
Deploy Crawl4AI
Web crawler API that turns pages into LLM-ready Markdown, with MCP
Just deployed
/data
Deploy and Host Crawl4AI on Railway
Crawl4AI is an open-source (Apache-2.0) web crawler and scraper built for LLMs, AI agents and data pipelines. It drives a headless Chromium, renders JavaScript-heavy pages and returns clean Markdown, structured JSON, screenshots or PDFs through a REST API, a web playground and an MCP endpoint.
About Hosting Crawl4AI
This template runs the official Crawl4AI 0.9.5 Docker image, pinned by digest and built from a small public GitHub repo, so Railway offers you an update when a new version is merged there. The container holds the API server, a headless Chromium and an internal Redis queue. Crawl4AI refuses to listen publicly without an API token, so the template generates a 64-character CRAWL4AI_API_TOKEN and every request must send it as a Bearer token. A volume at /data keeps the crawl cache and the job store across redeploys. Railway checks /health before switching traffic. Plan for at least 2 GB of memory, because each crawl runs a browser.
Common Use Cases
- Turn web pages into LLM-ready Markdown for RAG pipelines and AI agents
- Extract structured data with CSS or XPath schemas, or with an LLM of your choice
- Give AI assistants a crawling tool over MCP (
/mcp/sse) or from n8n, LangChain and similar tools
Dependencies for Crawl4AI Hosting
- A Railway service built from
aalfath/crawl4ai-railway-template(officialunclecode/crawl4aiimage with Chromium and Redis inside) - A Railway volume mounted at
/data
Deployment Dependencies
- Crawl4AI repository: https://github.com/unclecode/crawl4ai
- Crawl4AI 0.9.5 release: https://github.com/unclecode/crawl4ai/releases/tag/v0.9.5
- Self-hosting docs: https://docs.crawl4ai.com/core/self-hosting/
- Template repository: https://github.com/aalfath/crawl4ai-railway-template
Implementation Details
Find your token in the service's Variables tab, then call the API:
curl -X POST https://YOUR-DOMAIN/crawl \
-H "Authorization: Bearer YOUR-CRAWL4AI-API-TOKEN" \
-H "Content-Type: application/json" \
-d '{"urls": ["https://example.com"]}'
The playground is at /playground and the monitor dashboard at /dashboard; both use the same token. For LLM extraction, add LLM_PROVIDER (for example openai/gpt-4o-mini) and that provider's key (OPENAI_API_KEY, ANTHROPIC_API_KEY, GEMINI_API_TOKEN, ...) to the service's variables. Hooks and /execute_js stay off unless you set CRAWL4AI_HOOKS_ENABLED=true or CRAWL4AI_EXECUTE_JS_ENABLED=true; both run caller-supplied code, so enable them only if you trust every token holder.
Why Deploy Crawl4AI on Railway?
Railway is a singular platform to deploy your infrastructure stack. Railway will host your infrastructure so you don't have to deal with configuration, while allowing you to vertically and horizontally scale it.
By deploying Crawl4AI on Railway, you are one step closer to supporting a complete full-stack application with minimal burden. Host your servers, databases, AI agents, and more on Railway.
Template Content

