{"uid":"cap_GDdS_QjtzxbBrlSyJfZtk","slug":"prompt-guard-agentdiet-dev-html-to-markdown-web-distiller-with-bm25-0cc35746","name":"HTML-to-Markdown Web 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://prompt-guard.agentdiet.dev/v1/html-to-markdown)","url":"https://prompt-guard.agentdiet.dev/v1/html-to-markdown?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_b14t9bmeLdgWp1Op6g8_5","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"prompt-guard.agentdiet.dev","brandSlug":"prompt-guard-agentdiet-dev-mpp","brandBaseUrl":"https://prompt-guard.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches a URL or processes raw HTML and distills it into compact, agent-ready Markdown, structured JSON, skeleton outline, or BM25-focused token budget excerpt","exampleAgentPrompt":"Distill the page at https://docs.stripe.com/payments/payment-intents into compact markdown, use budget mode focused on the query 'payment intent lifecycle', and keep it under 500 tokens.","exampleUseCases":[{"title":"Token-efficient research page extraction","prompt":"Fetch https://en.wikipedia.org/wiki/Transformer_(machine_learning_model) and distill it into markdown, keeping only the sections relevant to 'attention mechanism' within a 300-token budget."},{"title":"Structured data extraction from product page","prompt":"Take this product page URL https://example.com/products/widget-pro and distill it in structured mode so I get the tables, metadata, and specs as clean JSON."},{"title":"Skeleton outline of a long article","prompt":"Can you fetch https://longblog.com/2024/ai-agents-explained and return just the skeleton outline so I can see the section structure without reading the whole thing?"}],"resultDescription":"Returns a 'data' object containing the distilled content (Markdown string, structured JSON, skeleton outline, or BM25-focused excerpt depending on mode), plus an 'roi_proof' object showing raw token count, distilled token count, tokens saved, compression ratio percentage, and estimated LLM cost saved in USD. Also includes optional cache status and billing metadata.","failureModes":["URL is unreachable or returns non-200 — fetch error returned","HTML payload is empty or malformed — empty or error distillation result","mode=budget used without providing query or max_tokens — may default or return error","Token ceiling too low (below 20) — validation error","Payment not provided or insufficient — HTTP 402 payment required response","Target URL blocks headless fetch (anti-bot) — empty or partial content"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to read a webpage but must stay within a strict token or cost budget, or when raw HTML is too noisy for direct LLM consumption. Especially useful for BM25-focused extraction where only query-relevant passages are needed, or when structured/skeleton modes help agents navigate large documents. Prefer over generic scrapers when token ROI metrics and compression ratios are needed to justify LLM processing costs.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T12:51:14.683Z","isFirstParty":false,"canonicalSlug":"prompt-guard-agentdiet-dev-html-to-markdown-web-distiller-with-bm25-0cc35746"}