{"uid":"cap__sIe83DHPSlj8E5DWCEkz","slug":"agentread-structured-web-extraction-api-94789589","name":"AgentRead Structured Web Extraction API","description":"Clean web content for AI agents, paid per request via x402. Paid endpoints return HTTP 402 with x402 v2 payment requirements; retry with a `PAYMENT-SIGNATURE` header produced by an x402 client (e.g. @x402/fetch). Only successful extractions are settled.","url":"https://agentread.omar-cv.workers.dev/v1/extract/structured?utm_source=zero.xyz","method":"POST","headers":{},"bodySchema":{"type":"object","properties":{"url":{"type":"string","maxLength":2048,"minLength":1,"description":"Absolute public http:// or https:// URL. Default ports only; no credentials; no IP literals."},"includeLinks":{"type":"boolean","description":"Keep hyperlinks and images in the Markdown (default true). When false, link text is kept as plain text."},"maxCharacters":{"type":"integer","maximum":100000,"minimum":100,"description":"Maximum Markdown characters to return (default 20000, max 100000)."}}},"responseSchema":{"type":"json","example":{"links":[],"finalUrl":"https://example.com/","headings":[],"markdown":"This domain is for use in documentation examples without needing permission. This is not a service; avoid relying on it for testing and monitoring purposes.","metadata":{"title":"Example Domain","byline":null,"language":"en","siteName":null,"description":null,"canonicalUrl":null,"publishedTime":null},"operation":"extract_url_structured","truncated":false,"extraction":{"words":25,"method":"lite","charset":"utf-8","warnings":[],"redirects":0,"characters":156,"durationMs":140,"statusCode":200,"contentType":"text/html","bytesFetched":577,"totalCharacters":156},"requestedUrl":"https://example.com/","schemaVersion":"1.0","linksTruncated":false,"headingsTruncated":false}},"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":"$0.005/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.005","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.005","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_mxYtaHQOcEnh24GgmtyT5","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.005","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Fetches a public URL and returns clean, structured Markdown content with metadata, headings, and links — optimized for AI agent consumption, billed per successful extraction via x402.","exampleAgentPrompt":"Can you fetch the content from https://techcrunch.com/2024/01/15/openai-announcement/ and give me the clean readable text — include the links and cap it at 50000 characters?","exampleUseCases":[{"title":"Article summarization pipeline","prompt":"Pull the article at https://www.wired.com/story/ai-regulation-2025/ and extract the clean text with headings so I can summarize it — keep the links in and allow up to 30000 characters."},{"title":"Competitor pricing page analysis","prompt":"Fetch the content from https://www.competitor.com/pricing and extract the structured Markdown so I can see what plans they're offering — strip out the links and give me up to 20000 characters."},{"title":"Research paper content ingestion","prompt":"Extract the readable content from https://arxiv.org/abs/2401.12345 so I can analyze it — include all links and headings and let it go up to 100000 characters."}],"resultDescription":"Returns a JSON object containing: cleaned Markdown body text, page metadata (title, byline, language, site name, description, canonical URL, published time), a list of headings, a list of hyperlinks, the final resolved URL after redirects, and extraction stats (word count, character count, duration, HTTP status, content type, bytes fetched, method used, warnings). Indicates whether content was truncated.","failureModes":["Non-public or credential-protected URLs return an error or empty extraction","URLs with IP literals or non-default ports are rejected by schema validation","Pages with heavy JavaScript rendering may return incomplete content via the 'lite' extraction method","Very large pages truncated at maxCharacters limit — truncated flag set to true","Network timeouts or unreachable hosts result in failed extraction (no charge)","402 payment required if x402 PAYMENT-SIGNATURE header is missing or invalid"],"whenToPreferThis":"Choose this endpoint when an AI agent needs clean, LLM-ready Markdown from an arbitrary public URL without writing a custom scraper. It is ideal for single-URL extraction tasks where structured metadata (title, headings, links) is needed alongside body text. Prefer this over raw HTTP fetch when HTML cleaning, Markdown conversion, and per-field metadata are required. The x402 micropayment model means you only pay for successful extractions, making it cost-efficient for intermittent use without subscriptions.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-11-03T06:30:41.059Z","isFirstParty":false,"canonicalSlug":"agentread-structured-web-extraction-api-94789589"}