{"uid":"cap_4e5hiBQo7WXuV0nnHKD9i","slug":"token-intel-agentdiet-dev-webpage-distiller-with-bm25-budget-control-d76272ab","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://token-intel.agentdiet.dev/v1/webpage-distiller)","url":"https://token-intel.agentdiet.dev/v1/webpage-distiller?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_X6vkUGhVUCJvj1KOY0_9n","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 compresses a URL or raw HTML into compact, agent-ready tokens using markdown, structured, skeleton, or BM25-focused budget distillation modes","exampleAgentPrompt":"Can you fetch https://stripe.com/docs/api/charges and distill it into markdown, keeping it under 800 tokens and focusing on the query 'charge creation parameters'?","exampleUseCases":[{"title":"Token-budget research before LLM call","prompt":"Grab https://openai.com/pricing and distill it in budget mode with the query 'GPT-4o token cost' and a strict ceiling of 500 tokens — I want to feed only the relevant pricing info to my next prompt without blowing my context window."},{"title":"Structured data extraction from a product page","prompt":"Distill https://www.apple.com/iphone in structured mode so I get the tables and metadata from that page as clean JSON — I'm building a product comparison and need the specs organized."},{"title":"Documentation skeleton for quick navigation","prompt":"Pull up https://docs.anthropic.com/en/api/getting-started and give me a skeleton outline of the page — I just want the section headings and key anchors so I can see the document structure at a glance."}],"resultDescription":"Returns a data object containing the distilled content (markdown text, structured JSON tables/metadata, skeleton outline, or BM25-focused excerpt depending on mode), plus an roi_proof block showing raw vs. distilled token counts, tokens saved, compression ratio percentage, estimated LLM cost saved in USD, and a ROI multiplier. Also includes cache status (HIT/MISS), cache key, latency, and billing details.","failureModes":["URL is unreachable or returns non-2xx HTTP status — endpoint may return an error status","HTML is malformed or too large to process within limits","max_tokens set below 20 — rejected by schema validation","BM25 query provided without mode=budget — query may be ignored","Paywalled or JavaScript-heavy pages may not yield useful content","Payment not provided or insufficient — HTTP 402 returned requiring x402 USDC payment"],"whenToPreferThis":"Choose this endpoint when you need to reduce the token footprint of web content before feeding it to an LLM, especially when working with documentation, product pages, or any lengthy HTML. The BM25 budget mode is uniquely useful when you have a specific query and a hard token ceiling — it retrieves only the most relevant passages. Prefer this over generic scrapers when token cost and compression ratio matter, or when you need structured output (tables, metadata) rather than raw HTML.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:25:58.900Z","isFirstParty":false,"canonicalSlug":"token-intel-agentdiet-dev-webpage-distiller-with-bm25-budget-control-d76272ab"}