{"uid":"cap_qUoZN7Y_aV2jmHkxfl97n","slug":"shopify-spy-agentdiet-dev-web-url-distiller-with-bm25-budget-control-2b38d093","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/pdf-extract)","url":"https://shopify-spy.agentdiet.dev/v1/pdf-extract?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__7_6IEdZ0M3xXdv9nvilM","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 a webpage or raw HTML and distills it into compact, agent-ready tokens using configurable modes (markdown, structured, skeleton, or BM25-focused budget)","exampleAgentPrompt":"Can you distill https://stripe.com/docs/payments into compact markdown under 2000 tokens, focusing on the query 'payment intent flow'?","exampleUseCases":[{"title":"Research competitor pricing page","prompt":"Fetch and distill https://competitor.com/pricing into clean markdown so I can see their pricing tiers without burning a ton of tokens."},{"title":"Extract structured data from a news article","prompt":"Grab https://techcrunch.com/2024/01/15/openai-funding and give me a structured summary — pull out tables, headings, and key metadata."},{"title":"Budget-constrained product page extraction","prompt":"Distill https://shopify.com/features into a BM25-focused excerpt about 'subscription billing', keeping it under 500 tokens."}],"resultDescription":"Returns a data object containing distilled content in the requested format (markdown text, structured JSON with tables/metadata, outline skeleton, or BM25-ranked budget excerpt), along with an roi_proof object showing raw vs distilled token counts, compression ratio, tokens saved, and estimated LLM cost saved in USD. Also includes cache status and billing details.","failureModes":["Invalid or unreachable URL returns an error status","HTML fetch timeout for slow or blocked pages","max_tokens below minimum (20) triggers validation error","mode=budget without a query may return unfiltered content","Paywalled or JavaScript-heavy pages may yield poor distillation quality","x402 payment failure if agent lacks sufficient USDC balance"],"whenToPreferThis":"Choose this endpoint when you need to feed web content into an LLM context window efficiently and cost-effectively, especially when you have a strict token budget or want BM25-ranked relevance filtering. Prefer it over raw web scrapers when you need clean markdown or structured output rather than raw HTML, and over general-purpose scrapers when ROI/cost-savings metrics matter to your workflow.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:25:39.840Z","isFirstParty":false,"canonicalSlug":"shopify-spy-agentdiet-dev-web-url-distiller-with-bm25-budget-control-2b0c3678"}