{"uid":"cap_xqSb5HbfbND-iRD_8743U","slug":"prompt-guard-agentdiet-dev-web-url-dom-distiller-with-bm25-budget-f744a1e5","name":"Web URL DOM 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/dom-stripper)","url":"https://prompt-guard.agentdiet.dev/v1/dom-stripper?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_j6EIi3O8wyRhZyrvhO7S0","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 tokens using markdown, structured, skeleton, or BM25-budget extraction modes","exampleAgentPrompt":"Fetch https://docs.stripe.com/api and distill it into clean markdown, keeping it under 2000 tokens and focusing on the authentication section.","exampleUseCases":[{"title":"LLM-cost-efficient docs ingestion","prompt":"Grab https://platform.openai.com/docs/api-reference and distill it into structured markdown under 1500 tokens — I want to feed it into a model without blowing my context window."},{"title":"BM25-focused competitive research","prompt":"Pull the page at https://anthropic.com/research and extract only the parts relevant to 'constitutional AI' using budget mode, capped at 800 tokens."},{"title":"Skeleton outline for large webpage","prompt":"Give me a skeleton outline of https://en.wikipedia.org/wiki/Large_language_model so I can see the section structure without all the body text."}],"resultDescription":"Returns a data object with distilled content (markdown, structured JSON tables/metadata, skeleton outline, or BM25-ranked excerpt), plus an roi_proof block showing raw vs distilled token counts, tokens saved, compression ratio percentage, estimated LLM cost saved in USD, and an ROI multiplier. Also includes cache status (HIT/MISS) and billing details.","failureModes":["Invalid or unreachable URL returns fetch error","HTML too large may exceed processing limits","mode=budget without a query returns unclear or unfiltered results","max_tokens below 20 is rejected by schema validation","Paywalled or bot-blocked pages may return empty or partial content","Payment failure (402) if USDC balance is insufficient"],"whenToPreferThis":"Choose this endpoint when you need to feed web page content to an LLM and want to minimize token usage and cost — especially when the raw HTML would be too large for your context window. It is preferable over generic scrapers when you need BM25-ranked budget excerpts, skeleton outlines, or structured JSON extraction, and when you want an explicit ROI/compression report alongside the distilled content.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:24:15.765Z","isFirstParty":false,"canonicalSlug":"prompt-guard-agentdiet-dev-web-url-dom-distiller-with-bm25-budget-f744a1e5"}