{"uid":"cap_V2VpOjgsqwmsLtpydLhjU","slug":"arxiv-digest-agentdiet-dev-web-content-distiller-with-bm25-budget-99089b82","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/article-extractor)","url":"https://arxiv-digest.agentdiet.dev/v1/article-extractor?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_eVT0ZEv0KP5JaAxw7IX1C","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 and distills a URL or raw HTML into Markdown, structured JSON, or a token-budgeted BM25 excerpt, returning compression metrics and ROI proof","exampleAgentPrompt":"Can you distill https://arxiv.org/abs/2310.06825 into clean markdown using budget mode, focused on the query 'transformer attention mechanisms', and cap it at 800 tokens?","exampleUseCases":[{"title":"Compress arXiv paper for LLM context","prompt":"Distill this arXiv paper URL https://arxiv.org/abs/2401.00123 into budget mode focused on 'retrieval augmented generation' and keep it under 1000 tokens so I can feed it to my LLM without blowing the context window."},{"title":"Extract structured tables from docs page","prompt":"Pull the structured tables and metadata out of https://stripe.com/docs/api in structured mode — I need the JSON output with all the pricing tiers and endpoint descriptions."},{"title":"Clean raw HTML for agent ingestion","prompt":"I have this big raw HTML blob from a product page — can you distill it down to clean markdown so my agent can read it without all the nav bars and ads?"}],"resultDescription":"Returns a 'data' object containing distilled content (Markdown text, structured JSON tables/metadata, skeleton outline, or BM25-ranked budget excerpt), an 'roi_proof' object with raw_tokens, distilled_tokens, tokens_saved, compression_ratio_pct, roi_multiplier, and llm_cost_saved_usd, plus optional cache hit/miss status and billing info.","failureModes":["URL is unreachable or returns non-200 — fetch error returned","HTML payload is empty or malformed — distillation fails with status error","max_tokens below minimum of 20 — validation error","mode=budget used without a query parameter — may return unranked or empty excerpt","Rate limit or payment failure via x402 — 402 response with payment instructions","URL contains no extractable text content (e.g. pure JavaScript SPA) — empty or minimal output"],"whenToPreferThis":"Choose this endpoint when you need to feed web content to an LLM and must control token costs — especially when you have a specific focus query and a hard token budget ceiling. It is distinct from generic scrapers because it provides BM25-ranked compression with quantified ROI metrics (tokens saved, LLM cost saved). Prefer it over raw fetch when content is verbose, when you need structured JSON tables from docs, or when you want a skeleton outline rather than full text. The built-in x402 micropayment model makes it suitable for high-frequency agent pipelines at $0.001 per call.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:30:26.233Z","isFirstParty":false,"canonicalSlug":"arxiv-digest-agentdiet-dev-web-content-distiller-with-bm25-budget-cb1848ab"}