{"uid":"cap_lAtY3br0qtSM11jJDGudb","slug":"sec-intel-agentdiet-dev-web-url-html-dom-distiller-bm25-budget-control-31f6a79c","name":"Web URL & HTML DOM Distiller (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/dom-stripper)","url":"https://sec-intel.agentdiet.dev/v1/dom-stripper?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_Bm_LrYmyzYLzgdouW72I-","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 a web URL or raw HTML and distills it into compact, agent-ready tokens using markdown, structured, skeleton, or BM25 budget modes","exampleAgentPrompt":"Can you fetch https://stripe.com/docs/payments and distill it into clean markdown, keeping it under 2000 tokens and focusing on the 'payment intents' topic?","exampleUseCases":[{"title":"Stripe docs ingestion on a budget","prompt":"Grab the Stripe checkout documentation at https://stripe.com/docs/checkout and distill it in budget mode with a max of 1500 tokens, focusing the BM25 query on 'session creation'."},{"title":"Competitor landing page snapshot","prompt":"Strip down https://competitor.com/pricing into structured mode so I can get the pricing table and key metadata without all the noise."},{"title":"Skeleton outline of a long article","prompt":"Fetch https://example.com/blog/ai-trends-2025 and return just the skeleton outline so I can see the section headings and structure without loading the full content."}],"resultDescription":"Returns a 'data' object containing the distilled content (markdown text, structured JSON tables/metadata, skeleton outline, or BM25-focused excerpt depending on mode), plus an 'roi_proof' object showing raw vs distilled token counts, compression ratio percentage, tokens saved, and estimated LLM cost saved in USD. Also includes optional cache hit/miss status and billing details.","failureModes":["Invalid or unreachable URL returns an error status","Missing required 'url' parameter causes a 400-level rejection","mode=budget without a 'query' or 'max_tokens' may return unfiltered content","Pages behind authentication or paywalls may return empty or partial distillation","Very large HTML payloads may hit processing limits","x402 payment failure if agent wallet has insufficient USDC balance"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to read web content but must stay within a token budget — especially useful for documentation pages, news articles, or competitor research where raw HTML is far too verbose. Prefer it over raw HTTP fetch when you want automatic compression, BM25 relevance filtering, or structured extraction (tables, metadata). The built-in ROI proof makes it easy to justify token savings across agent runs.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:26:10.084Z","isFirstParty":false,"canonicalSlug":"sec-intel-agentdiet-dev-web-url-html-dom-distiller-bm25-budget-control-31f6a79c"}