{"uid":"cap_fgDEQzyIR4t2G8a2IPqTn","slug":"arxiv-digest-agentdiet-dev-web-url-distiller-compact-agent-ready-b7009040","name":"Web URL Distiller — Compact Agent-Ready Token Extraction","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/api/diet)","url":"https://arxiv-digest.agentdiet.dev/api/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_xoROXtp5Jkql5MAgEVpLl","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 accepts raw HTML) and distills it into compact, token-efficient content using multiple modes including BM25 budget-controlled excerpts","exampleAgentPrompt":"Distill https://arxiv.org/abs/2401.00001 into compact markdown so I can read it without blowing my token budget — use budget mode with a max of 500 tokens and focus the BM25 query on 'transformer architecture'.","exampleUseCases":[{"title":"Token-budget research paper reading","prompt":"Fetch and distill https://arxiv.org/abs/2312.00752 in budget mode, focused on 'reinforcement learning from human feedback', and keep it under 300 tokens so I can process multiple papers cheaply."},{"title":"Structured product page extraction","prompt":"Pull the content from https://stripe.com/pricing and distill it in structured mode so I get a clean JSON table of their pricing tiers and features."},{"title":"Skeleton outline of long documentation","prompt":"Grab https://docs.openai.com/api-reference and give me a skeleton outline so I can see the high-level structure without reading the whole thing."}],"resultDescription":"Returns distilled page content in the chosen format (Markdown, structured JSON, skeleton outline, or BM25 excerpt), plus an ROI proof object showing raw vs distilled token counts, compression ratio, estimated LLM cost saved, and optional cache/billing metadata.","failureModes":["URL is unreachable or returns non-200 — distillation fails with fetch error","URL content is behind a login wall — returns empty or login-page content instead of target","max_tokens set too low (below 20) — rejected with validation error","mode=budget used without a query parameter — BM25 ranking has no focus signal","Raw HTML provided is malformed — parser may produce incomplete output","Payment not included or insufficient for x402 — returns HTTP 402 payment required"],"whenToPreferThis":"Choose this endpoint when your agent needs to read web pages but must stay within strict token budgets, or when you want to avoid paying high LLM costs for raw full-page content. It is especially useful for research agents processing many URLs, pipelines that need structured data or outlines from web pages, or any scenario where BM25-focused relevance extraction is preferable to full-page ingestion. Prefer this over raw fetch tools when token efficiency and cost savings are priorities.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:21:25.632Z","isFirstParty":false,"canonicalSlug":"arxiv-digest-agentdiet-dev-web-url-distiller-compact-agent-ready-b7009040"}