{"uid":"cap_Dc3YIVSE9yhR1pM85i5S2","slug":"company-enrich-agentdiet-dev-web-url-distiller-with-bm25-budget-control-85197a49","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/paywall-clean-extract)","url":"https://company-enrich.agentdiet.dev/v1/paywall-clean-extract?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_9ralFZvfAU_vDqlH5926s","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 compresses a webpage URL (or raw HTML) into compact, agent-ready tokens using configurable distillation modes including BM25-focused budget extraction","exampleAgentPrompt":"Can you distill https://stripe.com/docs/payments into clean markdown and keep it under 2000 tokens, focused on the query 'payment intents'?","exampleUseCases":[{"title":"Token-efficient research page ingestion","prompt":"Pull the content from https://openai.com/research/gpt-4 and distill it into clean markdown, but cap it at 1500 tokens and focus on anything about model capabilities."},{"title":"Structured data extraction from a landing page","prompt":"Fetch https://www.notion.so/product and return structured JSON tables or metadata — I want pricing tiers, feature lists, anything organized, not just raw text."},{"title":"Quick skeleton outline of a long article","prompt":"Give me a skeleton outline of https://en.wikipedia.org/wiki/Large_language_model — just the section headers and key structure, no full body text."}],"resultDescription":"Returns a 'data' object containing the distilled content (Markdown, structured JSON, skeleton outline, or BM25-focused excerpt depending on mode), along with an 'roi_proof' block showing raw token count, distilled token count, tokens saved, compression ratio percentage, estimated LLM cost saved in USD, and a ROI multiplier. Also includes cache status (HIT/MISS) and billing metadata.","failureModes":["Invalid or unreachable URL returns an error status","Pages behind hard paywalls or login walls may return incomplete content","Exceeding max_tokens with very small budgets may truncate critical content","mode=budget without a query falls back to default behavior","Raw HTML payloads that are malformed may fail to parse cleanly","Rate limiting or payment failure (402) if agent ID or payment is not configured"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to read web content but must stay within a token budget — especially for long documentation pages, blog posts, or landing pages where full HTML would be prohibitively expensive. Prefer this over raw fetch tools when you want built-in compression, BM25 query-focused ranking, and ROI metrics showing token savings. Ideal for agents that read many pages in a pipeline and need cost-efficient web access.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:25:57.908Z","isFirstParty":false,"canonicalSlug":"company-enrich-agentdiet-dev-web-url-distiller-with-bm25-budget-control-23650cfd"}