{"uid":"cap_U-dkE_hN6D4tOAyPFoIdA","slug":"cve-intel-agentdiet-dev-dom-stripper-web-url-distillation-to-agent-7fc94c8b","name":"DOM Stripper – 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://cve-intel.agentdiet.dev/v1/dom-stripper)","url":"https://cve-intel.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_-LKugtsjT5Xgpe23hXv7R","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"cve-intel.agentdiet.dev","brandSlug":"cve-intel-agentdiet-dev-mpp","brandBaseUrl":"https://cve-intel.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches a URL or raw HTML and distills it into compact, agent-ready text using BM25 budget control and multiple extraction modes (markdown, structured, skeleton, budget).","exampleAgentPrompt":"Can you fetch https://stripe.com/docs/api and distill it into compact markdown, staying under 2000 tokens, focused on the query 'payment intents'?","exampleUseCases":[{"title":"Compress documentation page for LLM context","prompt":"Pull the OpenAI API reference at https://platform.openai.com/docs/api-reference and distill it into structured markdown under 1500 tokens so I can include it in my agent's context window without blowing up costs."},{"title":"Budget-capped research extraction","prompt":"I need to extract the most relevant content from https://arxiv.org/abs/2310.01848 about 'transformer attention mechanisms' — keep it under 500 tokens using budget mode so my agent can process it efficiently."},{"title":"Skeleton outline for navigation planning","prompt":"Give me a skeleton outline of https://docs.github.com/en/rest so my agent can understand the page structure without reading the whole thing."}],"resultDescription":"Returns a 'data' object containing the distilled content in the requested format (Markdown text, structured JSON tables/metadata, a skeleton outline, or a BM25-ranked budget excerpt), along with ROI proof metrics including raw token count, distilled token count, tokens saved, compression ratio percentage, LLM cost saved in USD, and an ROI multiplier. Also includes optional cache hit/miss status and billing details.","failureModes":["URL is unreachable or returns a non-200 HTTP status — endpoint may return an error status","HTML payload is malformed or too large — distillation may fail or truncate","max_tokens set below minimum of 20 — rejected with validation error","query field omitted when mode=budget — BM25 ranking cannot be applied","Payment not provided (HTTP 402) — call blocked until x402 micropayment is made","Rate limiting if too many requests in a short window"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to ingest web page content but must stay within a token budget — especially useful when feeding documentation, news articles, or research pages into an LLM context window. Prefer it over raw web scraping tools when token cost efficiency matters, when you need BM25-ranked relevance filtering, or when you want structured/skeleton output rather than raw HTML. It is particularly well-suited for agentic pipelines where per-call LLM costs must be minimized.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:20:59.002Z","isFirstParty":false,"canonicalSlug":"cve-intel-agentdiet-dev-dom-stripper-web-url-distillation-to-agent-7fc94c8b"}