{"uid":"cap_rpfhhKmm-OO5j0r8Scc-I","slug":"hn-pulse-agentdiet-dev-web-url-html-distiller-with-bm25-budget-control-a2524a8d","name":"Web URL HTML 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/clean-html)","url":"https://hn-pulse.agentdiet.dev/v1/clean-html?utm_source=zero.xyz","method":"GET","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_qxxA9dBwJ4NuCltGSVWE3","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 a webpage URL (or accepts raw HTML) and distills it into compact, agent-ready tokens using configurable extraction modes including BM25-focused budget excerpts","exampleAgentPrompt":"Distill the content at https://stripe.com/docs/payments into clean markdown, keeping it under 500 tokens and focused on the query 'payment intents API' using budget mode.","exampleUseCases":[{"title":"Summarize a docs page for an agent","prompt":"Fetch the content from https://docs.openai.com/api-reference and distill it into structured markdown so I can pass it to my agent without blowing my context window."},{"title":"Budget-capped research extraction","prompt":"Grab the article at https://techcrunch.com/2024/05/01/openai-news and extract only the parts relevant to 'funding round', keeping the output under 300 tokens using budget mode."},{"title":"Skeleton outline of a landing page","prompt":"Pull the page at https://linear.app and give me a skeleton outline of its structure so I can quickly understand how it's organized without reading the whole thing."}],"resultDescription":"Returns a JSON object with a 'data' field containing distilled content (Markdown, structured tables, skeleton, or BM25-focused excerpt depending on mode), plus ROI proof metrics showing raw vs distilled token counts, compression ratio, tokens saved, and estimated LLM cost saved. Also includes cache hit/miss status and billing details.","failureModes":["Invalid or unreachable URL returns an error status","Raw HTML too large may be truncated or rejected","max_tokens below minimum (20) triggers validation error","mode=budget without a query may produce suboptimal BM25 excerpts","Paywalled or JavaScript-rendered pages may yield incomplete extraction","HTTP 402 payment required if agent lacks valid x402 payment credentials"],"whenToPreferThis":"Choose this endpoint when you need to feed webpage content to an LLM agent but want to minimize token consumption — especially when working with long documentation pages, articles, or HTML dumps. It is particularly valuable in budget-constrained agentic pipelines where you need BM25-focused relevance filtering within a strict token ceiling. Prefer it over raw fetch+parse approaches when you want built-in compression metrics and multiple output modes (markdown, structured, skeleton, budget).","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:21:02.403Z","isFirstParty":false,"canonicalSlug":"hn-pulse-agentdiet-dev-web-url-html-distiller-with-bm25-budget-control-a2524a8d"}