{"uid":"cap_CXaw_PrXMTGcokISetMIq","slug":"prompt-guard-agentdiet-dev-web-url-to-markdown-distiller-with-bm25-bd22bd06","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://prompt-guard.agentdiet.dev/v1/docs-to-markdown)","url":"https://prompt-guard.agentdiet.dev/v1/docs-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_WJlJGGCIJ0nlMtvlF1P5g","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"prompt-guard.agentdiet.dev","brandSlug":"prompt-guard-agentdiet-dev-mpp","brandBaseUrl":"https://prompt-guard.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-focused token-budgeted excerpts.","exampleAgentPrompt":"Fetch the Stripe pricing page at https://stripe.com/pricing and distill it into compact markdown — keep it under 800 tokens using budget mode focused on the query 'credit card fees'.","exampleUseCases":[{"title":"Compress documentation for LLM context","prompt":"Grab the OpenAI API docs page at https://platform.openai.com/docs/api-reference and convert it to clean markdown so I can feed it to my agent without blowing the context window."},{"title":"BM25 focused excerpt under token limit","prompt":"Distill https://docs.stripe.com/payments/checkout into a budget excerpt of at most 500 tokens, focused on the query 'subscription billing setup'."},{"title":"Structured data extraction from landing page","prompt":"Fetch https://anthropic.com/claude and extract it in structured mode so I get JSON tables and metadata rather than raw markdown."}],"resultDescription":"Returns a JSON object with a 'data' field containing the distilled content (Markdown, structured JSON, skeleton, or BM25 excerpt depending on mode), an 'roi_proof' object showing raw_tokens, distilled_tokens, tokens_saved, compression_ratio_pct, roi_multiplier, and llm_cost_saved_usd, plus optional cache hit/miss info and billing details.","failureModes":["Invalid or unreachable URL returns an error status","Missing required 'url' parameter causes a 400-level error","mode=budget without a query or max_tokens may return unfiltered content","Very large pages may hit processing limits or return partial content","Raw HTML input too large may be rejected","Payment failure via x402 prevents response delivery"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to ingest web page content within a strict token budget, or when you want BM25-ranked relevance filtering to focus on a specific query topic. It is especially useful for feeding documentation, landing pages, or research URLs into an LLM context efficiently. Prefer it over generic scrapers when token cost savings and compression metrics matter, or when you need structured/skeleton output rather than raw HTML.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:25:36.869Z","isFirstParty":false,"canonicalSlug":"prompt-guard-agentdiet-dev-web-url-to-markdown-distiller-with-bm25-bd22bd06"}