{"uid":"cap_zGEo7MSnodkAia05jfcZS","slug":"serp-extract-agentdiet-dev-webpage-distiller-compact-agent-ready-34ee47e7","name":"Webpage Distiller — Compact Agent-Ready Token Extractor","description":"Distill a web URL into compact agent-ready tokens (Live x402 v2, IETF MPP & MCP endpoint at https://serp-extract.agentdiet.dev/v1/webpage-distiller)","url":"https://serp-extract.agentdiet.dev/v1/webpage-distiller?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_NKuX0uYL2YI5Ql3V4OX6Z","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 output (Markdown, structured JSON, skeleton outline, or BM25-focused excerpt) with a measurable token-savings ROI proof.","exampleAgentPrompt":"Fetch https://stripe.com/docs/payments/accept-a-payment and distill it into compact markdown — keep it under 1000 tokens using budget mode focused on 'payment intent setup'.","exampleUseCases":[{"title":"Documentation page for coding agent","prompt":"Grab https://docs.openai.com/api-reference/chat and distill it into structured JSON so my coding agent can understand the chat completion API without blowing its context window."},{"title":"Token-budget research on competitor page","prompt":"Distill https://www.anthropic.com/product into budget mode with a max of 500 tokens, focusing on 'pricing and model capabilities' — I only want the most relevant parts."},{"title":"Skeleton outline of long article","prompt":"Fetch https://en.wikipedia.org/wiki/Large_language_model and give me a skeleton outline so I can see the document structure before deciding which sections to read in full."}],"resultDescription":"Returns a JSON object with a 'data' field containing the distilled content (Markdown text, structured 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 cache hit/miss status and optional billing details.","failureModes":["URL is unreachable or returns non-200 HTTP status — endpoint may error or return empty data","Raw HTML is malformed or too large — distillation may truncate or fail","max_tokens set below 20 — rejected by schema validation","BM25 query provided without mode=budget — query may be ignored","Paywalled or JavaScript-rendered pages may yield minimal or no extractable content","Invalid URL format causes immediate rejection"],"whenToPreferThis":"Choose this endpoint when you need to feed web content to an LLM but want to minimize token consumption and cost. It is especially valuable when working with long documentation pages, research articles, or competitor sites where you only need a focused excerpt (budget mode with BM25) or a structured overview (skeleton/structured mode). Prefer it over raw HTTP fetch when token efficiency, compression ROI tracking, and clean Markdown output matter — particularly in agentic pipelines where context window size is a binding constraint.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:23:04.420Z","isFirstParty":false,"canonicalSlug":"serp-extract-agentdiet-dev-webpage-distiller-compact-agent-ready-34ee47e7"}