{"uid":"cap_eWkMKC44wtAMyIVyt7aAz","slug":"nightshift-labs-web-extract-api-053a4e96","name":"Nightshift Labs Web Extract API","description":"Fetch any public web page and return clean Markdown of the main content plus title, meta description, word count and absolute links. Strips scripts, navigation and boilerplate. Good for feeding pages to an LLM.","url":"https://nightshift-x402.nightshift-labs.workers.dev/v1/web/extract?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 of a public page"},"maxChars":{"type":"string","description":"max markdown characters (default 20000, max 100000)"}}}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"example":{"type":"object"}}}}},"responseSchema":{"type":"json","example":{"url":"https://example.com/","links":[],"title":"Example Domain","status":200,"markdown":"# Example Domain\n\nThis domain is for use in…","truncated":false,"wordCount":30}},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.003","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":"$0.003/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.003","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.003","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_enAESY6YSv5BTBNH8h7Vz","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.003","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 by URL and returns its content as cleaned Markdown, along with metadata like title, links, word count, and HTTP status.","exampleAgentPrompt":"Can you fetch the content of https://example.com/article and give me the full text as markdown so I can read it?","exampleUseCases":[{"title":"Summarize a news article","prompt":"Go to https://techcrunch.com/2024/06/01/openai-new-model and pull the full article text as markdown so I can summarize it."},{"title":"Extract product details from webpage","prompt":"Fetch the page at https://store.example.com/products/widget-pro and extract all the readable content — I want the title, links, and full markdown text."},{"title":"Monitor public announcement page","prompt":"Pull the content from https://status.stripe.com and return it as markdown so I can check if there are any active incidents."}],"resultDescription":"A JSON object containing the page URL, HTTP status code, page title, full page content as cleaned Markdown (up to maxChars, default 20,000), an array of links found on the page, word count, and a truncated flag indicating whether the content was cut off.","failureModes":["Invalid or non-public URL returns an error or non-200 HTTP status","Paywalled or login-protected pages return incomplete or no content","Very large pages may be truncated if maxChars limit is exceeded","Network timeouts for slow or unresponsive servers","Payment failure or insufficient USDC balance blocks the request via x402 protocol"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to read the content of a specific public web page and receive it in structured, readable Markdown format with metadata. It is a good fit for pay-per-call agent workflows using USDC on Base via the x402 protocol, particularly when you need page title, links, and word count alongside the text. Prefer alternatives if you need to crawl entire sites, handle authenticated pages, or require structured data extraction with field mapping.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-11-19T09:35:06.615Z","isFirstParty":false,"canonicalSlug":"nightshift-labs-web-extract-api-053a4e96"}