{"uid":"cap_lt8Pe63PZBRwTZnX9ahYy","slug":"arxiv-digest-agentdiet-dev-url-to-markdown-web-distiller-with-bm25-9278c661","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://arxiv-digest.agentdiet.dev/v1/url-to-markdown)","url":"https://arxiv-digest.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_d9ctJLLi2xN1rMMCyhx4i","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"arxiv-digest.agentdiet.dev","brandSlug":"arxiv-digest-agentdiet-dev-mpp","brandBaseUrl":"https://arxiv-digest.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches a web URL (or accepts raw HTML) and converts it into compact, agent-ready Markdown or structured output with token budget enforcement and BM25-based relevance filtering","exampleAgentPrompt":"Fetch https://arxiv.org/abs/2406.01234 and distill it into compact markdown using budget mode with a focus query on 'transformer attention mechanisms' and a max of 500 tokens.","exampleUseCases":[{"title":"Research paper digest for agent","prompt":"Go to https://arxiv.org/abs/2405.12345 and distill it into markdown — I want a tight summary, max 800 tokens, focused on the methodology section."},{"title":"Competitor pricing page extraction","prompt":"Fetch https://www.competitor.com/pricing and convert it to structured JSON tables so I can see their pricing tiers clearly without all the extra HTML noise."},{"title":"Skeleton outline of documentation","prompt":"Pull https://docs.stripe.com/api and give me just a skeleton outline of the page so I can quickly see what sections exist without reading the whole thing."}],"resultDescription":"Returns a JSON object containing distilled content (Markdown text, structured JSON tables/metadata, skeleton outline, or BM25-filtered 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 indicator (HIT/MISS).","failureModes":["Invalid or unreachable URL returns an error status","Target site blocks scraping with 403/bot detection, returning fetch failure","Token budget too small (below 20) for meaningful content extraction","Raw HTML input malformed or empty leading to empty distillation output","Rate limiting or payment failure via x402 if USDC balance insufficient","mode=budget without a query may produce suboptimal BM25 filtering"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to ingest web content but must stay within a token budget — particularly when feeding live web pages into an LLM context window. It is ideal over generic web scrapers when you need BM25 relevance filtering (mode=budget with a query), structured JSON table extraction, or skeleton outlines rather than raw HTML dumps. Prefer it when token cost and compression ROI matter, since it returns explicit metrics on tokens saved and LLM cost avoided.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:21:29.026Z","isFirstParty":false,"canonicalSlug":"arxiv-digest-agentdiet-dev-url-to-markdown-web-distiller-with-bm25-9278c661"}