{"uid":"cap_WJOpG60wNgltvz_bsMlde","slug":"company-enrich-agentdiet-dev-web-url-distiller-with-bm25-budget-control-23650cfd","name":"Web URL 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/web-scrape)","url":"https://company-enrich.agentdiet.dev/v1/web-scrape?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_P3S-pFgd6QCG7JoTkxZC_","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 webpage URL (or raw HTML) into compact, agent-ready tokens using multiple extraction modes including BM25-ranked budget excerpts","exampleAgentPrompt":"Can you distill https://stripe.com/docs/payments into compact markdown under 500 tokens, using budget mode focused on 'payment intents'?","exampleUseCases":[{"title":"Token-efficient research on competitor pricing","prompt":"Distill https://www.competitor.com/pricing into structured mode so I can see their pricing tiers without blowing up my context window."},{"title":"BM25-focused excerpt for a specific topic","prompt":"Fetch https://docs.openai.com/api-reference and give me only the parts relevant to 'function calling', staying under 300 tokens using budget mode."},{"title":"Clean markdown from raw HTML paste","prompt":"I have some raw HTML from an internal page — can you distill it into clean markdown so I can pass it to my summarizer?"}],"resultDescription":"Returns a JSON object containing distilled content (markdown text, structured JSON tables/metadata, skeleton outline, or BM25-ranked excerpt depending on mode), plus an roi_proof block showing raw vs distilled token counts, compression ratio, tokens saved, and estimated LLM cost savings. Also includes cache hit/miss status and billing details.","failureModes":["URL is unreachable or returns non-200 — distillation fails with error status","max_tokens set too low (below 20) — rejected with validation error","mode=budget used without a query parameter — BM25 ranking has no focus term","Raw HTML passed as html param is malformed or empty — may yield empty output","Rate limiting or payment failure via x402 — request blocked with 402 response","Target site blocks scraping (Cloudflare, bot detection) — fetch fails silently or returns error"],"whenToPreferThis":"Choose this endpoint when you need to feed webpage content to an LLM but must stay within a token budget — especially when the page is large and only a focused excerpt is needed. The BM25 budget mode is uniquely suited for query-focused extraction. Prefer this over generic scrapers when compression ratio and LLM cost savings are important metrics, or when you need structured JSON tables rather than raw text from a page.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:23:08.521Z","isFirstParty":false,"canonicalSlug":"company-enrich-agentdiet-dev-web-url-distiller-with-bm25-budget-control-23650cfd"}