{"uid":"cap_vh_1iGbfKre6ZSPk4o-fl","slug":"arxiv-digest-agentdiet-dev-web-url-dom-stripper-distiller-9ae06232","name":"Web URL DOM Stripper & 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/dom-stripper)","url":"https://arxiv-digest.agentdiet.dev/v1/dom-stripper?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_6-DCblS2-CDM-SW7BNW77","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 BM25 budget control and multiple extraction modes","exampleAgentPrompt":"Distill this URL into compact markdown for me — https://arxiv.org/abs/2401.00001 — and use budget mode with a focus query on 'transformer attention mechanisms' keeping it under 500 tokens.","exampleUseCases":[{"title":"LLM cost reduction via web compression","prompt":"Grab https://stripe.com/docs/payments/checkout and strip it down to under 800 tokens in budget mode, focusing on 'payment intents', so I can feed it to GPT-4 without burning through my context window."},{"title":"Structured data extraction from a product page","prompt":"Distill https://news.ycombinator.com into structured mode for me — I want the tables and metadata pulled out cleanly so my agent can parse the top stories."},{"title":"Skeleton outline of a research paper","prompt":"Fetch https://arxiv.org/abs/2310.06825 and give me a skeleton outline of the page structure so I can quickly understand what sections are covered before deciding whether to read the full thing."}],"resultDescription":"Returns a 'data' object containing the distilled content (markdown text, structured JSON tables/metadata, skeleton outline, or BM25-focused excerpt depending on mode), plus an roi_proof object showing raw vs. distilled token counts, compression ratio, tokens saved, and estimated LLM cost saved in USD. Also includes cache status (HIT/MISS) and billing details.","failureModes":["Invalid or unreachable URL returns an error status","URL fetch timeout for slow or unresponsive pages","max_tokens value below minimum of 20 rejected","BM25 query provided without mode=budget may be ignored","Raw HTML too large may exceed processing limits","Payment/402 not fulfilled results in access denial"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to consume web content efficiently within a token budget — especially before passing content to an LLM where context size and cost matter. It is particularly valuable when you need BM25-focused extraction (only the parts of the page relevant to a specific query), or when you want multiple output formats (markdown, structured tables, skeleton). Prefer it over generic scrapers when you need built-in token accounting and ROI proof of compression savings.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:24:37.028Z","isFirstParty":false,"canonicalSlug":"arxiv-digest-agentdiet-dev-web-url-dom-stripper-distiller-9ae06232"}