{"uid":"cap_-0n_nQ_sTa3rNaxIT64m5","slug":"llms-generator-agentdiet-dev-html-url-to-markdown-distiller-with-bm25-ad6cb66c","name":"HTML/URL to Markdown 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://llms-generator.agentdiet.dev/v1/html-to-markdown)","url":"https://llms-generator.agentdiet.dev/v1/html-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_HKO5tvti_e1nPZG2jTSbw","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"llms-generator.agentdiet.dev","brandSlug":"llms-generator-agentdiet-dev-mpp","brandBaseUrl":"https://llms-generator.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches a URL or accepts raw HTML and distills it into compact, agent-ready Markdown or structured output with optional BM25-ranked token budget enforcement.","exampleAgentPrompt":"Fetch the Stripe docs page at stripe.com/docs/payments and distill it into markdown using budget mode, focused on the query 'payment intents', with a max of 500 tokens.","exampleUseCases":[{"title":"Compress docs page for agent context","prompt":"Grab the content from https://docs.anthropic.com/en/docs/overview and distill it into compact markdown — I need it under 800 tokens and focused on the query 'tool use'."},{"title":"Extract structured data from product page","prompt":"Take this raw HTML from our competitor's pricing page and distill it in structured mode so I get the pricing tiers and feature tables as clean JSON."},{"title":"Skeleton outline of long article","prompt":"Fetch https://en.wikipedia.org/wiki/Large_language_model and give me just a skeleton outline of the page structure — headings and key sections only — so I can navigate it without blowing my context window."}],"resultDescription":"Returns a JSON object with a 'data' field containing the distilled Markdown, structured JSON, skeleton outline, or BM25 budget excerpt depending on mode. Also includes an 'roi_proof' object showing raw_tokens, distilled_tokens, tokens_saved, compression_ratio_pct, roi_multiplier, and llm_cost_saved_usd. Optional 'cache' metadata indicates HIT/MISS status and latency. Billing details are included when payment is processed.","failureModes":["URL is unreachable or returns non-200 status — endpoint may return an error status","Raw HTML is malformed or empty — distillation may produce sparse or empty output","BM25 query provided without mode=budget — query may be ignored","max_tokens set below minimum of 20 — request rejected with validation error","Requested URL is paywalled or bot-blocked — content cannot be fetched","Token budget too small for meaningful content — minimal output returned"],"whenToPreferThis":"Choose this endpoint when you need to convert a live URL or raw HTML into compact, agent-friendly Markdown while staying within a token budget. It is especially valuable when LLM context costs matter, as the BM25 budget mode lets you filter content to only the most query-relevant tokens. Prefer it over generic scraping tools when you need ROI metrics on compression and token savings, or when you want structured JSON tables or skeleton outlines rather than raw HTML.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-28T00:32:13.837Z","isFirstParty":false,"canonicalSlug":"llms-generator-agentdiet-dev-html-url-to-markdown-distiller-with-bm25-ad6cb66c"}