{"uid":"cap_osrvLFecAi0d1HL9u3Fcq","slug":"shopify-intel-agentdiet-dev-web-url-html-distiller-with-bm25-budget-6313648b","name":"Web URL HTML 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/clean-html)","url":"https://shopify-intel.agentdiet.dev/v1/clean-html?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_ecKi9Lz36iyYBJbQ9dB4-","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 configurable modes including markdown, structured, skeleton, or BM25-budget-constrained excerpts","exampleAgentPrompt":"Pull the content from https://stripe.com/docs/api and distill it into clean markdown, keeping it under 2000 tokens focused on 'payment intents'.","exampleUseCases":[{"title":"Stripe docs research for coding agent","prompt":"Fetch https://stripe.com/docs/payments and distill it into structured markdown under 1500 tokens, focusing on 'checkout session creation' so I can pass it to my coding agent."},{"title":"Competitive pricing page extraction","prompt":"Grab the HTML from https://competitor.com/pricing and distill it into a structured JSON table so I can compare their plans quickly."},{"title":"Budget-capped news article summarization","prompt":"Distill https://techcrunch.com/2024/01/latest-article into markdown with a strict 500-token budget, using 'AI funding rounds' as the focus query."}],"resultDescription":"Returns a JSON object with 'data' containing the distilled content (markdown text, structured JSON tables, skeleton outline, or BM25-focused excerpt), an 'roi_proof' object showing raw tokens, distilled tokens, tokens saved, compression ratio percentage, and estimated LLM cost saved in USD, plus optional cache metadata and billing details.","failureModes":["URL is unreachable or returns non-200 status — endpoint may return an error status","Raw HTML too large to process within limits","Invalid mode enum value provided — defaults to markdown","max_tokens below minimum of 20 — rejected with validation error","Payment not authorized via x402 — returns HTTP 402","No query provided when mode=budget — BM25 focusing skipped or error returned"],"whenToPreferThis":"Choose this endpoint when an agent needs to consume web content within tight token budgets, especially when LLM cost reduction is a priority. Ideal for pipelines that need to pass webpage content to an LLM without blowing context windows, or when structured extraction from arbitrary HTML is needed on-the-fly. The BM25 budget mode is uniquely suited for targeted content retrieval from long pages.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:20:56.430Z","isFirstParty":false,"canonicalSlug":"shopify-intel-agentdiet-dev-web-url-html-distiller-with-bm25-budget-6313648b"}