{"uid":"cap_QO2E3HheyfFMqC5Pui_mR","slug":"hn-pulse-agentdiet-dev-bm25-budget-controlled-web-article-distiller-57245b09","name":"BM25 Budget-Controlled Web Article Distiller","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/article-extractor)","url":"https://hn-pulse.agentdiet.dev/v1/article-extractor?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_n6pQ8hSHH2vTPFrFcxl_9","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, skeleton outline, or a BM25-ranked token-budget excerpt","exampleAgentPrompt":"Distill https://techcrunch.com/2024/05/01/openai-gpt5/ into clean markdown using budget mode focused on 'model capabilities and benchmarks', keeping it under 800 tokens.","exampleUseCases":[{"title":"LLM-safe article ingestion pipeline","prompt":"Fetch https://www.wired.com/story/ai-regulation-2024/ and distill it into markdown so I can feed it to my LLM without wasting tokens on ads and navigation clutter."},{"title":"Query-focused budget excerpt for RAG","prompt":"I need only the most relevant passages from https://stripe.com/docs/payments/accept-a-payment about 'webhook event handling' — keep it under 500 tokens using budget mode."},{"title":"Structured metadata extraction from HTML","prompt":"Here's the raw HTML of a product page — can you distill it in structured mode to pull out the tables, prices, and metadata in clean JSON?"}],"resultDescription":"Returns a JSON object with a 'data' field containing the distilled content (Markdown string, structured JSON tables/metadata, skeleton outline, or BM25-ranked excerpt depending on mode), plus an 'roi_proof' object showing raw_tokens, distilled_tokens, tokens_saved, compression_ratio_pct, and llm_cost_saved_usd. Also includes cache status (HIT/MISS), billing info, and execution status.","failureModes":["URL is unreachable or returns non-200 — fetch fails with error status","HTML payload is empty or malformed — distillation returns minimal or empty data","mode=budget used without a query parameter — BM25 ranking cannot proceed","max_tokens set too low (below 20) — rejected by schema validation","Paywalled or JS-rendered pages may return incomplete content","Payment not provided — HTTP 402 returned requiring x402 USDC micropayment"],"whenToPreferThis":"Choose this endpoint when you need to feed web content to an LLM and want automatic token compression, BM25-focused excerpt extraction, or structured data parsing — especially when token cost matters. Prefer it over raw fetch/scrape tools when you want compression ratio reporting and multiple output modes (markdown, structured, skeleton, budget) in a single call. The BM25 budget mode is uniquely useful when you have a specific query and a strict context window.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:37:27.854Z","isFirstParty":false,"canonicalSlug":"hn-pulse-agentdiet-dev-bm25-budget-controlled-web-article-distiller-57245b09"}