{"uid":"cap_a869CucMcODj-bpWaxXsQ","slug":"alpha-stream-agentdiet-dev-html-to-markdown-distiller-with-bm25-f0b40741","name":"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/html-to-markdown)","url":"https://alpha-stream.agentdiet.dev/v1/html-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_iNuWoznL4hSLvtbGwdKs9","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 and distills a URL or raw HTML payload into compact Markdown, structured JSON, or a BM25-ranked token-budgeted excerpt for agent consumption","exampleAgentPrompt":"Fetch https://stripe.com/docs/api and distill it into markdown with a 2000-token budget, focused on the query 'payment intents authentication' using budget mode.","exampleUseCases":[{"title":"Compress docs page for agent context","prompt":"Pull https://docs.openai.com/api-reference and distill it into budget mode with max 1500 tokens, focused on the query 'streaming responses', so I can include just the relevant section in my agent's context window."},{"title":"Convert competitor landing page to structured data","prompt":"Take https://vercel.com/pricing and distill it in structured mode so I get all the pricing tables and metadata as clean JSON I can compare."},{"title":"Distill raw HTML from internal tool","prompt":"I've got a raw HTML string from our internal dashboard — can you distill it into markdown skeleton mode so I get just the page outline and headings without all the noise?"}],"resultDescription":"Returns a distilled payload in the requested mode (Markdown, structured JSON tables/metadata, skeleton outline, or BM25 budget excerpt), along with an roi_proof object showing raw token count, distilled token count, tokens saved, compression ratio percentage, and estimated LLM cost saved in USD. Also includes cache status (HIT/MISS) and billing info.","failureModes":["Missing required 'url' field returns validation error","Invalid or unreachable URL causes fetch failure","mode=budget without a 'query' field may return unranked or degraded output","max_tokens set below 20 is rejected by schema validation","Raw HTML too large may hit processing limits","Payment required (HTTP 402) if x402 payment header is missing or insufficient"],"whenToPreferThis":"Choose this endpoint when you need to reduce the token footprint of a webpage or HTML document before passing it to an LLM, especially when you want BM25-ranked budget control to focus on a specific query topic. Prefer this over generic scrapers when token cost savings and compression ROI metrics matter, or when you need structured JSON extraction from HTML rather than plain text.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:35:08.009Z","isFirstParty":false,"canonicalSlug":"alpha-stream-agentdiet-dev-html-to-markdown-distiller-with-bm25-f0b40741"}