{"uid":"cap_r4BZ84A4O-_Zz9SC45Dvx","slug":"alpha-stream-agentdiet-dev-agentdiet-html-to-markdown-web-distiller-f7eae983","name":"AgentDiet HTML-to-Markdown Web Distiller","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/html-to-markdown)","url":"https://alpha-stream.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_fHEZ5G0iiYvFWfNaFDfoX","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 raw HTML and distills it into compact, agent-ready Markdown, structured JSON, skeleton outline, or BM25-budgeted token excerpts","exampleAgentPrompt":"Fetch the page at https://docs.stripe.com/payments and distill it into compact markdown — use budget mode with a focus query of 'payment intents' and a max token limit of 800.","exampleUseCases":[{"title":"Research page for agent pipeline","prompt":"Grab https://en.wikipedia.org/wiki/Large_language_model and distill it into clean markdown so I can feed it to my agent without blowing the context window."},{"title":"Token-budgeted doc extraction","prompt":"Distill https://docs.openai.com/api-reference into structured mode and keep it under 500 tokens — focus the BM25 query on 'rate limits'."},{"title":"Skeleton outline of a long article","prompt":"I need a skeleton outline of https://www.nytimes.com/2024/01/15/technology/ai-agents.html — just the headings and key structure, no full text."}],"resultDescription":"Returns a JSON object with a 'data' field containing the distilled content (Markdown string, structured JSON tables/metadata, skeleton outline, or BM25-focused excerpt depending on mode), plus an 'roi_proof' object showing raw_tokens, distilled_tokens, tokens_saved, compression_ratio_pct, roi_multiplier, and llm_cost_saved_usd, along with optional cache hit/miss status and billing details.","failureModes":["Invalid or unreachable URL returns an error status","Malformed HTML input may produce incomplete distillation","max_tokens set below 20 is rejected by schema validation","BM25 query without mode=budget is ignored silently","Rate limiting or payment failure (HTTP 402) blocks the request","Some paywalled or bot-protected pages may return empty or partial content"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to consume web content but must stay within a token budget, reduce LLM inference costs, or receive structured/markdown-formatted web data rather than raw HTML. It is especially valuable in agentic pipelines where multiple pages must be ingested cheaply. Prefer it over generic scrapers when BM25-focused excerpt extraction or ROI-provable compression is needed.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:22:04.315Z","isFirstParty":false,"canonicalSlug":"alpha-stream-agentdiet-dev-agentdiet-html-to-markdown-web-distiller-f7eae983"}