{"uid":"cap_TvO1QcIIvtuFcGWaAr3CS","slug":"polymarket-odds-agentdiet-dev-web-article-html-distiller-with-bm25-2cf7908d","name":"Web Article & HTML 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://polymarket-odds.agentdiet.dev/v1/article-extractor)","url":"https://polymarket-odds.agentdiet.dev/v1/article-extractor?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_CysVwxZ60Hdno0uQb49C4","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"polymarket-odds.agentdiet.dev","brandSlug":"polymarket-odds-agentdiet-dev-mpp","brandBaseUrl":"https://polymarket-odds.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches a URL or processes raw HTML and distills it into markdown, structured JSON, skeleton outline, or a BM25-ranked token-budget excerpt","exampleAgentPrompt":"Pull the main article content from https://techcrunch.com/2024/05/01/openai-gpt-5/ and distill it into clean markdown, keeping it under 1000 tokens focused on the topic of model capabilities.","exampleUseCases":[{"title":"Research article extraction for LLM context","prompt":"Grab the full article from https://www.wired.com/story/ai-agents-future-work/ and distill it into clean markdown so I can paste it into my research prompt without all the nav menus and ads."},{"title":"Token-budget web page summarization","prompt":"Fetch https://stripe.com/docs/payments/payment-intents and extract only the parts most relevant to 'webhook event handling', keeping the result under 500 tokens so it fits in my context window."},{"title":"Structured data extraction from product page","prompt":"Take this HTML I've pasted and extract it in structured mode so I get the tables, metadata, and key fields as JSON rather than a wall of text."}],"resultDescription":"Returns a JSON object with a 'data' field containing the distilled content (markdown string, structured JSON tables/metadata, skeleton outline, or BM25-ranked excerpt depending on mode), along with an 'roi_proof' object showing raw_tokens, distilled_tokens, tokens_saved, compression_ratio_pct, roi_multiplier, and llm_cost_saved_usd. Also includes cache status (HIT/MISS) and billing details.","failureModes":["URL unreachable or returns non-200 — endpoint may return an error status","Paywalled or JS-rendered pages may yield empty or partial content","Token budget too low (below 20) — rejected by schema validation","HTML too large or malformed — distillation may be incomplete","BM25 query not provided when mode=budget — may fall back to default behavior","Payment failure via x402 — call blocked before execution"],"whenToPreferThis":"Choose this endpoint when you need to extract clean, readable content from a URL or raw HTML while controlling token consumption — especially when the full page would overflow an LLM context window. The BM25 budget mode is uniquely useful for query-focused extraction: you supply a query and a max_tokens ceiling and get back only the most relevant passages. Prefer this over generic scrapers when you need ROI metrics on compression, or when you want structured JSON tables/metadata rather than raw HTML. Also useful when you already have raw HTML and want to skip the fetch step.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:36:41.710Z","isFirstParty":false,"canonicalSlug":"polymarket-odds-agentdiet-dev-web-article-html-distiller-with-bm25-2cf7908d"}