{"uid":"cap_Qt3Rz63ivz4who_tetsYT","slug":"token-intel-agentdiet-dev-web-url-distillation-to-agent-ready-tokens-2c3e35b9","name":"Web URL Distillation to Agent-Ready Tokens","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/paywall-clean-extract)","url":"https://token-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_aOGXiJAc3lgF_Gah9q1fO","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 a URL or raw HTML and distills it into compact, token-efficient representations using BM25 budget control and multiple extraction modes.","exampleAgentPrompt":"Fetch and distill https://stripe.com/docs/api into compact markdown so I can read it without blowing my token budget — use budget mode with the query 'payment intents' and cap it at 2000 tokens.","exampleUseCases":[{"title":"Research page under strict token limit","prompt":"Pull the content from https://openai.com/research/gpt-4 and distill it down to at most 1500 tokens using budget mode, focusing on the query 'safety evaluations' so I only get the relevant parts."},{"title":"Clean structured data from a product page","prompt":"Grab https://www.apple.com/iphone-15-pro/ and extract it in structured mode so I get the tables and metadata as JSON — I want to compare specs without reading all the marketing copy."},{"title":"Skeleton outline of a long article","prompt":"Distill https://en.wikipedia.org/wiki/Large_language_model into a skeleton outline so I can see the document structure and section headers before deciding which parts to read in full."}],"resultDescription":"Returns a 'data' object containing the distilled content in the requested mode (Markdown, structured JSON, skeleton outline, or BM25-focused excerpt), plus an roi_proof block showing raw token count, distilled token count, tokens saved, compression ratio percentage, and estimated LLM cost saved in USD. Also includes cache status and billing details.","failureModes":["Invalid or unreachable URL returns an error status","Missing required 'url' parameter causes a 400-level error","mode=budget without a query or max_tokens may return unfiltered content","Paywalled or JavaScript-heavy pages may yield incomplete extraction","Token budget too low (below 20) rejected with validation error","Rate limiting or payment failure (x402) blocks the request"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to read a webpage but must stay within a token budget, minimize LLM costs, or receive clean structured content rather than raw HTML. Especially valuable in agentic pipelines where multiple pages must be read sequentially and token efficiency is critical. Prefer over generic scrapers when BM25 query-focused extraction is needed to surface only the most relevant passages.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T12:51:30.948Z","isFirstParty":false,"canonicalSlug":"token-intel-agentdiet-dev-web-url-distillation-to-agent-ready-tokens-2c3e35b9"}