{"uid":"cap_eusLQaIsVurqcskf6s7O3","slug":"agentdiet-paywall-clean-extract-context-window-distiller-b285dade","name":"AgentDiet Paywall-Clean Extract — Context Window Distiller","description":"Deterministic B2A/A2A/MCP/x402/MPP/L402 execution and intelligence node at https://status.agentdiet.dev settling in USDC on Base.","url":"https://status.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_O_8A1zkWfkNLbrt1KTWhu","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, strips paywalls and boilerplate, and returns a heavily compressed clean-text extraction with a compression ratio proof","exampleAgentPrompt":"Can you fetch and clean up https://example.com/long-article for me? I want just the essential content, stripping all the ads, nav menus, and boilerplate so it fits in my context window without wasting tokens.","exampleUseCases":[{"title":"Research article distillation for agent","prompt":"I'm about to send this news article at https://techcrunch.com/2024/01/15/ai-funding-roundup into my analysis pipeline — can you extract just the core readable content from it and strip everything else so I'm not burning thousands of tokens on headers and footers?"},{"title":"Paywalled content clean extraction","prompt":"Grab https://www.wsj.com/articles/some-article and pull out the cleanest version of the text you can — I want to read the actual content without all the paywall wrappers and site chrome getting in the way."},{"title":"Bulk context compression for RAG pipeline","prompt":"Before I index this page at https://docs.someproject.org/reference/api into my knowledge base, can you run it through AgentDiet to distill it down to just the meaningful content? I want to see the compression ratio too so I know how much I'm saving."}],"resultDescription":"Returns a JSON object with a 'data' field containing the clean extracted text, a 'status' field ('ok' on success), and an 'roi_proof' object that includes a 'compression_ratio_pct' value (e.g. 91.4) showing how much the content was compressed relative to the raw input.","failureModes":["URL is unreachable or returns a non-200 response — endpoint may return an error status","Paywalled content fully blocked without a cached or accessible version — data field may be empty or partial","Invalid or missing 'url' query parameter — likely returns a 400-style error","Rate limiting or payment verification failure via x402 — returns 402 Payment Required","Target URL returns binary or non-text content (PDF, image) — extraction may fail or return empty data"],"whenToPreferThis":"Choose this endpoint when you need to minimize token usage by cleaning and compressing web content before ingesting it into an AI context window or LLM prompt. It is ideal for agentic pipelines that need to fetch and process many URLs without hitting context limits, and for any scenario where raw webpage content (with ads, navigation, boilerplate) would otherwise waste a large fraction of the available token budget. Prefer it over generic web scrapers when token efficiency and a measurable compression proof are important outputs.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-22T12:44:22.745Z","isFirstParty":false,"canonicalSlug":"agentdiet-paywall-clean-extract-context-window-distiller-b285dade"}