{"uid":"cap_rHIYFHIcCQf4wfJvKtjIA","slug":"x402broker-com-webpage-distiller-with-bm25-budget-control-2faa938d","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://x402broker.com/v1/webpage-distiller)","url":"https://x402broker.com/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_3sTt_Q4-zQaJorywrxIsb","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"x402broker.com","brandSlug":"x402broker-com-mpp","brandBaseUrl":"https://x402broker.com","brandDocsUrl":null,"whatItDoes":"Fetches and distills any URL or raw HTML into clean Markdown, structured JSON, skeleton outline, or BM25-focused budget excerpt with token savings metrics","exampleAgentPrompt":"Fetch and distill https://docs.stripe.com/payments/payment-intents into clean markdown, and also give me a BM25-focused excerpt about webhook events with a max token budget of 500 tokens.","exampleUseCases":[{"title":"Token-efficient doc ingestion for agents","prompt":"Distill https://platform.openai.com/docs/guides/function-calling into markdown so I can feed it to my LLM without blowing my context window — show me how many tokens you saved."},{"title":"Focused competitor pricing research","prompt":"Fetch https://www.anthropic.com/pricing and extract only the parts about model pricing tiers using a BM25 query for 'API pricing per million tokens', with a max budget of 300 tokens."},{"title":"Structured data extraction from a webpage","prompt":"Pull https://en.wikipedia.org/wiki/List_of_S%26P_500_companies and distill it in structured mode so I get the tables and metadata as JSON rather than raw HTML."}],"resultDescription":"Returns a data object containing the distilled content (Markdown text, structured JSON tables/metadata, skeleton outline, or BM25-ranked excerpt depending on mode), plus an roi_proof block showing raw token count, distilled token count, tokens saved, compression ratio percentage, LLM cost saved in USD, and ROI multiplier. Also includes optional cache status (HIT/MISS) and billing details.","failureModes":["URL unreachable or returns non-200 status — fetch failure error","Invalid or malformed URL string — validation error","HTML payload too large to process within limits","BM25 budget mode used without a query parameter — missing required field error","max_tokens below minimum of 20 — schema validation error","Payment failure via x402 protocol — 402 response blocking execution","Timeout fetching slow or unresponsive URLs"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to consume webpage content within a tight token budget, wants BM25-ranked relevance filtering against a specific query, or needs structured/skeleton extraction rather than raw HTML. Especially valuable when LLM context costs matter and you want documented ROI proof of compression savings. Prefer over generic scrapers when you need token-aware distillation with cost accounting.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:30:35.451Z","isFirstParty":false,"canonicalSlug":"x402broker-com-webpage-distiller-with-bm25-budget-control-2faa938d"}