{"uid":"cap_hdM4abOJumlyQS8NmPtAw","slug":"domain-osint-agentdiet-dev-semantic-html-pruner-web-url-distillation-5f5f96a8","name":"Semantic HTML Pruner – Web URL Distillation 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://domain-osint.agentdiet.dev/v1/semantic-html-pruner)","url":"https://domain-osint.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_lcPGvQ7Tz6o1tFmT3tP","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"domain-osint.agentdiet.dev","brandSlug":"domain-osint-agentdiet-dev-mpp","brandBaseUrl":"https://domain-osint.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches a web page (or accepts raw HTML) and distills it into compact, token-efficient content using BM25 budget control and multiple extraction modes.","exampleAgentPrompt":"Pull the content from https://docs.stripe.com/payments/payment-intents and distill it into compact markdown, keeping it under 2000 tokens and focusing on the query 'payment intent lifecycle'.","exampleUseCases":[{"title":"LLM research pipeline token compression","prompt":"Distill https://arxiv.org/abs/2310.06825 into structured markdown so I can feed it to GPT-4 without burning through my context window — keep it under 3000 tokens."},{"title":"Focused BM25 budget extraction for QA","prompt":"Fetch https://docs.openai.com/api-reference and extract only the parts relevant to 'rate limits and error codes' using budget mode with a max of 1500 tokens."},{"title":"Skeleton outline of a long documentation page","prompt":"Give me a skeleton outline of https://developer.mozilla.org/en-US/docs/Web/API/Fetch_API so I can quickly navigate the structure without reading the full page."}],"resultDescription":"Returns a JSON object containing the distilled content (Markdown, structured tables/metadata, skeleton outline, or BM25-focused excerpt), an ROI proof block showing raw vs. distilled token counts, compression ratio, tokens saved, and estimated LLM cost saved in USD, plus optional cache hit/miss status and billing details.","failureModes":["URL is unreachable or returns non-200 status — endpoint may return an error status","HTML content is too large even after distillation to meet the max_tokens budget","BM25 query returns no relevant passages — excerpt may be empty or minimal","Payment not processed (x402) — request blocked without valid USDC payment","Invalid mode enum value — request rejected with validation error","URL is behind a login/paywall — fetched HTML is a login page, not target content"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to read a web page but must stay within a token budget, reduce LLM API costs, or receive structured/skeletonized content rather than raw HTML. Especially valuable in agentic pipelines where many URLs must be processed cost-efficiently, or when a BM25 focus query can dramatically reduce irrelevant content. Prefer over generic web scrapers when token-efficiency and ROI metrics matter.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T12:40:41.982Z","isFirstParty":false,"canonicalSlug":"domain-osint-agentdiet-dev-semantic-html-pruner-web-url-distillation-5f5f96a8"}