{"uid":"cap_fAE911eV8fDrNWHcKjZ5K","slug":"whale-momentum-agentdiet-dev-web-url-article-extractor-token-distiller-0a600103","name":"Web URL Article Extractor & Token Distiller","description":"Distill a URL or raw HTML payload with BM25 budget control (Live x402 v2, IETF MPP & MCP endpoint at https://whale-momentum.agentdiet.dev/v1/article-extractor)","url":"https://whale-momentum.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_bOAtK5jN8B2hLg_RPonLs","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"whale-momentum.agentdiet.dev","brandSlug":"whale-momentum-agentdiet-dev-mpp","brandBaseUrl":"https://whale-momentum.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches a webpage (or accepts raw HTML) and distills it into compact, agent-ready tokens using configurable modes including BM25 budget control","exampleAgentPrompt":"Can you fetch https://techcrunch.com/2024/01/15/openai-news/ and distill it into clean markdown, keeping it under 800 tokens focused on the funding details?","exampleUseCases":[{"title":"Research article extraction for agent","prompt":"Grab the article at https://www.wired.com/story/ai-agents-future and distill it into markdown so I can feed it to my summarization pipeline — keep it tight, under 1000 tokens."},{"title":"BM25 budget extraction for RAG pipeline","prompt":"Fetch https://docs.stripe.com/payments/payment-intents and extract only the parts relevant to 'refund handling' using budget mode with a max of 500 tokens, so I can use it as context in my RAG system."},{"title":"Structured data extraction from webpage","prompt":"Pull https://finance.yahoo.com/quote/AAPL and give me the content in structured mode so I get the tables and metadata as JSON rather than raw text."}],"resultDescription":"Returns a JSON object with a 'data' field containing the distilled content (Markdown, structured JSON tables, skeleton outline, or BM25-focused excerpt), an 'roi_proof' object showing raw token count, distilled token count, tokens saved, compression ratio percentage, and estimated LLM cost saved, plus optional cache hit/miss status and billing details.","failureModes":["URL is unreachable or returns a non-200 status — endpoint may return an error status","Raw HTML payload is malformed or empty — distillation may fail or return minimal content","max_tokens set too low (below 20) — rejected by schema validation","mode=budget used without a query parameter — BM25 filtering may behave unexpectedly","Payment not completed via x402 — request blocked with HTTP 402","URL behind authentication wall — fetcher cannot access gated content"],"whenToPreferThis":"Choose this endpoint when you need to feed webpage content to an LLM but want to minimize token usage and cost — especially useful in RAG pipelines, agent research tasks, or any scenario where you need to stay within a strict token budget. The BM25 budget mode is particularly valuable when you only care about a specific topic within a large page. Prefer this over raw HTTP fetch when you want structured output, boilerplate removal, and ROI metrics on compression savings.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T12:51:27.023Z","isFirstParty":false,"canonicalSlug":"whale-momentum-agentdiet-dev-web-url-article-extractor-token-distiller-0a600103"}