-and-credits): How Prompteryx is paid for: the free trial, monthly plans, AI credits, one-off top-up packs, pay-as-you-go usage credits, and changing or cancelling your plan. - [Projects in the Prompteryx app](https://www.prompteryx.ai/docs/app/projects): Projects in the Prompteryx app: group chats around a goal, with instructions every chat follows, files every chat can use, and team members. - [Schedule tasks from the chat](https://www.prompteryx.ai/docs/app/schedules): Run any chat task on a schedule from the message box: how often, where it runs, what happens when a run needs you, and where your schedules are listed. - [Welcome, settings and skins](https://www.prompteryx.ai/docs/app/settings): The welcome set-up for new accounts, what is in Settings, choosing light or dark and a skin, and where your account, plan and usage live. - [Share links for chats](https://www.prompteryx.ai/docs/app/sharing): Share a read-only copy of a Prompteryx chat with a link: what is included, what is hidden, how to update or remove a link, and publishing to Explore. - [Batch Prompter](https://www.prompteryx.ai/docs/batch-prompter): Run batch automations across AI platforms with Excel files - [Using Attached Files](https://www.prompteryx.ai/docs/chrome-extension/attached-files): Share images with the AI to provide visual context for your requests - [Execute on Current Tab](https://www.prompteryx.ai/docs/chrome-extension/current-tab): Run AI automations directly on the page you're currently viewing - [Exporting to Visual Studio](https://www.prompteryx.ai/docs/chrome-extension/exporting): Save your AI-driven actions as reusable, editable workflows - [Install the Prompteryx Chrome extension](https://www.prompteryx.ai/docs/chrome-extension/installation): Add and set up Prompteryx in Chrome, our Chrome extension - [Prompteryx Chrome extension overview](https://www.prompteryx.ai/docs/chrome-extension/overview): Bring AI-powered browser automation directly into your Chrome browser - [Using the Sidebar Agent](https://www.prompteryx.ai/docs/chrome-extension/sidebar-agent): Control browsers with natural language commands from the Chrome sidebar - [Migrate to Prompteryx Cloud Browser](https://www.prompteryx.ai/docs/cloud-browser-migration): Drop-in migration from Browserbase, Browser Use Cloud, or Puppeteer Cloud to the Prompteryx Cloud Browser — same CDP connect, lower cost. - [Cloud Browser quickstart](https://www.prompteryx.ai/docs/cloud-browser-quickstart): Spin up a real Chrome browser in the Prompteryx cloud and drive it with Playwright in under five minutes. API keys, SDK, and Sessions API copy-paste ready. - [Prompteryx Cloud Browser: overview and API](https://www.prompteryx.ai/docs/cloud-browser): Real Chrome browsers in the Prompteryx cloud, driven from your code over CDP: recordable, proxy-capable and metered to your plan. Or skip the session with managed Fetch and Search. - [Run the AI browser agent](https://www.prompteryx.ai/docs/developers/agent): Describe a goal. Prompteryx opens a browser, looks at the screen, clicks and types until the goal is met, and reports what it found and what it cost. - [Authentication & API Keys](https://www.prompteryx.ai/docs/developers/authentication): Create and use API keys to authenticate with all Prompteryx developer interfaces - [Drive a cloud browser](https://www.prompteryx.ai/docs/developers/browser): Start a real Chrome in the cloud, connect your own Playwright to it, and borrow AI only for the steps that are hard to script. - [Prompteryx CLI](https://www.prompteryx.ai/docs/developers/cli): Prompteryx from a terminal or a CI job. Sign in once in the browser; tokens refresh on their own. - [Use connected apps (Connect Hub)](https://www.prompteryx.ai/docs/developers/connect-hub): Send an email, add a row, post a message: 3,000 apps through the user's own connected accounts, with credentials that never leave the platform. - [Prompteryx for Make.com](https://www.prompteryx.ai/docs/developers/make): Run Prompteryx workflows and the AI browser agent from Make scenarios with the HTTP app, receive results with a custom webhook, or call Prompteryx tools through Make's MCP Client - [Prompteryx MCP server](https://www.prompteryx.ai/docs/developers/mcp): Use Prompteryx workflows, the AI browser agent and your connected apps from Claude, ChatGPT, Cursor, VS Code, Gemini CLI and any other MCP client - [MCP Tools Reference](https://www.prompteryx.ai/docs/developers/mcp/tools): Complete reference for all browser, workflow, integration, AI, and data tools available via MCP - [Prompteryx for n8n](https://www.prompteryx.ai/docs/developers/n8n): Run Prompteryx workflows and the AI browser agent from n8n, get results back by webhook, or give an n8n AI Agent the Prompteryx tools over MCP - [Prompteryx developer documentation](https://www.prompteryx.ai/docs/developers): Describe a goal in plain English. Prompteryx opens a browser, does the task, and can save the path as a reusable workflow. - [REST API Reference](https://www.prompteryx.ai/docs/developers/rest-api): Programmatically execute and manage your automation workflows via REST API - [Prompteryx TypeScript SDK](https://www.prompteryx.ai/docs/developers/sdk): The REST API with the typing done for you. Node 18+, ESM and CommonJS, browsers and edge runtimes with a global fetch. - [Webhooks](https://www.prompteryx.ai/docs/developers/webhooks): Trigger workflows from external events, and receive a signed callback when a run finishes - [Run workflows from anywhere](https://www.prompteryx.ai/docs/developers/workflows): Anything built on the Visual Studio canvas, or saved from an agent run, has an id. Run it with variables, wait for the result, put it on a schedule, or trigger it from a webhook. - [Prompteryx for Zapier](https://www.prompteryx.ai/docs/developers/zapier): Start Prompteryx workflows from any Zap and get the result back in another Zap, with Webhooks by Zapier - [AI Vision Settings](https://www.prompteryx.ai/docs/features/ai-vision): Tune the visual quality — and per-step cost — of the AI Browser Agent - [Chrome Automation Profiles](https://www.prompteryx.ai/docs/features/chrome-profiles): Run automations with persistent browser sessions - [Browser Profiles & Persistent Context](https://www.prompteryx.ai/docs/features/cloud-browser-profiles): How Cloud Browser profiles and the Persist Browser Context toggle work together — and how that compares to local Chrome profiles. - [Run automations on a cloud browser](https://www.prompteryx.ai/docs/features/cloud-browser): Run your automations on a cloud-hosted browser without needing a local Chrome installation. Execute workflows from anywhere, use residential proxies, and watch sessions in real-time. - [Workflow edit history](https://www.prompteryx.ai/docs/features/edit-history): Track changes and restore previous versions - [Workflow execution logs](https://www.prompteryx.ai/docs/features/execution-logs): Monitor and debug workflow execution in real-time - [Sharing & Collaboration](https://www.prompteryx.ai/docs/features/sharing): Share workflows with teammates and collaborate - [Video recording of automation runs](https://www.prompteryx.ai/docs/features/video-recording): Record workflow executions for review and debugging - [Install Prompteryx Desktop and the Chrome extension](https://www.prompteryx.ai/docs/getting-started/installation): Start right away on Cloud Browser, or set up Prompteryx in Chrome and Desktop app to run automations in your own Chrome - [Getting started with Prompteryx](https://www.prompteryx.ai/docs/getting-started/overview): What Prompteryx is, the ways you can automate with it, and where to go deeper. - [Prompteryx quick start](https://www.prompteryx.ai/docs/getting-started/quick-start): Your first task in the app in one minute, then your first workflow in five - [AI nodes](https://www.prompteryx.ai/docs/nodes/ai): AI-powered browser automation that sees and interacts with pages like a human. Uses computer vision to find elements when selectors fail. - [Prompteryx Browser Agent node (AI)](https://www.prompteryx.ai/docs/nodes/ai/prompteryx-browser-agent): AI-powered browser automation with computer vision - [Assertion Nodes](https://www.prompteryx.ai/docs/nodes/browser/assertions): Verify page elements, content, and states - [Blur Element node (browser action)](https://www.prompteryx.ai/docs/nodes/browser/blur): Remove focus from an element - [Check CAPTCHA Node](https://www.prompteryx.ai/docs/nodes/browser/check-captcha): Passive observer for the auto-CAPTCHA flow. Detects whether a CAPTCHA widget is on the page and waits for the background auto-solver to finish before continuing. - [Check & Uncheck Nodes](https://www.prompteryx.ai/docs/nodes/browser/check): Control checkbox and radio button elements - [Click Coordinates node (browser action)](https://www.prompteryx.ai/docs/nodes/browser/click-coordinates): Click at specific X/Y positions on the page - [Click Node](https://www.prompteryx.ai/docs/nodes/browser/click): Click on elements in a web page using CSS selectors or Playwright locators - [Cookie Nodes](https://www.prompteryx.ai/docs/nodes/browser/cookies): Manage browser cookies for authentication and session handling - [Dispatch Event node (browser action)](https://www.prompteryx.ai/docs/nodes/browser/dispatch-event): Simulate browser events like clicks, hovers, or form changes on any element - [Evaluate JavaScript Node](https://www.prompteryx.ai/docs/nodes/browser/evaluate-javascript): Execute custom JavaScript code in the browser context - [Browser Node Example Workflows](https://www.prompteryx.ai/docs/nodes/browser/examples): Pre-built tutorial workflows demonstrating every browser automation node - [Extract Data node (browser action)](https://www.prompteryx.ai/docs/nodes/browser/extract-data): Turn a list on a page into clean, structured records - [Extract Text Node](https://www.prompteryx.ai/docs/nodes/browser/extract-text): Extract text content from web page elements - [Fill Form node (browser action)](https://www.prompteryx.ai/docs/nodes/browser/fill-form): Fill many form fields in one step from a simple list - [Fill Node](https://www.prompteryx.ai/docs/nodes/browser/fill): Type text into input fields and text areas - [Focus Element node (browser action)](https://www.prompteryx.ai/docs/nodes/browser/focus): Set keyboard focus on elements for input - [Get Bounding Box node (browser action)](https://www.prompteryx.ai/docs/nodes/browser/get-bounding-box): Get the size and position of an element - [Highlight Element node (browser action)](https://www.prompteryx.ai/docs/nodes/browser/highlight-element): Visually highlight elements on the page for debugging - [Hover Node](https://www.prompteryx.ai/docs/nodes/browser/hover): Move mouse cursor over elements to trigger hover effects - [Open Page Node](https://www.prompteryx.ai/docs/nodes/browser/open-page): Navigate to a URL and load a web page - [Browser action nodes](https://www.prompteryx.ai/docs/nodes/browser): Navigate to a URL and load a web page - [Press Key Node](https://www.prompteryx.ai/docs/nodes/browser/press-key): Simulate keyboard key presses and shortcuts - [Screenshot Node](https://www.prompteryx.ai/docs/nodes/browser/screenshot): Capture screenshots of pages or specific elements - [Scroll Nodes](https://www.prompteryx.ai/docs/nodes/browser/scroll): Scroll the page or elements into view - [Select Option Node](https://www.prompteryx.ai/docs/nodes/browser/select-option): Select options from dropdown menus and select elements - [Select Text node (browser action)](https://www.prompteryx.ai/docs/nodes/browser/select-text): Select all text within an element - [Set Viewport Size node (browser action)](https://www.prompteryx.ai/docs/nodes/browser/set-viewport): Control the size of the browser viewport - [Solve CAPTCHA Node](https://www.prompteryx.ai/docs/nodes/browser/solve-captcha): Active solver. Detects the CAPTCHA on the page, calls the solver, and injects the token. Use when you want deterministic timing, or when Auto-CAPTCHA is turned off. - [Wait Nodes](https://www.prompteryx.ai/docs/nodes/browser/wait): Pause workflow execution until conditions are met - [For Each (Apply to Each) node (control flow)](https://www.prompteryx.ai/docs/nodes/control/for-each): Loop through arrays and execute actions for each item - [If Condition Node](https://www.prompteryx.ai/docs/nodes/control/if-condition): Branch your workflow based on conditions - [Control-flow nodes](https://www.prompteryx.ai/docs/nodes/control): Branch your workflow based on conditions. Compare values, check for existence, or evaluate expressions to determine which path to follow. - [Parallel Execution node (control flow)](https://www.prompteryx.ai/docs/nodes/control/parallel): Run multiple branches simultaneously for faster workflows - [Switch node (control flow)](https://www.prompteryx.ai/docs/nodes/control/switch): Send a workflow down one of several paths based on a value - [Data Store node (data)](https://www.prompteryx.ai/docs/nodes/data/data-store): Remember values between runs — dedupe items, count things, track what you've seen - [Filter node (data)](https://www.prompteryx.ai/docs/nodes/data/filter): Let only the items that match a condition continue - [Set Variable node (data)](https://www.prompteryx.ai/docs/nodes/data/set-variable): Save a value under a name so later steps can reuse it - [Connect Hub node: 3,000+ app integrations](https://www.prompteryx.ai/docs/nodes/integrations/connect-hub): Browse every app available through Prompteryx Connect Hub. Each Connect Hub action node taps into Pipedream's catalog of 3,000+ pre-built integrations. - [Integration example workflows](https://www.prompteryx.ai/docs/nodes/integrations/examples): Pre-built tutorial workflows for Gmail, Google Calendar, Google Drive, and Google Sheets - [Google Calendar node (integration)](https://www.prompteryx.ai/docs/nodes/integrations/google-calendar): Create and manage calendar events - [Google Sheets node (integration)](https://www.prompteryx.ai/docs/nodes/integrations/google-sheets): Read, write, and manage spreadsheet data - [HTTP Request node (integration)](https://www.prompteryx.ai/docs/nodes/integrations/http-request): Call any web API and use the response in your workflow - [OpenAI / ChatGPT node (integration)](https://www.prompteryx.ai/docs/nodes/integrations/openai): Generate text, images, and audio with OpenAI models - [Integration nodes](https://www.prompteryx.ai/docs/nodes/integrations): Read, write, and manage spreadsheet data — via Connect Hub - [Workflow node reference](https://www.prompteryx.ai/docs/nodes): Every building block you can drop onto the canvas, organized by category - [Workflow triggers](https://www.prompteryx.ai/docs/nodes/triggers): Start workflows manually with a button click. Perfect for testing, one-time runs, or user-initiated automations. Every workflow needs at least one trigger. - [Schedule Trigger node (trigger)](https://www.prompteryx.ai/docs/nodes/triggers/schedule): Run workflows automatically at specified times or intervals - [Webhook Trigger node (trigger)](https://www.prompteryx.ai/docs/nodes/triggers/webhook): Start workflows via HTTP requests from external services - [Documentation](https://www.prompteryx.ai/docs): Documentation for Prompteryx: the app, the AI Browser Agent, Visual Studio workflows, Prompteryx Desktop, cloud browsers, integrations and the API. - [Create browser automation workflows in Visual Studio](https://www.prompteryx.ai/docs/visual-builder/creating-workflows): Build automations in the Visual Studio - [Visual Studio workflow builder overview](https://www.prompteryx.ai/docs/visual-builder/overview): Build powerful automations visually with drag-and-drop nodes - [Visual Studio workflow builder documentation](https://www.prompteryx.ai/docs/visual-builder): Drag-and-drop automation builder featuring 70+ browser nodes and 200+ integrations - [Test and debug workflows in Visual Studio](https://www.prompteryx.ai/docs/visual-builder/testing): Debug and validate your automations before deployment --- # REST API guide for AI coding agents For coding agents (Claude Code, Cursor, ChatGPT…) helping a user drive Prompteryx. Generated from the live route code and verified against the deployed API; prefer it over /api/v1/openapi.json (partial) and SDK docs. ## What the API does Prompteryx is a browser-automation platform: AI agents that drive a real Chrome in the cloud, a visual workflow builder, and a REST API. Hand it a natural-language goal and get back the answer, a full step trace, and exact usage/cost telemetry. Base URL: https://www.prompteryx.ai ## Auth — TWO separate key families (do not mix them up) 1. Platform key "px_live_..." -> header Authorization: Bearer px_live_... Used by /api/v1/* (AI agent, workflows, executions, schedules, subscription, ...). 2. Cloud-browser key "pcb_live_..." -> header x-api-key: pcb_live_... REQUIRED for /api/v1/cloud-browser/* (sessions, fetch, search). A px_live_ key is rejected with 401 on this group. Both are created signed-in at https://www.prompteryx.ai/cloud-platform/api?tab=keys ("Platform API keys" card and "Cloud-browser keys" card). Each key is shown ONCE. ## Limits and billing - Rate limit per platform key: 60 requests/minute, 10,000/day. Responses carry X-RateLimit-Limit-Minute / -Remaining-Minute / -Limit-Day / -Remaining-Day; over the limit -> 429 RATE_LIMIT_EXCEEDED with Retry-After (seconds). - Billing unit = AI Credit (1 credit is roughly $0.01 of model cost). Runs also meter cloud-browser minutes / proxy MB / CAPTCHA solves against the account's plan. - ALWAYS set "maxCredits" on agent runs — it is a hard cost cap; the run stops there. ## Response envelope (platform /api/v1/* routes) Success: { "success": true, "data": { ... }, "meta": { "requestId", "timestamp" } } Error: { "success": false, "error": { "code", "message" } } + proper HTTP status. Common codes: MISSING_API_KEY / INVALID_API_KEY / API_KEY_EXPIRED (401), UNSUPPORTED_MODEL (400), QUOTA_EXHAUSTED (402 = out of AI credits; 429 = monthly workflow runs used up), QUOTA_EXCEEDED (Connect Hub calls: 429 + Retry-After, or 402 = not on the plan), FORBIDDEN / INSUFFICIENT_SCOPE (403), NOT_FOUND (404), RATE_LIMIT_EXCEEDED (429 + Retry-After). Do not retry QUOTA_* immediately; only RATE_LIMIT_EXCEEDED clears on its own. The /api/v1/cloud-browser/* group returns PLAIN JSON (no envelope). ## 1. Run an AI agent task — synchronous POST /api/v1/ai-browser/execute (Bearer px_live_) Body (JSON; only "instruction" required): instruction string the goal, plain English ("task" accepted as an alias) startUrl string starting page ("url" accepted as an alias). The default engines may not navigate there first: ALSO write it into the instruction ("Go to https://... then ...") model string see model list below; OMIT for the default (gemini-3.5-flash) maxSteps number default 30 maxCredits number hard AI-credit cap — always set this aiVision string screenshot-quality preset: adaptive (recommended), ultra-saver, low, saver, efficient, balanced, detailed, enhanced, precision, max-precision (cheaper presets = fewer image tokens) finalStepVision string one higher-quality look at the finished page (same slugs; "same" = off) outputSchema object JSON Schema for structured output (also accepted: output_schema) saveAsWorkflow bool save the run as a replayable zero-AI-cost workflow (+ savedWorkflowName) recordSession bool capture an MP4 of the run proxyEnabled bool residential proxy egress (+ proxyCountry, e.g. "us") agents number >1 = multi-agent swarm (see section 4) Response data: { status: "completed" | "max_steps_reached" | "error", finalAnswer: string, steps: [...], creditsUsed: number, usage: { aiCredits, tokensIn, tokensOut, costUSD, turns }, savedWorkflowId?: string, structuredOutput?: { data, error? } } A sync request can run for minutes (server allows up to ~13 min). For anything beyond a short task, use the async job mode below. ## 2. Async job mode — start / run / status / stop (for longer tasks) Same endpoint, same auth. Four calls: POST {"mode":"start", ...same fields as sync...} -> data: { jobId, sessionId, status:"running" } POST {"mode":"run","jobId":"..."} -> advances the job up to ~230s, returns status view GET /api/v1/ai-browser/execute?jobId=... -> cheap status view (does NOT advance the job) POST {"mode":"stop","jobId":"..."} -> data: { jobId, stopRequested:true, status } Drive it by looping mode:"run" until the view says terminal:true (each call does real work server-side). Status view fields: { jobId, sessionId, jobStatus: "running"|"awaiting_input"|"done"|"failed"|"stopped", status: "running"|"completed"|"error", terminal: bool, stepCount, steps, finalAnswer?, structuredOutput?, error?, errorCode?, savedWorkflowId?, creditsUsed, usage: { aiCredits, tokensIn, tokensOut, costUSD, turns } } ## 3. Models (the "model" field) Default (omit the field): gemini-3.5-flash. An id outside this set returns 400 UNSUPPORTED_MODEL with the full supported list (a few legacy gemini-* aliases pass validation but then fail at runtime — stick to this list). Verified list: Standard: gemini-3.5-flash, gemini-3.7-flash, gemini-3.6-flash, gemini-default Experimental: gemini-3-flash-preview, gemini-3.5-flash-lite, model-a, model-a1, model-b, model-j, model-k, model-k37 Anthropic/OpenAI computer use: claude-sonnet-4-6, claude-opus-4-8, gpt-5.6-terra, gpt-5.6-sol, gpt-5.5, gpt-6-astra, gpt-6.1-terra Generic vision: claude-fable-5-1-vision, claude-fable-5-vision, claude-opus-5-5-vision, claude-opus-5-vision, claude-sonnet-5-5-vision, claude-sonnet-4-6-vision, gpt-6-astra-vision, gpt-6.1-terra-vision, gpt-5.6-luna-vision, gpt-5.4-vision, gpt-4o-vision (Kimi models — kimi-k3-vision — see prompteryx.ai/legal/kimi for where their data is processed) Harness engines: modelc, model-d, model-d1, model-e, model-f, model-h, model-i Notes: model-e / model-f answer 503 MODEL_NOT_CONFIGURED unless the deployment carries their vendor keys; model-g needs deployment config (400 otherwise). For best cost/quality just omit "model"; for the benchmark-champion harness use model-h (beta). ## 4. Multi-agent swarm Add to the sync body: agents: 2..N, collaborate: true | false | "auto", maxRunCredits: number (cap for the WHOLE swarm; maxCredits caps each lane). collaborate true = agents share one work queue; false = N independent attempts; "auto" = a planner picks. Response adds: swarm: { mode, status, agents: [per-lane results], coverage } with merged top-level finalAnswer + usage summed across lanes. ## 5. Structured output Pass outputSchema (JSON Schema). The finished run is projected into it and the response carries structuredOutput: { data: | null, error?: "why it could not" }. structuredOutput is never silently absent when you supplied a schema. ## 6. Cloud-browser group (x-api-key: pcb_live_ — NOT the px_live_ key) POST /api/v1/cloud-browser/sessions body: { viewport?, recordSession?, persistContext?, profileId?, proxy?, country?, sessionTimeoutMinutes?, captureDownloads? } -> { id, connectUrl, liveURL, status, startedAt } (plain JSON, no envelope) Drive it yourself: chromium.connectOverCDP(connectUrl) from playwright-core. GET /api/v1/cloud-browser/sessions -> { sessions: [...] } (recent, newest first) GET /api/v1/cloud-browser/sessions/:id -> one session record DELETE /api/v1/cloud-browser/sessions?sessionId=ID (or DELETE /sessions/:id) -> { ok: true, proxyMB } Close sessions when done — they meter minutes. POST /api/v1/cloud-browser/fetch body: { url, format?: "text"|"markdown"|"html"|"links", waitUntil?, timeoutMs?, waitForSelector?, waitMs?, selectors?: [up to 10 CSS], screenshot?: bool, proxy?, country? } -> { url, finalUrl, title, status:"ok", content?|links?, extracted?, screenshotBase64? } One-shot: real Chromium renders the page (JS runs), you get token-efficient text. POST /api/v1/cloud-browser/search body: { query, limit? (1-25), proxy?, country? } -> { query, results: [{ title, url, snippet }] } (DuckDuckGo; no engine option) ## 7. Other verified platform endpoints (Bearer px_live_) GET /api/v1/auth/validate -> key + plan + credit balances (good first call) GET /api/v1/workflows?search=&limit=&offset= -> { workflows, pagination } POST /api/v1/workflows -> create { name, nodes:[{type,label,params}] } -> { workflowId } POST /api/v1/workflows/:id/execute -> body { variables?, options?, webhookUrl? } -> 202 { execution: { id, status:"pending", statusUrl } } GET /api/v1/executions/:id -> { execution: { status, outputs, nodeResults } } status: pending -> running -> COMPLETED|FAILED|STOPPED (compare case-insensitively; runs start within ~1 min) webhookUrl callback: POST { event:"workflow.completed"|"workflow.failed", data:{ executionId, status, outputs, ... } } signed X-Prompteryx-Signature-256: v1=HMAC-SHA256(whsec_ secret, "."); secret from the API Keys page; reject >5 min old. GET /api/v1/subscription -> plan, balances, usage GET /api/v1/schedules (+POST, PATCH/DELETE /:id) -> server-side cron schedules (min interval 5 min) GET /api/v1/profiles (+POST) -> Chrome profiles ## Quick recipes (copy-paste; replace PX_KEY / PCB_KEY) # 0) Verify the key works (free): curl -s https://www.prompteryx.ai/api/v1/auth/validate -H "Authorization: Bearer PX_KEY" # 1) One-shot agent task, cost-capped: curl -s -X POST https://www.prompteryx.ai/api/v1/ai-browser/execute \ -H "Authorization: Bearer PX_KEY" -H "Content-Type: application/json" \ -d '{"instruction":"Open https://books.toscrape.com and report the title and exact price of the first book listed.","maxSteps":8,"maxCredits":10}' # read .data.finalAnswer and .data.usage # 2) Async job for a longer task: curl -s -X POST https://www.prompteryx.ai/api/v1/ai-browser/execute \ -H "Authorization: Bearer PX_KEY" -H "Content-Type: application/json" \ -d '{"mode":"start","instruction":"Find the three cheapest science-fiction books on https://books.toscrape.com","maxSteps":25,"maxCredits":20}' # then loop: -d '{"mode":"run","jobId":""}' until .data.terminal == true # check: curl -s "https://www.prompteryx.ai/api/v1/ai-browser/execute?jobId=" -H "Authorization: Bearer PX_KEY" # abort: -d '{"mode":"stop","jobId":""}' # 3) Structured output: curl -s -X POST https://www.prompteryx.ai/api/v1/ai-browser/execute \ -H "Authorization: Bearer PX_KEY" -H "Content-Type: application/json" \ -d '{"instruction":"Open https://books.toscrape.com and read the first book listing.","maxSteps":8,"maxCredits":10,"outputSchema":{"type":"object","properties":{"title":{"type":"string"},"price":{"type":"string"}},"required":["title","price"]}}' # read .data.structuredOutput.data # 4) Swarm (three collaborating agents, whole-run cap): curl -s -X POST https://www.prompteryx.ai/api/v1/ai-browser/execute \ -H "Authorization: Bearer PX_KEY" -H "Content-Type: application/json" \ -d '{"instruction":"Collect title and price of every book in the Travel category on https://books.toscrape.com","agents":3,"collaborate":true,"maxSteps":20,"maxCredits":10,"maxRunCredits":25}' # 5) Cloud-browser session + one-shot fetch (pcb_live_ key!): curl -s -X POST https://www.prompteryx.ai/api/v1/cloud-browser/sessions \ -H "x-api-key: PCB_KEY" -H "Content-Type: application/json" -d '{}' # -> { id, connectUrl, ... } ... drive over CDP ... then: curl -s -X DELETE "https://www.prompteryx.ai/api/v1/cloud-browser/sessions?sessionId=" -H "x-api-key: PCB_KEY" curl -s -X POST https://www.prompteryx.ai/api/v1/cloud-browser/fetch \ -H "x-api-key: PCB_KEY" -H "Content-Type: application/json" \ -d '{"url":"https://books.toscrape.com","format":"text"}' ## Not yet available — do not attempt (honesty notes, verified 2026-09-03) - The npm package @prompteryx/sdk IS now published ("npm install @prompteryx/sdk") — a typed TypeScript wrapper over this same REST API. This raw HTTP guide still works fine. - /api/v1/openapi.json covers only a subset of routes and mentions a "px_test_" key environment that DOES NOT EXIST (only px_live_ keys exist). Prefer this file. - /api/v1/ai-browser/execute-stream is not SSE — do not stream; use async job mode. - No API-key access to: API-key management (/api/v1/api-keys needs a signed-in browser session), Connect Hub integrations, workflow templates, custom nodes, usage time-series. Recordings: POST /api/v1/recordings only (no GET list). - cloud-browser search has no "engine" option (always DuckDuckGo). ## Agent etiquette - Cap every run: maxCredits <= 10 for tests. Prefer maxSteps <= 10 for smoke tests. - Close cloud-browser sessions you create; stop async jobs you abandon (mode:"stop"). - Stay under 60 requests/min; poll async jobs no faster than every 5 seconds (GET), and drive them with mode:"run" calls rather than tight GET loops.