{"uid":"cap_uFy3w88UKuXW_J3eeWFKy","slug":"serp-extract-agentdiet-dev-web-url-to-compact-markdown-distiller-bm25-628faf6a","name":"Web URL to Compact Markdown Distiller (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/spa-markdown-reader)","url":"https://serp-extract.agentdiet.dev/v1/spa-markdown-reader?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_PChtRSTDXTS7ItlNN6NgD","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 raw HTML and distills it into compact, token-efficient Markdown, structured JSON, skeleton outline, or BM25-ranked budget excerpt for AI agents.","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 LLM context","prompt":"Grab the content at https://docs.openai.com/api-reference and distill it into structured markdown — I need it token-efficient enough to fit in my agent's context window."},{"title":"BM25 budget excerpt for research","prompt":"Pull https://en.wikipedia.org/wiki/Transformer_(machine_learning_model) and give me only the most relevant 300 tokens about 'attention mechanism' using budget mode."},{"title":"Extract structured tables from a report","prompt":"Distill https://www.sec.gov/cgi-bin/browse-edgar?action=getcompany&CIK=TSLA into structured mode so I get the tables and metadata as clean JSON without all the surrounding noise."}],"resultDescription":"Returns a JSON object with a 'data' field containing the distilled content (Markdown text, structured JSON tables/metadata, skeleton outline, or BM25-ranked 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 status and billing details.","failureModes":["Invalid or unreachable URL returns an error status","HTML fetch timeout for slow or JS-heavy SPAs","Token budget too low (below 20) causes validation error","BM25 query missing when mode=budget may return unfiltered content","Raw HTML too large may exceed processing limits","Paywalled or bot-protected pages may return empty or partial content"],"whenToPreferThis":"Choose this endpoint when you need to feed web content to an LLM but want to minimize token consumption — especially useful for long documentation pages, news articles, or SEC filings. Prefer it over raw fetch when you need BM25-ranked relevance filtering around a specific query, structured JSON extraction of tables, or a skeleton outline. It is particularly well-suited for agentic pipelines where context window cost and compression ratio matter.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:21:06.536Z","isFirstParty":false,"canonicalSlug":"serp-extract-agentdiet-dev-web-url-to-compact-markdown-distiller-bm25-628faf6a"}