{"uid":"cap_vORJiocZbrAHPI1xqhnI-","slug":"polymarket-odds-agentdiet-dev-web-url-article-extractor-distiller-f01803ac","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://polymarket-odds.agentdiet.dev/v1/article-extractor)","url":"https://polymarket-odds.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_kyvHl7VVFHmF3cM8byP3x","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"polymarket-odds.agentdiet.dev","brandSlug":"polymarket-odds-agentdiet-dev-mpp","brandBaseUrl":"https://polymarket-odds.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches a webpage by URL (or accepts raw HTML) and distills it into compact, agent-ready tokens using multiple modes including Markdown, structured JSON, skeleton outline, or BM25 budget-controlled excerpts.","exampleAgentPrompt":"Can you fetch https://stripe.com/docs/payments and distill it into clean markdown, keeping it under 800 tokens and focused on the query 'payment intents'?","exampleUseCases":[{"title":"Research article extraction for agents","prompt":"Pull the content from https://techcrunch.com/2024/05/01/openai-gpt5-launch and give me a clean markdown version so I can read it without all the ads and clutter."},{"title":"Token-budget web reading for LLM pipelines","prompt":"Fetch https://docs.anthropic.com/claude/reference/getting-started and distill it in budget mode with a max of 500 tokens, focused on the query 'authentication API keys'."},{"title":"Structured data extraction from webpage","prompt":"Extract the structured tables and metadata from https://en.wikipedia.org/wiki/List_of_S%26P_500_companies using structured mode so I can get the company data in JSON format."}],"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), a 'roi_proof' object showing raw vs distilled token counts, tokens saved, compression ratio percentage, LLM cost saved in USD, and ROI multiplier, plus optional cache hit/miss metadata and billing details.","failureModes":["URL unreachable or returns non-200 status — extraction fails with error status","Paywalled or JavaScript-heavy pages may return incomplete or empty content","Token budget too low (below 20) — rejected by schema validation","Invalid URL format — request rejected","Raw HTML too large may cause timeout or truncation","BM25 query with no matching content may return minimal excerpt"],"whenToPreferThis":"Choose this endpoint when your agent needs to read web pages within a token budget, especially for RAG pipelines, research workflows, or any scenario where full HTML would overwhelm context windows. Prefer it over raw HTTP fetching when you need clean, structured, or token-optimized content. The BM25 budget mode is uniquely useful when you have a specific question and need only the most relevant passage from a long page. The ROI proof output is helpful when you need to track token savings across many calls.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:26:16.460Z","isFirstParty":false,"canonicalSlug":"polymarket-odds-agentdiet-dev-web-url-article-extractor-distiller-f01803ac"}