{"uid":"cap_FtCmZvfDtm9NO1yr_cRwG","slug":"sec-intel-agentdiet-dev-web-url-to-markdown-distiller-with-bm25-0cc7bfa8","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://sec-intel.agentdiet.dev/v1/docs-to-markdown)","url":"https://sec-intel.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_mbdxSmi6fTZkR3PG6V11X","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"sec-intel.agentdiet.dev","brandSlug":"sec-intel-agentdiet-dev-mpp","brandBaseUrl":"https://sec-intel.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches a web URL (or accepts raw HTML) and distills it into compact, agent-ready Markdown, structured JSON, skeleton outline, or BM25-focused token budget excerpts","exampleAgentPrompt":"Fetch the Stripe documentation page at https://stripe.com/docs/payments and distill it into compact markdown, keeping it under 2000 tokens and focusing on the topic 'payment intents'.","exampleUseCases":[{"title":"Token-budget documentation fetch for agent","prompt":"Grab the OpenAI API docs page at https://platform.openai.com/docs/api-reference and distill it into markdown, capping it at 1500 tokens and focusing on 'rate limits' so I don't burn my context window."},{"title":"Structured extraction of a pricing page","prompt":"Fetch https://vercel.com/pricing and return it in structured mode so I get the plan names, prices, and features as clean JSON tables rather than raw HTML."},{"title":"Skeleton outline of a long blog post","prompt":"Take https://martinfowler.com/articles/microservices.html and give me just the skeleton outline — the headings and section structure — so I can navigate the article without loading the full text."}],"resultDescription":"Returns a JSON object with: the distilled content in the requested format (Markdown, structured JSON tables/metadata, skeleton outline, or BM25-focused excerpt) under 'data'; an 'roi_proof' object showing raw vs distilled token counts, tokens saved, compression ratio percentage, and estimated LLM cost saved in USD; optional 'cache' status (HIT/MISS) with latency; and billing details including fee charged ($0.001 per call).","failureModes":["Invalid or unreachable URL returns an error status","URL behind authentication wall returns incomplete or empty distillation","mode=budget without a query or max_tokens may return unfiltered content","Very large pages may be truncated or exceed processing limits","Raw HTML input that is malformed may produce poor distillation quality","Rate limiting or payment failure (HTTP 402) if USDC balance is insufficient"],"whenToPreferThis":"Choose this endpoint when you need to feed web page content to an LLM but want to minimize token usage and cost — especially for long documentation pages, articles, or HTML-heavy sites. It is superior to raw HTML fetching because it compresses content by up to 85% and provides BM25-targeted excerpts when you only care about a specific topic. Prefer it over generic scrapers when you need structured JSON tables, skeleton outlines, or strict token budget control with ROI metrics.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:26:00.256Z","isFirstParty":false,"canonicalSlug":"sec-intel-agentdiet-dev-web-url-to-markdown-distiller-with-bm25-0cc7bfa8"}