{"uid":"cap_pTz77k-A4MPLuFZNibN2F","slug":"defi-yield-agentdiet-dev-html-to-markdown-web-distiller-with-bm25-2d5714e4","name":"HTML to Markdown Web 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://defi-yield.agentdiet.dev/v1/html-to-markdown)","url":"https://defi-yield.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_jDyJwFbuDj0KQ3ra21fmv","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"defi-yield.agentdiet.dev","brandSlug":"defi-yield-agentdiet-dev-mpp","brandBaseUrl":"https://defi-yield.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches a URL or accepts raw HTML and distills it into compact, agent-ready Markdown or structured output with optional BM25-based token budget control","exampleAgentPrompt":"Fetch the Stripe docs page at https://stripe.com/docs/payments and distill it into compact markdown, keeping it under 2000 tokens and focusing on payment intents.","exampleUseCases":[{"title":"Documentation injection for agent context","prompt":"Grab the content from https://docs.openai.com/api-reference and distill it into clean markdown under 3000 tokens so I can inject it into my agent's system prompt without blowing the context window."},{"title":"Competitor pricing page extraction","prompt":"Pull the pricing page at https://anthropic.com/pricing and convert it into structured JSON tables so I can compare model costs programmatically."},{"title":"BM25 focused news article summarization","prompt":"Distill https://techcrunch.com/2024/05/01/openai-gpt5 into budget mode with a query focused on 'model capabilities benchmarks' and cap it at 500 tokens so I only get the most relevant parts."}],"resultDescription":"Returns a JSON object containing the distilled content (Markdown text, structured JSON tables/metadata, skeleton outline, or BM25-filtered excerpt depending on mode), an ROI proof block showing raw vs distilled token counts, compression ratio, tokens saved, and estimated LLM cost saved in USD, plus cache status and billing metadata.","failureModes":["Invalid or unreachable URL returns an error status","Pages behind authentication or paywalls may return incomplete or empty content","max_tokens set too low may result in severely truncated or meaningless output","query parameter ignored if mode is not set to budget","Raw HTML too large may exceed processing limits","Network timeouts on slow external pages","Non-HTML resources (PDFs, images) may produce poor distillation quality"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to read web content but must stay within a token budget, minimize LLM costs, or convert messy HTML into clean structured text. It is especially useful for injecting documentation, research pages, or competitor content into agent context windows efficiently. Prefer it over raw HTML fetching whenever token efficiency and structured output matter, or when BM25 keyword-focused extraction is needed to surface only the most relevant sections of a large page.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:23:44.932Z","isFirstParty":false,"canonicalSlug":"defi-yield-agentdiet-dev-html-to-markdown-web-distiller-with-bm25-2d5714e4"}