{"uid":"cap_NxwBww18GK8f1L8OSkwMP","slug":"token-intel-agentdiet-dev-html-url-distiller-with-bm25-budget-control-61d0db64","name":"HTML/URL 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://token-intel.agentdiet.dev/v1/clean-html)","url":"https://token-intel.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_bNLaBod2H9IDHib4PdzED","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"token-intel.agentdiet.dev","brandSlug":"token-intel-agentdiet-dev-mpp","brandBaseUrl":"https://token-intel.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches and distills a URL or raw HTML into clean Markdown, structured JSON, skeleton, or BM25-focused excerpts within a strict token budget","exampleAgentPrompt":"Distill the page at https://stripe.com/docs/payments into clean markdown, but cap it at 2000 tokens and focus on the section about payment intents using budget mode.","exampleUseCases":[{"title":"Compress docs before LLM reasoning","prompt":"Fetch the React documentation at https://react.dev/learn and distill it into markdown, staying under 1500 tokens and focusing on the hooks API — I need to pass this to my model without blowing my context window."},{"title":"Extract structured data from product page","prompt":"Take this raw HTML from our competitor's pricing page and distill it into structured JSON tables so I can compare their tiers programmatically — here's the HTML payload."},{"title":"BM25-focused research snippet extraction","prompt":"Pull the page at https://arxiv.org/abs/2310.06825 and give me only the sections most relevant to 'retrieval augmented generation benchmarks', capped at 800 tokens using budget mode."}],"resultDescription":"Returns a JSON object containing distilled content (Markdown, structured tables/metadata, skeleton outline, or BM25-scored excerpt depending on mode), ROI proof metrics (raw vs distilled token counts, compression ratio, estimated LLM cost savings), optional cache hit/miss status, and billing details including fee charged.","failureModes":["URL is unreachable or returns non-200 HTTP status — fetch failure error","HTML payload is empty or malformed — parsing error returned","max_tokens set below minimum of 20 — validation error","BM25 query missing when mode=budget — parameter error","Payment not provided or insufficient — HTTP 402 payment required","Rate limiting or abuse detection — request rejected"],"whenToPreferThis":"Choose this endpoint when you need to reduce token consumption before feeding web content to an LLM, especially when working with large pages where only a focused subset is relevant. It is ideal for RAG pipelines, autonomous agents that browse the web, and any workflow where LLM API cost or context window size is a constraint. The BM25 budget mode is uniquely powerful when you have a specific query and a hard token ceiling. Prefer this over generic scrapers when you need clean, LLM-ready output with measurable compression ROI.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:32:30.595Z","isFirstParty":false,"canonicalSlug":"token-intel-agentdiet-dev-html-url-distiller-with-bm25-budget-control-61d0db64"}