{"uid":"cap_DcD90Yjxe0BI5m86gXoAM","slug":"metalift-web-scrape-url-to-llm-ready-markdown-e4ec4130","name":"Metalift Web Scrape – URL to LLM-Ready Markdown","description":"","url":"https://app.metalift.ai/v1/scrape?utm_source=zero.xyz","method":"POST","headers":{},"bodySchema":{"type":"object","$schema":"https://json-schema.org/draft/2020-12/schema","required":["input"],"properties":{"input":{"type":"object","required":["type","method","bodyType","body"],"properties":{"body":{"type":"object","required":["url"],"properties":{"url":{"type":"string","format":"uri","description":"Absolute URL to scrape (public http/https)"},"render":{"type":"string","description":"static or dynamic (Playwright JS render). Not a strategy name."},"formats":{"type":"array","items":{"type":"string"},"description":"Output formats; typically [\"markdown\"]. Add \"json\" for structured extraction (+credits)."},"strategy":{"type":"string","description":"Execution profile: auto | article | spa | cloudflare | retail | authenticated | listing | jsonld | download | raw. Use auto (default) — amazon/ebay/walmart map to retail. Do not send strategy=static (that is a render mode)."},"response_detail":{"type":"string","description":"compact | standard | full (response size; default compact for agents)"}}},"type":{"type":"string","const":"http"},"method":{"enum":["POST","PUT","PATCH"],"type":"string"},"bodyType":{"enum":["json","form-data","text"],"type":"string"}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"example":{"type":"object"}}}}},"responseSchema":null,"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.002","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":"down","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_RvPrkhniesumlFHCKIu4i","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.005","costPer":"request","priority":0,"asset":null,"unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Fetches any URL and returns clean, LLM-ready markdown, handling Cloudflare/WAF blocks, JavaScript-rendered SPAs, and bot detection via residential proxies when needed.","exampleAgentPrompt":"Can you scrape the product page at https://www.example-retailer.com/products/widget-pro and give me the content as clean markdown — it's a JavaScript-rendered page so a normal fetch probably won't work?","exampleUseCases":[{"title":"Scraping Cloudflare-protected news article","prompt":"Fetch the full article text from https://www.ft.com/content/some-article — it's behind Cloudflare so a plain HTTP request won't work, I need the markdown content for my LLM pipeline."},{"title":"Extracting SPA product details for price monitoring","prompt":"Scrape https://www.bestbuy.com/site/apple-macbook-pro/6525065.p and return the page content as markdown — it's a JavaScript-rendered page so make sure it actually renders before extracting."},{"title":"Reading gated documentation site for AI ingestion","prompt":"Pull the content from https://docs.someplatform.io/api/overview as markdown — it might have bot detection so use whatever proxies you need to get through."}],"resultDescription":"Returns the full page content rendered and cleaned as LLM-ready markdown, including text from JavaScript-rendered elements and content behind WAF or bot-detection layers. Static pages are handled with a lighter code path. Pricing scales with the complexity of the path used (WAF escalation, JS render, or residential proxy).","failureModes":["URL is completely inaccessible or returns a permanent block even with residential proxies","Page requires login/authentication that cannot be bypassed","Malformed or unreachable URL returns an error","Rate limiting on target site even through proxy rotation","Timeout on very slow or unresponsive target pages"],"whenToPreferThis":"Use this endpoint instead of a plain HTTP fetch when the target page uses Cloudflare, other WAF/bot-detection systems, or is a JavaScript-rendered SPA that requires a real browser. For static pages, it still works but costs less. Prefer this over generic scraping services when you need reliable markdown output optimized for LLM consumption and automatic escalation through proxy tiers.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-03T06:28:18.208Z","isFirstParty":false,"canonicalSlug":"metalift-web-scrape-url-to-llm-ready-markdown-e4ec4130"}