{"uid":"cap_ux53yVeQLlOFjphUCwlR5","slug":"arxiv-digest-agentdiet-dev-web-distillation-with-bm25-budget-control-f85c1296","name":"Web 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/context-compress)","url":"https://arxiv-digest.agentdiet.dev/v1/context-compress?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__Kgnx_Dyc3xvrPJVYTn3z","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 compresses a URL or raw HTML into distilled Markdown, structured JSON, skeleton outline, or a BM25-ranked token-budget excerpt","exampleAgentPrompt":"Can you distill https://arxiv.org/abs/2406.12345 into clean Markdown using budget mode, focused on the query 'transformer attention efficiency', and keep it under 800 tokens?","exampleUseCases":[{"title":"Compress research paper for LLM context","prompt":"Grab this arxiv paper at https://arxiv.org/abs/2405.00001 and distill it into Markdown mode — I want just the key content without all the boilerplate, and keep it under 1500 tokens focused on 'retrieval augmented generation'."},{"title":"Extract structured data from a product page","prompt":"Distill https://stripe.com/pricing into structured mode so I can get all the pricing tiers and metadata in a clean JSON format — I don't want to process the full HTML."},{"title":"Summarize raw HTML from an internal dashboard","prompt":"I've got this raw HTML from our internal dashboard — can you compress it into a skeleton outline so I can see just the section headers and main data tables without all the noise?"}],"resultDescription":"Returns a 'data' object containing the distilled content (Markdown text, structured JSON tables/metadata, skeleton outline, or BM25-ranked excerpt), plus an 'roi_proof' object showing raw token count, distilled token count, tokens saved, compression ratio percentage, and estimated LLM cost saved in USD. Optionally includes cache status (HIT/MISS) and billing details.","failureModes":["URL is unreachable or returns non-200 status — endpoint may return an error status","HTML string is empty or malformed — distillation produces minimal output","mode=budget used without providing a query — BM25 ranking has no focus signal","max_tokens set below minimum of 20 — request rejected with validation error","Payment not completed via x402 — 402 Payment Required response before processing","Idempotency-Key collision with a prior failed request — may return cached error"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to fit web content into a strict LLM context window and wants quantified token savings (ROI proof). Prefer it over generic scrapers when BM25 query-focused compression is needed, or when multiple distillation modes (Markdown, structured, skeleton, budget) are required in a pay-per-call model. Especially useful when processing arxiv papers, documentation pages, or large HTML blobs that must be compressed before passing to downstream LLM steps.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:32:57.576Z","isFirstParty":false,"canonicalSlug":"arxiv-digest-agentdiet-dev-web-distillation-with-bm25-budget-control-7b7ea837"}