{"uid":"cap_TYPMlK0J6XgS0304nd5yH","slug":"arxiv-digest-agentdiet-dev-web-page-html-distillation-with-bm25-8dd4af9f","name":"Web Page & HTML 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/paywall-clean-extract)","url":"https://arxiv-digest.agentdiet.dev/v1/paywall-clean-extract?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_GJJ0mktA0y9atVw4SESIt","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 into clean Markdown, structured JSON, skeleton outline, or a BM25-focused token-budgeted excerpt — returning compression ROI metrics.","exampleAgentPrompt":"Can you distill https://arxiv.org/abs/2406.12345 into clean Markdown, keeping it under 800 tokens and focusing on the methodology section?","exampleUseCases":[{"title":"Token-budgeted research paper extraction","prompt":"Distill this ArXiv paper URL https://arxiv.org/abs/2312.00752 in budget mode, focusing on the results and conclusions, and cap it at 500 tokens so I can feed it to my LLM without blowing my context window."},{"title":"Structured table extraction from docs page","prompt":"Take this Stripe docs page at https://stripe.com/docs/api/charges and distill it in structured mode so I get the tables and metadata as JSON rather than raw HTML."},{"title":"Skeleton outline of a long article","prompt":"Fetch https://techcrunch.com/2024/05/01/some-long-article and give me just the skeleton outline — I want the heading structure without all the body content so I can decide which section to read in full."}],"resultDescription":"Returns a JSON object containing the distilled content (Markdown, structured JSON, skeleton, or BM25 excerpt) in the `data` field, an `roi_proof` object showing raw vs distilled token counts, compression ratio, tokens saved, and estimated LLM cost saved in USD, plus optional cache hit/miss status and billing details.","failureModes":["URL is unreachable or returns non-200 status — endpoint may return an error status","Raw HTML is empty or malformed — distillation may fail or return minimal output","mode=budget without a query parameter may produce suboptimal BM25 ranking","max_tokens set too low may truncate content aggressively","Paywalled or JavaScript-heavy pages may not render correctly","Payment not provided or insufficient — HTTP 402 returned requiring x402 payment"],"whenToPreferThis":"Choose this endpoint when you need to feed web content to an LLM with strict token constraints, want to avoid scraping boilerplate, need ROI-aware compression metrics, or want BM25-ranked relevance filtering against a specific query. It is especially valuable when cost per LLM token matters and you want quantified savings per call.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:36:21.353Z","isFirstParty":false,"canonicalSlug":"arxiv-digest-agentdiet-dev-web-page-html-distillation-with-bm25-8dd4af9f"}