{"uid":"cap_6aqqTSFUHybOE2lqtnYyx","slug":"arxiv-digest-agentdiet-dev-url-to-markdown-distiller-with-bm25-budget-f9425a30","name":"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/url-to-markdown)","url":"https://arxiv-digest.agentdiet.dev/v1/url-to-markdown?utm_source=zero.xyz","method":"POST","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_n0zzJQHhGeuUbYpQrawte","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 accepts raw HTML and distills it into clean Markdown, structured JSON, skeleton outline, or a BM25-focused token-budgeted excerpt","exampleAgentPrompt":"Can you fetch https://arxiv.org/abs/2401.00001 and distill it into clean markdown, keeping it under 500 tokens and focused on the methodology section?","exampleUseCases":[{"title":"Research paper content extraction","prompt":"Grab the content from https://arxiv.org/abs/2401.12345 and distill it into markdown using budget mode with 'transformer architecture' as the focus query, keeping it under 800 tokens."},{"title":"Competitor landing page summarization","prompt":"Fetch https://www.openai.com/pricing and distill it into structured mode so I can see the tables and pricing tiers as clean JSON."},{"title":"Documentation ingestion for agent context","prompt":"Take the raw HTML I'm pasting here from Stripe's docs page and distill it into a skeleton outline so I can see the section structure without all the filler content."}],"resultDescription":"Returns a JSON object containing: the distilled content (Markdown, structured JSON, skeleton, or BM25 excerpt) in the 'data' field; an 'roi_proof' object showing raw_tokens, distilled_tokens, tokens_saved, compression_ratio_pct, and llm_cost_saved_usd; optional cache metadata (HIT/MISS, latency_ms); and billing details including fee charged (typically $0.001 USD).","failureModes":["URL is unreachable or returns non-200 HTTP status — endpoint may return error status","HTML payload is empty or malformed — distillation returns minimal or empty content","max_tokens ceiling too low to capture meaningful content — truncated or empty excerpt returned","BM25 query produces no relevant matches in budget mode — low-signal excerpt returned","Payment not processed or x402 auth fails — request rejected with 402 error","Rate limiting or timeout on fetching slow/large pages — partial or failed response"],"whenToPreferThis":"Choose this endpoint when you need to fetch and clean a webpage for LLM consumption while controlling token cost — especially when dealing with bloated HTML, needing BM25-focused excerpts within a strict token budget, or wanting structured JSON/skeleton output rather than raw HTML. It is distinct from generic scrapers because it provides LLM-optimized compression with quantified ROI metrics (tokens saved, cost saved). Prefer it over raw HTTP fetch when you need to fit web content into a context window economically.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:34:16.847Z","isFirstParty":false,"canonicalSlug":"arxiv-digest-agentdiet-dev-url-to-markdown-distiller-with-bm25-budget-f9425a30"}