{"uid":"cap_wHLjoYXTOaFyQy7xPO62L","slug":"arxiv-digest-agentdiet-dev-web-content-distillation-with-bm25-budget-4b7660d5","name":"Web Content Distillation with 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/markdown-distill)","url":"https://arxiv-digest.agentdiet.dev/v1/markdown-distill?utm_source=zero.xyz","method":"POST","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_pHboNsIpld2vanLUSshRY","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 converts it to clean Markdown, structured JSON, or a token-budgeted BM25-ranked excerpt with compression metrics.","exampleAgentPrompt":"Distill https://arxiv.org/abs/2401.00001 into clean markdown using budget mode, focused on the query 'transformer attention mechanisms', and keep it under 500 tokens.","exampleUseCases":[{"title":"Fit research paper into LLM context","prompt":"Grab https://arxiv.org/abs/2312.12345 and distill it in budget mode, focused on 'reinforcement learning from human feedback', keeping the output under 800 tokens so it fits in my prompt."},{"title":"Convert docs page to clean markdown","prompt":"Fetch https://stripe.com/docs/api and convert it to clean markdown mode — I want to use it as context for my coding agent without all the nav and HTML noise."},{"title":"Distill raw HTML from clipboard","prompt":"I've got raw HTML from a scraped page — can you distill it directly in structured mode to pull out any tables and metadata? Here's the HTML: <html>...</html>"}],"resultDescription":"Returns a JSON object with a 'data' field containing the distilled content (Markdown text, structured tables, skeleton outline, or BM25 excerpt depending on mode), plus an 'roi_proof' object showing raw_tokens, distilled_tokens, tokens_saved, compression_ratio_pct, and llm_cost_saved_usd. Also includes optional cache hit/miss status and billing details.","failureModes":["URL unreachable or returns non-200 — endpoint may return error status","Token budget too low (max_tokens < 20) — rejected by schema validation","BM25 query missing when mode=budget — may return unranked or empty excerpt","Raw HTML too large — may timeout or exceed processing limits","Paywalled or JS-rendered pages may return incomplete content","Payment not provided — returns HTTP 402 requiring x402 payment"],"whenToPreferThis":"Choose this endpoint when you need to convert web pages or raw HTML into LLM-friendly token-efficient content, especially when you need strict token budget control via BM25 ranking. Ideal for agents that need to ingest live web content without blowing up context windows. Prefer over generic scraping tools when compression metrics (tokens saved, cost saved) matter, or when you need structured JSON tables extracted from HTML rather than raw text.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:30:19.292Z","isFirstParty":false,"canonicalSlug":"arxiv-digest-agentdiet-dev-web-content-distillation-with-bm25-budget-687b8b15"}