{"uid":"cap_Qe_48cjthVQ7YYw85eIyT","slug":"preflight-agentdiet-dev-web-url-to-markdown-distiller-with-bm25-1c06f5f6","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/html-to-markdown)","url":"https://preflight.agentdiet.dev/v1/html-to-markdown?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_OJtkDFJkSq13vle7LCex-","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 or raw HTML and distills it into compact, token-efficient markdown, structured JSON, skeleton outline, or BM25-focused excerpt with strict token budget controls","exampleAgentPrompt":"Fetch https://stripe.com/docs/payments and distill it into compact markdown using budget mode, focusing on 'payment intents', and keep it under 500 tokens.","exampleUseCases":[{"title":"Compress docs page for agent context","prompt":"Grab https://docs.anthropic.com/claude/reference and distill it into tight markdown so I can fit it into my agent's context window without burning too many tokens."},{"title":"BM25-focused excerpt for research agent","prompt":"Pull https://en.wikipedia.org/wiki/Large_language_model and give me only the parts relevant to 'training data and scaling laws' — budget mode, max 300 tokens."},{"title":"Structured table extraction from webpage","prompt":"Fetch https://coinmarketcap.com/currencies/bitcoin/ and extract it in structured mode so I get the tables and metadata as clean JSON."}],"resultDescription":"Returns a JSON object containing the distilled content (markdown text, structured tables/metadata, skeleton outline, or BM25-focused excerpt depending on mode), plus an roi_proof block showing raw vs distilled token counts, compression ratio, tokens saved, and estimated LLM cost saved in USD. Also includes cache status and billing details.","failureModes":["Invalid or unreachable URL returns an error status","Paywalled or bot-blocked pages may return empty or partial content","Token budget too low (below 20) is rejected by schema validation","BM25 query mode without a query string may return unfiltered content","Rate limiting or payment failures from x402 micropayment flow","Malformed raw HTML input may produce garbled markdown output"],"whenToPreferThis":"Choose this endpoint when you need to feed webpage content to an LLM but want to minimize token usage and cost — especially when working with long documentation pages, research articles, or data-heavy sites. It is particularly valuable in budget mode when you have a strict context window limit and want BM25-ranked relevance to a specific query. Prefer it over generic web scrapers when token efficiency and structured output (tables, metadata, skeleton) matter to your agent workflow.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T15:01:49.623Z","isFirstParty":false,"canonicalSlug":"preflight-agentdiet-dev-web-url-to-markdown-distiller-with-bm25-1c06f5f6"}