{"uid":"cap_UslQqfOtoyY6bt32icBUm","slug":"article-document-extraction-to-markdown-68248892","name":"Article & Document Extraction to Markdown","description":"Machine-payable x402 utilities for hashing, Base64, UUID generation, unit and timezone conversion, realtime crypto market data, webpage/document extraction, URL-to-Markdown, metadata, RAG ingestion and deterministic website change detection.","url":"https://x402-gateway-production-1f21.up.railway.app/article?utm_source=zero.xyz","method":"POST","headers":{},"bodySchema":{"type":"object","$schema":"https://json-schema.org/draft/2020-12/schema","required":["input"],"properties":{"input":{"type":"object","required":["type","method","bodyType","body"],"properties":{"body":{"type":"object","required":["url"],"properties":{"url":{"type":"string","format":"uri","description":"Public http(s) article or document URL."},"max_text_chars":{"type":"integer","maximum":150000,"minimum":1000},"timeout_seconds":{"type":"integer","maximum":60,"minimum":5}},"additionalProperties":false},"type":{"type":"string","const":"http"},"method":{"enum":["POST"],"type":"string"},"bodyType":{"enum":["json","form-data","text"],"type":"string"}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"example":{"type":"object"}}}}},"responseSchema":{"type":"json","example":{"status":"ready"}},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.002","displayCostAsset":"USDC","priceDynamic":false,"priceHint":null,"priceStatus":"priced","priceSource":"registry","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_9oqVHtfm-dk6K3pGl2ncX","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.002","costPer":"request","priority":0,"asset":null,"unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Fetches a public article or document URL and extracts its main text content, converting it to a clean readable format suitable for RAG ingestion and AI processing.","exampleAgentPrompt":"Pull the main article text from https://www.bbc.com/news/technology-article-12345 — limit it to 50000 characters — so I can feed it into my knowledge base.","exampleUseCases":[{"title":"RAG pipeline document ingestion","prompt":"Fetch the full text from this research paper URL https://arxiv.org/abs/2301.00001 and extract up to 100000 characters so I can chunk it and load it into my vector store."},{"title":"News article summarization prep","prompt":"Extract the readable article body from https://techcrunch.com/2024/05/01/some-article so I can summarize it — cap the text at 20000 characters."},{"title":"Policy document content extraction","prompt":"Grab the text content from https://example.com/terms-of-service with a 30-second timeout so I can analyze what changed in their latest terms."}],"resultDescription":"Returns a JSON object with status 'ready' and the extracted main text content of the article or document at the given URL, stripped of HTML boilerplate, ads, and navigation elements, suitable for downstream AI processing or RAG ingestion.","failureModes":["URL is not publicly accessible or requires authentication — returns error","Timeout exceeded if page loads slowly beyond timeout_seconds — returns timeout error","URL does not point to an article or parseable document — may return empty or minimal content","max_text_chars below minimum (1000) or above maximum (150000) — returns validation error","Paywalled content behind login walls cannot be extracted — returns limited or no content"],"whenToPreferThis":"Choose this endpoint when you need to extract clean readable text from a specific public article or document URL for AI processing, summarization, or RAG ingestion, especially when you want machine-payable per-call micropayment pricing via x402 without subscription overhead. Prefer this over full-site crawlers when you only need the body text of one specific URL.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-12T18:41:09.427Z","isFirstParty":false,"canonicalSlug":"article-document-extraction-to-markdown-68248892"}