{"uid":"cap_GKvmavm1MO-vT9xTG4F2p","slug":"shopify-spy-agentdiet-dev-web-url-distiller-with-bm25-budget-control-fe3b2a8d","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-spy.agentdiet.dev/v1/spa-markdown-reader)","url":"https://shopify-spy.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_sSbcWcNa824leLw9DjU1p","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 web URL or raw HTML into compact, agent-ready Markdown or structured tokens with configurable BM25 budget control","exampleAgentPrompt":"Fetch https://stripe.com/docs/payments and distill it into compact markdown using budget mode, focused on 'payment intents', and keep it under 500 tokens.","exampleUseCases":[{"title":"Distill docs page for agent context","prompt":"Grab https://docs.shopify.com/api/storefront and compress it into clean markdown so I can feed it to my agent — use budget mode with a max of 800 tokens focused on 'product variants'."},{"title":"Summarize competitor landing page","prompt":"Distill https://competitor.com into structured skeleton mode so I can see the key sections and headlines without reading the whole page."},{"title":"Extract relevant content from raw HTML","prompt":"I have a raw HTML blob from an internal tool — distill it into markdown mode and pull out the main content so my agent can process it without burning through tokens."}],"resultDescription":"Returns a distilled representation of the web page or HTML in one of four modes (markdown, structured, skeleton, or budget excerpt), along with an roi_proof object showing raw vs distilled token counts, compression ratio, tokens saved, and estimated LLM cost savings. Also includes cache status and billing metadata.","failureModes":["Invalid or unreachable URL returns an error status","Token budget too small (below 20) triggers a validation error","Unsupported mode value returns an enum validation error","Empty or malformed HTML input produces empty or degraded output","Payment failure (402) if agent wallet is unfunded","Rate limiting or timeout on slow or large target pages"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to read web content but must stay within a token budget, or when raw HTML from a page would be too large or noisy to pass directly to an LLM. It is especially useful for documentation pages, competitor research, and any agentic pipeline where LLM cost and context window size are constraints. Prefer it over generic scrapers when you need BM25-focused excerpts, structured JSON tables, or skeleton outlines rather than full raw text.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T12:43:52.840Z","isFirstParty":false,"canonicalSlug":"shopify-spy-agentdiet-dev-web-url-distiller-with-bm25-budget-control-2b0c3678"}