{"uid":"cap_iJiPgHxhnyDVp2jhmG3a5","slug":"prompt-guard-agentdiet-dev-agentdiet-rag-token-diet-web-url-distiller-7ea3cae0","name":"AgentDiet RAG Token Diet – Web URL Distiller","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-token-diet)","url":"https://prompt-guard.agentdiet.dev/v1/rag-token-diet?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_CzLreUv6b9OeLMgY0Hmqb","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 BM25 budget control and multiple extraction modes","exampleAgentPrompt":"Distill the content at https://stripe.com/docs/api into compact markdown, keeping it under 800 tokens and focusing on the 'authentication' topic using budget mode.","exampleUseCases":[{"title":"Distill documentation into agent context","prompt":"Fetch the Stripe docs at builtin://stripe-docs and distill them into structured markdown so I can pass just the relevant bits to my agent without overflowing the context window."},{"title":"BM25-focused budget excerpt for research","prompt":"Pull the page at https://openai.com/research/gpt-4 and give me a BM25-focused excerpt on 'safety benchmarks' with a hard cap of 500 tokens — I need just the relevant section, nothing else."},{"title":"Convert noisy HTML into structured tables","prompt":"I have raw HTML from a financial report page — distill it into structured JSON tables so my agent can parse the numbers without wading through all the junk markup."}],"resultDescription":"Returns a JSON object with a 'data' field containing the distilled content (Markdown, structured JSON tables/metadata, skeleton outline, or BM25 budget excerpt depending on mode), an 'roi_proof' object showing raw vs distilled token counts, tokens saved, compression ratio percentage, estimated LLM cost saved in USD, and an ROI multiplier. Also includes optional cache hit/miss status and billing metadata.","failureModes":["Invalid or unreachable URL returns an error status","HTML fetch timeout for slow or blocked pages","max_tokens below minimum of 20 triggers validation error","BM25 query provided without mode=budget may be ignored","Raw HTML too large may exceed processing limits","Non-public or paywalled URLs may return empty or partial content"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to read a webpage but must stay within a token budget or reduce LLM inference costs. It is especially useful for RAG pipelines where raw HTML is too noisy, for documentation ingestion with structured or skeleton modes, or when BM25-focused excerpts are needed to retrieve only topic-relevant content from a long page. Prefer it over generic scrapers when token efficiency and ROI proof are required outputs.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:21:29.939Z","isFirstParty":false,"canonicalSlug":"prompt-guard-agentdiet-dev-agentdiet-rag-token-diet-web-url-distiller-7ea3cae0"}