{"uid":"cap_baKDAkb_m2V0C5SnaZFOM","slug":"prompt-guard-agentdiet-dev-url-to-markdown-distiller-with-bm25-budget-e92d80ff","name":"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/url-to-markdown)","url":"https://prompt-guard.agentdiet.dev/v1/url-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_DIgfzQ_nwOmYcfMtim-w3","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 or structured tokens with optional BM25-ranked token budget control","exampleAgentPrompt":"Can you fetch https://stripe.com/docs/payments and distill it into clean markdown using budget mode focused on 'payment intents', keeping it under 800 tokens?","exampleUseCases":[{"title":"LLM context injection from docs","prompt":"Grab the content from https://docs.openai.com/api-reference and distill it into compact markdown so I can inject it into my agent's context without burning too many tokens."},{"title":"BM25 budget excerpt for research","prompt":"Fetch https://en.wikipedia.org/wiki/Transformer_(machine_learning_model) and give me only the parts most relevant to 'attention mechanism' in budget mode with a max of 500 tokens."},{"title":"Structured data extraction from pricing page","prompt":"Pull the page at https://vercel.com/pricing and distill it in structured mode so I get the pricing tiers and feature tables as clean JSON."}],"resultDescription":"Returns a JSON object containing distilled content (Markdown, structured tables, skeleton outline, or BM25-ranked excerpt depending on mode), an ROI proof block showing raw vs distilled token counts, compression ratio, and estimated LLM cost saved, plus optional cache status and billing details.","failureModes":["URL is unreachable or returns non-200 HTTP status — endpoint may return an error status","Raw HTML is malformed or too large — distillation may fail or truncate","max_tokens ceiling too low to return meaningful content — may return partial or empty excerpt","BM25 query too vague — budget mode may return low-relevance content","Rate limiting or payment failure via x402 — request rejected with 402 response"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to read web content but must stay within a token budget, or when you want a clean Markdown or structured representation of a webpage without manually parsing HTML. Especially valuable for LLM pipelines where raw webpage tokens are prohibitively expensive, or when you need BM25-focused excerpts relevant to a specific query rather than full-page content.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:21:02.051Z","isFirstParty":false,"canonicalSlug":"prompt-guard-agentdiet-dev-url-to-markdown-distiller-with-bm25-budget-e92d80ff"}