{"uid":"cap_bR1QobR9lSW7hteN1WfBz","slug":"arxiv-digest-agentdiet-dev-webpage-distiller-bm25-budget-controlled-6ea1bd51","name":"Webpage Distiller – BM25 Budget-Controlled Web Content Extractor","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":"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_ovgsFXK7nzTFjtZhZY81h","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 any URL or raw HTML into compact, agent-ready tokens using configurable modes including markdown, structured, skeleton, and BM25 budget extraction","exampleAgentPrompt":"Distill the content at https://stripe.com/docs/payments into compact markdown, keeping it under 800 tokens, focused on 'payment intents'.","exampleUseCases":[{"title":"LLM context-window budget for research","prompt":"Fetch https://arxiv.org/abs/2304.01373 and distill it into budget mode with a max of 500 tokens, focusing the BM25 query on 'transformer attention mechanisms' — I need just the relevant bits."},{"title":"Structured product data from e-commerce page","prompt":"Pull https://www.apple.com/shop/buy-iphone and distill it in structured mode so I get a clean JSON table of iPhone models, prices, and storage options."},{"title":"Quick skeleton outline of a docs page","prompt":"Can you grab https://docs.openai.com/api-reference and give me a skeleton outline so I can see the top-level sections without reading the whole thing?"}],"resultDescription":"Returns a JSON object containing the distilled content (markdown text, structured JSON tables/metadata, skeleton outline, or BM25-ranked excerpt depending on mode), along with ROI proof metrics including raw token count, distilled token count, tokens saved, compression ratio percentage, LLM cost saved in USD, and an ROI multiplier. Also includes optional cache hit/miss status and billing details.","failureModes":["URL is unreachable or returns a non-200 status — endpoint may return an error status","Raw HTML too large and no token budget set — may result in oversized output","Invalid mode enum value — API rejects with validation error","max_tokens below minimum of 20 — rejected by schema validation","BM25 query missing when mode=budget — results may be unfiltered","Payment not provided or insufficient — HTTP 402 returned blocking the response"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to read web content but must stay within a token budget, or when raw HTML is too verbose to pass directly to an LLM. Particularly valuable over generic scrapers when you need BM25-focused extraction (retrieve only query-relevant sections), structured JSON output from unstructured HTML, or verifiable compression metrics (ROI proof). Prefer over browser automation tools when you just need readable content, not JavaScript interaction.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:26:17.256Z","isFirstParty":false,"canonicalSlug":"arxiv-digest-agentdiet-dev-webpage-distiller-bm25-budget-controlled-6ea1bd51"}