{"uid":"cap_ZeciUE0FJ4Z_87VDGKt-O","slug":"shopify-spy-agentdiet-dev-web-url-to-agent-ready-token-distiller-fb120474","name":"Web URL to Agent-Ready Token Distiller","description":"Distill a URL or raw HTML payload with BM25 budget control (Live x402 v2, IETF MPP & MCP endpoint at https://shopify-spy.agentdiet.dev/v1/clean-html)","url":"https://shopify-spy.agentdiet.dev/v1/clean-html?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_9w-sIr-ZdzC8Y76sabrrs","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-spy.agentdiet.dev","brandSlug":"shopify-spy-agentdiet-dev-mpp","brandBaseUrl":"https://shopify-spy.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches and distills a webpage URL or raw HTML into compact, token-efficient markdown, structured data, skeleton outline, or BM25-focused excerpt for AI agents","exampleAgentPrompt":"Can you distill https://stripe.com/docs/payments into compact markdown and keep it under 2000 tokens, focusing on the query 'payment intents' using budget mode?","exampleUseCases":[{"title":"Token-budget research for AI agent","prompt":"Fetch https://openai.com/pricing and distill it in budget mode focused on 'GPT-4 token costs', keeping the output under 1500 tokens so I can feed it to my agent without blowing my context window."},{"title":"Structured data extraction from product page","prompt":"Pull the product specs and pricing tables from https://shopify.com/pricing and give them back to me as structured JSON so my agent can compare plans."},{"title":"Skeleton outline for site navigation","prompt":"Give me a skeleton outline of https://docs.anthropic.com so my agent can understand the top-level structure of the documentation without downloading the whole thing."}],"resultDescription":"Returns a distilled representation of the webpage in the requested mode: clean markdown, structured JSON with tables and metadata, a skeleton page outline, or a BM25-ranked budget excerpt. Also includes ROI proof metrics: raw token count, distilled token count, tokens saved, compression ratio percentage, estimated LLM cost saved in USD, and optionally cache hit/miss status and billing details.","failureModes":["Invalid or unreachable URL returns error status","URL blocked by robots.txt or anti-bot measures causes fetch failure","max_tokens set below minimum of 20 returns validation error","query parameter required but missing when mode=budget","Raw HTML too large may exceed processing limits","Payment/billing failure via x402 protocol if agent wallet insufficient"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to ingest live web content but must stay within a token budget or minimize LLM costs. It is especially valuable when the target page is HTML-heavy with navigation boilerplate, ads, or irrelevant content that would otherwise waste context. The BM25 budget mode makes it uniquely suited for query-focused extraction where only the most relevant passages matter. Prefer this over generic scrapers when you need token-count guarantees and ROI reporting built into the response.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:21:27.048Z","isFirstParty":false,"canonicalSlug":"shopify-spy-agentdiet-dev-web-url-to-agent-ready-token-distiller-fb120474"}