{"uid":"cap_h4zwfvC5FULhSLBq6P-mS","slug":"hn-pulse-agentdiet-dev-semantic-html-pruner-with-bm25-budget-control-5f462efc","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://hn-pulse.agentdiet.dev/v1/semantic-html-pruner)","url":"https://hn-pulse.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_OTGsrgUOxGXz_lBlp_LTg","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"hn-pulse.agentdiet.dev","brandSlug":"hn-pulse-agentdiet-dev-mpp","brandBaseUrl":"https://hn-pulse.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches and distills a URL or raw HTML into clean Markdown, structured JSON, a skeleton outline, or a BM25-ranked token-budget excerpt, with ROI proof of compression savings.","exampleAgentPrompt":"Fetch https://stripe.com/docs/payments and distill it into clean markdown using budget mode, focused on the query 'payment intents', with a max of 500 tokens — and show me how many tokens you saved.","exampleUseCases":[{"title":"Token-budget RAG preprocessing","prompt":"Pull https://docs.openai.com/api-reference and distill it in budget mode with the query 'function calling' and a ceiling of 800 tokens so I can feed just the relevant section to my model."},{"title":"Structured data extraction from product page","prompt":"Take this raw HTML from an e-commerce page and distill it in structured mode so I get the product tables, prices, and metadata as clean JSON — no nav bars or footers."},{"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 document structure and headings without reading the whole thing."}],"resultDescription":"Returns a JSON object with: a 'data' field containing the distilled output (Markdown string, structured JSON tables/metadata, skeleton outline, or BM25 excerpt depending on mode); an 'roi_proof' object showing raw_tokens, distilled_tokens, tokens_saved, compression_ratio_pct, roi_multiplier, and llm_cost_saved_usd; a 'status' field ('ok'); optional cache metadata (HIT/MISS, latency_ms); and optional billing metadata (fee_charged_usd).","failureModes":["URL is unreachable or returns non-200 — endpoint may error or return empty content","HTML payload too large to process within platform limits","mode=budget used without a query field — BM25 ranking has no focus term","max_tokens set below minimum of 20 — schema validation error","Rate limiting or payment failure via x402 — 402 response requiring payment","Page behind authentication/paywall — fetched HTML contains login wall, not content"],"whenToPreferThis":"Choose this endpoint when you need to reduce token consumption before passing web content to an LLM — especially when you have a strict token budget, want BM25-ranked relevance filtering around a specific query, or need web content in a clean structured form (Markdown, JSON tables, or outline). It is particularly valuable for agentic RAG pipelines, documentation ingestion, and cost-reduction workflows where raw HTML would be prohibitively large.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:32:48.067Z","isFirstParty":false,"canonicalSlug":"hn-pulse-agentdiet-dev-semantic-html-pruner-with-bm25-budget-control-5f462efc"}