{"uid":"cap_UQzR_MwBF2XZj0aeyqfEW","slug":"token-intel-agentdiet-dev-agentdiet-web-distillation-with-bm25-budget-cdbb507c","name":"AgentDiet Web Distillation 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://token-intel.agentdiet.dev/api/diet)","url":"https://token-intel.agentdiet.dev/api/diet?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_YQ_4pxhMvD_o1cp9tvuDK","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"token-intel.agentdiet.dev","brandSlug":"token-intel-agentdiet-dev-mpp","brandBaseUrl":"https://token-intel.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches and distills a URL or raw HTML into compressed Markdown, structured data, skeleton outline, or a BM25-ranked token-budget excerpt, returning ROI metrics on tokens saved.","exampleAgentPrompt":"Distill the page at https://stripe.com/docs/payments/accept-a-payment into markdown, keeping it under 800 tokens and focusing on the BM25 query 'accept card payment integration'.","exampleUseCases":[{"title":"Token-budget web research for an LLM pipeline","prompt":"Fetch https://docs.openai.com/api-reference and distill it in budget mode, using 'function calling parameters' as the focus query and capping the output at 500 tokens so I can pass it to my model without blowing the context window."},{"title":"Structured data extraction from a product page","prompt":"Take this raw HTML from an e-commerce product page and distill it into structured JSON tables — I need the pricing tiers, feature list, and metadata organized cleanly."},{"title":"Skeleton outline of long documentation","prompt":"Give me a skeleton outline of https://docs.anthropic.com/claude/reference so I can see the high-level structure of their API docs without reading the whole thing."}],"resultDescription":"Returns a JSON object with a 'data' field containing the distilled content (Markdown string, structured JSON tables, skeleton outline, or BM25-ranked excerpt depending on mode), plus 'roi_proof' showing raw_tokens, distilled_tokens, tokens_saved, compression_ratio_pct, roi_multiplier, and llm_cost_saved_usd, along with cache hit/miss status and billing details.","failureModes":["URL unreachable or returns non-200 — fetch error returned","HTML payload missing when url not provided and html field empty — validation error","max_tokens below minimum of 20 — schema validation rejection","BM25 query empty in budget mode — may return unfiltered or error","Idempotency key reuse with different parameters — may return cached prior result","Payment not fulfilled (x402) — 402 Payment Required response blocking execution"],"whenToPreferThis":"Choose this endpoint when you need to reduce the token footprint of web content before passing it to an LLM, especially when you have a strict context window budget or want to focus only on query-relevant passages via BM25 ranking. It is distinctly valuable over generic scrapers because it returns ROI metrics (tokens saved, cost saved) and supports four distillation modes including token-budget-controlled BM25 excerpting — ideal for autonomous agent pipelines that need to self-regulate context usage and LLM costs.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:36:35.768Z","isFirstParty":false,"canonicalSlug":"token-intel-agentdiet-dev-agentdiet-web-distillation-with-bm25-budget-cdbb507c"}