{"uid":"cap_S236L856h3S4wJGQYEWye","slug":"prompt-guard-agentdiet-dev-semantic-html-pruner-web-url-distiller-071baa81","name":"Semantic HTML Pruner — Web URL Distiller","description":"Distill a URL or raw HTML payload with BM25 budget control (Live x402 v2, IETF MPP & MCP endpoint at https://prompt-guard.agentdiet.dev/v1/semantic-html-pruner)","url":"https://prompt-guard.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_Mzz3AvBuQ3hkL0ceJlMc-","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"prompt-guard.agentdiet.dev","brandSlug":"prompt-guard-agentdiet-dev-mpp","brandBaseUrl":"https://prompt-guard.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches a URL (or accepts raw HTML) and compresses it into compact, agent-ready tokens using BM25 budget control and multiple distillation modes","exampleAgentPrompt":"Can you fetch https://docs.stripe.com/payments/checkout and distill it into compact markdown, keeping it under 2000 tokens — I need the key content without all the HTML noise?","exampleUseCases":[{"title":"Distill documentation for agent context","prompt":"Grab https://docs.openai.com/api-reference and compress it into structured markdown so I can drop it into my agent's context window without blowing the token limit."},{"title":"Budget-focused extraction from a news article","prompt":"Fetch this article at https://techcrunch.com/2025/01/15/ai-agents-explainer and extract the most relevant content about 'AI agent workflows' using a strict budget of 500 tokens."},{"title":"Convert raw HTML to clean skeleton outline","prompt":"I have some raw HTML from a product page — can you prune it down to just a skeleton outline so I can see the page structure without all the noise?"}],"resultDescription":"Returns a 'data' object containing the distilled content (Markdown text, structured JSON, skeleton outline, or BM25-focused excerpt depending on mode), plus an 'roi_proof' object showing raw token count, distilled token count, tokens saved, compression ratio percentage, and estimated LLM cost saved in USD. Also includes cache status and billing details.","failureModes":["Invalid or unreachable URL returns an error status","Token budget too low (max_tokens < 20) returns a validation error","BM25 query provided without mode=budget may be ignored","Raw HTML payload too large may time out or be rejected","Paywalled or JavaScript-rendered pages may return incomplete content","x402 payment failure results in 402 response blocking execution"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to read a webpage but must stay within a token budget, or when raw HTML is too verbose for an LLM context window. It is especially useful for processing documentation pages, news articles, or product pages where only the semantic content matters. Prefer the 'budget' mode with a BM25 query when you only need content relevant to a specific topic. Prefer 'structured' mode when you need tabular data or metadata. Use over generic scrapers when token efficiency and ROI metrics matter to your pipeline.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:24:29.821Z","isFirstParty":false,"canonicalSlug":"prompt-guard-agentdiet-dev-semantic-html-pruner-web-url-distiller-071baa81"}