{"uid":"cap_Ivwqo7mGdVa2IY229gQ5x","slug":"prompt-guard-agentdiet-dev-web-url-distiller-with-bm25-budget-control-96909af2","name":"Web URL 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/pdf-extract)","url":"https://prompt-guard.agentdiet.dev/v1/pdf-extract?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_4p7Hc5v3xFRTuI3TyIP_0","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 webpage or raw HTML and compresses it into compact, agent-ready tokens using configurable distillation modes including BM25-focused budget extraction","exampleAgentPrompt":"Distill the content at https://docs.stripe.com/payments/accept-a-payment into compact markdown, and use budget mode focused on the query 'payment intent' with a max of 500 tokens so it fits in my context window.","exampleUseCases":[{"title":"Documentation page summarization for agents","prompt":"Pull the Stripe docs page at https://docs.stripe.com/api and distill it into clean markdown — keep it under 800 tokens using budget mode with the query 'authentication API keys'."},{"title":"Competitive research with token efficiency","prompt":"Fetch https://openai.com/pricing and give me a structured extraction of all the pricing tables and metadata — I want JSON-style output, not raw HTML."},{"title":"Skeleton outline of a long article","prompt":"I need a skeleton outline of this article at https://www.nytimes.com/2024/01/15/technology/ai-agents.html — just the headings and key section structure, as compact as possible."}],"resultDescription":"Returns a distilled payload in the requested format (markdown, structured JSON tables/metadata, skeleton outline, or BM25-focused budget excerpt), along with ROI proof stats showing raw token count, distilled token count, tokens saved, compression ratio percentage, estimated LLM cost saved, and optional billing and cache metadata.","failureModes":["Invalid or unreachable URL returns an error status","Token budget too low (below minimum 20) causes validation failure","Mode set to 'budget' without a query may yield unfocused results","Raw HTML too large may time out or exceed processing limits","URL behind authentication or bot protection may return empty or blocked content"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to ingest a webpage or HTML document but must stay within a token budget or reduce LLM costs. It is especially useful when a BM25-focused excerpt is needed to retrieve only the most relevant section of a large page relative to a query. Prefer it over generic scrapers when you need compression metrics (ROI proof) and multiple output formats (markdown, structured, skeleton, budget) in a single call.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:26:10.088Z","isFirstParty":false,"canonicalSlug":"prompt-guard-agentdiet-dev-web-url-distiller-with-bm25-budget-control-247ee8c7"}