Website to Markdown – keyless HTML→clean Markdown for RAG, pay-per-use

A community-maintained Apify actor called Website to Markdown converts web pages into clean, LLM/RAG-ready Markdown at $0.10 per 5 pages converted (about $0.02 per page), with no OpenAI key or per-token cost. The tool strips navigation, ads and boilerplate, supports same-domain crawling to a default maxPages of 50 (hard cap 200) and optional overlap-aware chunking at a default 512-token chunk size with 50-token overlap for vector databases, and is available over MCP as a pay-per-use alternative to Firecrawl and Jina Reader. Developer Fredrik Hansson's actor had 2 total users and 1 monthly active user at publication.

Website to Markdown — Clean Markdown for LLMs & RAG Pricing from $44.00 / 1,000 pages converted per 5 s Go to Apify Store https://apify.com/store Website to Markdown — Clean Markdown for LLMs & RAG Turn any web page into clean, LLM/RAG-ready Markdown. Strips nav/ads/boilerplate, optional same-domain crawl and overlap-aware chunking for vector databases. Keyless and fast. Pricing from $44.00 / 1,000 pages converted per 5 s Rating 0.0 0 Developer Maintained by Community https://apify.com/noniner Fredrik Hansson Actor stats 0 Bookmarked 2 Total users 1 Monthly active users 36 minutes ago Last modified Categories Share Turn any web page into clean, LLM/RAG-ready Markdown . Point it at one URL or a whole docs site: it strips navigation, ads and boilerplate, keeps the main content, and returns tidy Markdown — optionally split into overlap-aware chunks ready to embed into a vector database. Deterministic and keyless — no OpenAI key, no per-token cost. Fast, cheap, and built for people and AI agents available over MCP . A clean Firecrawl https://www.firecrawl.dev/ / Jina Reader https://jina.ai/reader/ alternative on Apify: pay-per-use, no subscription. What it does - Boilerplate removal — drops nav , header , footer , aside , forms, scripts, ads and common menu/sidebar classes, then picks the richest <main / <article container. - Clean Markdown — turndown https://github.com/mixmark-io/turndown + GFM, so tables, code blocks and lists survive intact ATX headings, fenced code . - Same-domain crawl — set a crawl depth to walk a whole docs site; filter with include/exclude URL globs. - RAG chunking — optional: split each page into ~N-token chunks with overlap so vector-DB retrieval keeps context across chunk edges. - Token + word counts — every record carries a rough token estimate for budgeting. Input | Field | Type | Default | Notes | |---|---|---|---| | startUrls | string | — | Seed URLs required . | | maxPages | integer | 50 | Hard cap 200. One charge per page converted. | | maxDepth | integer | 0 | Same-domain crawl depth. 0 = only the seeds. | | maxConcurrency | integer | 5 | Pages fetched/converted in parallel. | | chunkForRag | boolean | false | Emit chunk records instead of page records. | | chunkSize | integer | 512 | Target chunk size in tokens. | | chunkOverlap | integer | 50 | Token overlap between chunks < chunkSize . | | includeUrlGlobs | string | — | Only follow matching links when crawling. | | excludeUrlGlobs | string | — | Never follow matching links wins over include . | Output One dataset record per page or per chunk when chunkForRag is on : { "url": "https://quotes.toscrape.com/", "title": "Quotes to Scrape", "markdown": " Quotes to Scrape\n\n \"The world as we have created it...\"\n...", "wordCount": 412, "tokenEstimate": 540} Chunk records add chunkIndex and drop wordCount . Example — messy page in, clean Markdown out A typical article arrives wrapped in nav bars, cookie banners, share widgets and footers. You get only the content: In: one blog/docs URL full HTML, ~180 KB of markup Out: RAG best practices Retrieval-augmented generation works best when your chunks keep their context. 1. Clean your sourceStrip boilerplate before you embed — nav links and cookie banners poison retrieval. Flip on chunkForRag and the same page comes back as embed-ready chunks with overlap and a token estimate per chunk — drop them straight into a vector DB. Pricing Pay-per-event: $0.10 per 5 pages converted ≈ $0.02 / page . No subscription, no token fees — you only pay for pages actually converted. Part of the No Niner no-code data toolkit One of 90+ no-code data tools — many chain directly into each other. Browse them all