{"uid":"cap_VByTDaaUUXLFC5KzTPzo8","slug":"polymarket-odds-agentdiet-dev-web-page-distiller-with-bm25-budget-9b8623fb","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://polymarket-odds.agentdiet.dev/v1/dom-stripper)","url":"https://polymarket-odds.agentdiet.dev/v1/dom-stripper?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_kWKIDfs0SF6Ix9ohRo_N-","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 Markdown, structured JSON, a skeleton outline, or a BM25-ranked token-budget excerpt focused on a query","exampleAgentPrompt":"Can you distill https://stripe.com/docs/payments into clean Markdown and keep it under 2000 tokens, focusing on the query 'payment intents'?","exampleUseCases":[{"title":"LLM cost-efficient doc summarization","prompt":"Pull the content from https://docs.openai.com/api-reference and distill it down to under 1500 tokens using budget mode, focused on the query 'embeddings API'."},{"title":"Structured product catalog extraction","prompt":"Take the HTML from this Shopify page and distill it into structured JSON tables with prices and product variants — here's the raw HTML: <html>...</html>."},{"title":"Webpage skeleton for navigation","prompt":"Fetch https://en.wikipedia.org/wiki/Artificial_intelligence and give me a skeleton outline of the page so I can see the main sections without all the detail."}],"resultDescription":"Returns a 'data' object containing the distilled content in the requested format (Markdown text, structured JSON tables/metadata, skeleton outline, or BM25-ranked excerpt), along with an 'roi_proof' object showing raw vs distilled token counts, tokens saved, compression ratio percentage, ROI multiplier, and estimated LLM cost saved in USD. Also includes cache status (HIT/MISS) and billing metadata.","failureModes":["URL is unreachable or returns non-200 status — endpoint may error or return empty content","HTML payload is malformed or too large — may fail parsing","mode=budget used without a 'query' field — BM25 ranking cannot execute","max_tokens set below minimum of 20 — validation error","Rate limiting or payment failure via x402 — HTTP 402 returned","Target page is JavaScript-rendered SPA with no static HTML — distillation may miss dynamic content"],"whenToPreferThis":"Choose this endpoint when you need to reduce the token footprint of a webpage before passing it to an LLM, especially when you want BM25-ranked excerpts focused on a specific query. Prefer it over generic scrapers when token budget control and compression ROI reporting matter. It is particularly useful for AI agent pipelines that need cost-efficient web context ingestion without building their own HTML parsing layer.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:30:53.756Z","isFirstParty":false,"canonicalSlug":"polymarket-odds-agentdiet-dev-web-page-distiller-with-bm25-budget-9b8623fb"}