{"uid":"cap_ifGiCWkDSt6c7RKfMWwB5","slug":"workflows-agentdiet-dev-html-to-markdown-distiller-with-bm25-budget-6516a757","name":"HTML 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://workflows.agentdiet.dev/v1/html-to-markdown)","url":"https://workflows.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_Z-ac4ZNOdClxeUYInnmFN","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"workflows.agentdiet.dev","brandSlug":"workflows-agentdiet-dev-mpp","brandBaseUrl":"https://workflows.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Converts a URL or raw HTML payload into compact, agent-ready Markdown with optional BM25-ranked token budget control","exampleAgentPrompt":"Can you fetch https://stripe.com/docs/payments and distill it into compact markdown using budget mode, focused on 'payment intents', keeping it under 500 tokens?","exampleUseCases":[{"title":"Research page compressed for agent context","prompt":"Grab https://openai.com/research/gpt-4 and distill it into clean markdown — I need it compact enough to fit in my context window without burning too many tokens."},{"title":"BM25 focused excerpt from documentation","prompt":"Fetch the Stripe docs at https://stripe.com/docs/api and extract only the sections most relevant to 'refunds and disputes' with a strict budget of 300 tokens."},{"title":"Raw HTML cleaned up for downstream parsing","prompt":"I have this raw HTML from a scraped product page — can you convert it to structured markdown so I can pull out the product name, price, and availability?"}],"resultDescription":"Returns a JSON object with a 'data' field containing the distilled content (Markdown, structured JSON tables, skeleton outline, or BM25 budget excerpt depending on mode), plus an 'roi_proof' object showing raw token count, distilled token count, tokens saved, compression ratio percentage, estimated LLM cost saved in USD, and ROI multiplier. Also includes optional cache hit/miss status and billing metadata.","failureModes":["URL is unreachable or returns non-200 — fetch failure error","HTML payload is empty or malformed — parsing error","max_tokens set below minimum of 20 — validation error","BM25 query provided without mode=budget — query may be ignored","Target page blocks bots or requires authentication — empty or partial content returned","Token budget too small for meaningful extraction — truncated or minimal output"],"whenToPreferThis":"Choose this endpoint when you need to fetch and compress web content into agent-friendly tokens, especially when LLM context window limits or cost constraints matter. It is particularly valuable over generic scraping tools when you need BM25-ranked budget control to surface only the most query-relevant content. Use it instead of raw HTML fetching whenever you want automated markdown conversion with built-in ROI metrics showing exactly how many tokens and dollars were saved.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:35:56.637Z","isFirstParty":false,"canonicalSlug":"workflows-agentdiet-dev-html-to-markdown-distiller-with-bm25-budget-6516a757"}