{"uid":"cap__bV5Mx0k6k4DLAMYUSEfu","slug":"hn-pulse-agentdiet-dev-web-page-html-distillation-with-bm25-budget-c4bb924a","name":"Web Page & HTML 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/docs-to-markdown)","url":"https://hn-pulse.agentdiet.dev/v1/docs-to-markdown?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_DBVUeeRjm04uQIIzBiorP","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 URL or accepts raw HTML and distills it into token-efficient Markdown, structured JSON, skeleton outlines, or BM25-ranked budget excerpts with strict token ceiling control","exampleAgentPrompt":"Can you fetch https://stripe.com/docs/api and distill it into clean markdown, keeping it under 2000 tokens and focusing on authentication details?","exampleUseCases":[{"title":"LLM-ready documentation extraction","prompt":"Grab the content from https://docs.openai.com/api-reference and convert it to markdown mode so I can feed it into my LLM without burning through my token budget."},{"title":"BM25-focused budget excerpt for research","prompt":"Pull the page at https://arxiv.org/abs/2310.06825 and give me only the sections most relevant to 'transformer attention mechanisms' with a strict cap of 1500 tokens using budget mode."},{"title":"Structured table extraction from HTML","prompt":"I have this raw HTML from a financial data page — can you distill it in structured mode to extract all the tables and metadata as clean JSON?"}],"resultDescription":"Returns a JSON object containing the distilled content (Markdown text, structured JSON tables/metadata, skeleton outline, or BM25-ranked excerpt depending on mode), an ROI proof block showing raw vs distilled token counts, compression ratio, and estimated LLM cost saved, plus optional cache status and billing details.","failureModes":["URL is unreachable or returns non-200 status — endpoint may return an error status","HTML payload is malformed or empty — distillation may produce minimal output","max_tokens ceiling too low to include meaningful content — may return truncated or empty excerpt","BM25 query not provided when mode=budget — may default to unfiltered budget truncation","Rate limiting or payment failure via x402 — returns 402 Payment Required"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to ingest web page or HTML content within a strict token budget, especially when feeding documentation, news articles, or structured web data into an LLM. It is preferred over raw scraping when token efficiency matters, and over generic scrapers when BM25 query-focused relevance filtering or multiple distillation modes (markdown, structured, skeleton, budget) are needed. Particularly valuable for agents that repeatedly access the same URLs and benefit from caching.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:34:23.388Z","isFirstParty":false,"canonicalSlug":"hn-pulse-agentdiet-dev-web-page-html-distillation-with-bm25-budget-c4bb924a"}