{"uid":"cap_KPP6ZhQ4y4w-Imhf1ogTR","slug":"web-page-to-markdown-fetcher-f9b03c48","name":"Web Page to Markdown Fetcher","description":"Read any public web page as clean Markdown for an LLM: main content without menus, scripts or ads, plus title, description, language and links. For agents without a browser.","url":"https://api.agent-data.workers.dev/api/v1/fetch?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"],"type":"string"},"queryParams":{"type":"object","required":["url"],"properties":{"url":{"type":"string","description":"http(s) URL"},"max_chars":{"type":"integer","maximum":100000,"minimum":500}}}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"example":{"type":"object"}}}}},"responseSchema":{"type":"json","example":{"url":"https://en.wikipedia.org/wiki/Bitcoin","links":["https://en.wikipedia.org/wiki/Satoshi_Nakamoto"],"title":"Bitcoin - Wikipedia","words":9120,"markdown":"# Bitcoin\n\nBitcoin is the first decentralized cryptocurrency...","truncated":true}},"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_eocpZ-coXhwLtznz12yEN","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 web page and returns its main content as clean Markdown, stripped of ads, menus, and scripts, along with metadata like title, description, language, and links.","exampleAgentPrompt":"Can you fetch the content of https://en.wikipedia.org/wiki/Ethereum and give me the main text as clean markdown, up to 10000 characters?","exampleUseCases":[{"title":"Research article from URL","prompt":"Grab the full readable content from https://www.bbc.com/news/technology-12345678 and summarize what it says — I want the main article text, not any ads or nav menus."},{"title":"Fact-check a claim from a webpage","prompt":"Fetch the page at https://docs.uniswap.org/concepts/how-uniswap-works and pull out the main content so I can verify what it says about liquidity pools."},{"title":"Monitor competitor blog post","prompt":"Get the text from https://openai.com/blog/gpt-4-technical-report as clean markdown so I can read through the key points without opening a browser."}],"resultDescription":"A JSON object containing the page's main body as Markdown text (ads, navigation, and scripts removed), along with the page title, description, detected language, an array of links found on the page, the word count, and a boolean indicating whether the content was truncated due to max_chars.","failureModes":["URL is not publicly accessible (private, paywalled, or requires login) — returns an error or empty content","URL points to a non-HTML resource (e.g. image or binary file) — may fail or return garbled content","Page uses heavy JavaScript rendering that cannot be executed server-side — returns incomplete or missing content","max_chars set too low, causing heavy truncation of important content","Invalid or malformed URL — returns a validation error","Rate limiting or network timeout for slow-loading pages"],"whenToPreferThis":"Use this endpoint when an AI agent needs to read the textual content of any public web page without spinning up a browser. It is ideal for LLM pipelines that need clean, structured Markdown input from arbitrary URLs — especially when pairing with a web search endpoint that returns URLs but not page bodies. Prefer this over raw HTML fetchers when downstream processing requires readable prose rather than DOM structure.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-11-14T18:35:11.748Z","isFirstParty":false,"canonicalSlug":"web-page-to-markdown-fetcher-f9b03c48"}