{"uid":"cap_wl2Y2zCoDxesxau03GqRT","slug":"agentreader-html-to-markdown-converter-74d1b4be","name":"AgentReader HTML to Markdown Converter","description":"Convert raw HTML you already have into clean markdown. Send JSON {\"html\": \"...\"} and get back markdown with scripts, styles and boilerplate stripped. Cheaper than /read when the agent has already fetched the page.","url":"https://agent-reader.agent-reader.workers.dev/clean","method":"POST","headers":{},"bodySchema":{"type":"object","properties":{"html":{"type":"string","description":"Raw HTML string to convert to markdown"}}},"responseSchema":null,"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.005","displayCostAsset":"USDC","priceDynamic":false,"priceHint":null,"priceStatus":"priced","priceSource":"probe","requiresHandshake":false,"reviewCount":0,"rating":{"score":"0.00","successRate":"0.00","reviews":0,"stars":null,"state":"unrated"},"availabilityStatus":"unknown","priceObserved":null,"sessionDeposit":null,"pricing":{"kind":"static","summary":"$0.003/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.003","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.003","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_-nCZfWKxJJFQHa9sCJoet","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.003","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Converts raw HTML strings into clean, LLM-ready markdown by stripping scripts, styles, and boilerplate","exampleAgentPrompt":"I already fetched this page's HTML — can you clean it up into markdown by stripping all the scripts, styles, and nav boilerplate so I can feed it to the model?","exampleUseCases":[{"title":"LLM context preparation pipeline","prompt":"I've got the raw HTML from a news article I scraped — strip out all the scripts, ads, and navigation clutter and give me clean markdown so I can pass it directly to the LLM."},{"title":"Batch pipeline cost reduction","prompt":"My agent already has the HTML for these product pages it fetched earlier. Convert them to clean markdown without re-fetching — I want to keep costs down by not hitting /read again."},{"title":"Content extraction from cached pages","prompt":"Here's the raw HTML I pulled from a cached snapshot of a blog post. Can you convert it to clean markdown with all the junk stripped out so I can summarize it?"}],"resultDescription":"Clean markdown text derived from the submitted HTML, with JavaScript, CSS, navigation, ads, and other boilerplate removed — leaving only the human-readable content in a format suitable for LLM ingestion.","failureModes":["Malformed or empty HTML string returns an error or empty markdown","Extremely large HTML payloads may be rejected or truncated","HTML with unusual encoding may produce garbled markdown","Pages that are entirely JavaScript-rendered with no static content yield minimal markdown"],"whenToPreferThis":"Choose this endpoint when your agent has already fetched the raw HTML of a page and you want to convert it to markdown without making a second network request to retrieve the URL. It is cheaper than the /read endpoint (which fetches and cleans from a URL) and avoids redundant HTTP calls. Ideal for pipelines where HTML is already in hand from a prior crawl, cache, or scrape step.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-14T06:30:53.615Z","isFirstParty":false}