{"uid":"cap_71m5xXYNoGHgtl8K0DFVA","slug":"shopify-intel-agentdiet-dev-web-url-dom-distiller-bm25-budget-control-bfd5df92","name":"Web URL DOM Distiller (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/dom-stripper)","url":"https://shopify-intel.agentdiet.dev/v1/dom-stripper?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_dCs10xYLlhi1hmKl2it6q","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 tokens using markdown, structured, skeleton, or BM25-budget extraction modes.","exampleAgentPrompt":"Can you distill https://stripe.com/docs/api into clean markdown and keep it under 2000 tokens, focusing on 'authentication' — I need the compact version for my pipeline?","exampleUseCases":[{"title":"Compressing docs page for LLM context","prompt":"Fetch https://docs.shopify.com/api/admin-rest and distill it into markdown under 1500 tokens, focusing on 'webhooks' — I need just the relevant bits for my agent."},{"title":"Stripping a blog post to plain text","prompt":"Take this HTML I have from a blog post and strip all the nav, ads, and boilerplate — give me clean markdown of just the article body."},{"title":"Skeleton outline of a landing page","prompt":"Can you give me a skeleton outline of https://openai.com/product so I can understand the page structure without reading the whole thing?"}],"resultDescription":"Returns a distilled version of the webpage or HTML in the requested mode (markdown, structured JSON tables, skeleton outline, or BM25-focused excerpt), along with ROI proof metrics showing raw vs distilled token counts, tokens saved, compression ratio, cost savings estimate, and optionally cache hit/miss status and billing details.","failureModes":["Invalid or unreachable URL returns an error status","HTML content too short or empty yields minimal distillation output","BM25 budget mode without a query may default to generic compression","max_tokens set below 20 is rejected by schema validation","Rate limiting or payment failure via x402 may block the request","Some paywalled or JavaScript-heavy pages may not be fully fetched"],"whenToPreferThis":"Choose this endpoint when you need to reduce token overhead before feeding a webpage to an LLM, especially when working within tight context windows. It is particularly valuable when you want BM25-focused extraction — retrieving only the most query-relevant tokens from a page — rather than full-page scraping. Prefer it over raw HTTP fetches when token cost savings and clean markdown output matter. It also supports direct HTML input, making it useful for offline or pre-fetched content distillation.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:23:51.426Z","isFirstParty":false,"canonicalSlug":"shopify-intel-agentdiet-dev-web-url-dom-distiller-bm25-budget-control-bfd5df92"}