{"uid":"cap_W-DLfWicHe3rFoErXsJj3","slug":"x402broker-com-article-extractor-with-bm25-budget-control-1dfc3274","name":"Article Extractor 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://x402broker.com/v1/article-extractor)","url":"https://x402broker.com/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_llqWSqwSbWO06wOf2qudR","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"x402broker.com","brandSlug":"x402broker-com-mpp","brandBaseUrl":"https://x402broker.com","brandDocsUrl":null,"whatItDoes":"Fetches and distills a URL or raw HTML into Markdown, structured data, or a token-budget excerpt using BM25 relevance scoring","exampleAgentPrompt":"Grab the article at https://techcrunch.com/2024/05/10/openai-funding and distill it into clean Markdown, keeping it under 800 tokens — use 'OpenAI funding round' as the focus query so I get only the most relevant parts.","exampleUseCases":[{"title":"LLM context window compression","prompt":"Take this URL https://docs.stripe.com/payments/payment-intents and distill it into a tight token budget of 500 tokens, focusing on 'payment intent lifecycle' so I can drop it straight into my LLM prompt without blowing the context window."},{"title":"Structured data extraction from news article","prompt":"Pull the article at https://reuters.com/markets/us/fed-rate-decision-2024 and return it as structured JSON with tables and metadata — I need the key figures and dates organized, not raw text."},{"title":"Webpage outline for research agent","prompt":"Give me a skeleton outline of https://en.wikipedia.org/wiki/Large_language_model — just the section headers and key structure so I can decide which parts are worth deep-reading."}],"resultDescription":"Returns a JSON object containing distilled content (Markdown text, structured JSON tables/metadata, skeleton outline, or BM25-scored budget excerpt depending on mode), plus ROI proof metrics (raw vs distilled token counts, compression ratio, estimated LLM cost saved), cache status (HIT/MISS), and billing details. The data field holds the actual distilled output.","failureModes":["Invalid or unreachable URL returns fetch error","Token budget too low (below 20) returns validation error","HTML payloads that are JavaScript-rendered may not parse correctly","Rate limiting or payment failure via x402 returns 402 status","Malformed HTML may produce incomplete distillation","BM25 query with no matching content may return minimal excerpt"],"whenToPreferThis":"Choose this endpoint when you need to feed web content into an LLM with strict token budgets, want BM25-relevance-filtered excerpts rather than full-page dumps, or need structured/skeleton extraction rather than raw HTML. Prefer it over generic scrapers when token cost savings and compression metrics matter, or when you want multiple distillation modes (markdown, structured, skeleton, budget) from a single API call at $0.001 per call.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:32:35.406Z","isFirstParty":false,"canonicalSlug":"x402broker-com-article-extractor-with-bm25-budget-control-1dfc3274"}