{"uid":"cap_YEUU8DFyKUed9JvjFyDM4","slug":"x402-audit-agentdiet-dev-webpage-distiller-bm25-token-budget-web-7c931665","name":"Webpage Distiller – BM25 Token Budget Web Content Extractor","description":"Distill a URL or raw HTML payload with BM25 budget control (Live x402 v2, IETF MPP & MCP endpoint at https://x402-audit.agentdiet.dev/v1/webpage-distiller)","url":"https://x402-audit.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_LpUOKTbclKSuMTdHTnUEg","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"x402-audit.agentdiet.dev","brandSlug":"x402-audit-agentdiet-dev-mpp","brandBaseUrl":"https://x402-audit.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches and distills any URL or raw HTML into compact, agent-ready tokens using multiple extraction modes including BM25 budget-controlled focus excerpts","exampleAgentPrompt":"Distill https://stripe.com/docs/payments into compact markdown tokens using budget mode focused on 'payment intents', capped at 500 tokens, so I can read it without blowing my context window.","exampleUseCases":[{"title":"Docs page for agent context injection","prompt":"Grab the Stripe docs page at builtin://stripe-docs and distill it into structured mode so I can pull out the key tables and metadata without loading the whole thing into my context."},{"title":"Token-budget excerpt for research query","prompt":"I need to read https://en.wikipedia.org/wiki/Large_language_model but I only have room for 300 tokens — distill it in budget mode focused on 'transformer architecture' so I get the most relevant parts."},{"title":"Clean markdown from messy product page","prompt":"Take https://www.apple.com/iphone/ and convert it to clean markdown so I can see the product info without all the nav menus, ads, and JavaScript noise."}],"resultDescription":"Returns a JSON object with a 'data' field containing the distilled content (Markdown, structured JSON tables/metadata, skeleton outline, or BM25-focused excerpt depending on mode), plus an 'roi_proof' object showing raw_tokens, distilled_tokens, tokens_saved, compression_ratio_pct, and llm_cost_saved_usd. Also includes cache status (HIT/MISS) and billing metadata.","failureModes":["Invalid or unreachable URL returns an error status","URL behind authentication or paywalls may return incomplete or empty content","Very large pages may hit timeout before full distillation","BM25 budget mode with no matching query terms may return sparse results","max_tokens set too low may truncate critical content","Raw HTML input that is malformed may produce garbled markdown output"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to ingest web content but must stay within a token budget — particularly for LLM pipelines where raw HTML would be too expensive or noisy. Prefer this over generic scrapers when you need BM25-focused relevance extraction, compression ratio reporting, or structured/skeleton output modes. Ideal for documentation ingestion, research summarization, and cost-aware web retrieval in agentic workflows.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:25:58.662Z","isFirstParty":false,"canonicalSlug":"x402-audit-agentdiet-dev-webpage-distiller-bm25-token-budget-web-7c931665"}