{"uid":"cap_Hr-6dSx6nbPdgCmTkfkSI","slug":"domain-osint-agentdiet-dev-web-page-html-distillation-with-bm25-37d44999","name":"Web Page & HTML Distillation 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://domain-osint.agentdiet.dev/v1/markdown-distill)","url":"https://domain-osint.agentdiet.dev/v1/markdown-distill?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_3xUCW_FifY9qmI2Fa_nu6","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"domain-osint.agentdiet.dev","brandSlug":"domain-osint-agentdiet-dev-mpp","brandBaseUrl":"https://domain-osint.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches a URL or accepts raw HTML and distills it into clean Markdown, structured JSON, a skeleton outline, or a BM25-ranked token-budget excerpt focused on a query.","exampleAgentPrompt":"Fetch https://stripe.com/docs/payments and distill it into clean markdown using budget mode focused on the query 'payment intents' with a max of 2000 tokens.","exampleUseCases":[{"title":"LLM-ready webpage summarization","prompt":"Grab the content from https://openai.com/research/gpt-4 and distill it into clean markdown so I can feed it into my prompt without wasting tokens."},{"title":"Query-focused token budget extraction","prompt":"Distill https://docs.aws.amazon.com/lambda/latest/dg/welcome.html using budget mode with the query 'cold start performance' and keep it under 1500 tokens."},{"title":"Raw HTML to structured data","prompt":"I have this raw HTML blob from a scraped product page — can you distill it into structured JSON tables and metadata so I can parse the specs and pricing?"}],"resultDescription":"Returns a JSON object with a 'data' field containing the distilled content (Markdown, structured JSON, skeleton, or BM25-ranked excerpt depending on mode), an 'roi_proof' object showing raw vs distilled token counts, compression ratio, and estimated LLM cost saved, plus optional cache status and billing details.","failureModes":["URL unreachable or returns non-200 status — fetch failure error","Invalid or malformed URL string — validation error","HTML payload too large — may hit processing limits","BM25 query missing when mode=budget — may return unfiltered or error","max_tokens below minimum of 20 — schema validation rejection","Payment not settled via x402 — 402 Payment Required response"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to ingest web page content efficiently within a token budget, especially when feeding external URLs into an LLM context. It is superior to raw fetching because it strips boilerplate, compresses content, and provides ROI proof of tokens saved. The BM25 budget mode is uniquely suited when only the most query-relevant passages of a long page are needed under a strict token ceiling.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:30:34.951Z","isFirstParty":false,"canonicalSlug":"domain-osint-agentdiet-dev-web-page-html-distillation-with-bm25-c0b211d1"}