{"uid":"cap_tOGyvw1CDCNkUml93j6G1","slug":"serp-extract-agentdiet-dev-html-to-markdown-distiller-with-bm25-95b0edb6","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://serp-extract.agentdiet.dev/v1/html-to-markdown)","url":"https://serp-extract.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_7W0yucTGUkxxRQNIQ1Fpo","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"serp-extract.agentdiet.dev","brandSlug":"serp-extract-agentdiet-dev-mpp","brandBaseUrl":"https://serp-extract.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches a URL or accepts raw HTML and converts it to compact, agent-ready Markdown with optional BM25 query-focused token budget trimming","exampleAgentPrompt":"Fetch https://docs.stripe.com/api/charges and distill it into compact markdown using budget mode, focused on the query 'charge creation parameters', keeping it under 500 tokens.","exampleUseCases":[{"title":"Summarize competitor pricing page","prompt":"Grab https://www.competitor.com/pricing and distill it into clean markdown — I want to see their pricing tiers without all the HTML noise, keep it under 800 tokens focused on the query 'pricing plans'."},{"title":"Extract article body from news URL","prompt":"Take this news article URL https://techcrunch.com/2024/05/01/some-article and convert it to clean markdown so I can read just the article text without ads or navigation clutter."},{"title":"Condense raw HTML for LLM context","prompt":"I have a raw HTML blob from a scraped page — can you distill it into structured markdown tables and metadata so it fits in my LLM context window? Use structured mode."}],"resultDescription":"Returns a JSON object with a 'data' field containing the distilled content (Markdown, structured tables/metadata, skeleton outline, or BM25-filtered excerpt depending on mode), plus an 'roi_proof' object showing raw_tokens, distilled_tokens, tokens_saved, compression_ratio_pct, roi_multiplier, and llm_cost_saved_usd. Also includes optional cache hit/miss status and billing details.","failureModes":["URL unreachable or returns non-200 — distillation cannot proceed","HTML too malformed to parse — may return empty or partial markdown","Token budget too low (below 20) — rejected by schema validation","BM25 query returns no relevant matches — budget excerpt may be empty","Rate limiting or payment failure via x402 — request blocked","Very large pages may hit processing limits or return truncated output"],"whenToPreferThis":"Choose this endpoint when you need to convert a live URL or raw HTML into compact, LLM-ready Markdown and want fine-grained control over token budgets. It is especially valuable when you want BM25 query-focused filtering to extract only the most relevant passage from a noisy webpage, keeping LLM context costs low. Prefer it over generic scrapers when you need compression ratios, ROI proof, and structured output modes (skeleton, tables, budget) in a single call.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:35:05.623Z","isFirstParty":false,"canonicalSlug":"serp-extract-agentdiet-dev-html-to-markdown-distiller-with-bm25-95b0edb6"}