{"uid":"cap_Xnv8FQXViS-fJtPYgmv_C","slug":"defi-yield-agentdiet-dev-url-to-markdown-web-distiller-with-bm25-67085b9b","name":"URL to Markdown Web 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://defi-yield.agentdiet.dev/v1/url-to-markdown)","url":"https://defi-yield.agentdiet.dev/v1/url-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_1h2-UotbNj8ZZN4BhfgzI","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"defi-yield.agentdiet.dev","brandSlug":"defi-yield-agentdiet-dev-mpp","brandBaseUrl":"https://defi-yield.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 excerpt with token budget enforcement","exampleAgentPrompt":"Grab the content from https://stripe.com/docs/payments and distill it into compact markdown — use budget mode with a focus query on 'payment intents' and cap it at 2000 tokens so I'm not wasting LLM budget.","exampleUseCases":[{"title":"Token-efficient doc lookup for agent","prompt":"Fetch https://docs.openai.com/api-reference and distill it into structured markdown — I want to stay under 1500 tokens, so use budget mode with the query 'function calling'."},{"title":"Competitor landing page intelligence","prompt":"Pull the content from https://anthropic.com and convert it to clean markdown so I can analyze it without blowing my token budget."},{"title":"SEC filing extraction for research","prompt":"Distill https://www.sec.gov/cgi-bin/browse-edgar?action=getcompany&CIK=TSLA&type=10-K into skeleton mode so I can see the outline of their latest 10-K filing quickly."}],"resultDescription":"Returns a JSON object with distilled content (Markdown text, structured JSON tables/metadata, skeleton outline, or BM25-focused excerpt depending on mode), plus an roi_proof block showing raw vs distilled token counts, compression ratio percentage, tokens saved, and estimated LLM cost saved in USD. Also includes cache status (HIT/MISS) and billing details.","failureModes":["Invalid or unreachable URL returns an error status","Target page blocks crawlers or requires authentication, returning empty or partial content","max_tokens set too low may yield truncated or empty budget excerpts","BM25 query with no relevant matches returns minimal content","Rate limiting or payment failure causes 402 response","Malformed HTML input may produce garbled Markdown output"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to read web content but wants to minimize token consumption and LLM costs — especially useful for long documentation pages, research articles, or any URL where raw HTML would be prohibitively large. The BM25 budget mode is uniquely valuable when you need topically focused excerpts within a strict token ceiling. Prefer it over generic web scrapers when token ROI reporting and cost savings measurement matter to your workflow.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:24:30.305Z","isFirstParty":false,"canonicalSlug":"defi-yield-agentdiet-dev-url-to-markdown-web-distiller-with-bm25-67085b9b"}