{"uid":"cap_CbRrCa3AYVuwdb75hthVB","slug":"serp-extract-agentdiet-dev-web-url-to-agent-ready-token-distiller-a8a14947","name":"Web URL to Agent-Ready Token Distiller","description":"Distill a web URL into compact agent-ready tokens (Live x402 v2, IETF MPP & MCP endpoint at https://serp-extract.agentdiet.dev/v1/article-extractor)","url":"https://serp-extract.agentdiet.dev/v1/article-extractor?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_nD3rJNSpvg1tI1YY5bPXd","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 and distills a webpage URL (or raw HTML) into compact, token-efficient markdown, structured JSON, skeleton outline, or BM25-budgeted excerpts for AI agent consumption","exampleAgentPrompt":"Can you fetch https://stripe.com/docs/payments and distill it into clean markdown, keeping it under 500 tokens using budget mode focused on 'payment intents'?","exampleUseCases":[{"title":"Token-budget article fetch for RAG","prompt":"Grab https://openai.com/research/gpt-4 and distill it into under 300 tokens using budget mode, focused on the query 'model capabilities and benchmarks' — I need it compact for my RAG pipeline."},{"title":"Structured metadata extraction from product page","prompt":"Fetch https://www.apple.com/iphone/ and extract it in structured mode so I get the tables and metadata as clean JSON — no bloat."},{"title":"Skeleton outline of documentation page","prompt":"Pull https://docs.anthropic.com/claude/reference/getting-started-with-the-api and give me a skeleton outline of the page so I can see the section headings without reading the whole thing."}],"resultDescription":"Returns a JSON object containing: distilled page content (as markdown, structured JSON, skeleton, or BM25-trimmed excerpt depending on mode), cache metadata (HIT/MISS, latency), billing details (fee charged in USD), and an ROI proof block showing raw token count, distilled token count, tokens saved, compression ratio percentage, and estimated LLM cost saved in USD.","failureModes":["Invalid or unreachable URL returns an error status","URL with bot-blocking returns empty or partial content","max_tokens set below minimum (20) triggers validation error","mode=budget without a query may produce suboptimal excerpts","Raw HTML passed without URL may parse inconsistently for complex pages","Payment not fulfilled (HTTP 402) blocks response if x402 not configured"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to read a webpage but token budget is a concern — it provides multiple distillation modes (markdown, structured, skeleton, budget) with built-in BM25 relevance filtering and an ROI proof showing exactly how many tokens and LLM dollars were saved. Prefer it over generic scrapers when you need clean, agent-ready output with measurable compression metrics and native HTTP 402 micropayment support.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:21:29.023Z","isFirstParty":false,"canonicalSlug":"serp-extract-agentdiet-dev-web-url-to-agent-ready-token-distiller-a8a14947"}