{"uid":"cap_GEDf2ziYdKY9lM-NbM3AU","slug":"hn-pulse-agentdiet-dev-web-distillation-with-bm25-budget-control-98e2e683","name":"Web Distillation with BM25 Budget Control","description":"Distill a URL or raw HTML payload with BM25 budget control (Live x402 v2, IETF MPP & MCP endpoint at https://hn-pulse.agentdiet.dev/v1/paywall-clean-extract)","url":"https://hn-pulse.agentdiet.dev/v1/paywall-clean-extract?utm_source=zero.xyz","method":"POST","headers":{},"bodySchema":{"type":"object","required":["url"],"properties":{"url":{"type":"string","minLength":1,"description":"Target webpage URL to fetch and distill (or builtin://stripe-docs)"},"html":{"type":"string","description":"Optional raw HTML string to distill directly without fetching"},"mode":{"enum":["markdown","structured","skeleton","budget"],"type":"string","default":"markdown","description":"Distillation mode"},"query":{"type":"string","description":"BM25 focus query when mode=budget"},"max_tokens":{"type":"integer","minimum":20,"description":"Strict token budget ceiling when mode=budget"}}},"responseSchema":{"type":"object","required":["status","roi_proof","data"],"properties":{"data":{"type":"object","description":"Distilled Markdown, structured JSON tables/metadata, skeleton outline, or BM25 budget excerpt."},"cache":{"type":"object","properties":{"status":{"enum":["HIT","MISS"],"type":"string"},"cache_key":{"type":"string"},"latency_ms":{"type":"number"}}},"status":{"type":"string","description":"Execution status ('ok')"},"billing":{"type":"object","properties":{"agent_id":{"type":"string"},"payment_method":{"type":"string"},"fee_charged_usd":{"type":"number"}}},"roi_proof":{"type":"object","properties":{"raw_tokens":{"type":"integer"},"tokens_saved":{"type":"integer"},"roi_multiplier":{"type":"number"},"distilled_tokens":{"type":"integer"},"llm_cost_saved_usd":{"type":"number"},"compression_ratio_pct":{"type":"number"}}}}},"example":null,"exampleRequest":null,"tags":[],"displayCostAmount":"0.001","displayCostAsset":"USD","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":"mpp","network":"tempo","amountUsd":"0.001","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"mpp","network":"tempo","amountUsd":"0.001","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_P3l9aIMM3xxnCGI-t8Xbr","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"hn-pulse.agentdiet.dev","brandSlug":"hn-pulse-agentdiet-dev-mpp","brandBaseUrl":"https://hn-pulse.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches and distills a URL or raw HTML into clean Markdown, structured JSON, a skeleton outline, or a BM25-focused token-budgeted excerpt","exampleAgentPrompt":"Can you fetch https://stripe.com/docs/api and distill it into clean markdown, keeping it under 2000 tokens and focusing on the 'authentication' topic using budget mode?","exampleUseCases":[{"title":"Token-budgeted research page extraction","prompt":"Grab the article at https://example.com/long-research-paper and give me a BM25-focused excerpt about 'interest rate policy' with a strict cap of 1500 tokens — I need to fit it into my context window."},{"title":"Structured data extraction from SaaS pricing page","prompt":"Go to https://linear.app/pricing and distill it in structured mode so I get the pricing tiers, features, and costs as clean JSON tables."},{"title":"Clean article markdown for AI summarization","prompt":"Fetch https://techcrunch.com/some-article and strip all the ads and navigation — just give me the main article content as clean markdown so I can summarize it."}],"resultDescription":"Returns a JSON object with a 'data' field containing the distilled content (Markdown string, structured JSON, skeleton outline, or BM25-focused excerpt), an 'roi_proof' object showing raw token count, distilled token count, tokens saved, compression ratio percentage, and estimated LLM cost saved in USD, plus optional cache status and billing details.","failureModes":["URL is unreachable or returns non-200 status — endpoint may return an error status","Paywalled or bot-blocked pages may return incomplete or empty content","Invalid mode enum value causes validation error","max_tokens set below 20 triggers schema validation failure","HTML payload is malformed and cannot be parsed","Query param missing when mode=budget may result in unfiltered output"],"whenToPreferThis":"Choose this endpoint when you need to reduce token costs before passing web content to an LLM, especially when working with long pages where only a relevant subsection is needed. The BM25 budget mode makes it uniquely suited for query-focused extraction with strict token caps. Prefer it over generic scrapers when you want provable ROI metrics (tokens saved, compression ratio) alongside the cleaned content.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:34:44.446Z","isFirstParty":false,"canonicalSlug":"hn-pulse-agentdiet-dev-web-distillation-with-bm25-budget-control-98e2e683"}