{"uid":"cap__ULhiEudrE6Sb1iI9YIFe","slug":"arxiv-digest-agentdiet-dev-web-content-distiller-with-bm25-budget-cb1848ab","name":"Web Content 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/clean-html)","url":"https://arxiv-digest.agentdiet.dev/v1/clean-html?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_gQd1kXY45glz7v8s4nbjQ","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-ranked token-budget excerpt","exampleAgentPrompt":"Distill the content at https://arxiv.org/abs/2301.00234 into clean markdown using budget mode, focused on the query 'transformer attention mechanisms', and keep it under 500 tokens.","exampleUseCases":[{"title":"Token-efficient research paper digest","prompt":"Grab this arxiv paper at https://arxiv.org/abs/2312.00752 and distill it into a BM25-focused excerpt about 'retrieval augmented generation', capped at 800 tokens, so I can feed it to my model without blowing my context window."},{"title":"Ad-free documentation extraction","prompt":"Fetch the Stripe docs page at https://stripe.com/docs/payments/payment-intents and give me a clean markdown version stripped of all navigation and boilerplate."},{"title":"Structured metadata from product page","prompt":"Take this raw HTML from a product listing and convert it into structured JSON tables with metadata — I need price, specs, and availability pulled out cleanly."}],"resultDescription":"Returns a JSON object with a 'data' field containing the distilled content (Markdown, structured JSON, skeleton, or BM25 excerpt), an 'roi_proof' object showing raw_tokens, distilled_tokens, tokens_saved, compression_ratio_pct, and llm_cost_saved_usd, optional cache hit/miss metadata, and billing details including fee charged in USD.","failureModes":["URL is unreachable or returns non-200 HTTP status — distillation fails with a fetch error","Raw HTML is empty or malformed beyond recovery — returns empty or minimal output","mode=budget used without providing a 'query' parameter — BM25 ranking cannot run","max_tokens set below 20 — rejected by schema validation","Payment not included or insufficient — HTTP 402 returned requiring x402 USDC payment","Target page is behind authentication or a JS-only SPA — content may be incomplete or empty"],"whenToPreferThis":"Choose this endpoint when you need to reduce token costs before passing web content to an LLM, when you need BM25-ranked focused excerpts from long pages, or when you want clean Markdown or structured JSON from arbitrary URLs without building your own scraper and parser pipeline. It is especially useful when context window limits require strict token budgeting, and it provides ROI proof showing exactly how many tokens and dollars were saved.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:32:11.324Z","isFirstParty":false,"canonicalSlug":"arxiv-digest-agentdiet-dev-web-content-distiller-with-bm25-budget-cb1848ab"}