{"uid":"cap_Y-A9KpVRRJodpq7XnE8JM","slug":"onchain-risk-agentdiet-dev-html-to-markdown-distiller-with-bm25-2ff6ccad","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://onchain-risk.agentdiet.dev/v1/html-to-markdown)","url":"https://onchain-risk.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_VxVB4I-I4VdrpxswSPif6","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 accepts raw HTML and distills it into compact Markdown, structured JSON, skeleton outline, or a BM25-ranked token-budget excerpt","exampleAgentPrompt":"Fetch https://stripe.com/docs/api and distill it into markdown using budget mode, focused on 'payment intents', keeping it under 2000 tokens so I can pass it to my LLM without blowing the context window.","exampleUseCases":[{"title":"Compress docs page for LLM context","prompt":"Grab the OpenAI API docs at https://platform.openai.com/docs/api-reference and distill them into compact markdown — I need it under 3000 tokens so I can fit it in my prompt without paying a fortune."},{"title":"BM25 relevance excerpt from earnings page","prompt":"Pull https://investor.apple.com/sec-filings/annual-reports and give me only the parts most relevant to 'revenue growth' using budget mode, capped at 1500 tokens."},{"title":"Convert raw HTML email to readable markdown","prompt":"I have this raw HTML newsletter blob — can you distill it into clean markdown so my agent can read and summarize it without all the noise?"}],"resultDescription":"Returns distilled content (Markdown, structured JSON tables/metadata, skeleton outline, or BM25 budget excerpt) along with an ROI proof object showing raw token count, distilled token count, tokens saved, compression ratio percentage, LLM cost saved in USD, and ROI multiplier. Also includes cache status (HIT/MISS) and billing details.","failureModes":["URL unreachable or returns non-200 — fetch failure with error status","HTML or URL produces empty or unparseable content — empty distillation result","max_tokens too small to contain meaningful content — truncated or error response","mode=budget without a query provided — BM25 ranking cannot execute","Invalid URL format — schema validation error","Payment not provided or insufficient — HTTP 402 payment required"],"whenToPreferThis":"Choose this endpoint when you need to reduce the token footprint of web content before passing it to an LLM, especially when working with a strict context window budget. The BM25 budget mode is uniquely valuable when you want only the most query-relevant portions of a long document. Prefer this over generic scraping tools when you care about LLM cost savings and receive quantified compression ROI. Also suitable for converting raw HTML payloads you already have, without a network fetch.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:33:52.276Z","isFirstParty":false,"canonicalSlug":"onchain-risk-agentdiet-dev-html-to-markdown-distiller-with-bm25-2ff6ccad"}