{"uid":"cap_wLati23GZEbOaaUvgM_Xx","slug":"polymarket-odds-agentdiet-dev-semantic-html-pruner-web-url-distiller-403081d4","name":"Semantic HTML Pruner – Web URL Distiller","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/semantic-html-pruner)","url":"https://polymarket-odds.agentdiet.dev/v1/semantic-html-pruner?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_qMZTBXUqndEYdiWkbhTQO","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 accepts raw HTML) and distills it into compact, agent-ready tokens using BM25 budget control and multiple extraction modes","exampleAgentPrompt":"Fetch https://stripe.com/docs/payments and distill it into compact markdown, keeping it under 2000 tokens and focusing on the query 'payment intent lifecycle'.","exampleUseCases":[{"title":"Distill docs page for RAG pipeline","prompt":"Pull https://docs.openai.com/api-reference and compress it into structured markdown under 1500 tokens so I can stuff it into my retrieval pipeline without blowing my context window."},{"title":"Extract tables from financial report","prompt":"Fetch https://example.com/annual-report-2024.html and extract it in structured mode so I get all the tables and metadata as JSON — I need the revenue figures."},{"title":"Budget-capped research on a news article","prompt":"Distill https://www.reuters.com/technology/ai-regulation-2024 using budget mode with a max of 500 tokens, focused on the query 'EU AI Act compliance requirements'."}],"resultDescription":"Returns a 'data' object containing the distilled content (Markdown string, structured JSON tables/metadata, skeleton outline, or BM25-ranked excerpt depending on mode), plus 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 metadata.","failureModes":["Invalid or unreachable URL returns fetch error","mode=budget requires query and max_tokens or falls back to defaults","Raw HTML too large may exceed processing limits","Paywalled or JS-rendered pages may return incomplete content","Missing required 'url' parameter returns 400 validation error","Token budget too small (below 20) rejected by schema validation"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to read a webpage but wants to minimize LLM token consumption and cost. Ideal when the raw HTML is too verbose for a context window, when only a specific section of a page is relevant (use budget mode with a query), or when structured extraction of tables and metadata is needed. Prefer over generic scraping tools when token efficiency and ROI reporting are important.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:21:02.407Z","isFirstParty":false,"canonicalSlug":"polymarket-odds-agentdiet-dev-semantic-html-pruner-web-url-distiller-403081d4"}