{"uid":"cap_PSeNEWSHWWfyT4v0WcDRm","slug":"hn-pulse-agentdiet-dev-web-url-to-compact-markdown-distiller-with-ac9e4655","name":"Web URL to Compact Markdown 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://hn-pulse.agentdiet.dev/v1/docs-to-markdown)","url":"https://hn-pulse.agentdiet.dev/v1/docs-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_VeVAVV2hR6MwRiHhSe01U","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"hn-pulse.agentdiet.dev","brandSlug":"hn-pulse-agentdiet-dev-mpp","brandBaseUrl":"https://hn-pulse.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches a web URL (or accepts raw HTML) and distills it into compact, agent-ready Markdown, structured JSON, skeleton outline, or BM25-focused budget excerpt with token savings reporting.","exampleAgentPrompt":"Can you distill https://stripe.com/docs/payments into compact markdown and keep it under 500 tokens, focused on 'payment intents'?","exampleUseCases":[{"title":"Documentation page summarization for agent","prompt":"Fetch https://docs.openai.com/api-reference and distill it into markdown with a 600-token budget, focusing on 'embeddings' so I can fit it into my context window."},{"title":"Structured data extraction from product page","prompt":"Take the HTML of this product listing page and distill it into structured JSON tables so I can pull out prices and specs without parsing the raw HTML myself."},{"title":"Skeleton outline of a long article","prompt":"Distill https://en.wikipedia.org/wiki/Large_language_model into a skeleton outline mode so I just get the section headings and top-level structure without all the body text."}],"resultDescription":"Returns a 'data' object containing the distilled content in the requested format (Markdown, structured JSON, skeleton, or BM25 excerpt), along with an 'roi_proof' object showing raw token count, distilled token count, tokens saved, compression ratio percentage, ROI multiplier, and estimated LLM cost saved in USD. Also includes cache hit/miss status and billing details.","failureModes":["Invalid or unreachable URL returns fetch error","mode=budget without a query or max_tokens may produce unfiltered output","Very large pages may exceed internal fetch limits","Raw HTML too large may be rejected","Token budget too low (below 20) will be rejected by schema validation","Non-HTML content types (PDFs, binary files) may not distill cleanly"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to ingest a webpage or documentation URL but must stay within a token budget, or when the raw HTML is too large to pass directly to an LLM. It is especially valuable for documentation scraping, research pipelines, and cost-sensitive agent workflows that need BM25-focused relevance filtering rather than full-page content. Prefer it over generic web scraping tools when token savings and compression metrics are important outputs.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T12:48:54.719Z","isFirstParty":false,"canonicalSlug":"hn-pulse-agentdiet-dev-web-url-to-compact-markdown-distiller-with-ac9e4655"}