{"uid":"cap_sSac2MMlJW3WP7jQBFaAK","slug":"workflows-agentdiet-dev-web-url-distiller-article-extractor-agentdiet-aab22b12","name":"Web URL Distiller & Article Extractor (AgentDiet)","description":"Distill a URL or raw HTML payload with BM25 budget control (Live x402 v2, IETF MPP & MCP endpoint at https://workflows.agentdiet.dev/v1/article-extractor)","url":"https://workflows.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_b_MZOHUlDNf5PU2-1aRss","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"workflows.agentdiet.dev","brandSlug":"workflows-agentdiet-dev-mpp","brandBaseUrl":"https://workflows.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches a URL or raw HTML and compresses it into compact, agent-ready tokens using markdown, structured, skeleton, or BM25 budget modes","exampleAgentPrompt":"Distill this article URL into clean markdown and keep it under 800 tokens, focusing on anything about AI agent costs: https://example.com/ai-agents-cost-analysis","exampleUseCases":[{"title":"Token-budget research extraction","prompt":"Fetch https://openai.com/pricing and distill it into a budget excerpt of at most 300 tokens, focusing on the query 'GPT-4 API cost per token' — I want to minimize what I send downstream to my LLM."},{"title":"Structured data pull from competitor page","prompt":"Pull the product page at https://competitor.com/plans and extract it in structured mode so I get tables, pricing tiers, and metadata as clean JSON rather than raw HTML."},{"title":"Quick skeleton outline of a long doc","prompt":"Get me a skeleton outline of https://docs.stripe.com/payments/accept-a-payment — just the headings and section structure in markdown, not the full content."}],"resultDescription":"Returns a JSON object with a 'data' field containing distilled content (markdown text, structured JSON tables/metadata, skeleton outline, or BM25 budget excerpt depending on mode), plus an 'roi_proof' object showing raw_tokens, distilled_tokens, tokens_saved, compression_ratio_pct, and llm_cost_saved_usd, and optional cache hit/miss info and billing details.","failureModes":["Invalid or unreachable URL returns an error status","Paywalled or bot-blocked pages may return empty or partial content","mode=budget without a query or max_tokens may return unfiltered output","Extremely large HTML payloads may exceed processing limits","x402 payment failure if agent lacks sufficient USDC balance","Malformed HTML input may produce garbled distillation"],"whenToPreferThis":"Choose this endpoint when you need to feed web page content to an LLM but want to minimize token usage and cost — especially with the budget mode and BM25 query focus for targeted extraction. Prefer it over generic scrapers when ROI proof (compression ratio, cost saved) matters to your pipeline, or when you need multiple output formats (markdown, structured, skeleton) from the same fetch. Best suited for AI agent workflows that must stay within strict context windows.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:26:05.728Z","isFirstParty":false,"canonicalSlug":"workflows-agentdiet-dev-web-url-distiller-article-extractor-agentdiet-aab22b12"}