{"uid":"cap_CMqh0IluVzbZdT6O0NQcf","slug":"arxiv-digest-agentdiet-dev-webpage-distiller-with-bm25-budget-control-3d550eea","name":"Webpage 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/webpage-distiller)","url":"https://arxiv-digest.agentdiet.dev/v1/webpage-distiller?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_Y_K3lQIM9Iv1z_9nQN6dq","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 clean Markdown, structured JSON, skeleton outline, or a BM25-ranked 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 focusing on the methodology section?","exampleUseCases":[{"title":"Research paper extraction for LLM context","prompt":"Grab this arXiv paper at https://arxiv.org/abs/2312.00752 and distill it in budget mode with the query 'transformer attention mechanism', keeping it under 800 tokens so I can fit it in my prompt."},{"title":"Structured data extraction from a product page","prompt":"Take this product page HTML I have and distill it in structured mode to pull out all the tables and metadata — here's the raw HTML: <html>...</html>."},{"title":"Lightweight webpage skeleton for navigation agent","prompt":"Fetch https://stripe.com/docs/payments and give me just a skeleton outline of the page structure so I can understand the navigation without burning through my token budget."}],"resultDescription":"Returns a JSON object with a 'data' field containing the distilled content (Markdown string, structured JSON tables/metadata, skeleton outline, or BM25-ranked excerpt depending on mode), plus an 'roi_proof' object showing raw vs distilled token counts, compression ratio percentage, tokens saved, and estimated LLM cost saved in USD. Optionally includes cache hit/miss status and billing details.","failureModes":["URL is unreachable or returns a non-200 response — endpoint may return an error status","Raw HTML is malformed or empty — distillation may return sparse or empty data","max_tokens is too low to return meaningful content — may truncate to minimum viable output","BM25 query in budget mode finds no relevant passages — returns lowest-scoring available content","Rate limiting or payment failure — returns HTTP 402 if payment is not provided or insufficient"],"whenToPreferThis":"Choose this endpoint when you need to inject web content into an LLM prompt and want to minimize token consumption, or when you need BM25-focused retrieval from a webpage given a specific query. It is especially valuable over raw HTML fetching or generic scrapers when token cost, context window limits, or structured extraction are primary concerns. The BM25 budget mode is uniquely suited for RAG pipelines where only topically relevant passages are needed.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:36:57.916Z","isFirstParty":false,"canonicalSlug":"arxiv-digest-agentdiet-dev-webpage-distiller-with-bm25-budget-control-3d550eea"}