{"uid":"cap_ZeBaoHZNSci2RMaTsLA82","slug":"prompt-guard-agentdiet-dev-web-url-html-distillation-with-bm25-budget-c6f43b81","name":"Web URL & HTML Distillation 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/prompt-compress)","url":"https://prompt-guard.agentdiet.dev/v1/prompt-compress?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_AG3ygK8ev-OhBQz-6b1qX","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 compresses a URL or raw HTML into compact, agent-ready tokens using markdown, structured, skeleton, or BM25-ranked budget modes.","exampleAgentPrompt":"Distill the content at https://stripe.com/docs/payments into markdown and keep it under 2000 tokens, focusing on 'payment intents' so I can feed it into my LLM without blowing the context window.","exampleUseCases":[{"title":"Research page compression for LLM context","prompt":"Fetch the Wikipedia article at https://en.wikipedia.org/wiki/Transformer_(machine_learning_model) and distill it into markdown under 1500 tokens, focusing on 'attention mechanism', so I can include it in my prompt without exceeding my context limit."},{"title":"Structured data extraction from product page","prompt":"Take the HTML from this e-commerce product page and distill it into structured JSON tables so I can pull out the specs and pricing cleanly — here's the URL: https://www.apple.com/macbook-pro/."},{"title":"Skeleton outline of documentation site","prompt":"Give me a skeleton outline of https://docs.openai.com/api-reference so I can quickly see the top-level structure and navigate to the right section without reading the whole page."}],"resultDescription":"Returns a distilled version of the webpage or HTML in the requested mode (Markdown, structured JSON tables/metadata, skeleton outline, or BM25-ranked budget excerpt), along with ROI proof showing raw token count, distilled token count, tokens saved, compression ratio percentage, and estimated LLM cost saved in USD. Also includes cache hit/miss status and billing details.","failureModes":["Missing required 'url' parameter returns validation error","Unreachable or invalid URL causes fetch failure","mode=budget without a 'query' or 'max_tokens' may return unfiltered content","Very large pages may exceed processing limits","Payment failure via x402 prevents execution","HTML too malformed to parse returns partial or empty distillation"],"whenToPreferThis":"Choose this endpoint when you need to compress web content or raw HTML into a token-efficient format before feeding it to an LLM, especially when working under strict token budgets. Ideal when you need BM25-ranked relevance filtering to focus on a specific topic within a large page. Prefer over generic scrapers when you need built-in ROI metrics (tokens saved, cost saved) and multiple distillation modes (markdown, structured, skeleton, budget).","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:20:21.663Z","isFirstParty":false,"canonicalSlug":"prompt-guard-agentdiet-dev-web-url-html-distillation-with-bm25-budget-c6f43b81"}