{"uid":"cap_0jveze3IkL8kPKk81Ywxw","slug":"shopify-intel-agentdiet-dev-web-url-distiller-with-bm25-budget-control-3ffa961f","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/web-scrape)","url":"https://shopify-intel.agentdiet.dev/v1/web-scrape?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_ftty9rTTLMVAIneD5EEi9","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 webpage URL (or raw HTML) and distills it into compact, agent-ready tokens using configurable modes including BM25-focused budget excerpting","exampleAgentPrompt":"Fetch the Stripe pricing page at https://stripe.com/pricing and distill it into compact markdown, keeping it under 800 tokens and focusing on the query 'payment fees'.","exampleUseCases":[{"title":"Competitive pricing research on a budget","prompt":"Scrape https://openai.com/pricing and distill it into structured tables using budget mode, focused on the query 'API pricing per token', and keep the output under 600 tokens."},{"title":"Extracting documentation skeleton for navigation","prompt":"Grab https://docs.github.com/en/rest and give me a skeleton outline of the page so I can see the top-level structure without all the detail."},{"title":"Token-efficient webpage summarization","prompt":"Pull the content from https://techcrunch.com and distill it into compact markdown — I need the full page but condensed as much as possible to save on tokens."}],"resultDescription":"Returns a 'data' object containing the distilled content (Markdown text, structured JSON tables/metadata, skeleton outline, or BM25 budget excerpt depending on mode), plus an 'roi_proof' object with raw_tokens, distilled_tokens, tokens_saved, compression_ratio_pct, roi_multiplier, and llm_cost_saved_usd. Also includes cache status (HIT/MISS) and billing details.","failureModes":["Invalid or unreachable URL returns an error status","mode=budget without a query or max_tokens may return unfiltered or oversized content","Very large pages may still exceed token budgets if max_tokens is set too low","Raw HTML input (html field) conflicts with URL fetching — only one should be used","Network timeouts on slow or blocked target sites","Pages behind authentication walls cannot be fetched"],"whenToPreferThis":"Choose this endpoint when you need to fetch and compress a specific webpage into token-efficient content for downstream LLM processing, especially when token cost control matters. It is particularly strong when you need BM25-ranked excerpt filtering around a specific query — ideal for research agents, RAG pipelines, or any scenario where raw webpage content is too verbose for your token budget.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T12:49:14.464Z","isFirstParty":false,"canonicalSlug":"shopify-intel-agentdiet-dev-web-url-distiller-with-bm25-budget-control-3ffa961f"}