{"uid":"cap_g_wVC02ODd2F14n9I_Gy9","slug":"web-extract-5e95d275","name":"Web Extract","description":"Any URL to clean, LLM-ready markdown and structured metadata.","url":"https://agentpay-extract.agentpay-apis.workers.dev/extract/v1/page?utm_source=zero.xyz","method":"GET","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":["GET","HEAD","DELETE"],"type":"string"},"queryParams":{"type":"object","required":["url"],"properties":{"url":{"type":"string","description":"http(s) URL to read"},"maxChars":{"type":"string","description":"Max markdown characters (1000-200000, default 50000)"}}}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"example":{"type":"object"}}}}},"responseSchema":{"type":"json"},"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_8gUAs_TaVWV4vMLNSIZ1e","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 any public URL and returns clean, LLM-ready markdown plus structured page metadata.","exampleAgentPrompt":"Can you fetch the page at https://en.wikipedia.org/wiki/Artificial_intelligence and convert it to clean markdown so I can read and analyze the content?","exampleUseCases":[{"title":"Research article summarization pipeline","prompt":"Go to https://www.nytimes.com/2024/05/01/technology/ai-regulation.html, extract the full article text as clean markdown, and then summarize the key points for me."},{"title":"Competitor pricing page ingestion","prompt":"Fetch the page at https://www.competitor.com/pricing and convert it to clean markdown — I want to see all the plan tiers and prices laid out clearly."},{"title":"Documentation page extraction for LLM context","prompt":"Pull the content from https://docs.stripe.com/api/charges and turn it into clean markdown so I can include it as context when answering developer questions."}],"resultDescription":"Returns a JSON object containing the page content converted to clean markdown (up to the specified character limit, default 50,000), along with structured metadata such as page title, description, and other extractable properties. The markdown is stripped of navigation, ads, and HTML noise so it can be fed directly into an LLM context window.","failureModes":["URL is unreachable or returns a non-200 status — extraction fails with an error","Page is behind a login wall or CAPTCHA — returns empty or partial content","JavaScript-heavy SPA pages may return incomplete content if JS is required to render","maxChars set below 1000 or above 200000 — rejected as out-of-range","Invalid or malformed URL — returns validation error","Very large pages may be truncated at the maxChars limit"],"whenToPreferThis":"Choose this endpoint when you need to convert any publicly accessible web page into clean, LLM-ready markdown in a single call — especially useful for reading articles, documentation pages, or product pages as part of an AI pipeline. Prefer this over raw HTTP fetching when you need noise-free text (no HTML tags, nav bars, or ads) and structured metadata returned together. It is ideal for agentic workflows where context from live web pages needs to be injected into LLM prompts without manual preprocessing.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-27T12:37:51.434Z","isFirstParty":false,"canonicalSlug":"web-extract-5e95d275"}