{"uid":"cap_L9N9abncWafsTjhjxBfp4","slug":"arxiv-digest-agentdiet-dev-web-url-to-markdown-distiller-with-bm25-4fab9d63","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://arxiv-digest.agentdiet.dev/v1/markdown-distill)","url":"https://arxiv-digest.agentdiet.dev/v1/markdown-distill?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_a_Rp9oVh8m6ZK-KspFeiz","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 URL or raw HTML and distills it into compact, agent-ready Markdown, structured JSON, skeleton outline, or BM25-focused token-budgeted excerpts","exampleAgentPrompt":"Distill the content at https://stripe.com/docs/payments into compact markdown using budget mode, focused on 'payment intents', and keep it under 500 tokens.","exampleUseCases":[{"title":"Compress documentation page for agent context","prompt":"Fetch https://docs.openai.com/api-reference and distill it into compact markdown so I can stuff it into my agent's context without blowing the token limit."},{"title":"BM25-focused research excerpt from arXiv paper","prompt":"Grab https://arxiv.org/abs/2305.10601 and extract only the parts most relevant to 'retrieval augmented generation' using budget mode, capped at 300 tokens."},{"title":"Structured data extraction from a product page","prompt":"Distill https://www.shopify.com/pricing into structured JSON tables so I can see all the pricing tiers and features in a clean format."}],"resultDescription":"Returns a JSON object with a 'data' field containing the distilled content (Markdown text, structured tables/metadata, skeleton outline, or BM25 excerpt depending on mode), plus an 'roi_proof' object showing raw token count, distilled token count, tokens saved, compression ratio percentage, LLM cost saved in USD, and ROI multiplier. Also includes optional cache status (HIT/MISS) and billing details.","failureModes":["Invalid or unreachable URL returns an error status","HTML too large or malformed may cause incomplete distillation","BM25 budget mode with no query string may return unfiltered or generic content","max_tokens set below 20 will be rejected by schema validation","Payment failure via x402 prevents the call from completing","Paywalled or bot-blocked pages may return empty or minimal content"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to read and process web pages but must stay within a tight token budget, or when you want structured/markdown output from raw HTML without implementing your own parser. It is especially valuable when you need BM25 relevance-focused excerpting to retrieve only the most query-relevant content from a long page, minimizing LLM inference costs. Prefer it over generic scrapers when you need built-in compression metrics (ROI proof) and multiple distillation modes in a single API call.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:25:51.738Z","isFirstParty":false,"canonicalSlug":"arxiv-digest-agentdiet-dev-web-url-to-markdown-distiller-with-bm25-0d5088d9"}