{"uid":"cap_CnMNLUELQI8sjDFF98tB2","slug":"arxiv-digest-agentdiet-dev-web-url-distiller-with-bm25-budget-control-a8ea5c02","name":"Web URL 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/paywall-clean-extract)","url":"https://arxiv-digest.agentdiet.dev/v1/paywall-clean-extract?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_yyegRK4Teb-azQNGQnhzJ","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 tokens using configurable extraction modes and a strict token budget ceiling","exampleAgentPrompt":"Fetch the page at https://arxiv.org/abs/2401.00001 and distill it into compact markdown, keeping it under 500 tokens — focus on the abstract and contributions.","exampleUseCases":[{"title":"Research paper fast-read for agent","prompt":"Grab this arXiv paper at https://arxiv.org/abs/2310.06825 and distill it into markdown under 800 tokens, focusing on the methodology section."},{"title":"Cost-saving doc ingestion for LLM pipeline","prompt":"I need to feed the Stripe docs page https://stripe.com/docs/api/charges into my LLM but I'm worried about token costs — can you distill it using budget mode, capped at 1000 tokens?"},{"title":"Structured data extraction from product page","prompt":"Distill https://shop.example.com/products/widget-pro into structured JSON mode so I can pull out the price, variants, and availability without all the HTML noise."}],"resultDescription":"Returns a distilled data object (Markdown text, structured JSON tables/metadata, skeleton outline, or BM25-ranked excerpt depending on mode), along with ROI proof metrics including raw vs distilled token counts, compression ratio, estimated LLM cost saved, and optional cache hit/miss status and billing details.","failureModes":["Invalid or unreachable URL returns an error status","Paywalled or bot-blocked pages may return incomplete content","max_tokens too low (below 20) rejected with validation error","mode=budget without a query param may produce unfocused excerpts","Rate limiting or payment failure via x402 may block the call","Raw HTML too large may be truncated or timeout"],"whenToPreferThis":"Choose this endpoint when an agent needs to read a web page but must stay within a token budget, minimize LLM inference costs, or extract only query-relevant content via BM25 ranking. It is especially valuable for pipelines that process many URLs and need compression metrics (ROI proof) to justify the fetch cost. Prefer it over generic scrapers when you need structured output modes (markdown, JSON tables, skeleton) or when the target is documentation-style content.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:23:02.218Z","isFirstParty":false,"canonicalSlug":"arxiv-digest-agentdiet-dev-web-url-distiller-with-bm25-budget-control-044c0cc8"}