{"uid":"cap_vUq95InnWaLbFkkg6vCZF","slug":"prompt-guard-agentdiet-dev-web-url-distiller-with-bm25-budget-control-604355a9","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://prompt-guard.agentdiet.dev/v1/article-extractor)","url":"https://prompt-guard.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_PgvxzQyEBO0C0ycSpNfhX","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 web URL or raw HTML into compact, agent-ready tokens using multiple extraction modes including BM25 budget-constrained summarization","exampleAgentPrompt":"Distill the article at https://techcrunch.com/2024/01/15/openai-update into compact markdown, keeping it under 500 tokens and focused on the topic of AI regulation.","exampleUseCases":[{"title":"LLM cost-aware research summarization","prompt":"Grab the content at https://arxiv.org/abs/2401.12345 and compress it to under 300 tokens using budget mode, focused on the methodology section, so I can include it in my prompt without blowing my token limit."},{"title":"Structured data extraction from product page","prompt":"Pull the page at https://stripe.com/pricing and extract it in structured mode so I get the pricing tiers and feature tables as clean JSON I can reason over."},{"title":"Documentation skeleton for developer onboarding","prompt":"Fetch https://docs.github.com/en/actions and give me a skeleton outline of the page so I can understand the high-level structure before diving in."}],"resultDescription":"Returns a 'data' object containing the distilled content in the requested format (Markdown, structured JSON, skeleton, or BM25 excerpt), along with an 'roi_proof' block showing raw_tokens, distilled_tokens, tokens_saved, compression_ratio_pct, llm_cost_saved_usd, and roi_multiplier. Also includes cache status and billing details.","failureModes":["Invalid or unreachable URL returns an error status","max_tokens below 20 rejected with validation error","mode=budget without a query may return unfiltered or fallback content","Paywalled or JavaScript-heavy pages may yield partial or empty extraction","Rate limiting or payment failure (x402) blocks the request"],"whenToPreferThis":"Choose this endpoint when you need to reduce token overhead before passing web content to an LLM — especially when working within a strict token budget or cost constraint. It is ideal for agentic pipelines that routinely fetch and process URLs, where BM25-focused extraction can target only the relevant passage rather than the full page. Prefer it over generic scrapers when you need ROI proof of compression savings or structured/skeleton modes for downstream parsing.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:25:55.937Z","isFirstParty":false,"canonicalSlug":"prompt-guard-agentdiet-dev-web-url-distiller-with-bm25-budget-control-247ee8c7"}