{"uid":"cap_-itnqS9xipJ6eCciLc1YW","slug":"defi-yield-agentdiet-dev-web-url-html-distiller-bm25-budget-controlled-778bd15e","name":"Web URL & HTML Distiller (BM25 Budget-Controlled)","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/article-extractor)","url":"https://defi-yield.agentdiet.dev/v1/article-extractor?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_nFhuvzQuo5Hxh22G7aL53","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 a web page or raw HTML and distills it into compact, agent-ready tokens with configurable modes including markdown, structured, skeleton, or BM25 budget-capped excerpts.","exampleAgentPrompt":"Can you fetch https://techcrunch.com/2024/05/01/openai-funding/ and distill it into clean markdown, keeping it under 800 tokens and focusing on the funding details?","exampleUseCases":[{"title":"Budget-capped research on breaking news","prompt":"Grab the article at https://www.reuters.com/technology/2024/05/openai-deal/ and distill it in budget mode focused on 'AI investment valuation', capping at 500 tokens so I don't blow my LLM budget."},{"title":"Structured data extraction from a product page","prompt":"Distill https://stripe.com/pricing into structured mode so I get the pricing tiers and features as clean JSON tables rather than a wall of HTML."},{"title":"Quick skeleton outline of a long technical doc","prompt":"I need a skeleton outline of https://docs.anthropic.com/en/docs/build-with-claude/prompt-engineering — just the headings and key sections, not the full content."}],"resultDescription":"Returns a data object containing the distilled content (markdown text, structured JSON tables/metadata, skeleton outline, or BM25-focused excerpt depending on mode), alongside an roi_proof block showing raw vs distilled token counts, compression ratio, tokens saved, and estimated LLM cost saved in USD. Also includes cache hit/miss status and billing details.","failureModes":["Invalid or unreachable URL returns an error status","Paywalled or bot-blocked pages may return empty or partial content","Very large pages may exceed processing limits even with token budget","Missing required 'url' parameter returns a validation error","BM25 budget mode without a 'query' field may produce generic results","Rate limiting or payment failure (x402) blocks the request"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to read a web page but must minimize token consumption — especially when the raw HTML would be too large to pass directly to an LLM. It is ideal over generic scrapers when you need BM25-focused excerpts relevant to a specific query, structured extraction of tables/metadata, or a skeleton outline of a long document. It is also preferable when you need a cost-savings proof (compression ratio, tokens saved, USD saved) for auditing agent efficiency.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:21:41.718Z","isFirstParty":false,"canonicalSlug":"defi-yield-agentdiet-dev-web-url-html-distiller-bm25-budget-controlled-778bd15e"}