{"uid":"cap_4SMzgUqueRAE_P3wL0Fw0","slug":"preflight-agentdiet-dev-web-url-html-distillation-with-bm25-budget-07c20120","name":"Web URL & HTML Distillation 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://preflight.agentdiet.dev/v1/clean-html)","url":"https://preflight.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_tOkB359yOXgTJKSW2svkS","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"preflight.agentdiet.dev","brandSlug":"preflight-agentdiet-dev-mpp","brandBaseUrl":"https://preflight.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches a URL or accepts raw HTML and distills it into compact, agent-ready tokens using markdown, structured, skeleton, or BM25-budgeted extraction modes","exampleAgentPrompt":"Distill the content at https://stripe.com/docs/api into compact markdown, keeping it under 2000 tokens and focused on the query 'payment intents' using budget mode.","exampleUseCases":[{"title":"Compress competitor pricing page for analysis","prompt":"Fetch and distill https://openai.com/pricing into structured mode so I can see the pricing tiers and model names without all the HTML noise."},{"title":"BM25-focused research excerpt under token budget","prompt":"Pull the content from https://arxiv.org/abs/2305.10601 and give me a budget-mode excerpt focused on 'retrieval augmented generation', keeping it under 1500 tokens so it fits in my prompt."},{"title":"Raw HTML cleanup for downstream agent","prompt":"I have raw HTML from a scrape — can you distill it into clean markdown? Here's the HTML: <html><body><nav>...</nav><main><h1>Product Features</h1><p>...</p></main></body></html>"}],"resultDescription":"Returns a data object containing distilled content in the requested mode (Markdown text, structured JSON tables/metadata, skeleton outline, or BM25-ranked budget excerpt), along with ROI proof metrics including raw_tokens, distilled_tokens, tokens_saved, compression_ratio_pct, and llm_cost_saved_usd. Also includes cache status (HIT/MISS) and billing details.","failureModes":["Invalid or unreachable URL returns an error status","HTML fetch timeout for slow or blocked websites","max_tokens too low (below 20) triggers validation error","BM25 query provided without mode=budget may be ignored","Payment failure via x402 prevents execution","Malformed raw HTML input may produce incomplete distillation","Rate limiting on the target domain causes fetch failure"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to consume web content efficiently within a token budget — particularly when feeding page content into an LLM context window and cost or context length is a concern. It is superior to raw scraping when you need noise-free markdown, structured extraction, or BM25-ranked relevance filtering. Prefer it over generic scrapers when you need provable compression ROI metrics and LLM cost savings tracking. The budget mode with a query parameter is especially valuable for long pages where only a topically relevant excerpt is needed.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:25:44.202Z","isFirstParty":false,"canonicalSlug":"preflight-agentdiet-dev-web-url-html-distillation-with-bm25-budget-09303c73"}