{"uid":"cap_yJl3CBXfj94Ulgiv4xArJ","slug":"sec-intel-agentdiet-dev-dom-stripper-url-html-distillation-with-bm25-206c9f4d","name":"DOM Stripper – 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/dom-stripper)","url":"https://sec-intel.agentdiet.dev/v1/dom-stripper?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_NxsOQWqo54Oe839ZbeDRu","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 any URL or raw HTML into clean Markdown, structured JSON, a skeleton outline, or a BM25-ranked token-budget excerpt for LLM cost reduction.","exampleAgentPrompt":"Grab the Stripe pricing page at https://stripe.com/pricing and distill it into clean markdown, keeping it under 800 tokens and focusing on the query 'payment processing fees'.","exampleUseCases":[{"title":"LLM cost-aware documentation fetch","prompt":"Fetch the OpenAI API docs at https://platform.openai.com/docs/api-reference and compress them to under 1000 tokens in budget mode, focusing on the query 'rate limits'."},{"title":"Structured data extraction from a news article","prompt":"Take this URL https://techcrunch.com/2024/01/15/ai-funding-roundup/ and distill it into structured mode so I get tables and metadata — I need to pull out company names and funding amounts."},{"title":"Skeleton outline of a long research page","prompt":"Can you distill https://arxiv.org/abs/2401.00001 into a skeleton outline so I can quickly understand the structure of the paper without burning through my token budget?"}],"resultDescription":"Returns a JSON object with a 'data' field containing the distilled content (Markdown string, structured tables/metadata JSON, skeleton outline, or BM25 excerpt), an 'roi_proof' object showing raw vs. distilled token counts, compression ratio, tokens saved, and estimated LLM cost saved in USD, a 'cache' status (HIT/MISS with latency), billing details, and an execution status string.","failureModes":["Invalid or unreachable URL returns a fetch error with status detail","HTML too large or malformed may yield incomplete distillation","mode=budget without a 'query' parameter may fall back to default truncation","max_tokens set below content minimum may produce very short or empty excerpts","Payment failure (402) if x402 USDC payment is not completed","Rate limiting or timeouts on slow target pages may cause partial results"],"whenToPreferThis":"Choose this endpoint when you need to reduce the token cost of feeding web content to an LLM — especially for documentation pages, news articles, or financial filings. Prefer it over raw web fetching when token budget matters or when you need BM25-ranked relevance filtering. Use budget mode with a query when you only need the most relevant excerpt. Prefer it over general-purpose scrapers when you need ROI proof (compression ratio, cost saved) returned alongside the content.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:32:34.305Z","isFirstParty":false,"canonicalSlug":"sec-intel-agentdiet-dev-dom-stripper-url-html-distillation-with-bm25-206c9f4d"}