{"uid":"cap_vLH_gOXvDHf_h_AJQEezH","slug":"arxiv-digest-agentdiet-dev-agentdiet-context-diet-web-url-distillation-696a8d31","name":"AgentDiet Context Diet — Web URL Distillation","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-diet)","url":"https://arxiv-digest.agentdiet.dev/v1/context-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_vcO2-aWvPenS_HVsnhk7s","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 compresses it into compact, agent-ready tokens using BM25 budget control and multiple distillation modes","exampleAgentPrompt":"Can you distill this URL into compact markdown within 800 tokens, focusing on the pricing section? Use budget mode with the query 'pricing plans': https://stripe.com/pricing","exampleUseCases":[{"title":"Research paper quick-read for agent","prompt":"Grab this ArXiv paper URL and distill it into structured markdown so I can read the key findings without blowing my context window: https://arxiv.org/abs/2401.00001"},{"title":"Token-budget extraction from docs page","prompt":"I need you to pull the Stripe docs page at https://stripe.com/docs/api and extract only the most relevant content about webhooks — keep it under 500 tokens using budget mode with the query 'webhooks'."},{"title":"Skeleton outline of a long article","prompt":"Get me a skeleton outline of this long blog post so I can see the structure before deciding whether to read the full thing: https://example.com/very-long-article"}],"resultDescription":"Returns a distilled version of the web page (Markdown, structured JSON tables/metadata, skeleton outline, or BM25-focused excerpt depending on mode), plus ROI proof metrics including raw token count, distilled token count, tokens saved, compression ratio percentage, LLM cost saved in USD, and ROI multiplier. Also includes cache status and billing info.","failureModes":["Invalid or unreachable URL returns fetch error","max_tokens set below minimum of 20 returns validation error","mode=budget without a query may yield unfocused results","Raw HTML too large may hit processing limits","Payment failure via x402 returns 402 status"],"whenToPreferThis":"Use this endpoint when an AI agent needs to read web content but must stay within a strict token budget, or when LLM input costs from large pages are a concern. Ideal for agent pipelines that process many pages, documentation lookups, research workflows, or any scenario where raw web content would be too large to pass directly into a model context. Prefer over generic web scrapers when token compression and cost savings are priorities.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T12:48:54.721Z","isFirstParty":false,"canonicalSlug":"arxiv-digest-agentdiet-dev-agentdiet-context-diet-web-url-distillation-696a8d31"}