> For the complete documentation index, see [llms.txt](https://doc.thordata.com/doc/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://doc.thordata.com/doc/faq/product-problem/other/can-pages-be-returned-as-markdown-for-llms.md).

# Can pages be returned as Markdown for LLMs?

Yes. Thordata's scraping browser (compatible with Playwright, Puppeteer, and Selenium) can output collected pages as Markdown for AI workflows, and paired with [MCP and the SERP API](https://www.thordata.com/products/serp-api/mcp-server?op=cianna\&from=mcp) it forms a discover → markdown → model chain. That cuts token spend and parsing effort; it is not the right choice when you must preserve original HTML styling or align structured fields, where JSON output fits better. Decodo also markets Markdown output — Thordata's difference is search and scraping inside one account.
