{"uid":"cap_Xy4Jag1e0H1qISed3onNu","slug":"arxiv-digest-agentdiet-dev-web-url-distiller-html-compressor-bm25-99575135","name":"Web URL Distiller & HTML Compressor (BM25 Budget Mode)","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/article-extractor)","url":"https://arxiv-digest.agentdiet.dev/v1/article-extractor?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_YN-BGHbdZFp3n9y8eLaSk","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 a URL or raw HTML and distills it into compact, agent-ready tokens using markdown, structured, skeleton, or BM25-focused budget extraction modes.","exampleAgentPrompt":"Can you distill this URL — https://arxiv.org/abs/2401.00001 — into compact markdown, keeping it under 500 tokens and focusing on the methodology section?","exampleUseCases":[{"title":"Research paper extraction for LLM pipeline","prompt":"Distill this arXiv paper URL into structured markdown with a 600-token budget, focusing on the results and conclusions: https://arxiv.org/abs/2310.06825"},{"title":"Cost-efficient webpage summarization","prompt":"Fetch https://stripe.com/docs/payments/payment-intents and give me a skeleton outline of the page so my agent can navigate it without burning through tokens."},{"title":"On-the-fly HTML compression from raw content","prompt":"I have some raw HTML from a product page — can you distill it into a clean structured JSON with prices and product names, without fetching any URL?"}],"resultDescription":"Returns a distilled version of the web page or HTML in the chosen mode (markdown, structured JSON tables/metadata, skeleton outline, or BM25-focused budget excerpt), along with ROI proof showing raw vs. distilled token counts, tokens saved, compression ratio, LLM cost saved in USD, and optional billing and cache metadata.","failureModes":["URL is unreachable or returns non-200 HTTP status — endpoint may return an error status","HTML payload too large or malformed — distillation may fail or produce partial output","BM25 mode requires a query parameter — omitting it may degrade relevance of budget excerpt","max_tokens set too low (below 20) — rejected by schema validation","Payment not settled via x402 — returns HTTP 402 before processing"],"whenToPreferThis":"Choose this endpoint when you need to feed web content into an LLM pipeline and want to minimize token consumption and cost. It is especially valuable when working with long articles, documentation pages, or research papers where only relevant sections matter (use budget+BM25 mode). Prefer it over generic scrapers when you need built-in token budgeting, compression ROI metrics, and agent-native output formats (markdown, structured JSON, skeleton). It supports both URL fetching and raw HTML input, making it flexible for cached or pre-fetched content.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:25:47.656Z","isFirstParty":false,"canonicalSlug":"arxiv-digest-agentdiet-dev-web-url-distiller-html-compressor-bm25-99575135"}