{"uid":"cap_rzEnr5mYmdnnbGJA374Cz","slug":"email-verify-agentdiet-dev-web-article-distiller-token-budget-4f679206","name":"Web Article Distiller & Token Budget Compressor","description":"Distill a URL or raw HTML payload with BM25 budget control (Live x402 v2, IETF MPP & MCP endpoint at https://email-verify.agentdiet.dev/v1/article-extractor)","url":"https://email-verify.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_nzBDC6fQ2t5_fV4GB7Z5S","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"email-verify.agentdiet.dev","brandSlug":"email-verify-agentdiet-dev-mpp","brandBaseUrl":"https://email-verify.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches a URL or raw HTML and distills it into compact agent-ready tokens using markdown, structured, skeleton, or BM25-budget modes with token savings reporting","exampleAgentPrompt":"Can you fetch https://stripe.com/docs/payments and distill it into clean markdown, keeping it under 800 tokens focused on 'payment intents'?","exampleUseCases":[{"title":"Research article token compression","prompt":"Grab the article at https://techcrunch.com/2024/05/01/openai-gpt5-launch and distill it into markdown so I can fit it into my prompt without blowing my context window."},{"title":"Budget-constrained competitor page extraction","prompt":"Fetch https://www.anthropic.com/product and give me only the most relevant content about 'pricing and rate limits' — keep it under 500 tokens using budget mode."},{"title":"Structured data extraction from documentation","prompt":"Pull https://docs.github.com/en/rest and extract it in structured mode so I get the tables, metadata, and key sections as JSON instead of raw HTML."}],"resultDescription":"Returns a 'data' object containing the distilled content (markdown text, structured JSON tables/metadata, skeleton outline, or BM25-ranked budget excerpt), along with an roi_proof block showing raw_tokens, distilled_tokens, tokens_saved, compression_ratio_pct, and llm_cost_saved_usd. Also includes cache status (HIT/MISS) and billing details.","failureModes":["URL unreachable or returns non-200 status — endpoint cannot fetch content","URL points to non-HTML content (PDF, binary) without raw HTML fallback","max_tokens set below minimum (20) — schema validation error","BM25 query provided without mode=budget — query may be ignored","Rate limiting or payment failure via x402 — billing error returned","Malformed URL input — fails minLength or format validation"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to ingest web content but must stay within a token budget or minimize LLM context costs. It is especially valuable when the raw HTML of a page is too large for direct inclusion, when you need BM25-focused extraction around a specific query, or when you want structured tables and metadata rather than raw text. Prefer it over generic scrapers when you need built-in ROI/compression metrics and multiple distillation modes in a single call.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:20:49.479Z","isFirstParty":false,"canonicalSlug":"email-verify-agentdiet-dev-web-article-distiller-token-budget-4f679206"}