{"uid":"cap_g4xioMAOn0BJlAeH0giRa","slug":"domain-osint-agentdiet-dev-web-url-to-markdown-distiller-with-bm25-58063130","name":"Web 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://domain-osint.agentdiet.dev/v1/docs-to-markdown)","url":"https://domain-osint.agentdiet.dev/v1/docs-to-markdown?utm_source=zero.xyz","method":"GET","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_WCAwvo60HruWcbhOMRc8r","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 web URL or raw HTML and distills it into compact, agent-ready Markdown, structured JSON, skeleton outline, or BM25-focused token budget excerpts","exampleAgentPrompt":"Fetch the page at https://docs.stripe.com/payments/checkout and distill it into compact markdown using budget mode, focused on 'payment intents', with a max of 500 tokens — I want to minimize my LLM costs.","exampleUseCases":[{"title":"Compress documentation for LLM context","prompt":"Grab the page at https://docs.openai.com/api-reference/completions and distill it into markdown mode — I want a clean, compact version I can paste into my agent's context without blowing the token limit."},{"title":"BM25-focused excerpt for research query","prompt":"Fetch https://en.wikipedia.org/wiki/Large_language_model and give me a budget-mode excerpt focused on 'training data and safety', capped at 300 tokens — just the most relevant parts to my query."},{"title":"Structured data extraction from a product page","prompt":"Take the HTML from this e-commerce product page and distill it into structured mode so I get tables and metadata — here's the URL: https://www.example-store.com/products/laptop-pro."}],"resultDescription":"Returns a JSON object containing the distilled content (Markdown text, structured JSON tables/metadata, skeleton outline, or BM25-ranked excerpt depending on mode), plus an roi_proof block showing raw token count, distilled token count, tokens saved, compression ratio percentage, estimated LLM cost saved in USD, and a cache status object indicating HIT/MISS with latency.","failureModes":["Invalid or unreachable URL returns an error status","URL behind authentication or bot protection may return empty or partial content","max_tokens set too low may produce severely truncated or unusable output","BM25 query with mode!=budget is ignored silently","Raw HTML input too large may exceed processing limits","Payment failure via x402 results in 402 response with no content returned"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to ingest web page content while minimizing token consumption and LLM costs — especially for documentation pages, research articles, or any URL whose full HTML would be too verbose for a context window. Prefer it over raw HTTP fetching when you need clean Markdown, structured tables, or a query-focused BM25 excerpt with a strict token budget ceiling. The built-in ROI proof makes it easy to measure compression gains per call.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:25:51.737Z","isFirstParty":false,"canonicalSlug":"domain-osint-agentdiet-dev-web-url-to-markdown-distiller-with-bm25-58063130"}