{"uid":"cap_fVA0pONKx86VyXaNhOZab","slug":"arxiv-digest-agentdiet-dev-web-url-to-markdown-distiller-with-bm25-ac7eeee6","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/docs-to-markdown)","url":"https://arxiv-digest.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_Nhyw9TUVSILzKnJaiO3If","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 webpage or raw HTML and distills it into compact, agent-ready Markdown or structured output with optional BM25-ranked token budgeting","exampleAgentPrompt":"Can you fetch the Stripe docs page at https://docs.stripe.com/payments/quickstart and distill it into clean markdown, keeping it under 1000 tokens using budget mode with the query 'payment intent setup'?","exampleUseCases":[{"title":"Documentation page for agent context","prompt":"Pull the OpenAI API reference page at https://platform.openai.com/docs/api-reference and distill it into compact markdown so I can include it in my agent's system prompt without blowing the token limit."},{"title":"Focused research extraction with BM25","prompt":"I need only the section about 'rate limiting' from https://docs.anthropic.com/claude/reference — use budget mode with that query and cap it at 500 tokens so it fits neatly into my pipeline."},{"title":"Structured data from a product page","prompt":"Take this e-commerce page https://example-store.com/products/widget and extract it in structured mode so I get the product name, price, and specs as clean JSON rather than raw HTML."}],"resultDescription":"Returns a JSON object with a 'data' field containing the distilled content (Markdown text, structured JSON tables, skeleton outline, or BM25-ranked excerpt depending on mode), an 'roi_proof' object showing raw token count, distilled token count, tokens saved, compression ratio percentage, and estimated LLM cost saved in USD, plus an optional 'cache' object indicating HIT/MISS status and latency.","failureModes":["URL is unreachable or returns non-200 HTTP status — endpoint may return an error status","Provided HTML is malformed or empty — distillation may produce minimal or empty output","max_tokens ceiling set too low (below 20) — request rejected by schema validation","mode=budget used without a query parameter — BM25 ranking cannot focus without a query","Payment not attached or insufficient — HTTP 402 returned with payment required details","Rate limiting or timeout on the remote URL — fetch may fail with a timeout error"],"whenToPreferThis":"Choose this endpoint when you need to feed webpage content to an LLM but want to minimize token usage and cost — especially when working with long documentation pages, product pages, or any URL whose raw HTML is too large to pass directly. The BM25 budget mode is particularly valuable when you only need a specific section of a large page. Prefer this over generic scrapers when you need built-in compression ratio reporting and cost-savings proof alongside the content.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:26:17.837Z","isFirstParty":false,"canonicalSlug":"arxiv-digest-agentdiet-dev-web-url-to-markdown-distiller-with-bm25-0d5088d9"}