{"uid":"cap_jByx20tYA0Sw2yuVlTxOb","slug":"company-enrich-agentdiet-dev-web-article-html-distiller-with-bm25-adb8ee88","name":"Web Article & HTML Distiller with BM25 Budget Control","description":"Distill a URL or raw HTML payload with BM25 budget control (Live x402 v2, IETF MPP & MCP endpoint at https://company-enrich.agentdiet.dev/v1/article-extractor)","url":"https://company-enrich.agentdiet.dev/v1/article-extractor?utm_source=zero.xyz","method":"POST","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_LOEpCaqnVu8p21AQPHaLA","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"company-enrich.agentdiet.dev","brandSlug":"company-enrich-agentdiet-dev-mpp","brandBaseUrl":"https://company-enrich.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches a URL or accepts raw HTML and distills it into clean Markdown, structured JSON, a skeleton outline, or a BM25-ranked token-budget excerpt focused on a query.","exampleAgentPrompt":"Can you distill this URL https://stripe.com/docs/payments into clean Markdown, and if it's too long keep it under 2000 tokens focused on the topic 'payment intents' using budget mode?","exampleUseCases":[{"title":"LLM context compression for long articles","prompt":"Fetch this Reuters article at https://www.reuters.com/technology/ai-regulation-2024 and distill it down to under 1500 tokens focused on 'EU AI regulation' so I can pass just the relevant parts to my model."},{"title":"Structured table extraction from docs","prompt":"Pull the pricing page at https://openai.com/pricing and distill it in structured mode so I get the data as JSON tables I can actually work with."},{"title":"Skeleton outline of technical documentation","prompt":"Take https://docs.aws.amazon.com/lambda/latest/dg/welcome.html and give me a skeleton outline of the page structure so I can quickly see what sections exist before deciding what to read."}],"resultDescription":"Returns a 'data' object containing the distilled content (Markdown text, structured JSON tables/metadata, skeleton outline, or BM25-ranked excerpt), plus an 'roi_proof' block showing raw vs distilled token counts, tokens saved, compression ratio percentage, estimated LLM cost saved in USD, and a cache status indicator showing HIT/MISS with latency.","failureModes":["URL unreachable or returns non-200 — fetch fails with error status","HTML too large to process within service limits — may truncate or error","mode=budget without providing query — BM25 ranking has no focus signal","max_tokens set below meaningful content threshold (minimum 20) — very short outputs","Invalid or malformed URL string — schema validation error","Rate limit or payment failure via x402 — 402 response requiring USDC payment","Paywalled or JavaScript-rendered pages may return incomplete HTML"],"whenToPreferThis":"Choose this endpoint when you need to reduce a large HTML page or URL into a compact, LLM-ready representation under a strict token budget — especially when you want BM25 relevance ranking to focus extraction on a specific query topic. It is superior to generic scrapers when token cost matters, as it provides measurable compression ROI metrics. Prefer it over browser automation tools for read-only content extraction where raw HTML is accessible.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:30:16.510Z","isFirstParty":false,"canonicalSlug":"company-enrich-agentdiet-dev-web-article-html-distiller-with-bm25-adb8ee88"}