{"uid":"cap_WLD6SuDex-7r3l9-1SMkp","slug":"preflight-agentdiet-dev-web-url-to-markdown-distiller-with-bm25-df9ebf30","name":"Web URL to Markdown 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://preflight.agentdiet.dev/v1/markdown-distill)","url":"https://preflight.agentdiet.dev/v1/markdown-distill?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_Jjv1EMka2j1kdIs9aKr2c","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 a webpage by URL (or accepts raw HTML) and distills it into compact, agent-ready markdown, structured JSON, skeleton outline, or BM25-focused budget excerpt with token savings metrics","exampleAgentPrompt":"Fetch https://stripe.com/docs/payments and distill it into compact markdown using budget mode, focused on 'payment intents', keeping it under 500 tokens.","exampleUseCases":[{"title":"Documentation page for agent context","prompt":"Grab https://docs.openai.com/api-reference and distill it into clean markdown so I can include it in my agent's context window without blowing the token limit."},{"title":"BM25-focused excerpt for research query","prompt":"Distill https://en.wikipedia.org/wiki/Transformer_(machine_learning) in budget mode, focused on the query 'attention mechanism', max 300 tokens — I just need the relevant bits."},{"title":"Structured data extraction from web page","prompt":"Fetch https://news.ycombinator.com and distill it in structured mode so I get the top stories as a JSON table I can process programmatically."}],"resultDescription":"Returns a JSON object with a 'data' field containing the distilled content (markdown text, structured tables, skeleton outline, or BM25-focused excerpt depending on mode), plus an 'roi_proof' object showing raw_tokens, distilled_tokens, tokens_saved, compression_ratio_pct, and llm_cost_saved_usd. Also includes optional cache hit/miss status and billing details.","failureModes":["URL is unreachable or returns non-200 — endpoint may return an error status","HTML payload is malformed or empty — distillation may produce minimal or no output","max_tokens set too low — content may be severely truncated or empty","BM25 query does not match any content — budget mode may return very little","Rate limiting or payment failure via x402 — call rejected with 402 status","Invalid mode enum value — API returns validation error"],"whenToPreferThis":"Choose this endpoint when you need to fetch and compress a webpage into a form suitable for LLM context windows, especially when token budget is a concern. It is superior to raw web scraping when you need clean markdown, structured tables, or BM25-focused excerpts rather than raw HTML. Prefer budget mode when you have strict token limits and a known query focus. Best for agent pipelines that repeatedly read documentation, articles, or data pages and need to minimize LLM costs.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:26:26.865Z","isFirstParty":false,"canonicalSlug":"preflight-agentdiet-dev-web-url-to-markdown-distiller-with-bm25-1c06f5f6"}