{"uid":"cap_MLr5zDpI96bjYuECCu3hO","slug":"sec-intel-agentdiet-dev-web-url-token-distiller-bm25-budget-control-c2eb82d7","name":"Web URL Token Distiller (BM25 Budget Control)","description":"Distill a URL or raw HTML payload with BM25 budget control (Live x402 v2, IETF MPP & MCP endpoint at https://sec-intel.agentdiet.dev/v1/token-optimizer)","url":"https://sec-intel.agentdiet.dev/v1/token-optimizer?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_yYmuZg6T9Q2QXlyAKsEHI","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"sec-intel.agentdiet.dev","brandSlug":"sec-intel-agentdiet-dev-mpp","brandBaseUrl":"https://sec-intel.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches a URL or raw HTML and distills it into compact, token-efficient agent-ready content using markdown, structured, skeleton, or BM25-budgeted extraction modes.","exampleAgentPrompt":"Can you distill https://stripe.com/docs/payments into compact markdown, keeping it under 2000 tokens and focused on the query 'payment intents'?","exampleUseCases":[{"title":"Compress docs page for agent context","prompt":"Fetch https://docs.openai.com/guides/function-calling and distill it into clean markdown so I can include it in my agent's context without blowing the token limit."},{"title":"Budget-focused content extraction","prompt":"I need the most relevant content from https://en.wikipedia.org/wiki/Retrieval-augmented_generation about 'vector databases', but cap it at 500 tokens using budget mode."},{"title":"Structured data extraction from raw HTML","prompt":"Here's the raw HTML from a product page — can you distill it into structured JSON tables pulling out the key metadata and pricing info?"}],"resultDescription":"Returns a 'data' object containing the distilled content (markdown text, structured JSON tables/metadata, skeleton outline, or BM25-ranked excerpt), plus an 'roi_proof' object showing raw vs. distilled token counts, tokens saved, compression ratio percentage, ROI multiplier, and estimated LLM cost saved in USD. Also includes optional cache hit/miss status and billing details.","failureModes":["URL is unreachable or returns a non-200 status — endpoint may return an error status","HTML payload is too large or malformed — distillation may fail or produce partial output","mode=budget used without a query or max_tokens — BM25 ranking has no focus","Payment not provided or declined — HTTP 402 returned blocking the response","URL is behind authentication/paywall — fetched HTML may be login page instead of target content","max_tokens set too low (below 20) — request rejected by schema validation"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to read web content but must stay within a token budget, reduce LLM inference costs, or receive clean structured output rather than raw HTML. It is especially useful over generic web scrapers when you need BM25-focused extraction (retrieving only the most query-relevant passages), ROI transparency on token savings, or multiple distillation modes (markdown, structured, skeleton, budget) in a single paid-per-call microservice.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:22:03.407Z","isFirstParty":false,"canonicalSlug":"sec-intel-agentdiet-dev-web-url-token-distiller-bm25-budget-control-c2eb82d7"}