{"uid":"cap_DUVY8aKqynGBjJnp2e85Y","slug":"preflight-agentdiet-dev-web-url-html-distillation-with-bm25-budget-0f423b35","name":"Web URL & HTML Distillation 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://preflight.agentdiet.dev/v1/article-extractor)","url":"https://preflight.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_5JuIkfNmZ5DXU_mpDdaAq","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"preflight.agentdiet.dev","brandSlug":"preflight-agentdiet-dev-mpp","brandBaseUrl":"https://preflight.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches and distills a web URL or raw HTML into compact, agent-ready tokens using configurable extraction modes and optional BM25 budget control","exampleAgentPrompt":"Distill this URL into clean markdown and keep it under 500 tokens, focusing on anything about pricing: https://example.com/pricing — use budget mode with that token ceiling.","exampleUseCases":[{"title":"Token-efficient research from live web","prompt":"I need to read this long documentation page without blowing my token budget — can you distill https://stripe.com/docs/payments into markdown and cap it at 800 tokens?"},{"title":"Focused BM25 excerpt for a specific question","prompt":"Fetch https://en.wikipedia.org/wiki/Transformer_(machine_learning_model) and extract only the parts relevant to 'attention mechanism', keeping it under 300 tokens in budget mode."},{"title":"Structured data extraction from a webpage","prompt":"Pull the tables and metadata from https://finance.yahoo.com/quote/AAPL into structured JSON format so I can see the key financial figures."}],"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), plus an 'roi_proof' object showing raw token count, distilled token count, tokens saved, compression ratio percentage, ROI multiplier, and estimated LLM cost saved in USD. Also includes cache status (HIT/MISS) and billing details.","failureModes":["URL is unreachable or returns a non-200 HTTP status — endpoint may return an error status","max_tokens set below 20 — rejected by schema validation","mode=budget used without a query — BM25 ranking may fall back to generic compression","HTML payload too large — may be truncated or time out","Paywalled or JavaScript-rendered pages may return minimal content","Payment not provided — returns HTTP 402 requiring x402 micropayment"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to read a webpage or HTML document but must minimize token usage or LLM cost. It is especially valuable when using mode=budget with a BM25 query to extract only the most relevant passages from a long page, or mode=structured to pull tables and metadata into JSON. Prefer it over generic scrapers when token compression ratio and cost savings are explicit requirements, or when the agent is operating under a strict context-window budget.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:26:35.838Z","isFirstParty":false,"canonicalSlug":"preflight-agentdiet-dev-web-url-html-distillation-with-bm25-budget-09303c73"}