{"uid":"cap_SOZSLJXiQLEzYUaj9jE8z","slug":"shopify-spy-agentdiet-dev-web-url-html-to-compact-markdown-distiller-6321e4d7","name":"Web URL & HTML to Compact Markdown Distiller","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/html-to-markdown)","url":"https://shopify-spy.agentdiet.dev/v1/html-to-markdown?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_EkvtIn2TfJxvTvwHgUwFg","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 URL or raw HTML and distills it into compact, agent-ready Markdown, structured JSON, skeleton outline, or BM25-focused budget excerpt with token savings metrics","exampleAgentPrompt":"Fetch the page at https://example.com/product and distill it into compact markdown — use budget mode with 'pricing plans' as the focus query and cap it at 500 tokens so I don't blow my LLM context window.","exampleUseCases":[{"title":"Compress competitor pricing page for agent","prompt":"Grab the pricing page at https://stripe.com/pricing, distill it into structured mode, and give me the tables and key metadata so I can compare it with our own pricing."},{"title":"BM25 budget excerpt for research query","prompt":"Fetch https://openai.com/research/gpt-4 and extract only the parts most relevant to 'context window and token limits' — use budget mode and keep it under 300 tokens."},{"title":"Convert documentation URL to clean markdown","prompt":"Distill https://docs.shopify.com/api/admin into clean markdown mode so I can feed it directly to my LLM without all the HTML noise."}],"resultDescription":"Returns a distilled version of the web page or HTML in the requested mode (Markdown, structured JSON, skeleton outline, or BM25 budget excerpt), along with ROI proof showing raw token count, distilled token count, tokens saved, compression ratio, estimated LLM cost savings, and optional cache and billing metadata.","failureModes":["Invalid or unreachable URL returns an error status","HTML too large or malformed may produce incomplete distillation","max_tokens set too low may result in heavily truncated or empty output","BM25 query not matching any content returns minimal or empty budget excerpt","Rate limiting or payment failure (HTTP 402) if agent credentials are missing","Network timeout if the target URL is slow to respond"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to fetch and consume web content within a strict token budget, or when you need clean, structured Markdown from a URL without manually scraping and cleaning HTML. It is especially useful when downstream LLM costs matter and you want measurable compression savings, or when you need BM25-focused extraction to pull only the most relevant section of a large page.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:25:46.303Z","isFirstParty":false,"canonicalSlug":"shopify-spy-agentdiet-dev-web-url-html-to-compact-markdown-distiller-6321e4d7"}