{"uid":"cap_IyN533to4vJhvLvcBwuHl","slug":"cve-intel-agentdiet-dev-web-url-distiller-with-bm25-budget-control-3c25b8bd","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/rag-chunk)","url":"https://cve-intel.agentdiet.dev/v1/rag-chunk?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_dmBEPEuT5xdNJ2JkND5CP","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 using markdown, structured, skeleton, or BM25-budget modes","exampleAgentPrompt":"Distill https://stripe.com/docs/payments into compact markdown and tell me how many tokens you saved compared to the raw page.","exampleUseCases":[{"title":"Budget-capped research on security advisory page","prompt":"Fetch https://nvd.nist.gov/vuln/detail/CVE-2024-1234 and give me a BM25-focused excerpt about 'remote code execution' in no more than 500 tokens."},{"title":"Structured table extraction from competitor pricing page","prompt":"Pull https://openai.com/pricing and distill it into structured JSON tables so I can compare the model tiers and their costs."},{"title":"Skeleton outline of long documentation page","prompt":"Give me a skeleton outline of https://docs.aws.amazon.com/lambda/latest/dg/welcome.html so I can see the document structure without reading the whole thing."}],"resultDescription":"Returns a distilled payload under 'data' containing markdown, structured JSON, skeleton outline, or BM25-focused excerpt depending on mode. Also includes roi_proof with raw token count, distilled token count, tokens saved, compression ratio percentage, and estimated LLM cost saved in USD. Optionally includes cache hit/miss status and billing details.","failureModes":["URL unreachable or returns non-200 status — endpoint may return an error status","HTML too sparse to distill meaningfully — low compression ratio returned","max_tokens set below minimum of 20 — validation error","mode=budget used without a query — BM25 ranking may be undefined","Payment required (HTTP 402) if x402 credentials are missing or insufficient"],"whenToPreferThis":"Use this endpoint when an AI agent needs to ingest web content within a strict token budget, wants structured or markdown-distilled output rather than raw HTML, or needs BM25-ranked excerpts focused on a specific query. Ideal for RAG pipelines, LLM context window management, and cost-sensitive web reading tasks. Prefer over raw fetch when token efficiency and structured output matter.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:21:37.928Z","isFirstParty":false,"canonicalSlug":"cve-intel-agentdiet-dev-web-url-distiller-with-bm25-budget-control-464618d3"}