{"uid":"cap_IMk5fXPo1iVzEc2vf1-HP","slug":"llms-generator-agentdiet-dev-semantic-html-pruner-web-url-distiller-baf7c6f4","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://llms-generator.agentdiet.dev/v1/semantic-html-pruner)","url":"https://llms-generator.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_O_jIwyqkhROJwy4p1cXcG","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"llms-generator.agentdiet.dev","brandSlug":"llms-generator-agentdiet-dev-mpp","brandBaseUrl":"https://llms-generator.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches a webpage URL (or accepts raw HTML) and distills it into compact, agent-ready tokens using BM25 budget control and multiple extraction modes","exampleAgentPrompt":"Can you fetch https://docs.stripe.com/payments and distill it into clean markdown, keeping it under 800 tokens and focusing on the query 'payment intents'?","exampleUseCases":[{"title":"Research page within LLM token budget","prompt":"Grab https://en.wikipedia.org/wiki/Transformer_(machine_learning_model) and distill it into budget mode focused on 'attention mechanism', keeping it under 500 tokens so it fits in my context window."},{"title":"Extract structured tables from documentation","prompt":"Pull the pricing page at https://aws.amazon.com/ec2/pricing/ and extract it in structured mode so I get all the tables and metadata as clean JSON."},{"title":"Get a skeleton outline of a long article","prompt":"Fetch https://www.paulgraham.com/greatwork.html and give me a skeleton outline of the page — just the headings and section structure, nothing more."}],"resultDescription":"Returns a 'data' object containing the 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 a ROI multiplier. Optionally includes cache status (HIT/MISS) and billing details.","failureModes":["URL is unreachable or returns non-200 — fetch failure with error status","URL content is already minimal and token savings are negligible","mode=budget without a query or max_tokens may return unfiltered content","Raw HTML passed via 'html' field is malformed — parser may produce degraded output","Payment/402 failure if x402 credentials are not supplied","Rate limiting if too many concurrent requests are made"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to read a webpage but must stay within a token budget, or when raw HTML contains too much noise (navigation, ads, boilerplate) for effective LLM processing. It is especially valuable in agentic pipelines where context window space is scarce and multiple pages must be processed. Prefer this over generic scrapers when you need BM25-ranked relevance filtering (budget mode) or structured extraction of tables and metadata (structured mode). It is purpose-built for LLM agent consumption rather than full-text archiving or SEO crawling.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:24:34.819Z","isFirstParty":false,"canonicalSlug":"llms-generator-agentdiet-dev-semantic-html-pruner-web-url-distiller-baf7c6f4"}