{"uid":"cap_JrJA7K77BDdaEKhUeYGgi","slug":"arxiv-digest-agentdiet-dev-web-content-distiller-with-bm25-budget-b3dac199","name":"Web Content 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://arxiv-digest.agentdiet.dev/v1/context-bloat-eliminator)","url":"https://arxiv-digest.agentdiet.dev/v1/context-bloat-eliminator?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_KKUmtBF-8mDvVCEgEIq29","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 distills a URL or raw HTML into clean Markdown, structured JSON, skeleton outline, or a BM25-ranked token-budget excerpt for LLM context compression","exampleAgentPrompt":"Distill this URL into clean Markdown and trim it to 800 tokens using BM25 budget mode focused on 'transformer architecture': https://arxiv.org/abs/2106.09685","exampleUseCases":[{"title":"RAG pipeline context compression","prompt":"Fetch and compress this research paper URL into a 1000-token BM25 excerpt focused on 'attention mechanism' so I can pass it to my LLM without blowing the context window: https://arxiv.org/abs/1706.03762"},{"title":"Docs page skeleton for agent navigation","prompt":"Give me a skeleton outline of this Stripe documentation page so my agent can quickly understand its structure without reading the full content: https://stripe.com/docs/api"},{"title":"Structured data extraction from HTML","prompt":"I have raw HTML from a product listing page — distill it into structured JSON tables pulling out pricing, specs, and metadata so I can compare products programmatically."}],"resultDescription":"Returns a 'data' object containing the distilled content (Markdown text, structured JSON tables/metadata, skeleton outline, or BM25-ranked excerpt depending on mode), plus an 'roi_proof' object showing raw token count, distilled token count, tokens saved, compression ratio percentage, 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 fetch error","Missing required 'url' field returns 400 validation error","mode=budget without a 'query' field may produce unranked results","max_tokens below minimum of 20 rejected with validation error","Paywalled or bot-blocked pages may return incomplete or empty distillation","Payment failure via x402 returns 402 status blocking execution"],"whenToPreferThis":"Choose this endpoint when you need to compress a live webpage or raw HTML into a token-efficient form before passing it to an LLM, especially when you need BM25-ranked relevance filtering against a specific query or need to enforce a strict token budget ceiling. Prefer it over generic scrapers when you care about downstream LLM cost savings and want ROI metrics (compression ratio, tokens saved, cost saved) alongside the distilled content. The budget mode is particularly valuable in RAG pipelines where context window management is critical.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:34:10.189Z","isFirstParty":false,"canonicalSlug":"arxiv-digest-agentdiet-dev-web-content-distiller-with-bm25-budget-cb1848ab"}