{"uid":"cap_htIgoYCco_TIgp-Wzftdd","slug":"defi-yield-agentdiet-dev-semantic-html-pruner-web-url-to-agent-ready-7f7aa80e","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://defi-yield.agentdiet.dev/v1/semantic-html-pruner)","url":"https://defi-yield.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_4CdJ8Qp3t7qygTURxA07w","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"defi-yield.agentdiet.dev","brandSlug":"defi-yield-agentdiet-dev-mpp","brandBaseUrl":"https://defi-yield.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches a URL or raw HTML and distills it into compact, token-efficient text using BM25-driven budget control, returning markdown, structured JSON, skeleton outlines, or focused excerpts.","exampleAgentPrompt":"Distill https://docs.stripe.com/payments/checkout into clean markdown, keeping it under 1500 tokens — focus the BM25 budget on payment intent setup.","exampleUseCases":[{"title":"Scrape docs page into agent context","prompt":"Fetch https://docs.openai.com/api-reference/chat and compress it into structured markdown under 2000 tokens so I can include it in my agent's context window without blowing the budget."},{"title":"BM25 budget excerpt for targeted research","prompt":"Pull https://arxiv.org/abs/2310.06825 and give me only the parts relevant to 'chain-of-thought reasoning', capped at 800 tokens — use budget mode with that as the query."},{"title":"Skeleton outline of a long article","prompt":"Take https://en.wikipedia.org/wiki/Transformer_(machine_learning_model) and return just a skeleton outline of the page structure so I can see the major sections without reading the whole thing."}],"resultDescription":"Returns a JSON object with a 'data' field containing the distilled content (markdown text, structured JSON tables/metadata, 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, ROI multiplier, and estimated LLM cost saved in USD. Also includes cache status (HIT/MISS) and billing details.","failureModes":["URL is unreachable or returns non-200 — fetch failure error","Invalid or malformed URL string — schema validation error","mode=budget used without a query or max_tokens — missing parameter error","Raw HTML too large to process within timeout — payload size error","Target site blocks scraping (bot protection, CAPTCHA) — fetch blocked error","max_tokens set below minimum of 20 — validation error"],"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 long documentation pages, news articles, or any URL-based content that would otherwise exceed context windows or inflate LLM costs. Prefer it over generic scrapers when you need BM25 query-focused excerpts or structured/skeleton output modes rather than raw HTML. Ideal for agentic pipelines that need to fetch and digest web content cheaply at $0.001 per call with built-in ROI tracking.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T12:40:41.983Z","isFirstParty":false,"canonicalSlug":"defi-yield-agentdiet-dev-semantic-html-pruner-web-url-to-agent-ready-7f7aa80e"}