{"uid":"cap_D3GUZrZpsB0phm0gIRdSI","slug":"github-audit-agentdiet-dev-agentdiet-web-article-extractor-distiller-c56ae26b","name":"AgentDiet Web Article Extractor & Distiller","description":"Distill a URL or raw HTML payload with BM25 budget control (Live x402 v2, IETF MPP & MCP endpoint at https://github-audit.agentdiet.dev/v1/article-extractor)","url":"https://github-audit.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_tRvOE8JtENXCrsuNOlXHZ","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"github-audit.agentdiet.dev","brandSlug":"github-audit-agentdiet-dev-mpp","brandBaseUrl":"https://github-audit.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches a URL or raw HTML and distills it into compact, agent-ready tokens using markdown, structured, skeleton, or BM25-budget modes","exampleAgentPrompt":"Distill the article at https://techcrunch.com/2024/05/01/openai-new-model into compact markdown, keeping it under 800 tokens and focusing the BM25 budget on 'AI safety regulations'.","exampleUseCases":[{"title":"Compress news article for LLM context","prompt":"Fetch and distill https://www.reuters.com/technology/openai-launches-new-model-2024/ into clean markdown under 500 tokens — I need to feed it into my agent without blowing the context window."},{"title":"Extract structured product data from docs","prompt":"Pull the Stripe pricing page at https://stripe.com/pricing and distill it in structured mode so I get the pricing tiers and features as clean JSON tables."},{"title":"Focus-extract relevant section from long page","prompt":"Distill https://en.wikipedia.org/wiki/Large_language_model in budget mode with a max of 300 tokens, focusing the BM25 query on 'transformer architecture training'."}],"resultDescription":"Returns a distilled representation of the target webpage or HTML in the requested mode (markdown, structured JSON, skeleton outline, or BM25 budget excerpt), along with ROI proof metrics including raw token count, distilled token count, tokens saved, compression ratio percentage, estimated LLM cost saved in USD, and optional cache status and billing details.","failureModes":["Invalid or unreachable URL returns an error status","HTML fetch blocked by anti-bot measures or paywalls","mode=budget without query or max_tokens may produce suboptimal output","max_tokens too low (below 20) rejected by schema validation","Payment/402 failure if agent wallet has insufficient USDC balance","Very large pages may exceed processing limits or increase latency"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to ingest web content but must stay within a strict token budget, or when raw HTML is too noisy for direct LLM consumption. It is especially useful when feeding live web pages into LLM context windows, extracting article content without boilerplate, or focusing retrieval on a specific sub-topic via BM25. Prefer it over generic scrapers when token efficiency and compression metrics matter, or when you need structured JSON tables extracted from a webpage rather than raw text.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:25:36.019Z","isFirstParty":false,"canonicalSlug":"github-audit-agentdiet-dev-agentdiet-web-article-extractor-distiller-c56ae26b"}