{"uid":"cap_AAlomDbBIjLF-Z6lbb_I4","slug":"arxiv-digest-agentdiet-dev-web-url-context-compressor-bm25-budget-8679870d","name":"Web URL Context Compressor (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-compress)","url":"https://arxiv-digest.agentdiet.dev/v1/context-compress?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_uiYocMZpFVFdkfUk3ATAP","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 web URL or raw HTML into compact, agent-ready tokens using configurable extraction modes and BM25 budget control","exampleAgentPrompt":"Fetch and distill https://arxiv.org/abs/2501.12345 into compact markdown using budget mode, focused on 'transformer attention mechanisms', capped at 500 tokens.","exampleUseCases":[{"title":"Arxiv paper digest for research agent","prompt":"Distill https://arxiv.org/abs/2312.00752 into structured mode so I can get the key tables and metadata without blowing my token budget."},{"title":"LLM cost savings on long documentation","prompt":"Compress the Stripe docs page at builtin://stripe-docs into budget mode, focused on 'webhook setup', and keep it under 300 tokens so I can include it in my prompt cheaply."},{"title":"Skeleton outline of a competitor page","prompt":"Give me a skeleton outline of https://openai.com/pricing so I can see the page structure and section headings without processing the full content."}],"resultDescription":"Returns a 'data' object containing the distilled content (markdown text, structured JSON tables/metadata, skeleton outline, or BM25-ranked budget excerpt depending on mode), along with an roi_proof block showing raw vs. distilled token counts, tokens saved, compression ratio percentage, ROI multiplier, and estimated LLM cost saved in USD. Also includes optional billing and cache hit/miss metadata.","failureModes":["URL is unreachable or returns non-200 status — endpoint may return an error status","Raw HTML is malformed or empty — distillation may produce minimal output","max_tokens set below minimum of 20 — rejected by schema validation","mode=budget used without a query parameter — BM25 ranking may be unfocused","Payment via x402 fails or is underfunded — request is blocked with 402 response","URL points to paywalled or bot-blocked content — fetch returns incomplete HTML"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to ingest web content within a strict token budget, especially for long pages like documentation, research papers, or news articles. It is superior to raw fetch+parse approaches because it provides built-in compression metrics (ROI proof), multiple extraction modes (markdown, structured, skeleton, budget), and BM25-ranked focus excerpts for query-specific retrieval. Prefer it over general web scrapers when LLM cost reduction and token accounting are explicit goals.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:21:47.115Z","isFirstParty":false,"canonicalSlug":"arxiv-digest-agentdiet-dev-web-url-context-compressor-bm25-budget-8679870d"}