{"uid":"cap_JXzwJy_h4N6ZGxte9Lsye","slug":"sec-intel-agentdiet-dev-web-url-distillation-token-diet-rag-endpoint-f6ca82d2","name":"Web URL Distillation & Token-Diet RAG Endpoint","description":"Distill a URL or raw HTML payload with BM25 budget control (Live x402 v2, IETF MPP & MCP endpoint at https://sec-intel.agentdiet.dev/v1/rag-token-diet)","url":"https://sec-intel.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_uGspn8YfypDdCgB2VTbd9","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"sec-intel.agentdiet.dev","brandSlug":"sec-intel-agentdiet-dev-mpp","brandBaseUrl":"https://sec-intel.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches a URL or accepts 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 focused on the query 'payment intents' using budget mode.","exampleUseCases":[{"title":"Compress docs page for RAG pipeline","prompt":"Fetch and distill https://docs.openai.com/api-reference into structured markdown so I can feed it into my RAG pipeline without blowing my token budget — keep it under 1000 tokens."},{"title":"BM25-focused excerpt from a news article","prompt":"Pull the article at https://techcrunch.com/2024/01/15/openai-news and extract only the parts relevant to 'funding round valuation' using budget mode, capped at 500 tokens."},{"title":"Skeleton outline of a lengthy whitepaper","prompt":"Give me a skeleton outline of the content at https://arxiv.org/html/2401.00123 so I can quickly understand the document structure without reading the whole thing."}],"resultDescription":"Returns a JSON object with a 'data' field containing the distilled output (Markdown, structured JSON, skeleton, or BM25 excerpt depending on mode), an 'roi_proof' object showing raw vs distilled token counts, tokens saved, compression ratio percentage, estimated LLM cost saved, and ROI multiplier, plus optional cache status and billing details.","failureModes":["URL is unreachable or returns non-200 — endpoint may return an error status","HTML content is too large and cannot be processed within service limits","Invalid mode enum value causes a validation error","max_tokens set below 20 triggers minimum constraint violation","BM25 query provided without mode=budget may be ignored or cause unexpected output","x402 payment not completed results in 402 Payment Required response","Paywalled or JavaScript-heavy pages may yield poor distillation quality"],"whenToPreferThis":"Choose this endpoint when you need to feed web content into an LLM or RAG system and want to minimize token consumption and cost. It is ideal when you have a URL (or raw HTML) and need clean, structured, or relevance-filtered output with quantified token savings. Prefer it over generic web scrapers when you need BM25-focused excerpts, skeleton outlines, or structured JSON tables extracted from web pages, especially within a strict token budget.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T12:51:30.387Z","isFirstParty":false,"canonicalSlug":"sec-intel-agentdiet-dev-web-url-distillation-token-diet-rag-endpoint-f6ca82d2"}