{"uid":"cap_aR3oUFaHN_P7ksk_k-0No","slug":"orbit-web-tools-web-page-to-markdown-633500bb","name":"orbit Web Tools: Web Page to Markdown","description":"Web utilities for agents, computed live at call time: URL health/redirect/x402 check, web page to Markdown (robots.txt honoured), DNS lookup with SPF/DMARC, email address validation (MX, disposable, role, typo), HTTP security-header audit and AI-agent readiness audit (llms.txt, AI crawler rules, x402, MCP, OpenAPI). $0.001 per call. By orbit-builder.","url":"https://orbit-web.orbit-builder.workers.dev/v1/read?utm_source=zero.xyz","method":"GET","headers":{},"bodySchema":{"type":"object","$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":"public http(s) URL"},"max_chars":{"type":"integer","description":"truncate markdown (500-50000, default 20000)"}}}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"example":{"type":"object"}}}}},"responseSchema":{"type":"json","example":{"url":"https://en.wikipedia.org/wiki/HTTP_402","links":[{"url":"https://en.wikipedia.org/wiki/HTTP","text":"HTTP"}],"title":"HTTP 402 - Wikipedia","words":820,"status":200,"markdown":"# HTTP 402\n\n…","truncated":false,"description":null}},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.001","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":"$0.001/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.001","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.001","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_CEzr80xYBFA0EAKMD8Fqm","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Fetches a public web page and returns LLM-ready Markdown with title, meta, main content, and links — scripts/nav/footer stripped","exampleAgentPrompt":"Can you fetch the main content of https://en.wikipedia.org/wiki/HTTP_402 and give it to me as clean markdown, keeping headings and links but stripping the nav and footer? Use up to 20000 characters.","exampleUseCases":[{"title":"Feed webpage to LLM pipeline","prompt":"Grab the content of https://openai.com/research/gpt-4 as clean markdown so I can pass it into my summarization pipeline — strip all the nav and footer noise, keep headings and links, and limit it to 15000 characters."},{"title":"Research competitor landing page","prompt":"Fetch https://www.anthropic.com and convert it to readable markdown — I want the title, meta description, and the main body text so I can analyse their messaging, up to 20000 chars."},{"title":"Extract article for offline reading","prompt":"Pull the article at https://www.wired.com/story/the-ai-that-writes-the-news and return it as LLM-ready markdown with the first 50 links included, capped at 10000 characters."}],"resultDescription":"A JSON object containing: the final URL, HTTP status, page title, meta description, canonical URL, language, full Markdown of main content (scripts/nav/footer removed, headings/lists/links preserved), an array of up to 50 absolute links (each with url and text), word count, and a truncated boolean indicating whether max_chars was hit.","failureModes":["URL disallowed by robots.txt → 403 (not charged)","Non-HTML content type (e.g. PDF, image) → 415 Unsupported Media Type","URL unreachable or invalid → connection/HTTP error","max_chars outside 500-50000 range → validation error","Page requires JavaScript rendering → content may be empty or minimal (no JS rendering supported)","Private/intranet URLs → fetch failure"],"whenToPreferThis":"Choose this endpoint when you need clean, LLM-ready Markdown from a public webpage without JavaScript rendering — ideal for feeding static article or documentation pages into an LLM context window. It respects robots.txt automatically and strips boilerplate (nav, scripts, footer), making it more reliable than raw HTML fetching. At $0.001 USDC per call it's cost-effective for single-page reads. Prefer alternatives if you need JS-rendered SPAs, authenticated pages, or structured data extraction beyond Markdown.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-30T06:41:21.172Z","isFirstParty":false,"canonicalSlug":"orbit-web-tools-web-page-to-markdown-633500bb"}