{"uid":"cap_J0yDPJt8txzixZyaBAvsU","slug":"sec-intel-agentdiet-dev-web-url-html-distillation-with-bm25-budget-278f92b7","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://sec-intel.agentdiet.dev/v1/clean-html)","url":"https://sec-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_1AbIOO9oiqBfeInjWS_zS","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"sec-intel.agentdiet.dev","brandSlug":"sec-intel-agentdiet-dev-mpp","brandBaseUrl":"https://sec-intel.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches and distills a web URL or raw HTML into compact, agent-ready tokens using configurable extraction modes and BM25-ranked budget control","exampleAgentPrompt":"Distill the content at https://stripe.com/docs/payments into clean markdown, keeping it under 2000 tokens and focusing on the query 'payment intents API' using budget mode.","exampleUseCases":[{"title":"Token-efficient research digest","prompt":"Fetch and distill https://openai.com/research/gpt-4 into structured markdown so I can read the key points without burning through my context window — keep it tight."},{"title":"Budget-capped competitor page extraction","prompt":"Pull the content from https://anthropic.com/claude and distill it using budget mode with a max of 1500 tokens, focusing on the query 'model capabilities and pricing'."},{"title":"Structured data extraction from HTML","prompt":"I have a raw HTML blob from a financial news article — distill it into structured tables and metadata so my agent can process the key figures."}],"resultDescription":"Returns a 'data' object containing the distilled content (Markdown text, structured JSON tables/metadata, skeleton outline, or BM25-ranked excerpt depending on mode), alongside an roi_proof block showing raw vs distilled token counts, compression ratio, tokens saved, and estimated LLM cost saved in 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 sites","max_tokens below minimum (20) triggers validation error","BM25 query mode without a query string may return unfiltered content","Payment failure via x402 returns HTTP 402 with no content","Malformed raw HTML in the 'html' field may produce degraded output"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to read web content but must stay within a strict token budget or minimize LLM API costs. It is especially useful when fetching long documentation pages, news articles, or HTML-heavy sites where raw content would be too large for a context window. The BM25 budget mode makes it distinctly valuable when the agent needs topically focused extraction rather than the full page. Prefer it over generic scrapers when you need built-in token accounting and cost-savings telemetry.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:23:16.050Z","isFirstParty":false,"canonicalSlug":"sec-intel-agentdiet-dev-web-url-html-distillation-with-bm25-budget-278f92b7"}