{"uid":"cap_yssox3S8Hf93YBMRwVlQT","slug":"cve-intel-agentdiet-dev-webpage-distiller-with-bm25-budget-control-9ff004e8","name":"Webpage 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/webpage-distiller)","url":"https://cve-intel.agentdiet.dev/v1/webpage-distiller?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_vX562uMJO_FTMx3aMTvWZ","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 compact, token-efficient agent-ready content using multiple modes including BM25-ranked budget excerpts","exampleAgentPrompt":"Distill the content at https://docs.stripe.com/api into clean markdown, but cap it at 2000 tokens and focus the BM25 query on 'payment intents' so I only get the most relevant sections.","exampleUseCases":[{"title":"Token-efficient documentation reading","prompt":"Fetch and distill https://platform.openai.com/docs/api-reference into markdown, keeping it under 1500 tokens and using 'embeddings endpoint' as the focus query so I get only what's relevant."},{"title":"Structured data extraction from a webpage","prompt":"Pull the page at https://en.wikipedia.org/wiki/List_of_countries_by_GDP and distill it in structured mode so I get the tables and metadata as clean JSON."},{"title":"Skeleton outline of a long article","prompt":"I have this raw HTML from a TechCrunch article — can you distill it in skeleton mode so I get a quick outline of the headings and key sections without reading the whole thing?"}],"resultDescription":"Returns a 'data' object containing the distilled content in the requested mode (Markdown, structured JSON tables/metadata, skeleton outline, or BM25-ranked budget excerpt), plus an roi_proof object showing raw vs distilled token counts, tokens saved, compression ratio percentage, LLM cost saved in USD, and ROI multiplier. Also includes cache status (HIT/MISS) and billing details.","failureModes":["URL is unreachable or returns non-200 status — endpoint may return an error status","HTML payload is malformed or empty — distillation may fail or return minimal content","max_tokens set too low (below 20) — rejected by schema validation","BM25 query provided but mode is not 'budget' — query may be ignored","Rate limiting or payment failure via x402 — request blocked","Idempotency-Key collision on retries — may return cached prior result"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to read web content efficiently without exhausting LLM context windows or incurring high token costs. It is especially valuable when you have a specific query focus and want BM25-ranked excerpts under a strict token budget, or when you need structured JSON tables/metadata extracted from HTML rather than raw prose. Prefer it over generic scraping tools when token economy and ROI tracking matter, or when you already have raw HTML and want it cleaned into agent-ready format.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:32:58.946Z","isFirstParty":false,"canonicalSlug":"cve-intel-agentdiet-dev-webpage-distiller-with-bm25-budget-control-9ff004e8"}