{"uid":"cap_mCGAHkrzjd0zWHWSt9QNQ","slug":"prompt-guard-agentdiet-dev-web-distiller-with-bm25-budget-control-4b2eae12","name":"Web 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/paywall-clean-extract)","url":"https://prompt-guard.agentdiet.dev/v1/paywall-clean-extract?utm_source=zero.xyz","method":"POST","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_PlT_90Q9MGWTvVcsZ6X8N","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 and distills a URL or raw HTML into clean Markdown, structured JSON, skeleton outline, or BM25-ranked budget excerpt with token savings proof","exampleAgentPrompt":"Fetch the page at https://stripe.com/docs/payments/payment-intents and distill it into clean markdown, keeping it under 800 tokens and focused on the query 'payment confirmation flow'.","exampleUseCases":[{"title":"Token-budget web research for LLM pipeline","prompt":"Pull the content from https://en.wikipedia.org/wiki/Transformer_(machine_learning_model) and give me a BM25-focused excerpt under 600 tokens centered on the query 'attention mechanism self-attention'."},{"title":"Structured data extraction from product page","prompt":"Distill https://www.apple.com/shop/buy-iphone into structured mode so I get the product tables, prices, and metadata as clean JSON."},{"title":"Skeleton outline of a long documentation page","prompt":"Grab https://docs.python.org/3/library/asyncio.html and return a skeleton outline of its sections so I can quickly navigate what's covered without reading the whole thing."}],"resultDescription":"Returns a JSON object with a 'data' field containing the distilled content (Markdown text, structured JSON tables/metadata, skeleton outline, or BM25-ranked excerpt depending on mode), plus an 'roi_proof' object showing raw_tokens, distilled_tokens, tokens_saved, compression_ratio_pct, and llm_cost_saved_usd. Also includes cache hit/miss status and optional billing info.","failureModes":["URL unreachable or returns non-200 HTTP status — distillation fails with an error status","HTML too large or malformed to parse — may return partial content or error","mode=budget requires both 'query' and 'max_tokens'; omitting them may yield unfiltered output","Paywall or JavaScript-rendered pages may not be fully accessible, returning incomplete content","Token budget ceiling too low (under 20) rejected by schema validation","Rate limiting or payment failure via x402 returns 402 Payment Required"],"whenToPreferThis":"Choose this endpoint when you need to feed web content to an LLM but want to minimize token consumption and cost — especially when you have a specific query focus (use mode=budget with BM25) or need structured output from unstructured HTML. Ideal over generic scrapers when token budget control and ROI proof matter, or when you need to process paywall-style or complex HTML pages into clean Markdown without building your own extraction pipeline.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:32:08.508Z","isFirstParty":false,"canonicalSlug":"prompt-guard-agentdiet-dev-web-distiller-with-bm25-budget-control-4b2eae12"}