{"uid":"cap_zuu3r0YoBU5A1Jqxj8Zd0","slug":"domain-osint-agentdiet-dev-web-url-article-extractor-token-distiller-90587727","name":"Web URL Article Extractor & Token Distiller","description":"Distill a URL or raw HTML payload with BM25 budget control (Live x402 v2, IETF MPP & MCP endpoint at https://domain-osint.agentdiet.dev/v1/article-extractor)","url":"https://domain-osint.agentdiet.dev/v1/article-extractor?utm_source=zero.xyz","method":"GET","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_ZpB-RH5J5HEzEDKxBx6lx","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"domain-osint.agentdiet.dev","brandSlug":"domain-osint-agentdiet-dev-mpp","brandBaseUrl":"https://domain-osint.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches a webpage URL (or raw HTML) and distills it into compact, agent-ready tokens using BM25 budget control and multiple extraction modes","exampleAgentPrompt":"Fetch https://stripe.com/docs/api and distill it into markdown, keeping it under 2000 tokens and focusing the BM25 query on 'payment intents'.","exampleUseCases":[{"title":"LLM cost reduction for documentation","prompt":"Grab the content from https://docs.openai.com/api-reference and compress it into a budget of 1500 tokens using BM25 focused on 'embeddings', so I can include it in my prompt without blowing my token limit."},{"title":"Structured data extraction from news article","prompt":"Extract the article at https://techcrunch.com/2024/01/15/funding-round-story in structured mode so I get clean JSON tables and metadata rather than raw HTML."},{"title":"Skeleton outline of a long webpage","prompt":"Give me a skeleton outline of https://en.wikipedia.org/wiki/Large_language_model so I can see the section headers and structure without reading the whole page."}],"resultDescription":"Returns a JSON object with a 'data' field containing the distilled content (markdown, structured JSON, skeleton, or BM25 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 hit/miss status, latency, billing info, and execution status.","failureModes":["Invalid or unreachable URL returns an error status","URL that blocks bots or requires JavaScript rendering may return incomplete content","max_tokens set too low may produce truncated or empty output","mode=budget without a query parameter may fall back to default behavior","Rate limiting or payment failure (402) if x402 payment is not properly configured","HTML parsing failures on malformed or unusual page structures"],"whenToPreferThis":"Choose this endpoint when you need to reduce token overhead from web content before feeding it into an LLM — especially when working with documentation pages, news articles, or any URL where raw HTML would be too large. It is ideal when you have a strict token budget (use mode=budget with max_tokens and a BM25 query), need structured metadata extraction, or want a skeleton outline for navigation. Prefer it over generic scrapers when LLM cost efficiency and compression ratio transparency matter.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:21:54.626Z","isFirstParty":false,"canonicalSlug":"domain-osint-agentdiet-dev-web-url-article-extractor-token-distiller-90587727"}