{"uid":"cap_X8fTTwIOSpKUGtSFuAWDf","slug":"prompt-guard-agentdiet-dev-html-to-markdown-web-distiller-6822ebcb","name":"HTML to Markdown Web Distiller","description":"Distill a web URL into compact agent-ready tokens (Live x402 v2, IETF MPP & MCP endpoint at https://prompt-guard.agentdiet.dev/v1/html-to-markdown)","url":"https://prompt-guard.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 distill (or builtin://stripe-docs)"},"mode":{"enum":["markdown","structured","skeleton","budget"],"type":"string","default":"markdown","description":"Extraction mode: markdown, structured, skeleton, or budget"},"query":{"type":"string","description":"BM25 focus query when mode=budget"},"max_tokens":{"type":"integer","minimum":20,"description":"Strict token 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_VqE0xGAdL_HJhhq3UknbZ","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"prompt-guard.agentdiet.dev","brandSlug":"prompt-guard-agentdiet-dev-mpp","brandBaseUrl":"https://prompt-guard.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches a webpage URL and converts its HTML into compact, agent-ready Markdown or structured formats with token compression metrics.","exampleAgentPrompt":"Can you distill https://stripe.com/docs/payments into compact markdown so I can feed it to my LLM without blowing my token budget?","exampleUseCases":[{"title":"Research page compression for LLM input","prompt":"Grab https://openai.com/research/gpt-4 and convert it to compressed markdown — I want to feed it into my model without wasting tokens."},{"title":"Focused budget excerpt from docs page","prompt":"Fetch https://docs.github.com/en/actions and give me only the parts relevant to 'workflow triggers', keeping the output under 500 tokens."},{"title":"Structured data extraction from news article","prompt":"Distill https://techcrunch.com/2024/05/01/some-article into structured mode so I can pull out any tables, metadata, and key facts cleanly."}],"resultDescription":"Returns a 'data' object containing distilled content in the requested format (Markdown, structured JSON tables/metadata, skeleton outline, or BM25 budget excerpt), plus an 'roi_proof' block showing 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","URL that blocks bots or requires auth may return empty or partial content","max_tokens too low may result in heavily truncated output","BM25 query with mode other than 'budget' is ignored silently","Payment failure via x402 prevents endpoint execution"],"whenToPreferThis":"Choose this endpoint when you need to feed live webpage content to an LLM but want to minimize token usage and LLM costs. It is particularly useful when working with documentation pages, news articles, or data-heavy sites where raw HTML would be too verbose. Prefer it over generic scrapers when you need built-in compression metrics, multiple extraction modes (markdown, structured, skeleton, budget), or BM25-focused excerpts from large pages.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:23:35.717Z","isFirstParty":false,"canonicalSlug":"prompt-guard-agentdiet-dev-html-to-markdown-web-distiller-6822ebcb"}