{"uid":"cap_QalU5H35IUT8re3EuZxSv","slug":"email-verify-agentdiet-dev-semantic-html-pruner-web-url-to-agent-afe602c4","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://email-verify.agentdiet.dev/v1/semantic-html-pruner)","url":"https://email-verify.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_ADpvd_XXAqRIBAgxeFg9z","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"email-verify.agentdiet.dev","brandSlug":"email-verify-agentdiet-dev-mpp","brandBaseUrl":"https://email-verify.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches a URL or raw HTML and distills it into compact, token-efficient Markdown, structured JSON, skeleton outline, or BM25-focused budget excerpt for LLM consumption","exampleAgentPrompt":"Can you fetch the Stripe documentation page at https://stripe.com/docs/payments and distill it into clean Markdown, keeping it under 2000 tokens and focusing on the payment intents section?","exampleUseCases":[{"title":"Token-budget research for LLM pipelines","prompt":"Grab the content from https://openai.com/research/gpt-4 and distill it using budget mode with a focus query on 'multimodal capabilities', keeping the result under 1500 tokens so I can pipe it into my agent without blowing my context window."},{"title":"Structured data extraction from a pricing page","prompt":"Pull the pricing page at https://vercel.com/pricing and distill it into structured mode so I get clean JSON tables of their plans and features — I need to compare tiers programmatically."},{"title":"Skeleton outline of long documentation","prompt":"Take the React documentation at https://react.dev/learn and give me a skeleton outline so I can see the high-level structure and headings without reading the whole thing."}],"resultDescription":"Returns a JSON object with a 'data' field containing the distilled content (Markdown string, structured JSON tables/metadata, skeleton outline, or BM25-focused budget excerpt depending on mode), an 'roi_proof' object with raw_tokens, distilled_tokens, tokens_saved, compression_ratio_pct, roi_multiplier, and llm_cost_saved_usd, plus optional cache metadata and billing details.","failureModes":["Invalid or unreachable URL returns an error status","Target site blocks the fetcher (403/bot protection) causing empty or failed extraction","Malformed HTML input may produce incomplete distillation","Token budget too low (below 20) is rejected by schema validation","Rate limiting or payment failure (x402) blocks the request","Mode=budget without a query or max_tokens may produce undefined behavior"],"whenToPreferThis":"Choose this endpoint when you need to feed web content into an LLM and want to minimize token usage and cost — especially when the raw HTML is too large for your context window. It is ideal for agentic pipelines that repeatedly scrape or monitor web pages and need reproducible, structured, or token-bounded output. Prefer it over generic scrapers when you need BM25 relevance filtering (budget mode), structured JSON extraction, or explicit compression-ratio proof for cost accounting.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:20:57.988Z","isFirstParty":false,"canonicalSlug":"email-verify-agentdiet-dev-semantic-html-pruner-web-url-to-agent-afe602c4"}