{"uid":"cap_nfSO-5QNq3bMPLGVDpTLV","slug":"mesh-agentdiet-dev-article-extractor-with-bm25-budget-control-4f81d340","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://mesh.agentdiet.dev/v1/article-extractor)","url":"https://mesh.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_rbMj2VYtAB9N1gaRD43GY","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"mesh.agentdiet.dev","brandSlug":"mesh-agentdiet-dev-mpp","brandBaseUrl":"https://mesh.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches and distills a URL or raw HTML into clean Markdown, structured JSON, skeleton outline, or BM25-ranked token-budget excerpt","exampleAgentPrompt":"Pull the main article content from https://example.com/news/article and distill it using budget mode focused on 'AI regulation' with a max of 500 tokens, so I can read just the relevant parts without wasting tokens.","exampleUseCases":[{"title":"Token-budget webpage research","prompt":"Fetch https://openai.com/research/gpt-4 and distill it in budget mode with the query 'model architecture and parameters', keeping it under 300 tokens so I only get the relevant sections."},{"title":"HTML-to-Markdown conversion for doc pipeline","prompt":"I have this raw HTML from our CMS — can you distill it into clean Markdown so I can feed it into our documentation pipeline? Here's the HTML: <html>...</html>"},{"title":"Structured data extraction from article","prompt":"Go to https://techcrunch.com/2024/01/15/some-article and extract it in structured mode so I get the metadata, tables, and key facts as JSON rather than raw text."}],"resultDescription":"Returns a `data` object containing the distilled content in the requested format (Markdown text, structured JSON with tables/metadata, skeleton outline, or BM25-ranked excerpt), plus an `roi_proof` block showing raw_tokens, distilled_tokens, tokens_saved, compression_ratio_pct, roi_multiplier, and llm_cost_saved_usd. Also includes cache status (HIT/MISS) and billing details.","failureModes":["Invalid or unreachable URL returns a fetch error","HTML too large or malformed may fail distillation","mode=budget without a query or max_tokens may produce suboptimal output","Rate limiting or payment failure ($0.001/call via x402) blocks execution","Private or paywalled pages may return empty or partial content","max_tokens set too low may truncate meaning fully"],"whenToPreferThis":"Choose this endpoint when you need to fetch and clean web content for LLM consumption while minimizing token usage — especially with budget mode + BM25 query for topic-focused extraction. Prefer it over generic scrapers when you need ROI proof (tokens saved, cost reduced) or when you want structured JSON output from articles. The built-in token budget ceiling (max_tokens) makes it ideal for cost-constrained agent pipelines.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:30:20.804Z","isFirstParty":false,"canonicalSlug":"mesh-agentdiet-dev-article-extractor-with-bm25-budget-control-4f81d340"}