{"uid":"cap_wHKqQHkmrDNtekXrRbeAy","slug":"agentdiet-dom-stripper-44270c83","name":"AgentDiet DOM Stripper","description":"Distill a URL or raw HTML payload with BM25 budget control (Live x402 v2, IETF MPP & MCP endpoint at https://agentdiet.dev/v1/dom-stripper)","url":"https://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":["x402"],"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":"unknown","protocol":"x402","network":"base","amountUsd":null,"per":"call","confidence":"unknown"},{"kind":"static","protocol":"mpp","network":"tempo","amountUsd":"0.001","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_sIxTg8b-B6bOvxkE0LG91","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null},{"uid":"pm_ViSkebTnq3cwpp9GYZiVA","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Strips 85–97% of HTML token bloat from a URL, returning a semantically distilled, agent-readable version of the page's DOM","exampleAgentPrompt":"Can you strip the HTML from https://example.com/article and give me just the clean, readable content — I need it condensed enough to fit in my LLM context window?","exampleUseCases":[{"title":"LLM context window optimization","prompt":"Fetch https://techcrunch.com/2024/05/01/ai-funding-roundup and strip out all the HTML bloat so I can pipe just the meaningful text into my language model without blowing the token budget."},{"title":"Research pipeline preprocessing","prompt":"I need to distill a bunch of web pages for my research agent — start with https://en.wikipedia.org/wiki/Transformer_(machine_learning_model) and give me the semantic content with 90%+ of the HTML noise removed."},{"title":"Agent web browsing summarization","prompt":"My agent needs to read https://news.ycombinator.com but the raw HTML is too large — can you run it through the DOM stripper and return the cleaned, token-efficient version?"}],"resultDescription":"Returns a token-reduced, semantically distilled representation of the target webpage's DOM — typically stripping 85–97% of HTML overhead while preserving the meaningful text and structure. The output is suitable for direct injection into LLM context windows or downstream agent processing.","failureModes":["Invalid or unreachable URL returns an error response","Pages behind authentication or paywalls may return incomplete or empty content","Very large or complex pages may time out","Dynamic JavaScript-rendered content may not be fully captured via GET","Rate limiting or payment failure (x402) blocks the request"],"whenToPreferThis":"Choose this endpoint when you need to feed web page content into an LLM or AI agent and must minimize token usage. It is specifically optimized for semantic distillation — not just raw text extraction — making it superior to naive HTML stripping when preserving meaningful structure matters. Prefer it over generic scrapers when token budget is the primary constraint.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-20T12:43:24.255Z","isFirstParty":false,"canonicalSlug":"agentdiet-dom-stripper-44270c83"}