{"uid":"cap_4tawB5cDU_d0HxpEk7vGB","slug":"cve-intel-agentdiet-dev-web-content-distiller-with-bm25-budget-control-6271e718","name":"Web Content 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/paywall-clean-extract)","url":"https://cve-intel.agentdiet.dev/v1/paywall-clean-extract?utm_source=zero.xyz","method":"POST","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_gKTPdGW1XTohLHjobQ6_D","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 and distills a URL or raw HTML into compressed Markdown, structured data, skeleton outline, or BM25-focused token-budgeted excerpt","exampleAgentPrompt":"Can you distill https://stripe.com/docs/payments/accept-a-payment into clean Markdown using budget mode, focused on 'integration steps', and keep it under 500 tokens?","exampleUseCases":[{"title":"LLM context token budget trimming","prompt":"Take this webpage https://docs.openai.com/api-reference and distill it in budget mode with the query 'authentication and rate limits', capping the output at 300 tokens so it fits in my prompt."},{"title":"Structured data extraction from HTML page","prompt":"I have the raw HTML from a product pricing page — can you distill it in structured mode to pull out the tables and pricing metadata as JSON?"},{"title":"Skeleton outline of long documentation","prompt":"Distill https://developer.mozilla.org/en-US/docs/Web/HTTP/Overview into a skeleton outline so I can see the high-level structure without reading the whole page."}],"resultDescription":"Returns distilled content in the chosen format (Markdown, structured JSON, skeleton, or BM25 excerpt), along with ROI proof metrics including raw token count, distilled token count, tokens saved, compression ratio percentage, and estimated LLM cost saved in USD. Also includes cache hit/miss status and billing details.","failureModes":["Invalid or unreachable URL returns fetch error","mode=budget without a query or max_tokens may yield unoptimized output","Very large HTML payloads may hit processing limits","Paywalled pages that block server-side fetching return empty or partial content","Payment not authorized returns HTTP 402"],"whenToPreferThis":"Choose this endpoint when you need to feed live web content into an LLM but want to minimize token usage and cost. It is especially valuable when the target page is noisy, long, or structured (e.g. documentation, pricing tables, CVE advisories), and you need BM25-focused extraction to surface only the most relevant content within a strict token budget. Prefer this over generic scrapers when token cost savings and compression metrics matter to your workflow.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:30:11.450Z","isFirstParty":false,"canonicalSlug":"cve-intel-agentdiet-dev-web-content-distiller-with-bm25-budget-control-176ef31e"}