{"uid":"cap_TShTt8pryfqjwEEFcg1GE","slug":"domain-osint-agentdiet-dev-web-url-distiller-with-bm25-budget-control-6722d2b6","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://domain-osint.agentdiet.dev/v1/web-scrape)","url":"https://domain-osint.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_AYi1DyPQrWyd3khPEu51G","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"domain-osint.agentdiet.dev","brandSlug":"domain-osint-agentdiet-dev-mpp","brandBaseUrl":"https://domain-osint.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches a URL or raw HTML and distills it into compact, agent-ready tokens using markdown, structured, skeleton, or BM25-budgeted extraction modes","exampleAgentPrompt":"Distill the webpage at https://stripe.com/docs/api into compact markdown, keeping it under 1000 tokens and focusing on the authentication section using budget mode.","exampleUseCases":[{"title":"Documentation page for agent context","prompt":"Fetch the OpenAI API docs at https://platform.openai.com/docs/guides/embeddings and distill them into markdown under 800 tokens, focusing on the query 'embedding dimensions and pricing'."},{"title":"Structured data extraction from landing page","prompt":"Scrape https://www.anthropic.com and give me the content in structured mode so I can see the key tables, metadata, and links in JSON format."},{"title":"Skeleton outline of a long article","prompt":"Get the skeleton outline of this blog post at https://martinfowler.com/articles/microservices.html so I can see the heading structure without reading the whole thing."}],"resultDescription":"Returns a 'data' object containing the distilled content (markdown text, structured JSON tables/metadata, skeleton headings, or a BM25-ranked excerpt), plus an 'roi_proof' object showing raw token count, distilled token count, tokens saved, compression ratio percentage, ROI multiplier, and estimated LLM cost saved in USD. Also includes cache status (HIT/MISS) and billing details.","failureModes":["URL is unreachable or returns non-200 status — endpoint may return an error status","max_tokens set below 20 — rejected by schema validation","mode=budget used without a query parameter — BM25 ranking cannot operate","Raw HTML too large to process within budget — truncation or error","Paywalled or JavaScript-heavy pages may return incomplete content","Invalid URL format — schema requires minLength:1 string"],"whenToPreferThis":"Choose this endpoint when you need to fetch and compress web content into a strict token budget before passing it to an LLM, especially when context window cost or size is a concern. It is superior to raw scraping when you need BM25-ranked relevance filtering (mode=budget), structured JSON extraction, or skeleton outlines. Prefer it over generic scraping tools when ROI-proof compression metrics are needed or when working within the agentdiet.dev B2A ecosystem with x402 micropayment support.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:25:54.952Z","isFirstParty":false,"canonicalSlug":"domain-osint-agentdiet-dev-web-url-distiller-with-bm25-budget-control-6722d2b6"}