{"uid":"cap_BWawVAyD0SSto5t5rD7Uv","slug":"serp-extract-agentdiet-dev-web-url-markdown-distiller-with-bm25-e2e8f15a","name":"Web URL Markdown Distiller with BM25 Budget Control","description":"Distill a web URL into compact agent-ready tokens (Live x402 v2, IETF MPP & MCP endpoint at https://serp-extract.agentdiet.dev/v1/markdown-distill)","url":"https://serp-extract.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 distill (or builtin://stripe-docs)"},"mode":{"enum":["markdown","structured","skeleton","budget"],"type":"string","default":"markdown","description":"Extraction mode: markdown, structured, skeleton, or budget"},"limit":{"type":"integer","default":20,"maximum":100,"minimum":1,"description":"Maximum number of items to return per page (1-100)"},"query":{"type":"string","description":"BM25 focus query when mode=budget"},"cursor":{"type":"string","description":"Opaque pagination cursor for fetching the next page"},"max_tokens":{"type":"integer","minimum":20,"description":"Strict token 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_g2XtCM8YM3CFsBTr3-RQp","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 webpage (or accepts raw HTML) and distills it into compact, agent-ready Markdown, structured JSON, skeleton outline, or BM25-ranked token-budgeted excerpts","exampleAgentPrompt":"Distill https://stripe.com/docs/payments into compact markdown using budget mode focused on 'payment intents', keeping it under 500 tokens so I can feed it into my LLM cheaply.","exampleUseCases":[{"title":"Summarize competitor pricing page","prompt":"Fetch https://openai.com/pricing and distill it into clean structured markdown so I can compare their pricing tiers without wasting context tokens."},{"title":"BM25 budget excerpt for research","prompt":"Pull https://arxiv.org/abs/2310.06825 and give me a BM25-ranked excerpt focused on 'retrieval augmented generation', capped at 300 tokens."},{"title":"Skeleton outline of documentation","prompt":"Distill https://docs.anthropic.com/claude/reference into a skeleton outline so I can see the high-level structure of their API docs without reading the whole thing."}],"resultDescription":"Returns a JSON object with a 'data' field containing the distilled content (Markdown text, structured JSON tables/metadata, skeleton outline, or BM25-focused 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 cache status (HIT/MISS) and billing details.","failureModes":["Invalid or unreachable URL returns fetch error","max_tokens set below minimum of 20 causes validation error","BM25 query parameter ignored if mode is not 'budget'","Raw HTML too large may exceed processing limits","Paywalled or bot-blocked pages may return empty or partial content","Payment failure via x402 returns 402 status"],"whenToPreferThis":"Choose this endpoint when you need to compress web content to fit LLM context windows, reduce token costs, or extract clean structured information from noisy HTML pages. Particularly valuable when you have a strict token budget and need BM25-ranked relevant excerpts rather than full page content. Prefer over general scrapers when LLM cost reduction and agent-ready formatting are the primary goals.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:22:38.364Z","isFirstParty":false,"canonicalSlug":"serp-extract-agentdiet-dev-web-url-markdown-distiller-with-bm25-e2e8f15a"}