{"uid":"cap_wQhWNnIiyHM3WremcU5od","slug":"company-enrich-agentdiet-dev-semantic-html-pruner-web-url-distiller-e91aeb9c","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://company-enrich.agentdiet.dev/v1/semantic-html-pruner)","url":"https://company-enrich.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_8WBGazhnovL4IUVd8uNH8","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"company-enrich.agentdiet.dev","brandSlug":"company-enrich-agentdiet-dev-mpp","brandBaseUrl":"https://company-enrich.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches a URL (or accepts raw HTML) and distills it into compact, agent-ready tokens using BM25 budget control and multiple extraction modes","exampleAgentPrompt":"Fetch the page at https://stripe.com/docs/payments and distill it into compact markdown using budget mode, focused on 'payment intents', and keep it under 1500 tokens so I can pass it to my LLM without blowing the context window.","exampleUseCases":[{"title":"Token-efficient competitor research","prompt":"Pull the page at https://www.competitor.com/pricing and distill it into structured mode so I get clean tables and metadata without all the HTML noise — I need to compare their pricing tiers."},{"title":"Query-focused documentation summarization","prompt":"Distill https://docs.openai.com/api-reference into budget mode with the query 'rate limits' and cap it at 800 tokens — I only need the bits relevant to rate limiting."},{"title":"Skeleton outline of a long article","prompt":"Fetch https://en.wikipedia.org/wiki/Large_language_model and give me a skeleton outline so I can see the high-level structure without reading the whole page."}],"resultDescription":"Returns a JSON object with a 'data' field containing the distilled content (Markdown, structured JSON, skeleton, or BM25 excerpt depending on mode), plus an 'roi_proof' object showing raw_tokens, distilled_tokens, tokens_saved, compression_ratio_pct, roi_multiplier, and llm_cost_saved_usd. Also includes cache status (HIT/MISS) and billing details.","failureModes":["Invalid or unreachable URL returns an error status","max_tokens below minimum of 20 is rejected","mode=budget without a query may yield unfiltered results","Rate limiting or paywalled pages may return incomplete content","Raw HTML input that is malformed may degrade distillation quality","Payment failure (402) if USDC balance is insufficient"],"whenToPreferThis":"Choose this endpoint when you need to pass web content to an LLM but want to minimize token usage and cost — especially when the source page is large, noisy, or HTML-heavy. Prefer budget mode + a BM25 query when you only need a specific section of the page. Use structured mode when you need clean tables or metadata. This is distinct from a full web crawler — it distills a single URL at a time with tight token control.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:24:36.429Z","isFirstParty":false,"canonicalSlug":"company-enrich-agentdiet-dev-semantic-html-pruner-web-url-distiller-e91aeb9c"}