{"uid":"cap_fILW-pBCY6D5DiVlsG2LE","slug":"serp-extract-agentdiet-dev-url-to-markdown-distiller-with-bm25-budget-2671d190","name":"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://serp-extract.agentdiet.dev/v1/url-to-markdown)","url":"https://serp-extract.agentdiet.dev/v1/url-to-markdown?utm_source=zero.xyz","method":"POST","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_uhatBrGW7FbTO0M5gsRZn","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"serp-extract.agentdiet.dev","brandSlug":"serp-extract-agentdiet-dev-mpp","brandBaseUrl":"https://serp-extract.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches a URL or accepts raw HTML and distills it into compact, token-efficient Markdown with optional BM25-ranked budget capping for query-focused extraction.","exampleAgentPrompt":"Fetch https://stripe.com/docs/payments and distill it into markdown using budget mode, focused on the query 'payment intents', with a max of 500 tokens.","exampleUseCases":[{"title":"Token-budget article extraction for RAG","prompt":"Grab this news article at https://techcrunch.com/2024/01/15/openai-update and distill it down to at most 300 tokens in budget mode, focused on the query 'funding round', so I can feed it into my RAG pipeline without blowing my token budget."},{"title":"Structured table extraction from docs page","prompt":"Pull the pricing page at https://anthropic.com/pricing and distill it into structured mode so I get JSON tables of all their model tiers and costs."},{"title":"Skeleton outline of a long research page","prompt":"Take this raw HTML I have from a Wikipedia article on transformer architecture and give me a skeleton outline of its sections so I can decide which parts to read in full."}],"resultDescription":"Returns a JSON object with a 'data' field containing the distilled content (Markdown string, 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, and estimated LLM cost saved in USD. Also includes optional cache hit/miss status and billing details.","failureModes":["URL is unreachable or returns non-200 status — endpoint may return an error status","max_tokens set below 20 — rejected by schema validation","HTML input is empty or malformed — distillation may return minimal or empty content","BM25 query provided without mode=budget — query may be ignored","Rate limiting or payment failure via x402 — HTTP 402 returned if payment not attached"],"whenToPreferThis":"Choose this endpoint when you need to convert a live webpage or raw HTML into compact, LLM-ready Markdown while controlling token costs — especially when using the BM25 budget mode to focus extraction on a specific query within a strict token ceiling. It is particularly useful over generic scraping APIs when you need quantified compression metrics (tokens saved, cost saved) and when operating in cost-sensitive agentic pipelines where every token counts.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:33:14.869Z","isFirstParty":false,"canonicalSlug":"serp-extract-agentdiet-dev-url-to-markdown-distiller-with-bm25-budget-2671d190"}