{"uid":"cap_bhWVfZXQCkf7a7JI5iEko","slug":"serp-extract-agentdiet-dev-web-page-distiller-with-bm25-budget-control-3ec9b410","name":"Web Page 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://serp-extract.agentdiet.dev/v1/paywall-clean-extract)","url":"https://serp-extract.agentdiet.dev/v1/paywall-clean-extract?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_N9PP_vn0pFiVSaJpL8D9e","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"serp-extract.agentdiet.dev","brandSlug":"serp-extract-agentdiet-dev-mpp","brandBaseUrl":"https://serp-extract.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches and distills a URL or raw HTML into markdown, structured data, skeleton, or BM25-ranked token-budget excerpts","exampleAgentPrompt":"Pull the main content from https://techcrunch.com/2025/01/15/openai-funding/ and distill it into clean markdown, keeping it under 800 tokens using budget mode with the query 'OpenAI funding round valuation'.","exampleUseCases":[{"title":"Token-budget research page extraction","prompt":"Fetch https://en.wikipedia.org/wiki/Large_language_model and give me only the sections most relevant to 'transformer architecture training', keeping the output under 500 tokens using budget mode."},{"title":"Structured data extraction from HTML","prompt":"I have this raw HTML from a product page — can you distill it into structured JSON tables and metadata so I can see the pricing, specs, and reviews cleanly?"},{"title":"Clean markdown from paywalled article","prompt":"Distill https://www.wsj.com/articles/some-article-slug into clean markdown so I can read the actual content without all the navigation, ads, and boilerplate cluttering it up."}],"resultDescription":"Returns a JSON object containing the distilled content (markdown text, structured JSON tables/metadata, skeleton outline, or BM25-ranked excerpt depending on mode), an ROI proof block showing raw vs. distilled token counts, compression ratio, tokens saved, and estimated LLM cost saved in USD, plus cache status (HIT/MISS) and billing details including fee charged.","failureModes":["URL unreachable or returns non-200 — fetch failure error","HTML too large or malformed — parsing error","max_tokens too small to extract meaningful content — budget underflow","BM25 query missing when mode=budget — validation error","Rate limit exceeded — 429 response","Payment failure via x402 — 402 response with payment details"],"whenToPreferThis":"Choose this endpoint when you need to reduce token consumption by extracting only the relevant content from a URL or HTML blob before passing it to an LLM. It is especially valuable when operating under strict token budgets (use budget mode with a BM25 query), when you need structured tables or metadata from a page (structured mode), or when you want a navigable outline of a long document (skeleton mode). Prefer it over generic scrapers when ROI metrics and token compression reporting matter to your pipeline.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:32:42.672Z","isFirstParty":false,"canonicalSlug":"serp-extract-agentdiet-dev-web-page-distiller-with-bm25-budget-control-705ae0b1"}