{"uid":"cap_3GcmPZre6QTPpTmo0gHKB","slug":"serp-extract-agentdiet-dev-semantic-html-pruner-web-url-distillation-7f851bed","name":"Semantic HTML Pruner – Web URL Distillation to Agent-Ready Tokens","description":"Distill a web URL into compact agent-ready tokens (Live x402 v2, IETF MPP & MCP endpoint at https://serp-extract.agentdiet.dev/v1/semantic-html-pruner)","url":"https://serp-extract.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 distill (or builtin://stripe-docs)"},"mode":{"enum":["markdown","structured","skeleton","budget"],"type":"string","default":"markdown","description":"Extraction mode: markdown, structured, skeleton, or budget"},"limit":{"type":"integer","default":20,"maximum":100,"minimum":1,"description":"Maximum number of items to return per page (1-100)"},"query":{"type":"string","description":"BM25 focus query when mode=budget"},"cursor":{"type":"string","description":"Opaque pagination cursor for fetching the next page"},"max_tokens":{"type":"integer","minimum":20,"description":"Strict token 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_8Wepk5X6Ty5mcwA8-6Kdr","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"serp-extract.agentdiet.dev","brandSlug":"serp-extract-agentdiet-dev-mpp","brandBaseUrl":"https://serp-extract.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches a URL or raw HTML payload and distills it into compact, agent-ready Markdown, structured JSON, skeleton outline, or BM25-focused budget excerpts with token-saving metrics.","exampleAgentPrompt":"Can you fetch the page at https://stripe.com/docs/payments and distill it into clean markdown, staying under 800 tokens and focusing on the topic of payment intents?","exampleUseCases":[{"title":"Token-budgeted research on a documentation page","prompt":"Pull the content from https://docs.openai.com/api-reference and give me only the parts relevant to 'function calling', keeping it under 600 tokens in budget mode."},{"title":"Clean markdown extraction for agent grounding","prompt":"Distill https://www.ycombinator.com/companies into readable markdown so I can feed it to my agent without blowing through my context window."},{"title":"Structured data extraction from a web page","prompt":"Fetch https://coinmarketcap.com/currencies/bitcoin/ and return the content in structured mode so I can get the tables and metadata as clean JSON."}],"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 vs distilled token counts, compression ratio percentage, tokens saved, ROI multiplier, and estimated LLM cost saved in USD. Also includes billing details and optional cache hit/miss status with latency.","failureModes":["Invalid or unreachable URL returns an error status","max_tokens below minimum of 20 rejected with validation error","mode=budget without a query may return unfiltered content","Raw HTML too large may exceed processing limits","Paywalled or bot-protected pages may return incomplete or empty content","Payment/billing failure if x402 payment not provided or insufficient"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to consume web page content efficiently without exhausting its context window. It is especially valuable when the target page is HTML-heavy with navigation, ads, or boilerplate, and you need clean Markdown or structured JSON. Use budget mode with a BM25 query when you want only the most relevant passage within a strict token ceiling. Prefer this over generic scrapers when token cost savings and compression metrics are important inputs to your pipeline.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:21:27.049Z","isFirstParty":false,"canonicalSlug":"serp-extract-agentdiet-dev-semantic-html-pruner-web-url-distillation-7f851bed"}