{"uid":"cap_UC8gLPf0h1BlFNiw8OD6X","slug":"prompt-guard-agentdiet-dev-web-article-distiller-with-bm25-budget-96b6f96b","name":"Web Article Distiller 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://prompt-guard.agentdiet.dev/v1/article-extractor)","url":"https://prompt-guard.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_h2sal6xsTBwUCkc9jIE_k","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"prompt-guard.agentdiet.dev","brandSlug":"prompt-guard-agentdiet-dev-mpp","brandBaseUrl":"https://prompt-guard.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches and distills a URL or raw HTML into clean Markdown, structured JSON, skeleton outline, or a BM25-ranked token-budget excerpt","exampleAgentPrompt":"Pull the article at https://www.bbc.com/news/technology and distill it into clean markdown, keeping it under 500 tokens and focused on the topic of AI regulation.","exampleUseCases":[{"title":"Research digest from news article","prompt":"Fetch https://www.wired.com/story/openai-gpt4-analysis and distill it into structured markdown so I can read the key points without all the ads and clutter."},{"title":"Token-budget extraction for LLM context","prompt":"I need to feed this long Wikipedia page https://en.wikipedia.org/wiki/Large_language_model into my AI pipeline — can you distill it down to at most 800 tokens focused on the query 'training data and scaling laws'?"},{"title":"Raw HTML cleanup for downstream processing","prompt":"I've got this raw HTML from a product page — can you distill it into structured JSON tables pulling out the pricing and feature information?"}],"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 vs distilled token counts, compression ratio percentage, tokens saved, 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 status — endpoint may return an error status","Raw HTML is empty or malformed — distillation may return minimal or empty output","max_tokens set too low (below 20) — rejected by schema validation","BM25 query provided without mode=budget — query may be ignored","Target site blocks crawlers or returns CAPTCHA — content unavailable","Payment not provided — HTTP 402 returned requiring x402 micropayment"],"whenToPreferThis":"Choose this endpoint when you need to reduce web content to fit within an LLM context window, especially when you want BM25-ranked relevance filtering against a specific query. It is ideal when you need token-efficient web reading with measurable ROI (tokens saved, cost saved). Prefer it over generic scrapers when you need distillation modes (markdown, structured, skeleton, budget) rather than raw HTML, and when you want built-in token accounting for cost-aware agent pipelines.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:32:24.450Z","isFirstParty":false,"canonicalSlug":"prompt-guard-agentdiet-dev-web-article-distiller-with-bm25-budget-96b6f96b"}