{"uid":"cap_uHPwKCYNXhLwM6bwup5o0","slug":"defi-yield-agentdiet-dev-webpage-distiller-with-bm25-budget-control-d797d031","name":"Webpage Distiller 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://defi-yield.agentdiet.dev/v1/webpage-distiller)","url":"https://defi-yield.agentdiet.dev/v1/webpage-distiller?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_i2nkvK4VOPFbWaZ-Iy73r","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"defi-yield.agentdiet.dev","brandSlug":"defi-yield-agentdiet-dev-mpp","brandBaseUrl":"https://defi-yield.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","exampleAgentPrompt":"Fetch and distill https://docs.stripe.com/payments/payment-intents into clean markdown using budget mode, focusing on 'payment intent lifecycle' and keeping it under 2000 tokens.","exampleUseCases":[{"title":"Token-budgeted doc extraction for agent pipeline","prompt":"Distill https://docs.openai.com/api-reference into markdown, focus the BM25 query on 'function calling', and cap the output at 1500 tokens so it fits in my prompt context."},{"title":"Structured table extraction from pricing page","prompt":"Pull the pricing page at https://vercel.com/pricing and distill it into structured JSON tables so I can compare plan tiers and limits programmatically."},{"title":"Skeleton outline of a long article","prompt":"Grab https://en.wikipedia.org/wiki/Ethereum and give me just the skeleton outline — headings and subheadings — so I can navigate what sections exist before reading further."}],"resultDescription":"Returns a data object containing the distilled webpage content in the requested format (Markdown, structured JSON, skeleton, or BM25 excerpt), along with an roi_proof object showing raw vs distilled token counts, tokens saved, compression ratio percentage, LLM cost saved in USD, and ROI multiplier. Also includes cache status (HIT/MISS) and billing details.","failureModes":["Invalid or unreachable URL returns fetch error","HTML too large may exceed processing limits","BM25 budget mode without a query defaults or errors","Token budget below minimum (20) rejected with validation error","Rate limiting or payment failure blocks execution","Paywalled or bot-protected pages may return incomplete content"],"whenToPreferThis":"Choose this endpoint when you need to reduce LLM token costs by compressing webpage content before passing it to a model, especially when working with documentation sites, long articles, or product pages. Particularly valuable in budget mode when you have a strict token ceiling and want BM25-focused relevance filtering. Prefer over generic scrapers when you need built-in token savings metrics and multiple output modes (markdown, structured, skeleton).","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:32:49.792Z","isFirstParty":false,"canonicalSlug":"defi-yield-agentdiet-dev-webpage-distiller-with-bm25-budget-control-d797d031"}