{"uid":"cap_6LchF_FjAPJwDTANZT6EQ","slug":"shopify-intel-agentdiet-dev-web-url-distiller-with-bm25-budget-control-e0a88d2d","name":"Web URL Distiller with BM25 Budget Control","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/spa-markdown-reader)","url":"https://shopify-intel.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 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_HYyAKhxIisjttsBof-cXg","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 outline, or BM25-focused excerpt with token budget control","exampleAgentPrompt":"Fetch the page at https://stripe.com/docs/payments and distill it into compact markdown — use budget mode with a 2000 token ceiling and focus the BM25 query on 'payment intents'.","exampleUseCases":[{"title":"Distill documentation within token budget","prompt":"Grab the Stripe docs at https://stripe.com/docs/api and distill them into markdown, budget mode, max 1500 tokens, with BM25 focus on 'webhook events' — I need a compact version that fits in my context window."},{"title":"Extract structured data from product page","prompt":"Fetch https://shopify.com/pricing and distill it into structured JSON tables — I want all the plan names, prices, and features extracted cleanly."},{"title":"Skeleton outline of a long article","prompt":"Read this page https://en.wikipedia.org/wiki/Large_language_model and give me a skeleton outline — just the headings and key structure, nothing more."}],"resultDescription":"Returns a distilled representation of the webpage in the requested mode: Markdown text, structured JSON tables/metadata, a skeleton outline of headings, or a BM25-focused excerpt within a strict token budget. Also includes ROI proof metrics (raw vs distilled token counts, compression ratio, tokens saved, estimated LLM cost saved) and optional cache status.","failureModes":["URL is unreachable or returns non-200 status — endpoint may return an error status","URL points to a paywalled or bot-blocked page — distillation may return empty or partial content","max_tokens set below 20 — validation error returned","BM25 query provided without mode=budget — query may be ignored","Raw HTML is malformed — distillation may produce incomplete output","Rate limit or payment failure — HTTP 402 returned requiring payment"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to read and compress web content to fit within context window limits, especially when token cost matters. Ideal for reading documentation pages, extracting structured data from product or pricing pages, or getting focused excerpts using BM25 relevance filtering. Prefer over generic scrapers when you need built-in token budgeting, ROI metrics, and multiple distillation modes in one call.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:25:54.951Z","isFirstParty":false,"canonicalSlug":"shopify-intel-agentdiet-dev-web-url-distiller-with-bm25-budget-control-3ffa961f"}