{"uid":"cap_ieD2va48RAeEVVE9d2IPv","slug":"domain-osint-agentdiet-dev-web-page-html-distiller-with-bm25-budget-af749961","name":"Web Page & 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://domain-osint.agentdiet.dev/v1/clean-html)","url":"https://domain-osint.agentdiet.dev/v1/clean-html?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_AzcESMpTK4dJdpRbbLgVF","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"domain-osint.agentdiet.dev","brandSlug":"domain-osint-agentdiet-dev-mpp","brandBaseUrl":"https://domain-osint.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches a URL or accepts raw HTML and distills it into clean Markdown, structured JSON, skeleton outline, or a token-budget BM25 excerpt","exampleAgentPrompt":"Can you fetch https://stripe.com/docs/api and distill it into clean markdown using budget mode, focused on the query 'payment intents', with a max of 500 tokens?","exampleUseCases":[{"title":"Documentation page summarization for coding agent","prompt":"Go to https://docs.openai.com/api-reference and distill it into structured markdown mode so I can feed just the relevant content to my coding agent without blowing the context window."},{"title":"Focused research excerpt on a news article","prompt":"Fetch https://techcrunch.com/2025/01/15/ai-funding-roundup and extract only the parts relevant to my query 'Series B funding rounds' using budget mode, keeping it under 300 tokens."},{"title":"Structured data extraction from a product page","prompt":"Take the raw HTML from this e-commerce product listing and distill it in structured mode to pull out the tables, prices, and metadata cleanly."}],"resultDescription":"Returns a distilled content object (Markdown text, structured JSON tables/metadata, skeleton outline, or BM25-ranked excerpt), along with ROI proof metrics showing raw vs distilled token counts, tokens saved, compression ratio percentage, and estimated LLM cost saved in USD. Also includes cache status (HIT/MISS) and billing details.","failureModes":["URL is unreachable or returns a non-200 status — endpoint may return an error status","max_tokens set below 20 — schema validation error","mode=budget used without providing a query — BM25 ranking may be undefined","Raw HTML is empty or malformed — distillation may return minimal output","Payment not provided or insufficient — HTTP 402 returned requiring x402 USDC payment"],"whenToPreferThis":"Choose this endpoint when you need to reduce token costs before passing web content to an LLM, especially when you have a specific query focus (BM25 budget mode) or need structured extraction from messy HTML. It is preferable over raw web fetching when token budget is a concern, and over general-purpose scrapers when you need clean Markdown or structured JSON output with built-in compression metrics.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:34:06.635Z","isFirstParty":false,"canonicalSlug":"domain-osint-agentdiet-dev-web-page-html-distiller-with-bm25-budget-af749961"}