{"uid":"cap_rBabcYSN4SBpUoPsBY5If","slug":"sec-intel-agentdiet-dev-web-url-distillation-bm25-token-budget-cb227dcf","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/api/diet)","url":"https://sec-intel.agentdiet.dev/api/diet?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_sbAilOxf_T4ZyJlbx1YqH","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 webpage (or accepts raw HTML) and compresses it into compact agent-ready tokens using selectable modes including BM25-ranked budget excerpts","exampleAgentPrompt":"Distill the content at https://stripe.com/docs/payments into compact markdown and tell me how many tokens were saved compared to the raw page.","exampleUseCases":[{"title":"Summarize competitor pricing page","prompt":"Fetch and distill https://openai.com/pricing into structured mode so I can see all the pricing tables and metadata without burning my entire context window."},{"title":"BM25 budget excerpt for research","prompt":"Pull the Wikipedia page on transformer neural networks and give me a budget excerpt of at most 300 tokens focused on the query 'attention mechanism self-attention'."},{"title":"Skeleton outline before deep read","prompt":"Give me a skeleton outline of https://docs.anthropic.com/en/docs/overview so I can see the high-level structure of the documentation before deciding which sections to read in full."}],"resultDescription":"Returns a status field, distilled content (Markdown text, structured JSON tables/metadata, skeleton outline, or BM25-ranked excerpt depending on mode), cache hit/miss info with latency, billing details, and an roi_proof object showing raw vs distilled token counts, compression ratio, tokens saved, and estimated LLM cost saved in USD.","failureModes":["URL unreachable or returns non-200 status — endpoint may return an error status","HTML too large or malformed — distillation may be incomplete","max_tokens too low to represent any meaningful content — returns minimal excerpt","BM25 query finds no relevant passages — budget excerpt may be nearly empty","Payment failure via x402 — request blocked before processing","Invalid mode enum value — request rejected with validation error"],"whenToPreferThis":"Choose this endpoint when you need to pass web content to an LLM but want to minimize token usage and cost — especially when working with large documentation pages, competitor sites, or research articles. It is particularly valuable when you need BM25-focused excerpts (mode=budget) to extract only the most query-relevant sentences within a strict token ceiling. Prefer it over raw fetch-and-pass workflows whenever context window size or LLM inference cost is a concern.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T12:51:28.179Z","isFirstParty":false,"canonicalSlug":"sec-intel-agentdiet-dev-web-url-distillation-bm25-token-budget-7df9e187"}