{"uid":"cap_CMuytbIaObvFvqsRPo84O","slug":"html-to-markdown-converter-ee9cf299","name":"HTML to Markdown Converter","description":"Convert raw HTML already held by an agent into deterministic, clean, LLM-ready Markdown without fetching the source URL. Returns the title, byline, excerpt, Markdown, and character count.","url":"https://manyfish-seller.redcliff-d7368db1.westus2.azurecontainerapps.io/api/v1/content/html-to-markdown","method":"POST","headers":{},"bodySchema":{"type":"object","properties":{"html":{"type":"string","pattern":".*\\S.*","minLength":1},"sourceUrl":{"type":"string","pattern":"^[hH][tT][tT][pP][sS]?://[^\\s]+$","maxLength":2048}}},"responseSchema":{"type":"json","example":{"title":"Example","byline":null,"excerpt":"Article text.","markdown":"# Example\n\nArticle text.","markdownCharacters":24}},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.001","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":"$0.001/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.001","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.001","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_TDbrjKebF5X4o-uYyrxbe","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Extracts readable content from supplied HTML and converts it into compact Markdown without fetching any external URL.","exampleAgentPrompt":"I have this raw HTML from a news article — can you extract just the readable content and convert it into clean, compact Markdown for me? Here's the HTML: <html><body><h1>Breaking News</h1><p>Something happened today...</p></body></html>","exampleUseCases":[{"title":"Readable article from scraped HTML","prompt":"I scraped this HTML from a blog post and it's full of nav bars and ads — can you pull out just the readable content and give it back to me as clean Markdown? Here's the HTML: <html><body><nav>...</nav><article><h1>My Post</h1><p>Hello world.</p></article><footer>...</footer></body></html>"},{"title":"Pipeline ingestion of web content","prompt":"I'm building a content pipeline — take this raw HTML page I collected and convert it into compact Markdown so I can store it in my knowledge base. HTML: <html><body><h2>Product Overview</h2><ul><li>Feature A</li><li>Feature B</li></ul></body></html>"},{"title":"Chatbot context from HTML emails","prompt":"I've got the HTML body of an email newsletter and I need it as Markdown so my chatbot can read it cleanly — can you convert this HTML for me? <html><body><p>Welcome to our monthly update!</p><p>This month we launched...</p></body></html>"}],"resultDescription":"The agent receives the HTML content converted into compact, readable Markdown text, with readable structure preserved (headings, lists, links, tables) and HTML boilerplate or noise removed, without any external URL being fetched.","failureModes":["Empty or whitespace-only HTML input returns a validation error","Malformed HTML may result in partial or degraded Markdown output","Very large HTML payloads may exceed processing limits or time out","Invalid sourceUrl format returns a schema validation error","HTML with no readable text content may return an empty or minimal Markdown response"],"whenToPreferThis":"Use this endpoint when you already have raw HTML in memory and need it converted to Markdown without triggering an outbound HTTP fetch. It is ideal for pipelines that scrape HTML separately, process email HTML bodies, or handle HTML from APIs, and want clean Markdown output for LLM context windows, knowledge bases, or downstream text processing. Prefer this over PDF-to-Markdown or image-to-Markdown siblings when your input is HTML specifically.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-14T12:31:25.274Z","isFirstParty":false}