{"uid":"cap_6RDZtXlVxFqA7PmNg3ZLw","slug":"company-enrich-agentdiet-dev-semantic-html-pruner-with-bm25-budget-0051f21d","name":"Semantic HTML Pruner with BM25 Budget Control","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":"POST","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_FKR2-hOuds2pR5_P4pLno","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 and distills a URL or raw HTML into clean Markdown, structured JSON, a skeleton outline, or a BM25-focused token-budget excerpt — returning compression metrics and LLM cost savings.","exampleAgentPrompt":"Strip down https://stripe.com/docs/payments/payment-intents to clean markdown using budget mode focused on 'payment confirmation flow', keeping it under 800 tokens — I want to see how many tokens you saved.","exampleUseCases":[{"title":"Token-efficient documentation ingestion","prompt":"Fetch https://docs.openai.com/api-reference and distill it in budget mode with the query 'function calling' and a max of 1000 tokens — I need just the relevant parts without blowing my context window."},{"title":"Structured data extraction from landing page","prompt":"Pull https://www.competitor.com/pricing and distill it in structured mode so I get the pricing tables and metadata as clean JSON — I want to compare their tiers."},{"title":"Clean markdown from a news article","prompt":"Take this raw HTML I'm pasting and convert it to clean markdown so my agent can read the article without all the nav, ads, and footer noise."}],"resultDescription":"Returns a 'data' object containing the distilled content (Markdown text, structured JSON tables/metadata, skeleton outline, or BM25-focused excerpt depending on mode), alongside an roi_proof block showing raw_tokens, distilled_tokens, tokens_saved, compression_ratio_pct, and llm_cost_saved_usd, plus optional cache hit/miss info and billing details.","failureModes":["URL unreachable or returns non-200 HTTP status — endpoint may return an error status","HTML payload too large or malformed — distillation may fail or return partial results","max_tokens set below minimum (20) — request rejected with validation error","mode=budget used without a query — BM25 ranking has no focus signal, output may be low quality","Payment not attached or insufficient — HTTP 402 returned requiring x402 USDC payment","Idempotency-Key reuse with different parameters — may return cached result from prior call"],"whenToPreferThis":"Choose this endpoint when you need to feed web page content to an LLM but want to minimize token usage and cost — especially when you need BM25-ranked budget control to focus on a specific query within a token ceiling. It is preferable over raw fetch-and-pass approaches when page bloat is a concern, and over generic scrapers when you need LLM-ready output formats (Markdown, structured JSON, skeleton). Ideal for agent pipelines where context window efficiency matters.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:34:44.217Z","isFirstParty":false,"canonicalSlug":"company-enrich-agentdiet-dev-semantic-html-pruner-with-bm25-budget-0051f21d"}