{"uid":"cap_VRiF6UpKF8rHYpsWnhWPX","slug":"polymarket-odds-agentdiet-dev-webpage-distiller-with-bm25-budget-2fcbd29b","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://polymarket-odds.agentdiet.dev/v1/webpage-distiller)","url":"https://polymarket-odds.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_AiycM5Gj-w5Swkssy19vu","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 and distills a URL or raw HTML into compact Markdown, structured JSON, outline skeleton, or BM25-focused budget excerpt with token savings metrics","exampleAgentPrompt":"Fetch https://stripe.com/docs/payments and distill it into clean markdown using budget mode focused on the query 'payment intents', capped at 2000 tokens — I want to see how many tokens you saved me.","exampleUseCases":[{"title":"Summarize competitor pricing page","prompt":"Go to https://www.notion.so/pricing and distill it into structured mode so I can see pricing tiers, plan names, and features as clean JSON tables."},{"title":"BM25 budget extraction for RAG pipeline","prompt":"Distill https://docs.openai.com/api-reference into budget mode with the query 'rate limits' and a max of 1500 tokens — I need just the relevant sections without blowing my context window."},{"title":"Convert raw HTML snippet to Markdown","prompt":"I have a raw HTML blob from a scraped article — can you distill it directly into clean markdown without fetching anything? Here's the HTML: <html>...</html>"}],"resultDescription":"Returns a 'data' object containing the distilled content (Markdown text, structured JSON tables/metadata, outline skeleton, or BM25-focused 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 cache hit/miss status and billing details.","failureModes":["Invalid or unreachable URL returns fetch error with non-ok status","HTML too large or malformed may result in truncated or empty distillation","max_tokens set too low (below 20) triggers schema validation error","query field ignored unless mode=budget is specified","Rate limiting or payment failure (402) if x402 payment not attached","Timeout on slow-loading or JavaScript-heavy pages that require rendering"],"whenToPreferThis":"Choose this endpoint when you need to compress web content to fit inside LLM context windows, especially when you want token savings metrics (ROI proof) alongside the distilled content. It is particularly valuable when you have a specific BM25 query and want only the most relevant excerpt from a large page (budget mode), or when you need structured tables/metadata extracted from a product or documentation page. Prefer it over generic scrapers when token efficiency and cost savings are a priority for your agent pipeline.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:31:58.020Z","isFirstParty":false,"canonicalSlug":"polymarket-odds-agentdiet-dev-webpage-distiller-with-bm25-budget-2fcbd29b"}