{"uid":"cap_WZWV8lApnBW-sk_SXVvFX","slug":"san-foundation-web-extract-fbb86b20","name":"SAN Foundation Web Extract","description":"Fetch and extract the readable content of a single URL. Returns the page title, publish date when known, the most relevant excerpts (optionally focused by an `objective`), and the full readable text of the page.","url":"https://gateway.sanfoundation.com/x402/v1/web-extract","method":"POST","headers":{},"bodySchema":{"type":"object","$schema":"https://json-schema.org/draft/2020-12/schema","required":["input"],"properties":{"input":{"type":"object","required":["type","method"],"properties":{"type":{"type":"string","const":"http"},"method":{"enum":["POST"],"type":"string"},"queryParams":{"type":"object","required":["url"],"properties":{"url":{"type":"string","format":"uri","description":"Absolute http(s) URL to fetch and extract."},"objective":{"type":"string","description":"Optional natural-language objective used to bias the excerpt selection."}}}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"example":{"type":"object","properties":{"url":{"type":"string"},"title":{"type":"string"},"excerpts":{"type":"array","items":{"type":"string"}},"full_content":{"type":"string"},"publish_date":{"type":"string","nullable":true}}}}}}},"responseSchema":null,"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.01","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":"$0.01/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.01","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.01","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_oSN25LMBUeerjNQ-QXtsm","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.01","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Fetches a URL and returns its readable content including title, publish date, relevant excerpts, and full text","exampleAgentPrompt":"Can you fetch the article at https://techcrunch.com/2024/05/01/openai-news and extract the readable content, focusing on the parts about funding?","exampleUseCases":[{"title":"Research article content extraction","prompt":"Grab the full readable text from this research paper page at https://arxiv.org/abs/2401.12345 — I want all the content plus any excerpts specifically about the methodology."},{"title":"Fact-check a news story","prompt":"Fetch the article at https://bbc.com/news/technology-12345678 and pull out the key excerpts about the data breach — I want the publish date too so I know how fresh this is."},{"title":"Competitive intelligence from a blog post","prompt":"Extract the readable content from https://stripe.com/blog/payments-infrastructure-2024 and focus the excerpts on anything discussing pricing or fees."}],"resultDescription":"A JSON object containing the page URL, title, publish date (when available), an array of the most relevant text excerpts (optionally focused by the provided objective), and the full readable text of the page with boilerplate and navigation stripped away.","failureModes":["URL is behind a login or paywall — returns empty or partial content","URL is invalid or unreachable — returns a fetch error","Page has no extractable readable content (e.g. pure JavaScript SPA) — full_content may be empty","Publish date not available — publish_date field returns null","Payment not processed — 402 response before content is returned"],"whenToPreferThis":"Choose this endpoint when you need clean, readable text from a specific known URL rather than a web search. It is ideal when you already have a URL and want article body text, excerpts focused on a particular topic, and metadata like publish date. Prefer it over a search endpoint when you don't need discovery — just extraction from a known source. The optional objective parameter makes it especially useful for focused research where you want relevance-ranked excerpts rather than the full dump.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-14T00:33:19.647Z","isFirstParty":false}