{"uid":"cap_oEQEkuFs0YmDkXzxywxiR","slug":"x402-audit-agentdiet-dev-webpage-distiller-with-bm25-budget-control-8e458ac3","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://x402-audit.agentdiet.dev/v1/webpage-distiller)","url":"https://x402-audit.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_duiU6wB0ZK05qRdHI-jJC","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 a URL or raw HTML into compact, agent-ready tokens using BM25-ranked budget control to stay within a strict token ceiling","exampleAgentPrompt":"Can you distill https://stripe.com/docs/payments/accept-a-payment into compact markdown using budget mode, focused on 'accept a payment', and keep it under 800 tokens?","exampleUseCases":[{"title":"Documentation page within token budget","prompt":"Fetch https://docs.openai.com/api-reference/chat and distill it in budget mode focused on 'streaming responses', capped at 500 tokens — I need just the relevant parts without blowing my context window."},{"title":"Competitive pricing page research","prompt":"Distill https://www.anthropic.com/pricing into structured mode so I get the pricing tables and metadata in a clean format I can compare programmatically."},{"title":"Inline HTML cleanup for agent pipeline","prompt":"I have a raw HTML blob from a scraped product page — can you distill it into markdown so I can pass it to my LLM without all the nav and footer noise?"}],"resultDescription":"Returns a 'data' object containing distilled content (Markdown, structured JSON, skeleton outline, or BM25-ranked excerpt depending on mode), along with an 'roi_proof' object showing raw vs. distilled token counts, compression ratio, tokens saved, estimated LLM cost saved in USD, and ROI multiplier. Also includes optional cache status (HIT/MISS) and billing metadata.","failureModes":["URL is unreachable or returns non-200 — distillation fails with fetch error","max_tokens set below 20 — rejected by schema validation","mode=budget used without a query field — BM25 ranking has no focus term","Raw HTML provided is empty or malformed — distillation yields minimal output","Payment not authorized via x402 — 402 response blocking execution"],"whenToPreferThis":"Choose this endpoint when you need to read a webpage but must stay within a strict token budget, or when you want BM25-ranked relevance filtering so only the most query-relevant content is returned. It is especially valuable when piping web content into an LLM context window where cost and length matter. Prefer it over generic scrapers when you need token-count metrics, compression ROI, and multi-mode distillation (markdown, structured, skeleton, or budget) in a single call.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:34:05.916Z","isFirstParty":false,"canonicalSlug":"x402-audit-agentdiet-dev-webpage-distiller-with-bm25-budget-control-8e458ac3"}