{"uid":"cap_nD1v1ZQIHn3RnkcTmr3cI","slug":"shopify-intel-agentdiet-dev-webpage-distiller-compact-agent-ready-a2d7d425","name":"Webpage Distiller — Compact Agent-Ready Token Extraction","description":"Distill a URL or raw HTML payload with BM25 budget control (Live x402 v2, IETF MPP & MCP endpoint at https://shopify-intel.agentdiet.dev/v1/webpage-distiller)","url":"https://shopify-intel.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 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_MdhNGB0IZYNtEU1c-2FxN","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"shopify-intel.agentdiet.dev","brandSlug":"shopify-intel-agentdiet-dev-mpp","brandBaseUrl":"https://shopify-intel.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches a URL or raw HTML and distills it into compact, agent-ready markdown, structured JSON, skeleton outlines, or BM25-focused budget excerpts with token savings reporting.","exampleAgentPrompt":"Distill https://stripe.com/docs/api into compact markdown using budget mode, focused on 'authentication' with a max of 500 tokens, so I can fit it into my prompt without blowing my context window.","exampleUseCases":[{"title":"Research page distillation for agent RAG","prompt":"Fetch https://openai.com/research/gpt-4 and distill it into clean markdown so I can drop it into my agent's context — strip out all the nav menus and ads."},{"title":"Token-budget excerpt for tight LLM context","prompt":"Pull the content from https://docs.shopify.com/api/admin and give me only the parts relevant to 'webhooks', keeping it under 300 tokens in budget mode."},{"title":"Structured data extraction from product page","prompt":"Take https://www.apple.com/iphone-15-pro/ and extract it in structured mode so I get the product specs and pricing as a clean JSON table."}],"resultDescription":"Returns a data object containing the distilled content in the requested format (markdown string, structured JSON tables/metadata, skeleton outline, or BM25-ranked budget excerpt), plus an roi_proof object with raw_tokens, distilled_tokens, tokens_saved, compression_ratio_pct, and llm_cost_saved_usd, along with optional cache hit/miss status and billing details.","failureModes":["Invalid or unreachable URL returns an error status","max_tokens too small (below 20) causes a validation error","mode=budget without a query may return unfiltered or empty excerpts","Raw HTML that exceeds server size limits may be rejected","Paywalled or bot-blocked pages may return incomplete content","Missing required 'url' parameter causes a 400-level error"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to read web pages but must control LLM token usage — especially for long documentation pages, product pages, or research articles. The BM25 budget mode is uniquely suited for retrieval-augmented generation where only query-relevant content is needed under a strict token ceiling. Prefer over generic scrapers when you need built-in compression metrics and ROI proof of token savings.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:26:06.666Z","isFirstParty":false,"canonicalSlug":"shopify-intel-agentdiet-dev-webpage-distiller-compact-agent-ready-a2d7d425"}