{"uid":"cap_uBnpYMagKPAcYdo97PYBt","slug":"domain-osint-agentdiet-dev-web-url-rag-token-distiller-a1aa8d20","name":"Web URL RAG Token Distiller","description":"Distill a URL or raw HTML payload with BM25 budget control (Live x402 v2, IETF MPP & MCP endpoint at https://domain-osint.agentdiet.dev/v1/rag-token-diet)","url":"https://domain-osint.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_3MlyfSYlw_Yqhg5KhIqPL","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"domain-osint.agentdiet.dev","brandSlug":"domain-osint-agentdiet-dev-mpp","brandBaseUrl":"https://domain-osint.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches a URL or raw HTML and compresses it into compact, agent-ready tokens using BM25 budget control and multiple extraction modes","exampleAgentPrompt":"Distill https://stripe.com/docs/api into compact markdown using budget mode, focusing on 'authentication endpoints', and keep it under 500 tokens.","exampleUseCases":[{"title":"Compress docs page for RAG pipeline","prompt":"Fetch https://docs.openai.com/api-reference and distill it into structured markdown so I can feed it into my RAG system without burning through my token budget."},{"title":"Extract relevant section within token limit","prompt":"Pull https://www.sec.gov/cgi-bin/browse-edgar?action=getcompany and extract only the parts about annual filings using budget mode with my query set to 'annual report 10-K' and a max of 300 tokens."},{"title":"Get skeleton outline of a long article","prompt":"Take https://en.wikipedia.org/wiki/Large_language_model and give me a skeleton outline of the page so I can quickly understand its structure without reading the whole thing."}],"resultDescription":"Returns a distilled version of the target web page as Markdown, structured JSON tables/metadata, a skeleton outline, or a BM25-focused budget excerpt — along with an ROI proof object showing raw vs distilled token counts, compression ratio, tokens saved, and estimated LLM cost saved in USD. Also includes cache hit/miss status and billing details.","failureModes":["Invalid or unreachable URL returns an error status","HTML payload too large may exceed processing limits","Budget mode without a query may produce suboptimal BM25 ranking","max_tokens set below 20 rejected by schema validation","Payment failure via x402 prevents execution","Rate limiting or bot-blocking on target domain may return empty or partial content"],"whenToPreferThis":"Choose this endpoint when you need to feed web page content into an LLM or RAG pipeline and want to minimize token usage. It is especially valuable when pages are long, token budgets are tight, or you need BM25-focused excerpts matching a specific query. Prefer it over raw scraping when you need built-in compression metrics and ROI proof. It also supports direct HTML input if you already have the raw content.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:24:15.766Z","isFirstParty":false,"canonicalSlug":"domain-osint-agentdiet-dev-web-url-rag-token-distiller-a1aa8d20"}