{"uid":"cap_x16fQrKp_oFa8OYLliPMm","slug":"github-audit-agentdiet-dev-web-url-distillation-bm25-budget-a148e2f1","name":"Web URL Distillation & BM25 Budget Extraction API","description":"Distill a URL or raw HTML payload with BM25 budget control (Live x402 v2, IETF MPP & MCP endpoint at https://github-audit.agentdiet.dev/v1/paywall-clean-extract)","url":"https://github-audit.agentdiet.dev/v1/paywall-clean-extract?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_oWa3JNYTVFtp_4tSkqliA","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"github-audit.agentdiet.dev","brandSlug":"github-audit-agentdiet-dev-mpp","brandBaseUrl":"https://github-audit.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches a webpage URL (or raw HTML) and distills it into compact, agent-ready tokens with configurable extraction modes including BM25-focused budget control.","exampleAgentPrompt":"Fetch the page at https://stripe.com/docs/payments and distill it into clean markdown, keeping it under 1500 tokens and focusing on the query 'payment intents setup'.","exampleUseCases":[{"title":"Token-budget research on a long doc page","prompt":"Grab https://docs.openai.com/api-reference and compress it into no more than 800 tokens using budget mode, focusing on the query 'streaming responses'."},{"title":"Structured data extraction from an e-commerce page","prompt":"Pull the page at https://example-shop.com/products/widget-pro and extract it in structured mode so I get the prices, variants, and metadata as JSON."},{"title":"Skeleton outline of a lengthy article","prompt":"Distill https://en.wikipedia.org/wiki/Large_language_model into a skeleton outline so I can quickly see the headings and structure without reading the whole thing."}],"resultDescription":"Returns a 'data' 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, estimated LLM cost saved in USD, and a ROI multiplier. Also includes cache status (HIT/MISS) and billing info.","failureModes":["URL is unreachable or returns non-200 — fetch error returned","Paywalled page blocks fetch — may return truncated or empty content","max_tokens set below minimum of 20 — validation error","BM25 query provided but mode is not 'budget' — query may be ignored","Raw HTML too large — may hit size limits or timeout","Invalid URL format — parameter validation error"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to read web content but must stay within a token budget, or when raw HTML needs to be cleaned and structured for downstream processing. It is especially useful when scraping long documentation pages, product catalogs, or articles where full-page ingestion would be prohibitively expensive. Prefer it over general scrapers when you need BM25-ranked relevance filtering or quantified compression ROI metrics.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:22:16.815Z","isFirstParty":false,"canonicalSlug":"github-audit-agentdiet-dev-web-url-distillation-bm25-budget-a148e2f1"}