{"uid":"cap_jAli76y9hYUf2Wb6W4oy-","slug":"agentdiet-article-extractor-efa49eca","name":"AgentDiet Article 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/article-extractor?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_RSKKZWO0yFdF1o03Ts3Nj","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":"Extracts clean, distilled article content from a URL, stripping boilerplate to reduce token consumption by up to 85-91%","exampleAgentPrompt":"Extract the clean article text from https://example.com/some-news-story — strip all the ads, navigation, and boilerplate so I get just the readable content without wasting tokens.","exampleUseCases":[{"title":"RAG pipeline article ingestion","prompt":"Pull the clean article text from https://techcrunch.com/2024/01/15/some-article and strip all the HTML junk so I can feed just the meaningful content into my RAG system without blowing up my context window."},{"title":"News summarization with token savings","prompt":"Get me the distilled readable content from this Reuters article at https://www.reuters.com/article/some-story so I can summarize it — I want the main text only, no sidebar clutter."},{"title":"Research assistant web reading","prompt":"Fetch and clean the article at https://arxiv.org/abs/2401.00001 — just the core content, compressed as much as possible so it fits efficiently in my context."}],"resultDescription":"Returns a JSON object with a 'data' field containing the extracted clean article content, a 'status' field ('ok' on success), and a 'roi_proof' object showing the compression_ratio_pct (e.g. 91.4%) achieved by stripping boilerplate.","failureModes":["Invalid or unreachable URL returns an error status","Paywalled or bot-blocked pages may return incomplete content","Non-article pages (homepages, SPAs) may yield poor extraction quality","Missing required 'input' parameter returns schema validation error","Payment failure (insufficient USDC balance) returns HTTP 402"],"whenToPreferThis":"Choose this endpoint when you need to extract readable article content from a URL while minimizing token consumption — ideal for RAG pipelines, LLM summarization tasks, or any workflow where feeding raw HTML would waste context window space. At $0.001/call with ~91% compression ratios, it is cost-effective for high-volume article ingestion compared to fetching raw HTML and cleaning it yourself.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-22T12:42:39.088Z","isFirstParty":false,"canonicalSlug":"agentdiet-article-extractor-efa49eca"}