{"uid":"cap_mojiTvsqsBbfdsSDaHsO-","slug":"company-enrich-agentdiet-dev-web-scrape-distill-with-bm25-budget-a0527946","name":"Web Scrape & Distill 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/web-scrape)","url":"https://company-enrich.agentdiet.dev/v1/web-scrape?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_UOfX88yf3eHnyRu0oWq3w","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 and distills a URL or raw HTML into compact Markdown, structured JSON, skeleton outline, or a BM25-focused excerpt within a strict token budget","exampleAgentPrompt":"Fetch https://stripe.com/pricing and distill it into clean markdown using budget mode focused on the query 'pricing tiers', keeping the output under 300 tokens.","exampleUseCases":[{"title":"Compress competitor pricing page for LLM analysis","prompt":"Scrape https://openai.com/pricing and distill it into budget mode focused on 'API pricing plans', keeping the result under 400 tokens so I can feed it to my model cheaply."},{"title":"Extract structured tables from a news article","prompt":"Take this raw HTML I have from a TechCrunch article and distill it in structured mode so I get the tables and metadata as clean JSON — I'll paste the HTML directly."},{"title":"Outline a lengthy documentation page","prompt":"Fetch https://docs.anthropic.com/claude/reference/getting-started-with-the-api and give me a skeleton outline of its sections so I can navigate the content without reading the whole thing."}],"resultDescription":"Returns a JSON object containing the distilled content (Markdown text, structured JSON tables/metadata, a skeleton outline, or a BM25-ranked excerpt), along with ROI proof metrics including raw token count, distilled token count, tokens saved, compression ratio percentage, and estimated LLM cost saved in USD. Also includes cache status (HIT/MISS) and billing details.","failureModes":["Invalid or unreachable URL returns a fetch error","HTML too large may be truncated or exceed processing limits","BM25 mode without a query defaults to unfiltered distillation","max_tokens set below minimum of 20 is rejected","Rate limiting or payment failure returns HTTP 402"],"whenToPreferThis":"Choose this endpoint when you need to reduce the token cost of feeding web content to an LLM — especially when working with large pages, strict context windows, or when only a topically relevant excerpt is needed. Its BM25 budget mode is uniquely suited for query-focused extraction with a hard token ceiling, making it more cost-effective than generic scrapers that return full raw HTML.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:33:15.910Z","isFirstParty":false,"canonicalSlug":"company-enrich-agentdiet-dev-web-scrape-distill-with-bm25-budget-a0527946"}