{"uid":"cap_h64r822YiH6yp66a_5Qzg","slug":"onchain-risk-agentdiet-dev-html-to-markdown-web-distiller-with-bm25-945e9877","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://onchain-risk.agentdiet.dev/v1/html-to-markdown)","url":"https://onchain-risk.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_pB8iVzB4tP3hrRTbkNKL9","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"onchain-risk.agentdiet.dev","brandSlug":"onchain-risk-agentdiet-dev-mpp","brandBaseUrl":"https://onchain-risk.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches a URL or raw HTML and distills it into compact, agent-ready Markdown, structured JSON, skeleton outline, or BM25-focused token-budgeted excerpts","exampleAgentPrompt":"Fetch the URL https://stripe.com/docs/api and distill it into compact markdown using budget mode with a max of 2000 tokens, focused on the query 'payment intents'.","exampleUseCases":[{"title":"Cheap LLM-ready doc fetching","prompt":"Grab the content from https://docs.openai.com/api-reference and compress it into markdown so I can feed it to my agent without burning through my token budget — keep it under 3000 tokens."},{"title":"Structured data extraction from webpage","prompt":"Pull the page at https://en.wikipedia.org/wiki/Bitcoin and convert it into structured JSON tables and metadata so I can parse the key facts programmatically."},{"title":"BM25-focused content slice","prompt":"Fetch https://sec.gov/cgi-bin/browse-edgar?action=getcompany and extract only the parts about 'annual filings and 10-K forms' using budget mode with a 1500 token ceiling."}],"resultDescription":"Returns a 'data' object containing the distilled content in the requested format (Markdown, structured JSON tables/metadata, skeleton outline, or BM25-focused excerpt), alongside an ROI proof block showing raw token count, distilled token count, tokens saved, compression ratio percentage, and estimated LLM cost saved in USD. Also includes cache status and billing metadata.","failureModes":["URL is unreachable or returns a non-200 response — endpoint may return an error status","Invalid or malformed URL causes a fetch failure","mode=budget requested without a query or max_tokens — may fall back to defaults","HTML payload too large causing timeout or truncation","Payment not processed via x402 — request may be rejected with HTTP 402","Requested URL blocks bots or requires authentication — content may be empty or partial"],"whenToPreferThis":"Choose this endpoint when you need to feed web content to an LLM efficiently and want to minimize token consumption and cost. It is especially valuable when working with long documentation pages, SEC filings, or any HTML-heavy source where only a focused excerpt is needed (use budget+BM25 mode). Prefer it over raw web scrapers when you need token-count guarantees, ROI tracking, or multiple output formats (markdown, structured, skeleton) from the same service.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T12:51:30.654Z","isFirstParty":false,"canonicalSlug":"onchain-risk-agentdiet-dev-html-to-markdown-web-distiller-with-bm25-945e9877"}