{"uid":"cap_WgOJBaGBR3CmW5VF1yMd0","slug":"hn-pulse-agentdiet-dev-webpage-distiller-with-bm25-budget-control-d7673342","name":"Webpage Distiller 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/webpage-distiller)","url":"https://hn-pulse.agentdiet.dev/v1/webpage-distiller?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_SNtx0dpXFCASLQ2qpgHH9","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 compressed Markdown, structured JSON, skeleton outline, or BM25-ranked token-budgeted excerpts focused on a specific query","exampleAgentPrompt":"Fetch the page at https://docs.stripe.com/payments/payment-intents and distill it into clean Markdown, keeping it under 800 tokens and focusing on the query 'payment intent lifecycle' using budget mode.","exampleUseCases":[{"title":"Research digest from documentation page","prompt":"Go to https://docs.openai.com/guides/function-calling and distill it into clean Markdown so I can read through the key content without all the navigation clutter and ads."},{"title":"Token-budget extraction for RAG pipeline","prompt":"Fetch https://en.wikipedia.org/wiki/Transformer_(machine_learning_model) and give me a BM25 budget excerpt focused on 'attention mechanism', capped at 500 tokens so it fits my context window."},{"title":"Structured data extraction from product page","prompt":"Take the HTML from this product listing page I'm pasting and extract it in structured mode so I get the tables, metadata, and key fields as JSON rather than raw HTML."}],"resultDescription":"Returns a JSON object containing the distilled content (Markdown, structured JSON tables/metadata, skeleton outline, or BM25 excerpt depending on mode), cache status (HIT/MISS), billing details including fee charged, and an ROI proof block showing raw token count, distilled token count, tokens saved, compression ratio percentage, LLM cost saved in USD, and an ROI multiplier.","failureModes":["URL is unreachable or returns non-200 — fetch failure error","URL points to non-HTML content (PDF, binary) — unsupported content type","Token budget too restrictive (max_tokens too low) — may return minimal or empty excerpt","BM25 query returns no matching content — sparse result","Rate limiting or payment failure via x402 — 402 Payment Required response","Malformed HTML input — parsing error or degraded output quality"],"whenToPreferThis":"Choose this endpoint when you need to bring live web content into an LLM pipeline while controlling token costs — especially when you want BM25-focused relevance filtering to extract only the portions of a page matching a query within a strict token budget. It is preferable to raw HTTP fetching when you need clean Markdown or structured output instead of raw HTML, and better than generic scrapers when compression ratio and ROI proof matter to your workflow.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:33:56.810Z","isFirstParty":false,"canonicalSlug":"hn-pulse-agentdiet-dev-webpage-distiller-with-bm25-budget-control-d7673342"}