{"uid":"cap_aR2uSXtdOSBA9tq9hc-U0","slug":"prompt-guard-agentdiet-dev-rag-token-diet-url-html-distiller-with-5a5f6f66","name":"RAG Token Diet – URL & HTML 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-token-diet)","url":"https://prompt-guard.agentdiet.dev/v1/rag-token-diet?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_KcI4WJwG-jvH_VtcZFdLD","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 webpage URL or raw HTML into compressed Markdown, structured JSON, skeleton outline, or a BM25-focused budget excerpt to reduce LLM token consumption.","exampleAgentPrompt":"Distill the content at https://stripe.com/docs/payments into Markdown and keep it under 800 tokens, focusing the BM25 budget on 'payment intents' so I only get the relevant sections.","exampleUseCases":[{"title":"RAG pipeline token budget enforcement","prompt":"Fetch https://openai.com/pricing and distill it using budget mode with a max of 500 tokens, focused on 'API pricing per million tokens' — I need just the relevant pricing section for my RAG pipeline."},{"title":"Structured table extraction from e-commerce page","prompt":"Take this product page HTML and distill it into structured JSON so I can pull out the product names, prices, and availability without wading through all the nav and footer noise."},{"title":"Skeleton outline for long documentation page","prompt":"Distill https://docs.aws.amazon.com/ec2/latest/userguide/concepts.html into a skeleton outline mode so I can see the high-level structure before deciding which sections to read in full."}],"resultDescription":"Returns a 'data' object containing the distilled content (Markdown text, structured JSON tables/metadata, skeleton outline, or BM25-focused excerpt depending on mode), alongside an 'roi_proof' object showing raw token count, distilled token count, tokens saved, compression ratio percentage, and estimated LLM cost saved in USD. Also includes optional cache hit/miss status and billing details.","failureModes":["URL is unreachable or returns non-200 — distillation fails with fetch error","raw HTML is malformed or empty — parser returns minimal or empty output","mode=budget without a query or max_tokens — BM25 filtering may be undefined or fall back to default","token budget too low (below 20) — rejected by schema validation","page is JavaScript-rendered only — static fetcher may return shell HTML with little content","payment not settled via x402 — 402 response requiring payment before processing"],"whenToPreferThis":"Choose this endpoint when you need to reduce token costs before passing webpage content to an LLM, especially when operating within strict context-window budgets or RAG pipelines. Prefer it over generic scrapers when you need compression metrics (ROI proof), BM25-focused relevance filtering, or multiple distillation output modes (Markdown, structured, skeleton). It is ideal for agentic workflows where minimizing LLM inference costs on web-fetched content is a priority.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:35:52.739Z","isFirstParty":false,"canonicalSlug":"prompt-guard-agentdiet-dev-rag-token-diet-url-html-distiller-with-5a5f6f66"}