{"uid":"cap_NMfPX3CWF6IQSesiZM8St","slug":"cve-intel-agentdiet-dev-web-url-html-distiller-with-bm25-budget-control-6ceb23b7","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://cve-intel.agentdiet.dev/v1/clean-html)","url":"https://cve-intel.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_lkj7CXplv6MN3Ho__Rn1Z","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"cve-intel.agentdiet.dev","brandSlug":"cve-intel-agentdiet-dev-mpp","brandBaseUrl":"https://cve-intel.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches a webpage URL (or accepts raw HTML) and distills it into compact, agent-ready tokens using configurable modes including BM25 budget-constrained extraction","exampleAgentPrompt":"Can you fetch https://stripe.com/docs/payments and distill it into clean markdown, keeping it under 500 tokens and focusing on the query 'payment intents'?","exampleUseCases":[{"title":"Token-budget research from live URL","prompt":"Go to https://openai.com/pricing and distill it into budget mode with max 300 tokens, focusing on the query 'GPT-4 cost per token' — I need just the relevant pricing info without blowing my context window."},{"title":"Structured data extraction from webpage","prompt":"Fetch https://en.wikipedia.org/wiki/Bitcoin and give me the structured mode output — I want tables and metadata extracted cleanly so I can parse the key facts about Bitcoin."},{"title":"Skeleton outline of documentation page","prompt":"Distill https://docs.github.com/en/actions into skeleton mode so I can see the outline and heading structure of the GitHub Actions docs without reading the whole page."}],"resultDescription":"Returns a JSON object containing distilled page content in the requested format (Markdown, structured JSON, skeleton outline, or BM25-focused excerpt), along with ROI proof metrics showing raw token count, distilled token count, tokens saved, compression ratio percentage, and estimated LLM cost saved in USD. Also includes cache hit/miss status and billing information.","failureModes":["URL is unreachable or returns non-200 status — fetch fails and an error status is returned","Invalid or malformed URL provided — validation error returned","mode=budget used without a query or max_tokens — may fall back to defaults or return an error","Raw HTML too large to process within time limits — timeout or truncation","Payment not completed via x402 — 402 Payment Required response blocks execution","max_tokens set below minimum of 20 — validation error"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to read a webpage but must stay within a token budget, or when raw HTML needs to be cleaned and compressed before being fed into an LLM context. It is especially valuable when only a relevant slice of a page is needed (BM25 budget mode with a query), when structured tables/metadata need to be extracted, or when you want measurable proof of token savings. Prefer it over generic scrapers when token efficiency and LLM cost reduction are priorities.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:25:44.534Z","isFirstParty":false,"canonicalSlug":"cve-intel-agentdiet-dev-web-url-html-distiller-with-bm25-budget-control-6ceb23b7"}