{"uid":"cap_v_L6JdGvLmZ7ZzX-7ZlCH","slug":"x402-audit-agentdiet-dev-web-url-markdown-distillation-with-bm25-f84499cf","name":"Web URL Markdown 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://x402-audit.agentdiet.dev/v1/markdown-distill)","url":"https://x402-audit.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_-h_ljT7IcTZgYVK2VV1WZ","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"x402-audit.agentdiet.dev","brandSlug":"x402-audit-agentdiet-dev-mpp","brandBaseUrl":"https://x402-audit.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches a webpage 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 proof","exampleAgentPrompt":"Distill https://stripe.com/docs/payments into compact markdown, using budget mode focused on 'payment intents' with a max of 500 tokens, so I can feed the key content into my agent without burning context.","exampleUseCases":[{"title":"Token-budget docs extraction for agent","prompt":"Grab the Stripe docs at builtin://stripe-docs and distill them in budget mode, focusing the BM25 query on 'webhooks', capped at 300 tokens — I need just the relevant bits for my agent's context window."},{"title":"Structured data from a product page","prompt":"Fetch https://example.com/product/electric-bike and distill it in structured mode so I get JSON tables of specs, pricing, and metadata — no fluff, just the parseable data."},{"title":"Skeleton outline of a long article","prompt":"Take this URL https://techcrunch.com/2024/01/ai-trends and give me a skeleton outline of the page structure and headings so I can quickly navigate what's covered without reading the whole thing."}],"resultDescription":"Returns a JSON object with a 'data' field containing the distilled content (Markdown string, structured JSON tables/metadata, skeleton outline, or BM25-focused excerpt depending on mode), plus an 'roi_proof' object showing raw_tokens, distilled_tokens, tokens_saved, compression_ratio_pct, roi_multiplier, and llm_cost_saved_usd. Also includes optional cache hit/miss info and billing details.","failureModes":["Invalid or unreachable URL returns an error status","max_tokens below minimum of 20 causes validation error","mode=budget without a query may return unfocused results","Raw HTML too large may be truncated or rejected","Rate limits or payment failures (HTTP 402) block the request","Non-public or paywalled pages may return empty or partial content"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to ingest web content within tight token constraints, especially when LLM context cost matters. It is particularly valuable for fetching documentation pages, product pages, or articles and reducing them to only the semantically relevant portion via BM25 focus. Prefer this over raw fetch-and-paste when token budget control, compression metrics, or structured extraction (tables, metadata) are needed alongside the content.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:21:27.510Z","isFirstParty":false,"canonicalSlug":"x402-audit-agentdiet-dev-web-url-markdown-distillation-with-bm25-f84499cf"}