{"uid":"cap_xljebk4N8cfCK7Nsm53XN","slug":"llms-generator-agentdiet-dev-semantic-html-pruner-with-bm25-budget-8d7fc6e8","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://llms-generator.agentdiet.dev/v1/semantic-html-pruner)","url":"https://llms-generator.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_DcKGc2Fy4pLrqMAuHuyNC","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"llms-generator.agentdiet.dev","brandSlug":"llms-generator-agentdiet-dev-mpp","brandBaseUrl":"https://llms-generator.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches a URL or accepts raw HTML and distills it into token-efficient Markdown, structured JSON, skeleton outline, or BM25-ranked budget excerpt for AI agent consumption","exampleAgentPrompt":"Can you distill https://stripe.com/docs/api into clean Markdown, keeping it under 2000 tokens and focusing on the query 'authentication and API keys'?","exampleUseCases":[{"title":"Research page distillation for RAG pipeline","prompt":"Fetch https://openai.com/research/gpt-4 and distill it into structured Markdown under 1500 tokens — I want to feed it to my RAG pipeline without paying for all the nav and footer noise."},{"title":"BM25-focused competitor pricing extraction","prompt":"Grab https://anthropic.com/pricing and give me only the parts relevant to 'API token pricing tiers' using budget mode with a max of 800 tokens."},{"title":"Documentation skeleton for agent planning","prompt":"Take the raw HTML of the Stripe webhooks docs page I'm pasting and return a skeleton outline so my agent can plan which sections to read in detail."}],"resultDescription":"Returns a JSON object with a 'data' field containing the distilled content (Markdown text, structured JSON tables/metadata, a skeleton outline, or a BM25-ranked budget excerpt depending on mode), plus an 'roi_proof' object showing raw_tokens, distilled_tokens, tokens_saved, compression_ratio_pct, llm_cost_saved_usd, and roi_multiplier, along with optional cache hit/miss status and billing details.","failureModes":["URL is unreachable or returns non-200 status — endpoint may return an error status","HTML payload is empty or malformed — distillation may return minimal or empty data","Token budget (max_tokens) set too low for meaningful content — excerpt may be truncated heavily","BM25 query provided without mode=budget — query may be ignored","Rate limiting or payment failure via x402 — request rejected before processing","URL blocks headless fetching (bot protection) — content fetch fails"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to consume web page content efficiently without burning large token budgets on raw HTML boilerplate, navigation, and scripts. It is especially valuable when you need BM25-ranked relevance filtering (mode=budget with a query) to extract only the portions of a page relevant to a specific question, or when you want structured JSON tables or a skeleton outline rather than raw Markdown. Prefer it over generic scrapers when token cost savings and ROI proof matter, and when working within constrained LLM context windows.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:37:23.746Z","isFirstParty":false,"canonicalSlug":"llms-generator-agentdiet-dev-semantic-html-pruner-with-bm25-budget-8d7fc6e8"}