{"uid":"cap_YNLjs3gAdM2o7nR02IAz-","slug":"sec-intel-agentdiet-dev-semantic-html-pruner-with-bm25-budget-control-5b74554e","name":"Semantic HTML Pruner 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/semantic-html-pruner)","url":"https://sec-intel.agentdiet.dev/v1/semantic-html-pruner?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_WsiFnkot7PvzvZaGVc_Ko","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 URL or accepts raw HTML and distills it into clean Markdown, structured data, or a token-budgeted excerpt using BM25 relevance ranking","exampleAgentPrompt":"Can you fetch https://stripe.com/docs/payments and distill it into clean markdown, using budget mode focused on 'payment intents' with a max of 1500 tokens?","exampleUseCases":[{"title":"Token-budget web research for LLM pipelines","prompt":"Pull https://openai.com/research/gpt-4 and compress it down to at most 800 tokens using BM25 budget mode, focused on the query 'model capabilities and benchmarks' — I need to feed it to my downstream LLM without blowing the context window."},{"title":"Structured data extraction from product page","prompt":"Fetch https://www.apple.com/iphone/ and return the content in structured mode so I get the tables, product metadata, and key specs as JSON rather than a wall of text."},{"title":"Skeleton outline of a long documentation page","prompt":"I have this raw HTML from our internal wiki — can you distill it in skeleton mode to give me just the heading structure and section outline so I can understand the document layout without reading the whole thing?"}],"resultDescription":"Returns a data object containing the distilled content (Markdown text, structured JSON with tables/metadata, a skeleton outline, or a BM25-ranked budget excerpt), plus an roi_proof object showing raw_tokens, distilled_tokens, tokens_saved, compression_ratio_pct, and llm_cost_saved_usd. Also includes cache status (HIT/MISS) and billing details.","failureModes":["URL is unreachable or returns non-200 status — endpoint may return an error status","HTML payload is empty or malformed — distillation may produce empty or low-quality output","BM25 query not provided when mode=budget — may default to unfiltered content","max_tokens ceiling too low (below 20) — rejected by schema validation","Rate limiting or payment failure via x402 — billing object absent, request rejected","Timeout fetching a slow or large URL — partial content or timeout error returned"],"whenToPreferThis":"Choose this endpoint when you need to reduce the token footprint of web content before passing it to an LLM, especially when working with large documentation pages, e-commerce sites, or any URL where raw HTML would exceed context limits. It is particularly valuable when you have a specific topic focus (use budget+BM25 mode) or need structured tables and metadata extracted (use structured mode). Prefer it over generic scrapers when token cost savings and LLM-ready output format are priorities.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-28T00:34:21.173Z","isFirstParty":false,"canonicalSlug":"sec-intel-agentdiet-dev-semantic-html-pruner-with-bm25-budget-control-5b74554e"}