{"uid":"cap_MYwpQIYok_sffRVxGzj-L","slug":"stride-gateway-web-extract-api-2637f52a","name":"Stride Gateway Web Extract API","description":"Web scraping API: fetch any public web page and get its readable content as clean markdown — title, author, canonical URL, boilerplate stripped. Honest User-Agent, robots.txt honored (explicit Disallow returns an unpaid 403), private/internal targets refused, at most 3 safety-revalidated redirects, 1MB input / 100k character output caps. HTML pages only. Use for research agents, content extraction, summarization pipelines, and RAG ingestion. Cached up to 5 minutes per URL.","url":"https://gateway.stride20k.com/web/extract","method":"GET","headers":{},"bodySchema":null,"responseSchema":{"type":"json","example":{"ok":true,"data":{"url":"https://example.com/","title":"Example Domain","author":null,"finalUrl":"https://example.com/","markdown":"# Example Domain\n\nThis domain is for use in documentation examples without needing permission.","charCount":131,"truncated":false,"canonicalUrl":null},"meta":{"cached":false,"source":"direct fetch (buyer-directed)","fetchedAt":"2026-07-04T00:00:00.000Z","attribution":null},"endpoint":"/web/extract"}},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.03","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":"$0.03/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.03","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.03","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_i8Pe8wQQgdBe-CGZ6At53","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.03","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 readable content as clean markdown, stripping boilerplate and preserving title, author, and canonical URL","exampleAgentPrompt":"Fetch the article at https://www.theverge.com/2024/1/15/example-story and give me the full readable content as clean markdown, without any nav bars or ads.","exampleUseCases":[{"title":"Summarize competitor blog posts","prompt":"Go to https://www.hubspot.com/marketing-statistics and pull the main content as clean markdown so I can summarize the key stats for our weekly competitive intel report."},{"title":"Ingest documentation into knowledge base","prompt":"Fetch the page at https://docs.stripe.com/payments/payment-intents and extract all the readable content as markdown so I can add it to our internal RAG knowledge base."},{"title":"Extract author and article body","prompt":"Pull the article from https://techcrunch.com/2024/03/10/openai-funding-round and give me the title, author, and full body text as clean markdown, stripping out any ads or sidebar clutter."}],"resultDescription":"A JSON object containing: the requested URL, the final URL after redirects, the page title (or null), the author (or null), the canonical URL (or null), the full readable page content as a markdown string, a character count, a truncated flag (true if content exceeded 100k chars), a cached flag, and the ISO 8601 timestamp of when the page was fetched.","failureModes":["URL is disallowed by robots.txt — returns a 403 error","URL points to a private or internal target — refused with an error","Page is not HTML (e.g. PDF, image) — not supported","Redirect chain exceeds 3 hops — request fails","Input URL exceeds 1MB — rejected","Output truncated at 100k characters (truncated flag set to true)","Upstream page is unavailable or times out — fetch error returned","Malformed or non-absolute URL — validation error"],"whenToPreferThis":"Use this endpoint when you need to fetch and read the human-readable content of a specific public web page — ideal for research agents, summarization pipelines, and RAG ingestion workflows. It respects robots.txt, caps output size, and returns cached results within 5 minutes, making it well-suited for repeated or high-frequency page reads. Prefer it over raw HTTP fetching when you want boilerplate-stripped markdown with metadata like title, author, and canonical URL already extracted.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-15T06:47:44.574Z","isFirstParty":false}