{"uid":"cap_R_rJESXQFYFKDNt0X0bKg","slug":"prompt-guard-agentdiet-dev-web-url-to-compact-markdown-distiller-bm25-03990d4c","name":"Web URL to Compact Markdown Distiller (BM25 Budget)","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/spa-markdown-reader)","url":"https://prompt-guard.agentdiet.dev/v1/spa-markdown-reader?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_4Kxi3np48G0lX-1rUIYS7","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 excerpt.","exampleAgentPrompt":"Fetch https://stripe.com/docs/api and distill it into compact Markdown using budget mode, focusing on 'payment intent creation' and keeping it under 800 tokens.","exampleUseCases":[{"title":"Distill documentation for agent context","prompt":"Grab https://docs.openai.com/api-reference and distill it into a skeleton outline so I can quickly understand the structure without blowing my context window."},{"title":"BM25-focused research extraction","prompt":"Fetch https://en.wikipedia.org/wiki/Large_language_model and give me only the parts most relevant to 'training data and compute cost', capped at 500 tokens using budget mode."},{"title":"Structured data extraction from a live page","prompt":"Pull https://finance.yahoo.com/quote/AAPL and distill it in structured mode so I can get the tables and key metadata as JSON."}],"resultDescription":"Returns a JSON object with a 'data' field containing the distilled content (Markdown text, structured JSON, skeleton outline, or BM25 excerpt depending on mode), an 'roi_proof' object showing raw_tokens, distilled_tokens, tokens_saved, compression_ratio_pct, and llm_cost_saved_usd, plus optional cache status and billing details.","failureModes":["Invalid or unreachable URL returns an error status","JavaScript-heavy SPA pages may time out or partially render","max_tokens too low may yield an empty or truncated excerpt","BM25 query with no relevant matches returns minimal content","Raw HTML too large may be rejected or truncated","Payment not provided triggers HTTP 402 response"],"whenToPreferThis":"Choose this endpoint when you need to feed live web content to an LLM but must stay within a token budget or reduce inference cost. It is especially useful for SPA pages that require JavaScript rendering, for situations where you want BM25-focused relevance filtering rather than full-page dumps, or when you need structured/tabular extraction. Prefer it over generic scrapers when token efficiency and ROI metrics matter to your agent pipeline.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:23:25.308Z","isFirstParty":false,"canonicalSlug":"prompt-guard-agentdiet-dev-web-url-to-compact-markdown-distiller-bm25-03990d4c"}