{"uid":"cap_tUW0NM_5-n7BnNO0RvuLC","slug":"cve-intel-agentdiet-dev-rag-token-diet-web-url-distiller-f030d8d7","name":"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://cve-intel.agentdiet.dev/v1/rag-token-diet)","url":"https://cve-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_AzvVRzncrFT2665sfpoPN","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"cve-intel.agentdiet.dev","brandSlug":"cve-intel-agentdiet-dev-mpp","brandBaseUrl":"https://cve-intel.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches a URL (or raw HTML) and compresses it into compact, agent-ready tokens using multiple distillation modes including BM25 budget-controlled extraction","exampleAgentPrompt":"Distill https://nvd.nist.gov/vuln/detail/CVE-2024-1234 into compact markdown — use budget mode with the query 'severity CVSS score patch' and cap it at 500 tokens.","exampleUseCases":[{"title":"Compress docs page for RAG indexing","prompt":"Fetch https://docs.stripe.com/api/charges and distill it into structured JSON tables so I can index it in my RAG pipeline without blowing my token budget."},{"title":"Budget-focused CVE advisory extraction","prompt":"Grab the page at https://cve.mitre.org/cgi-bin/cvename.cgi?name=CVE-2024-5678 and extract only the parts relevant to 'affected versions and remediation' using budget mode, keeping it under 300 tokens."},{"title":"Skeleton outline of a long article","prompt":"Take this URL https://en.wikipedia.org/wiki/Large_language_model and give me a skeleton outline of its structure — just the headings and key sections, nothing else."}],"resultDescription":"Returns a 'data' object containing the distilled content (Markdown, structured JSON, skeleton, or BM25 excerpt depending on mode), plus an 'roi_proof' object showing raw vs distilled token counts, compression ratio percentage, tokens saved, ROI multiplier, and estimated LLM cost saved in USD. Also includes optional cache hit/miss status and billing details.","failureModes":["Invalid or unreachable URL returns an error status","max_tokens set below 20 triggers a validation error","BM25 query provided without mode=budget may be ignored","Rate limiting or payment failure via x402 returns HTTP 402","HTML fetch blocked by anti-scraping measures on target site","Very large pages may exceed processing limits or have long latency"],"whenToPreferThis":"Choose this endpoint when you need to feed web content into an LLM or RAG pipeline and want to minimize token consumption and cost. It is especially valuable when you have a strict token budget (use mode=budget with a query and max_tokens), need clean Markdown from noisy HTML, or want to extract structured tables from documentation pages. Prefer it over generic scrapers when token efficiency and LLM cost reduction are primary concerns.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T12:51:34.132Z","isFirstParty":false,"canonicalSlug":"cve-intel-agentdiet-dev-rag-token-diet-web-url-distiller-f030d8d7"}