{"uid":"cap_J9AmXNUYRxQysL3bLG8Jv","slug":"alpha-stream-agentdiet-dev-url-html-to-markdown-distiller-with-bm25-be7a1f80","name":"URL/HTML to 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://alpha-stream.agentdiet.dev/v1/url-to-markdown)","url":"https://alpha-stream.agentdiet.dev/v1/url-to-markdown?utm_source=zero.xyz","method":"POST","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_NLwT9ZLHecinDSsoXhMNs","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"alpha-stream.agentdiet.dev","brandSlug":"alpha-stream-agentdiet-dev-mpp","brandBaseUrl":"https://alpha-stream.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches a URL or processes raw HTML and distills it into compact Markdown, structured JSON, or a BM25-ranked token-budget excerpt for AI agent consumption","exampleAgentPrompt":"Distill the contents of https://stripe.com/docs/api into compact markdown using budget mode, focused on 'payment intents', and keep it under 2000 tokens.","exampleUseCases":[{"title":"Token-budget webpage summarization for agents","prompt":"Fetch https://openai.com/blog/gpt-4o and distill it down to at most 500 tokens using budget mode, focusing on the query 'multimodal capabilities' — I need just the most relevant content for my agent."},{"title":"Structured data extraction from documentation site","prompt":"Grab the HTML from the Stripe pricing page at https://stripe.com/pricing and distill it into structured JSON tables so I can see all the fee tiers clearly."},{"title":"Agent-ready markdown from raw HTML","prompt":"I have some raw HTML from a scraped product page — can you distill it into clean markdown so my agent can read it without wasting tokens on all the nav and footer junk?"}],"resultDescription":"Returns a distilled payload in the requested mode (Markdown, structured JSON, skeleton outline, or BM25 budget excerpt), along with ROI proof metrics including raw token count, distilled token count, tokens saved, compression ratio percentage, and estimated LLM cost saved in USD. Also includes cache hit/miss status and billing info.","failureModes":["URL unreachable or returns non-200 status — fetch error with no distilled content","Invalid or missing URL with no html fallback — validation error","Token budget too low (below 20) — schema validation rejection","Unsupported content type at URL (e.g. binary PDF) — distillation failure","Rate limit or payment failure via x402 — 402 Payment Required response","BM25 query provided without mode=budget — query silently ignored or misapplied"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to consume webpage content but must stay within a token budget, or when raw HTML needs to be cleaned into agent-readable Markdown. The BM25 budget mode is especially valuable when only the most query-relevant portions of a page are needed, minimizing LLM costs. Prefer over generic scrapers when you need built-in compression metrics and ROI proof of token savings.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:33:38.333Z","isFirstParty":false,"canonicalSlug":"alpha-stream-agentdiet-dev-url-html-to-markdown-distiller-with-bm25-be7a1f80"}