{"uid":"cap_rGRDwtftCF4JKFVtSK2-k","slug":"cve-intel-agentdiet-dev-web-url-distiller-with-bm25-budget-control-464618d3","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://cve-intel.agentdiet.dev/v1/web-scrape)","url":"https://cve-intel.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_pK3S0YzYZ9TzIbciEpFAG","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"cve-intel.agentdiet.dev","brandSlug":"cve-intel-agentdiet-dev-mpp","brandBaseUrl":"https://cve-intel.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches a webpage (or accepts raw HTML) and distills it into compact, agent-ready tokens with configurable extraction modes and strict token-budget control","exampleAgentPrompt":"Can you fetch https://stripe.com/docs/payments and distill it into compact markdown, keeping it under 800 tokens and focused on 'payment intents'?","exampleUseCases":[{"title":"Compress docs page for context window","prompt":"Grab the content from https://docs.openai.com/api-reference/chat and compress it into markdown under 600 tokens so I can fit it in my prompt."},{"title":"BM25-focused research excerpt","prompt":"Fetch https://en.wikipedia.org/wiki/Retrieval-augmented_generation and give me only the sections most relevant to 'vector databases', strict budget of 300 tokens."},{"title":"Structured data extraction from a webpage","prompt":"Scrape https://coinmarketcap.com/currencies/bitcoin/ in structured mode so I get the price tables and metadata as clean JSON rather than raw HTML."}],"resultDescription":"Returns a JSON object with a 'data' field containing the distilled content (markdown text, structured JSON tables/metadata, skeleton outline, or BM25-filtered excerpt depending on mode), plus an 'roi_proof' object showing raw_tokens, distilled_tokens, tokens_saved, compression_ratio_pct, and estimated llm_cost_saved_usd, and an optional 'cache' object indicating HIT/MISS status.","failureModes":["Invalid or unreachable URL returns an error status","max_tokens below minimum of 20 is rejected with a validation error","BM25 query with mode other than 'budget' may be ignored","Raw HTML too large may exceed processing limits","Paywalled or JavaScript-heavy pages may return incomplete content","x402 payment failure results in a 402 response before processing begins"],"whenToPreferThis":"Choose this endpoint when you need to fetch a live webpage and compress its content to fit within an LLM context window, especially when you need strict token-budget control via BM25 relevance filtering. It is ideal for agent pipelines that must read documentation, news, or data pages without consuming the full raw token count, and when you need ROI/compression metrics alongside the distilled output. Prefer it over generic scraping APIs when token efficiency and agent-readiness of the output are priorities.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:20:56.146Z","isFirstParty":false,"canonicalSlug":"cve-intel-agentdiet-dev-web-url-distiller-with-bm25-budget-control-464618d3"}