{"uid":"cap_rjtkfJCX-mIirnlkkJWal","slug":"arxiv-digest-agentdiet-dev-web-content-distillation-api-with-bm25-077ffa38","name":"Web Content Distillation API 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/api/diet)","url":"https://arxiv-digest.agentdiet.dev/api/diet?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_Ofpx07FV-a1448bLJvy5G","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 URL or raw HTML payload into clean Markdown, structured JSON, skeleton outline, or a BM25-focused token-budget excerpt","exampleAgentPrompt":"Can you distill https://arxiv.org/abs/2401.00001 into clean markdown, focusing on the abstract and methods sections, and keep the output under 500 tokens using budget mode with the query 'transformer attention mechanism'?","exampleUseCases":[{"title":"Token-budget web page summarization","prompt":"Fetch and distill https://en.wikipedia.org/wiki/Reinforcement_learning into budget mode with the query 'reward function policy gradient' and cap it at 300 tokens so I can include it in my prompt without blowing my context window."},{"title":"Structured table extraction from documentation","prompt":"Take the raw HTML from the Stripe pricing page and distill it in structured mode so I get the pricing tiers and feature comparisons as clean JSON tables."},{"title":"Skeleton outline of a long article","prompt":"Distill https://www.nature.com/articles/s41586-024-00001-0 in skeleton mode so I can see the section headings and subheadings before deciding which parts to read in full."}],"resultDescription":"Returns a JSON object with a 'data' field containing the distilled content (Markdown string, structured JSON, skeleton outline, or BM25-filtered excerpt depending on mode), an 'roi_proof' object showing raw_tokens, distilled_tokens, tokens_saved, compression_ratio_pct, roi_multiplier, and llm_cost_saved_usd, plus optional cache hit/miss info and billing details.","failureModes":["URL is unreachable or returns non-2xx — fetch fails with error status","HTML payload is malformed or empty — distillation returns minimal or empty data","max_tokens set below minimum of 20 — validation error","mode=budget used without a query — BM25 filtering may be undefined or error","Rate limiting or payment failure via x402 — 402 response requiring payment","Target site blocks scraping — returns empty or partial content","Very large pages may exceed processing limits"],"whenToPreferThis":"Choose this endpoint when you need to compress web content to fit within LLM context windows, especially with precise token budget control or BM25 query-focused filtering. It is ideal for agentic pipelines that must process arbitrary URLs cheaply ($0.001/call) and need ROI proof of compression savings. Prefer it over generic scrapers when you need multiple distillation modes (markdown, structured, skeleton, budget) and built-in token accounting.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:34:42.207Z","isFirstParty":false,"canonicalSlug":"arxiv-digest-agentdiet-dev-web-content-distillation-api-with-bm25-077ffa38"}