{"uid":"cap_9FkC1ZL_pr-JhAjUGDeel","slug":"cve-intel-agentdiet-dev-web-url-html-distiller-bm25-budget-mode-e1a12142","name":"Web URL & HTML Distiller (BM25 Budget Mode)","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/api/diet)","url":"https://cve-intel.agentdiet.dev/api/diet?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_7vM6vqYPm5mvJ67qXcSKV","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 URL or raw HTML and compresses it into compact, agent-ready tokens with configurable distillation modes and BM25 budget control","exampleAgentPrompt":"Distill https://stripe.com/docs/payments into compact markdown, and keep it under 800 tokens using budget mode focused on the query 'payment intents'.","exampleUseCases":[{"title":"Compress documentation page for agent","prompt":"Grab the content from https://docs.openai.com/api-reference and distill it into structured markdown so I can include it in my agent's context without using too many tokens."},{"title":"BM25-focused budget extraction for research","prompt":"Pull https://en.wikipedia.org/wiki/Zero-day_vulnerability and extract only the most relevant sections about exploitation timelines — keep it under 500 tokens using budget mode with that as the focus query."},{"title":"Skeleton outline of a long article","prompt":"Get me a skeleton outline of https://www.wired.com/story/ai-agents-future so I can quickly understand the structure and main headings without reading the whole thing."}],"resultDescription":"Returns a 'data' object containing the distilled content (markdown, structured JSON, skeleton, or BM25-focused excerpt), along with an roi_proof block showing raw_tokens, distilled_tokens, tokens_saved, compression_ratio_pct, and llm_cost_saved_usd. Also includes cache status (HIT/MISS) and billing details.","failureModes":["Invalid or unreachable URL returns an error status","Token budget too small (max_tokens < 20) causes validation error","mode=budget without a query may return less focused results","Raw HTML too large may exceed processing limits","Paywalled or JavaScript-heavy pages may yield incomplete extraction","x402 payment failure blocks request if payment header is missing or insufficient"],"whenToPreferThis":"Choose this endpoint when you need to feed web content into an LLM context efficiently — especially when the raw page is too large. It is uniquely suited for token-budget-constrained workflows where BM25 relevance scoring can focus extraction on a specific query topic. Prefer it over generic scrapers when you need roi_proof metrics (compression ratio, LLM cost saved) alongside the content.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:23:35.411Z","isFirstParty":false,"canonicalSlug":"cve-intel-agentdiet-dev-web-url-html-distiller-bm25-budget-mode-e1a12142"}