{"uid":"cap_7GhvwVSxjXHlfrrmKYMAJ","slug":"llms-generator-agentdiet-dev-web-url-to-markdown-distiller-with-bm25-7ef89a1f","name":"Web URL 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://llms-generator.agentdiet.dev/v1/html-to-markdown)","url":"https://llms-generator.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_RvyRo2kDuuqJI8pB63b77","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"llms-generator.agentdiet.dev","brandSlug":"llms-generator-agentdiet-dev-mpp","brandBaseUrl":"https://llms-generator.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches a web URL or raw HTML and distills it into compact, agent-ready Markdown, structured JSON, skeleton outline, or BM25-focused token-budgeted excerpts","exampleAgentPrompt":"Can you fetch https://stripe.com/docs/payments and distill it into clean markdown, keeping it under 2000 tokens and focusing on the payment intents section?","exampleUseCases":[{"title":"Research page summarized for agent","prompt":"Grab https://openai.com/research/gpt-4 and distill it into compact markdown so I can use it in my agent's context window without blowing my token budget."},{"title":"BM25 focused excerpt from documentation","prompt":"Fetch https://docs.aws.amazon.com/lambda/latest/dg/welcome.html and give me only the parts relevant to 'cold start latency', capped at 500 tokens."},{"title":"Structured data extraction from landing page","prompt":"Pull https://example.com/pricing and distill it in structured mode so I get the pricing table and metadata as JSON rather than raw text."}],"resultDescription":"Returns a JSON object containing the distilled content (Markdown, structured JSON, skeleton, or BM25 excerpt) in `data`, an `roi_proof` object with raw_tokens, distilled_tokens, tokens_saved, compression_ratio_pct, roi_multiplier, and llm_cost_saved_usd, optional cache metadata (HIT/MISS, latency_ms), and billing details including fee_charged_usd.","failureModes":["URL is unreachable or returns a non-200 response — endpoint may return an error status","Raw HTML input is too large or malformed — distillation may fail or truncate","mode=budget used without a query parameter — BM25 filtering cannot proceed","max_tokens set below 20 — rejected by schema validation","Target URL blocks scrapers/bots — content may be empty or incomplete","Payment not provided or insufficient — HTTP 402 response blocking execution"],"whenToPreferThis":"Choose this endpoint when you need to reduce the token cost of ingesting web content into an LLM context — especially when working with documentation pages, landing pages, or any URL where you need BM25-focused relevance filtering or a strict token budget. It is superior to raw HTML fetching when token efficiency matters, and preferable over generic scrapers when you need structured JSON tables, skeleton outlines, or Markdown output with compression metrics included.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:24:18.220Z","isFirstParty":false,"canonicalSlug":"llms-generator-agentdiet-dev-web-url-to-markdown-distiller-with-bm25-7ef89a1f"}