{"uid":"cap_3JBkswP1EPvV0AaLwU79m","slug":"freshproof-web-reader-url-to-clean-markdown-990963b9","name":"FreshProof Web Reader — URL to Clean Markdown","description":"Retrieve a public webpage as clean deterministic Markdown with source metadata, resolved links, retrieval time, and a content hash for AI agents.","url":"https://freshproof-api-mainnet.up.railway.app/v1/read","method":"POST","headers":{},"bodySchema":{"type":"object","properties":{"url":{"type":"string","pattern":"^https?://","maxLength":4096},"options":{"type":"object","default":{"includeLinks":true,"maxCharacters":50000,"includeMetadata":true},"required":["includeLinks","includeMetadata","maxCharacters"],"properties":{"includeLinks":{"type":"boolean","default":true},"maxCharacters":{"type":"integer","default":50000,"maximum":100000,"minimum":1000},"includeMetadata":{"type":"boolean","default":true}},"additionalProperties":false}}},"responseSchema":{"type":"json","example":{"data":{"links":[{"url":"https://www.iana.org/help/example-domains","text":"More information"}],"title":"Example Domain","source":{"finalUrl":"https://example.com/","statusCode":200,"contentType":"text/html","retrievedAt":"2026-08-03T08:00:00.000Z","requestedUrl":"https://example.com/","redirectChain":[]},"markdown":"# Example Domain\n\nThis domain is for use in illustrative examples.","metadata":{"language":"en","description":"Example Domain"},"warnings":[],"truncated":false,"contentHash":"cccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccc","characterCount":66},"success":true}},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.002","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":"$0.002/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.002","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.002","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_Upat2F95Vj0960YooAqWQ","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.002","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Fetches a public webpage and returns clean, deterministic Markdown with resolved links, retrieval metadata, and a content hash for AI agent use.","exampleAgentPrompt":"Fetch the page at https://en.wikipedia.org/wiki/Transformer_(deep_learning_architecture) and give me clean markdown with all links included and up to 50000 characters, plus the content hash so I can check if it changes later.","exampleUseCases":[{"title":"LLM context window loading","prompt":"Grab https://docs.stripe.com/api/charges as clean markdown — include the links and metadata — so I can feed it directly into my prompt as up-to-date reference material."},{"title":"Content fingerprinting for change detection","prompt":"Fetch https://www.apple.com/newsroom/ as markdown and give me the content hash, so I can compare it next week and see if anything changed on the page."},{"title":"Readable news article extraction","prompt":"Pull https://www.reuters.com/technology/artificial-intelligence/ into clean readable markdown, keep the links, and limit it to 30000 characters so it fits in my context window."}],"resultDescription":"A structured response containing the page rendered as clean deterministic Markdown, resolved hyperlinks, source URL metadata, retrieval timestamp, and a content hash (fingerprint) that can be used to detect future changes or verify the snapshot.","failureModes":["URL is not publicly accessible or behind authentication — returns error","URL exceeds 4096 characters — rejected by schema validation","maxCharacters set below minimum of 1000 — rejected by schema validation","Page returns non-HTML or binary content — may fail or return empty markdown","Network timeout or upstream server unavailable — retrieval error","URL uses non-http/https scheme — rejected by pattern validation"],"whenToPreferThis":"Choose this endpoint when you need a clean, deterministic text rendering of a public webpage for feeding into an LLM, storing a verifiable snapshot, or checking content later against a hash. It is distinct from raw HTML scrapers because it produces normalized Markdown with a content fingerprint and resolved links — ideal for agents that need reproducible, comparable web content rather than raw DOM data. Prefer it over PDF converters (use the sibling PDF endpoint for PDFs) and over fact-extraction endpoints when you need the full page content rather than structured claims.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-15T00:30:42.530Z","isFirstParty":false}