{"uid":"cap_wqXa2UHlGyNRwl9mdZYxa","slug":"cve-intel-agentdiet-dev-semantic-html-pruner-web-url-to-agent-ready-2a304719","name":"Semantic HTML Pruner – Web URL to Agent-Ready Tokens","description":"Distill a URL or raw HTML payload with BM25 budget control (Live x402 v2, IETF MPP & MCP endpoint at https://cve-intel.agentdiet.dev/v1/semantic-html-pruner)","url":"https://cve-intel.agentdiet.dev/v1/semantic-html-pruner?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_oQPzPciBznoFJZHcCVcb6","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"cve-intel.agentdiet.dev","brandSlug":"cve-intel-agentdiet-dev-mpp","brandBaseUrl":"https://cve-intel.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches a URL or accepts raw HTML and distills it into compact, agent-ready content using BM25 budget control and multiple extraction modes","exampleAgentPrompt":"Fetch https://stripe.com/docs/payments/checkout and distill it into clean markdown, keeping it under 2000 tokens and focusing on anything related to subscription billing.","exampleUseCases":[{"title":"Budget-capped research scraping","prompt":"Pull https://en.wikipedia.org/wiki/Large_language_model and give me only the parts about training data — keep it under 800 tokens using BM25 budget mode focused on 'training dataset corpus'."},{"title":"Structured metadata extraction from product page","prompt":"Go to https://aws.amazon.com/ec2/pricing/ and extract it in structured mode so I get the pricing tables and metadata as clean JSON, not a wall of HTML."},{"title":"Skeleton outline for long documentation","prompt":"Distill https://docs.python.org/3/library/asyncio.html into a skeleton outline so I can see the section headings and structure without reading the whole thing."}],"resultDescription":"Returns a 'data' object with distilled content (markdown text, structured JSON tables/metadata, skeleton outline, or BM25-ranked excerpt depending on mode), plus an 'roi_proof' block showing raw token count, distilled token count, tokens saved, compression ratio percentage, estimated LLM cost saved in USD, and ROI multiplier. Also includes optional cache status (HIT/MISS) and billing details.","failureModes":["Invalid or unreachable URL returns an error status","Pages behind authentication or paywalls may return empty or partial content","Very large pages may hit processing limits before distillation completes","BM25 budget mode with an irrelevant query may return minimal or low-quality excerpts","max_tokens set too low may truncate critical content","HTML-heavy JavaScript-rendered pages may not be fully captured by fetch","Payment failure via x402 returns 402 before processing begins"],"whenToPreferThis":"Choose this endpoint when you need to feed web content to an LLM but want to minimize token usage and cost — especially when you have a strict token budget or a specific focus query. It is ideal over raw web scraping when the agent needs clean, structured or markdown-formatted output rather than raw HTML. Prefer BM25 budget mode when only a topically relevant slice of a large page is needed. Use structured mode when tables or metadata need to be parsed programmatically.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T12:49:34.119Z","isFirstParty":false,"canonicalSlug":"cve-intel-agentdiet-dev-semantic-html-pruner-web-url-to-agent-ready-2a304719"}