{"uid":"cap_6WeOS8O5XE6C4OSP90FRn","slug":"prompt-guard-agentdiet-dev-web-url-distiller-with-bm25-budget-control-edc98a95","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/rag-chunk)","url":"https://prompt-guard.agentdiet.dev/v1/rag-chunk?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_f19OUco2zzDtWXDoLrGnS","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 accepts raw HTML) and distills it into compact, agent-ready markdown, structured data, skeleton outline, or BM25-focused token-budgeted excerpts","exampleAgentPrompt":"Can you distill https://docs.stripe.com/payments into compact markdown using budget mode, focusing on 'payment intents' and keeping it under 500 tokens?","exampleUseCases":[{"title":"Token-budget documentation fetch","prompt":"Grab the Stripe docs page at https://docs.stripe.com/api and distill it in budget mode focused on 'refunds', keeping the result under 300 tokens so it fits in my prompt."},{"title":"Structured table extraction from webpage","prompt":"Pull https://en.wikipedia.org/wiki/List_of_countries_by_GDP and distill it in structured mode so I get the tables and metadata as clean JSON."},{"title":"Skeleton outline of long article","prompt":"Distill https://www.nytimes.com/2024/01/15/technology/ai-agents.html into a skeleton outline so I can quickly see the document structure without reading the whole thing."}],"resultDescription":"Returns a JSON object with a 'data' field containing the distilled content (markdown string, structured JSON tables/metadata, skeleton outline, or BM25-focused excerpt depending on mode), plus an 'roi_proof' object showing raw_tokens, distilled_tokens, tokens_saved, compression_ratio_pct, and llm_cost_saved_usd, along with cache hit/miss status and billing details.","failureModes":["URL is unreachable or returns non-200 status — fetch fails with error","HTML payload too large to process within service limits","mode=budget used without providing a query parameter — BM25 ranking not possible","max_tokens set below minimum of 20 — validation error","Target URL blocks bot/crawler user agents — empty or partial content returned","Invalid URL format provided — schema validation error"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to read web content but must stay within a token budget, reduce LLM inference costs, or pre-process HTML into structured/clean formats before passing to a language model. It is especially valuable in RAG pipelines where token efficiency matters, or when a page contains many tables, navigation noise, and boilerplate that inflate raw token counts. Prefer over generic scrapers when BM25 query-focused chunking is needed to retrieve only the most relevant section of a long document.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:25:44.794Z","isFirstParty":false,"canonicalSlug":"prompt-guard-agentdiet-dev-web-url-distiller-with-bm25-budget-control-247ee8c7"}