{"uid":"cap_m03SQY8ZQ7kSO-upvPugJ","slug":"web-page-crawl-to-clean-text-bbcfc9b9","name":"Web Page Crawl to Clean Text","description":"Page crawl to clean text. GET /api/v1/crawl?url=https://… → 402 $0.003 USDC. Pay, retry, get title+text+links. crawl, reader.","url":"https://aws-bedrock.grok.me/api/v1/crawl","method":"GET","headers":{},"bodySchema":{"type":"object","$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","HEAD","DELETE"],"type":"string"},"queryParams":{"type":"object","properties":{"modelId":{"type":"string","description":"OpenRouter model id"}}}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"example":{"type":"object"}}}}},"responseSchema":null,"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":"$0.001/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_PjqRhKPfeNBXiGxqKKPPJ","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"EPjFWdd5AufqSSqeM2qN1xzybapC8G4wEGGkZwyTDt1v","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Fetches any public URL and returns its title, clean readable text, and extracted links","exampleAgentPrompt":"Can you grab the text content from this article — https://techcrunch.com/2024/05/01/openai-launches-gpt-5/ — and summarize what it says?","exampleUseCases":[{"title":"Summarize a news article","prompt":"Fetch the full text from https://www.bbc.com/news/technology-67890123 and give me a two-paragraph summary of the main points."},{"title":"Extract docs page for LLM context","prompt":"Pull the clean text from https://docs.stripe.com/api/charges and include it as context so you can answer my question about how Stripe charges work."},{"title":"Monitor competitor blog post content","prompt":"Read the content at https://openai.com/blog/introducing-gpt-4o and tell me what new features they announced."}],"resultDescription":"Returns the page title, clean readable body text (boilerplate and ads stripped), and a list of extracted hyperlinks from the crawled URL. Response is structured JSON with title, text, and links fields, suitable for feeding directly into an LLM context window.","failureModes":["Payment required (402) — agent must pay $0.001 USDC and retry","URL is behind a login or paywall — returns partial or empty text","Page is JavaScript-heavy SPA — may return limited content if JS is not rendered","Invalid or malformed URL — returns error","Target site blocks crawlers (robots.txt or rate limiting) — may return empty or error","Network timeout on slow target servers"],"whenToPreferThis":"Choose this endpoint when you need fast, clean plain-text extraction from a known URL — especially for feeding web content into an LLM pipeline. It is purpose-built for agent use cases where you have a specific URL and want the readable content without HTML noise. Prefer it over general web search when you already have the URL. It complements the sibling search endpoint (which finds URLs) — use search to discover URLs, then this crawl endpoint to read their content.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-14T18:32:56.945Z","isFirstParty":false}