{"uid":"cap_TEowDboo9q5Skr9yvjWQF","slug":"agentdiet-paywall-clean-url-extractor-881ad5c0","name":"AgentDiet Paywall-Clean URL Extractor","description":"Deterministic B2A/A2A/MCP/x402/MPP/L402 execution and intelligence node at https://rag-diet.agentdiet.dev settling in USDC on Base.","url":"https://rag-diet.agentdiet.dev/v1/paywall-clean-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","POST"],"type":"string"},"queryParams":{"type":"object","properties":{"url":{"type":"string"},"mode":{"type":"string"}}}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"example":{"type":"object"}}}}},"responseSchema":{"type":"json","example":{"data":{},"status":"ok","roi_proof":{"compression_ratio_pct":91.4}}},"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_0vIVSM-A-pl6ePS27LwP0","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 URL and returns a compressed, token-efficient text extraction by stripping boilerplate, ads, and noise — achieving up to 91% compression ratio for agent context windows.","exampleAgentPrompt":"Fetch and clean this article URL for me — https://example.com/long-article — and give me just the core content stripped of all the ads and navigation junk so it fits in my context window.","exampleUseCases":[{"title":"RAG pipeline web content ingestion","prompt":"I need to pull the main text from this research page — https://arxiv.org/abs/2401.12345 — and strip all the headers, footers, and sidebars so I can feed just the meaningful content into my vector store without wasting tokens."},{"title":"Agent reading a news article cheaply","prompt":"Grab this news article at https://techcrunch.com/2024/06/01/some-story and give me only the article body — no ads, no related links, nothing extra — I want it compressed as much as possible for my AI to summarize."},{"title":"LLM context window budget management","prompt":"I'm hitting token limits — can you fetch https://docs.example.com/api-reference and return only the essential content with all the boilerplate stripped out, so I can squeeze it into a single context window?"}],"resultDescription":"Returns a JSON object with a 'data' field containing the cleaned, compressed page content, a 'status' field ('ok' on success), and a 'roi_proof' object that includes 'compression_ratio_pct' showing how much the content was reduced (e.g. 91.4% compression).","failureModes":["Invalid or unreachable URL returns an error status","Paywalled pages that cannot be fetched return empty or partial data","Malformed input schema (missing 'type' or 'method') causes validation failure","Payment not settled in USDC on Base results in 402 Payment Required","Rate limiting or network timeouts on the target URL may produce incomplete extraction"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to fetch web content but must conserve context window tokens — especially in RAG pipelines, multi-step reasoning chains, or any workflow where raw HTML or full webpage text would be too large. It is ideal for agent-to-agent (A2A) and machine-to-machine contexts where deterministic, reproducible text extraction at $0.001 USDC per call is acceptable and x402/L402 micropayment settlement on Base is already supported.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-22T12:44:22.743Z","isFirstParty":false,"canonicalSlug":"agentdiet-paywall-clean-url-extractor-881ad5c0"}