{"uid":"cap_3BKdafcUYUwXKn_Znbqf9","slug":"alpha-stream-agentdiet-dev-web-url-article-extractor-distiller-7a26a6c3","name":"Web URL Article Extractor & Distiller","description":"Distill a URL or raw HTML payload with BM25 budget control (Live x402 v2, IETF MPP & MCP endpoint at https://alpha-stream.agentdiet.dev/v1/article-extractor)","url":"https://alpha-stream.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_73nfkza-FPtrcSS5xyGLI","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"alpha-stream.agentdiet.dev","brandSlug":"alpha-stream-agentdiet-dev-mpp","brandBaseUrl":"https://alpha-stream.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches a webpage by URL (or accepts raw HTML) and distills it into compact, token-efficient Markdown, structured JSON, skeleton outline, or BM25-focused budget excerpt for AI agents.","exampleAgentPrompt":"Distill the article at https://techcrunch.com/2024/05/01/openai-news into clean markdown, and if there's too much content use budget mode with a 500-token ceiling focused on 'OpenAI funding'.","exampleUseCases":[{"title":"Research article extraction for agent","prompt":"Grab the content from https://www.nature.com/articles/d41586-024-00001-0 and distill it into clean markdown so I can read the key findings without all the webpage clutter."},{"title":"Token-budget web summarization","prompt":"Fetch https://stripe.com/docs/payments/accept-a-payment and give me a tight summary in budget mode focused on 'Accept a payment' — keep it under 300 tokens so it fits in my prompt."},{"title":"Structured data extraction from webpage","prompt":"Pull the page at https://en.wikipedia.org/wiki/Large_language_model and distill it into structured mode so I can get the tables and metadata as JSON."}],"resultDescription":"Returns a JSON object with a 'data' field containing the distilled content (Markdown text, structured JSON tables/metadata, skeleton outline, or BM25-focused excerpt depending on mode), plus an 'roi_proof' object showing raw token count, distilled token count, tokens saved, compression ratio percentage, and estimated LLM cost saved in USD. Also includes optional cache hit/miss status and billing details.","failureModes":["URL is unreachable or returns non-200 HTTP status — endpoint may return an error status","Paywalled or JavaScript-rendered pages may yield incomplete or empty content","max_tokens set too low may produce truncated or empty budget excerpts","Raw HTML input is malformed or empty, yielding no extractable content","Payment/402 failure if agent wallet has insufficient USDC balance"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to ingest webpage content but must stay within token budgets or minimize LLM costs — especially when BM25 query-focused extraction is needed to zero in on relevant sections. Prefer over generic scraping tools when you need token-count ROI metrics or multiple distillation modes (markdown, structured, skeleton, budget) in a single call. Ideal for agents doing research, document parsing, or RAG pipelines where raw HTML would be too noisy and expensive.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:25:36.871Z","isFirstParty":false,"canonicalSlug":"alpha-stream-agentdiet-dev-web-url-article-extractor-distiller-7a26a6c3"}