{"uid":"cap_bWfYzdVre9mU8p22u2qjy","slug":"polymarket-odds-agentdiet-dev-web-url-html-distiller-with-bm25-budget-3420977b","name":"Web URL 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/clean-html)","url":"https://polymarket-odds.agentdiet.dev/v1/clean-html?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_cjV4TyRukDx349_yNBIMh","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 raw HTML and distills it into compact, agent-ready tokens using configurable modes including markdown, structured, skeleton, or BM25-focused budget extraction","exampleAgentPrompt":"Can you distill https://stripe.com/docs/api into clean markdown and keep it under 2000 tokens, focusing on the authentication section?","exampleUseCases":[{"title":"LLM cost-efficient news article extraction","prompt":"Fetch https://techcrunch.com/2025/01/15/ai-funding-roundup and distill it into markdown under 800 tokens, using BM25 budget mode focused on 'AI startup funding rounds'."},{"title":"Structured data extraction from a pricing page","prompt":"Grab https://openai.com/pricing and distill it into structured JSON tables so I can compare model prices without wasting tokens on all the surrounding page content."},{"title":"Skeleton outline of lengthy documentation","prompt":"Take https://docs.aws.amazon.com/s3/index.html and give me a skeleton outline of the page structure so I can decide which section to dig into next."}],"resultDescription":"Returns a distilled version of the webpage in the requested format (markdown, structured JSON, skeleton, or BM25 budget excerpt), along with ROI proof metrics including raw token count, distilled token count, tokens saved, compression ratio percentage, and estimated LLM cost saved in USD. Also includes cache status and billing info.","failureModes":["URL is unreachable or returns non-200 — status error with no data","HTML payload too large or malformed — parsing failure","max_tokens set below minimum of 20 — validation error","mode=budget used without a query parameter — may return unfiltered or degraded output","Rate limiting or payment failure via x402 — 402 response with payment requirements"],"whenToPreferThis":"Choose this endpoint when you need to reduce token costs before passing web content to an LLM, when you want BM25-focused relevance filtering to extract only query-relevant content from a large page, or when you need structured or skeleton extraction from arbitrary URLs. Prefer this over general-purpose scrapers when token budget control and ROI tracking matter, or when you need multiple distillation modes (markdown, structured, skeleton, budget) from a single service.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:21:55.472Z","isFirstParty":false,"canonicalSlug":"polymarket-odds-agentdiet-dev-web-url-html-distiller-with-bm25-budget-3420977b"}