{"uid":"cap_Jl8d8lhvCkMPqiPyki68m","slug":"llms-generator-agentdiet-dev-web-url-article-extractor-distiller-b23c2171","name":"Web URL Article Extractor & Distiller","description":"Distill a URL or raw HTML payload with BM25 budget control (Live x402 v2, IETF MPP & MCP endpoint at https://llms-generator.agentdiet.dev/v1/article-extractor)","url":"https://llms-generator.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_FFkssU1dMENM7aY58JI8Q","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"llms-generator.agentdiet.dev","brandSlug":"llms-generator-agentdiet-dev-mpp","brandBaseUrl":"https://llms-generator.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches and distills a web URL or raw HTML into compact, agent-ready tokens using multiple extraction modes including BM25 budget-controlled summarization","exampleAgentPrompt":"Can you distill https://stripe.com/docs/payments into compact markdown — using budget mode focused on 'payment intents' with a max of 500 tokens?","exampleUseCases":[{"title":"Budget-capped research on a documentation page","prompt":"Fetch the content from https://docs.openai.com/api-reference and give me only the parts about 'function calling', keeping it under 300 tokens using budget mode."},{"title":"Clean article extraction for LLM context","prompt":"Extract the main article text from https://techcrunch.com/2025/01/15/ai-agents-explainer as clean markdown so I can pass it into my analysis pipeline without all the nav and ads."},{"title":"Structured metadata pull from a webpage","prompt":"Pull https://github.com/openai/openai-python in structured mode and give me a JSON summary of the page's key tables and metadata."}],"resultDescription":"Returns a JSON object with a 'data' field containing the distilled content (markdown text, structured JSON tables/metadata, skeleton outline, or BM25-focused excerpt depending on mode), plus an roi_proof object showing raw_tokens, distilled_tokens, tokens_saved, compression_ratio_pct, and llm_cost_saved_usd. Also includes cache status (HIT/MISS) and billing info.","failureModes":["URL is unreachable or returns non-200 HTTP status — endpoint may return an error status","URL points to non-HTML content (PDF, image) — extraction may fail or return empty data","Token budget too low (max_tokens < 20) — rejected by schema validation","BM25 query provided without mode=budget — query may be ignored","HTML payload too large — may timeout or be truncated","Paywalled or JS-rendered pages may return incomplete content"],"whenToPreferThis":"Choose this endpoint when you need to reduce the token cost of injecting web content into an LLM context window, especially when you want BM25-focused excerpts relevant to a specific query, or when you need structured/skeleton views of a page rather than raw HTML. Ideal for agent pipelines that need to read many URLs cheaply without blowing the context budget. Prefer over generic scrapers when token economy and ROI proof matter.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:26:19.270Z","isFirstParty":false,"canonicalSlug":"llms-generator-agentdiet-dev-web-url-article-extractor-distiller-b23c2171"}