{"uid":"cap_C-a9UNtXvAn2sSe_ajdBN","slug":"cve-intel-agentdiet-dev-web-url-distiller-with-bm25-budget-control-8e725f02","name":"Web URL 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://cve-intel.agentdiet.dev/v1/article-extractor)","url":"https://cve-intel.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_b8WLhtNs4i6cirWxdWFqF","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"cve-intel.agentdiet.dev","brandSlug":"cve-intel-agentdiet-dev-mpp","brandBaseUrl":"https://cve-intel.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches and distills any webpage URL (or raw HTML) into compact, agent-ready tokens using configurable extraction modes including BM25-ranked budget excerpts","exampleAgentPrompt":"Can you fetch https://techcrunch.com/2024/01/15/openai-update and distill it into a focused excerpt about safety announcements, keeping it under 300 tokens using budget mode?","exampleUseCases":[{"title":"CVE article extraction for security agent","prompt":"Grab the content from https://nvd.nist.gov/vuln/detail/CVE-2024-12345 and distill it into structured JSON so I can pull out the severity score, affected products, and remediation steps."},{"title":"Token-budget news summarization","prompt":"Distill https://www.reuters.com/technology/ai-regulation-news-2024 into markdown but cap it at 200 tokens — use budget mode with 'AI regulation Europe' as the focus query."},{"title":"Competitive research page skeleton","prompt":"Can you fetch https://stripe.com/pricing and give me just the skeleton outline of the page structure? I want to see the headings and key sections without all the detail."}],"resultDescription":"Returns a JSON object with: a 'data' field containing the distilled content (Markdown text, structured JSON tables/metadata, skeleton outline, or BM25-ranked excerpt depending on mode); an 'roi_proof' object showing raw_tokens, distilled_tokens, tokens_saved, compression_ratio_pct, roi_multiplier, and llm_cost_saved_usd; optional 'cache' metadata (HIT/MISS, latency_ms); optional 'billing' metadata; and a 'status' field confirming execution.","failureModes":["URL is unreachable or returns non-200 HTTP status — endpoint may return an error status","URL points to non-HTML content (PDF, binary) that cannot be parsed — distillation may fail or return empty data","max_tokens set below minimum of 20 — request rejected with validation error","mode=budget used without providing a query — BM25 ranking has no focus signal","Raw HTML provided via html parameter is malformed — distillation may produce incomplete output","Rate limiting or payment failure via x402 — request blocked with 402 Payment Required"],"whenToPreferThis":"Choose this endpoint when your agent needs to read web pages without blowing through its token budget — especially when you want BM25-ranked excerpts focused on a specific query, or when you need structured/skeleton extraction rather than raw HTML parsing. Ideal for research agents, CVE monitoring pipelines, and any workflow that needs to ingest many URLs efficiently. Prefer this over generic scrapers when token compression ROI and cost savings metrics matter to your workflow.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:25:45.469Z","isFirstParty":false,"canonicalSlug":"cve-intel-agentdiet-dev-web-url-distiller-with-bm25-budget-control-464618d3"}