{"uid":"cap__8xiaYAjTwdWriSzljOkX","slug":"onchain-risk-agentdiet-dev-web-url-distillation-bm25-budget-extractor-b508375f","name":"Web URL Distillation & BM25 Budget Extractor","description":"Distill a URL or raw HTML payload with BM25 budget control (Live x402 v2, IETF MPP & MCP endpoint at https://onchain-risk.agentdiet.dev/v1/paywall-clean-extract)","url":"https://onchain-risk.agentdiet.dev/v1/paywall-clean-extract?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_eix16mYqePsg4B4kX-3pH","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"onchain-risk.agentdiet.dev","brandSlug":"onchain-risk-agentdiet-dev-mpp","brandBaseUrl":"https://onchain-risk.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches a webpage URL (or accepts raw HTML) and distills it into compact, agent-ready tokens using markdown, structured, skeleton, or BM25 budget modes with token-ceiling control","exampleAgentPrompt":"Can you distill https://stripe.com/docs/payments into compact markdown, keeping it under 2000 tokens so I can fit it into my context window?","exampleUseCases":[{"title":"Research article extraction for agent","prompt":"Fetch and distill https://en.wikipedia.org/wiki/Transformer_(machine_learning_model) into clean markdown so I can use it in my prompt — keep it under 1500 tokens."},{"title":"Paywall content budget extraction","prompt":"I need you to pull https://techcrunch.com/2024/01/15/some-article and extract only the parts relevant to 'AI startup funding' using budget mode with a max of 800 tokens."},{"title":"Structured data from product page","prompt":"Distill https://aws.amazon.com/ec2/pricing/ in structured mode so I get the pricing tables and metadata in a clean JSON format I can compare."}],"resultDescription":"Returns a JSON object containing the distilled content (markdown text, structured JSON tables/metadata, skeleton outline, or BM25-ranked excerpt depending on mode), plus an ROI proof object showing raw vs distilled token counts, compression ratio percentage, tokens saved, and estimated LLM cost saved in USD. Also includes cache status (HIT/MISS) and optional billing details.","failureModes":["Invalid or unreachable URL returns an error status","Paywalled pages may return incomplete or no content","Very large pages may exceed processing limits","BM25 budget mode with no query returns generic excerpt","rate limiting or payment failure via x402 protocol","HTML-only mode fails if neither url nor html is provided"],"whenToPreferThis":"Choose this endpoint when you need to fetch and compress web pages into LLM-friendly tokens with strict budget control, especially when context window size is a concern. It is ideal when you want ROI metrics on token savings, need BM25-focused extraction around a specific query, or want structured/skeleton output rather than raw HTML. Prefer it over generic scrapers when token efficiency and agent-readiness are priorities.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:20:26.732Z","isFirstParty":false,"canonicalSlug":"onchain-risk-agentdiet-dev-web-url-distillation-bm25-budget-extractor-22601b41"}