{"uid":"cap_bzOS7rI0I2Q-Cdta3fvHS","slug":"sec-intel-agentdiet-dev-web-url-distillation-bm25-token-budget-7df9e187","name":"Web URL Distillation & BM25 Token-Budget Extraction","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/paywall-clean-extract)","url":"https://sec-intel.agentdiet.dev/v1/paywall-clean-extract?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_84K4nyD5Cj0IaAXkqTyIw","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 and compresses a webpage (or raw HTML) into compact agent-ready tokens using markdown, structured, skeleton, or BM25 budget modes with ROI proof","exampleAgentPrompt":"Distill the content at https://stripe.com/docs/payments into compact markdown with a 1000-token budget, focusing on 'payment intent flow', and show me how many tokens you saved.","exampleUseCases":[{"title":"LLM-cost-efficient doc reading","prompt":"Fetch and compress https://docs.openai.com/api-reference into clean markdown capped at 800 tokens, using BM25 to focus on 'function calling' — I want to minimize tokens sent to my LLM."},{"title":"Structured data extraction from landing page","prompt":"Pull the pricing tiers and feature table from https://linear.app/pricing and return it as structured JSON so I can compare plans without reading the whole page."},{"title":"Quick skeleton outline of long article","prompt":"Give me just the skeleton outline of https://www.paulgraham.com/greatwork.html — I want the headings and section structure without the full text."}],"resultDescription":"Returns a 'data' object containing distilled content in the requested mode (markdown text, structured JSON tables/metadata, skeleton outline, or BM25-focused excerpt), plus an 'roi_proof' object showing raw vs distilled token counts, tokens saved, compression ratio percentage, estimated LLM cost saved in USD, and ROI multiplier. Also includes cache hit/miss status and billing details.","failureModes":["Invalid or unreachable URL returns an error status","max_tokens below minimum of 20 is rejected","mode=budget without a query may return unfiltered content","Paywalled or JavaScript-heavy pages may yield incomplete extraction","HTML too large may be truncated or fail","Cache MISS on first fetch may increase latency"],"whenToPreferThis":"Choose this endpoint when an agent needs to ingest web content but must stay within a token budget or minimize LLM inference costs. It is especially valuable when the target URL is long-form documentation, a data-rich landing page, or a news article, and only a focused or compressed version is needed. Prefer it over raw fetch/scrape tools when token efficiency and ROI tracking matter, or when you need structured tables or a skeleton outline rather than raw HTML.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:22:44.525Z","isFirstParty":false,"canonicalSlug":"sec-intel-agentdiet-dev-web-url-distillation-bm25-token-budget-7df9e187"}