{"uid":"cap_1CHH74ng-cT65N5O0evta","slug":"email-verify-agentdiet-dev-web-url-dom-stripper-agent-ready-token-c26add11","name":"Web URL DOM Stripper & Agent-Ready Token Distiller","description":"Distill a URL or raw HTML payload with BM25 budget control (Live x402 v2, IETF MPP & MCP endpoint at https://email-verify.agentdiet.dev/v1/dom-stripper)","url":"https://email-verify.agentdiet.dev/v1/dom-stripper?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_Sg3GtbEk960nZ7bDHIVyJ","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"email-verify.agentdiet.dev","brandSlug":"email-verify-agentdiet-dev-mpp","brandBaseUrl":"https://email-verify.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches a URL (or accepts raw HTML) and distills it into compact, agent-ready tokens using BM25 budget control and multiple extraction modes","exampleAgentPrompt":"Can you fetch https://stripe.com/docs/api and distill it into compact markdown within a 2000-token budget, focusing on payment intents?","exampleUseCases":[{"title":"Distill docs page for agent context","prompt":"Grab https://docs.openai.com/api-reference and distill it into clean markdown so I can feed it to my agent without blowing up the context window — keep it under 3000 tokens."},{"title":"BM25-focused pricing page extraction","prompt":"Fetch https://vercel.com/pricing and extract only the parts relevant to 'pro plan limits and overages' using budget mode with a max of 1500 tokens."},{"title":"Skeleton outline of a long article","prompt":"Pull https://en.wikipedia.org/wiki/Large_language_model and give me just the skeleton outline of the page structure — I want headings and key sections, not full content."}],"resultDescription":"Returns a data object containing the distilled content in the requested format (markdown, structured JSON tables/metadata, skeleton outline, or BM25-ranked excerpt), alongside an roi_proof block showing raw vs distilled token counts, compression ratio, tokens saved, and estimated LLM cost saved in USD. Optional billing and cache metadata are also included.","failureModes":["Invalid or unreachable URL returns an error status","max_tokens below minimum (20) causes validation error","mode=budget without a query parameter may return unfiltered content","Raw HTML too large may time out or be truncated","Paywalled or bot-protected pages may return incomplete content","x402 payment failure prevents execution"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to ingest web content efficiently without consuming excessive LLM context tokens. It is ideal when fetching documentation, articles, or any structured webpage where token cost matters. It outperforms generic web scrapers because it returns multiple distillation modes (markdown, structured, skeleton, budget) and provides ROI proof showing exactly how many tokens and dollars were saved. Prefer the budget+BM25 mode when you only need content relevant to a specific query.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:23:06.328Z","isFirstParty":false,"canonicalSlug":"email-verify-agentdiet-dev-web-url-dom-stripper-agent-ready-token-c26add11"}