{"uid":"cap_ktCVxQTA2kxmi63hx_Mli","slug":"arxiv-digest-agentdiet-dev-agentdiet-rag-token-diet-web-url-distiller-7bdbaa9f","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://arxiv-digest.agentdiet.dev/v1/rag-token-diet)","url":"https://arxiv-digest.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_ad18XbtBtVCislYoMFXAP","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"arxiv-digest.agentdiet.dev","brandSlug":"arxiv-digest-agentdiet-dev-mpp","brandBaseUrl":"https://arxiv-digest.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches and compresses a webpage or raw HTML into compact, agent-ready tokens using BM25 budget control and multiple distillation modes","exampleAgentPrompt":"Can you fetch https://arxiv.org/abs/2401.00123 and distill it into compact markdown, keeping it under 500 tokens and focusing on 'retrieval augmented generation' so I can fit it in my context window?","exampleUseCases":[{"title":"Fit research paper into context window","prompt":"Grab https://arxiv.org/abs/2310.11511 and distill it into budget mode focused on 'chain-of-thought prompting', capped at 300 tokens — I need to stuff it into a tight LLM prompt."},{"title":"Extract structured product data from store page","prompt":"Take this URL https://shop.example.com/products/widget-pro and pull out a structured JSON summary of the product info, pricing, and specs — use structured mode so I get clean tables."},{"title":"Skeleton outline of long documentation page","prompt":"Get the skeleton outline of https://docs.stripe.com/api — just the headings and section structure, no full content, so I can navigate it quickly without blowing my token budget."}],"resultDescription":"Returns a JSON object with a 'data' field containing distilled content (Markdown text, structured JSON tables/metadata, skeleton outline, or BM25-ranked excerpt depending on mode), plus an 'roi_proof' object showing raw vs distilled token counts, tokens saved, compression ratio percentage, LLM cost saved in USD, and an ROI multiplier. Optionally includes cache status (HIT/MISS) and billing details.","failureModes":["URL is unreachable or returns non-200 — fetch failure with status error","URL content is too large or unparseable HTML — distillation may return empty or partial data","mode=budget with no query param — BM25 ranking cannot be applied, may fall back to truncation","max_tokens set below 20 — rejected by schema validation","Rate limiting or payment failure via x402 — 402 response requiring payment","Paywalled or bot-blocked pages — fetch succeeds but content is login wall or CAPTCHA"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to read and process web pages but must stay within tight LLM token budgets — especially for RAG pipelines, long documentation pages, or research papers. It is superior to raw fetch + manual truncation because it provides BM25-ranked relevance filtering, multiple distillation modes (markdown, structured, skeleton, budget), and built-in ROI proof showing exactly how many tokens and LLM dollars were saved. Prefer it over generic scrapers when token economy and context-window fit are primary concerns.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:21:30.827Z","isFirstParty":false,"canonicalSlug":"arxiv-digest-agentdiet-dev-agentdiet-rag-token-diet-web-url-distiller-7bdbaa9f"}