{"uid":"cap_i7DrqQhYCMS1juteHHkry","slug":"x402broker-dom-stripper-36f3977c","name":"x402broker DOM Stripper","description":"Distill a URL or raw HTML payload with BM25 budget control (Live x402 v2, IETF MPP & MCP endpoint at https://x402broker.com/v1/dom-stripper)","url":"https://x402broker.com/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_KWkhcpjrfW_PRzGgJfb7T","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null},{"uid":"pm_YMFA0TF8fJzEaFupDCdnf","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":"Fetches a URL and strips 85-97% of HTML token bloat, returning semantically distilled page content optimized for LLM consumption","exampleAgentPrompt":"Fetch https://techcrunch.com/2024/05/01/openai-new-model/ and strip out all the HTML bloat so I just get the meaningful article content — I need to feed it into my LLM without burning through my context window.","exampleUseCases":[{"title":"LLM context-window cost reduction","prompt":"Pull https://en.wikipedia.org/wiki/Transformer_(deep_learning_architecture) and distill it down to just the meaningful text — I want to pass it to GPT-4 without wasting tokens on nav bars, footers, and markup."},{"title":"Agent web research pipeline","prompt":"My agent needs to read this product page at https://stripe.com/pricing and extract only the actual pricing content — can you strip all the HTML noise so it fits cleanly in the prompt?"},{"title":"Competitive intelligence scraping","prompt":"Grab https://www.competitor.com/features and give me just the semantic content with all the HTML, scripts, and sidebar junk removed so I can analyze what features they're advertising."}],"resultDescription":"A semantically distilled version of the fetched webpage with 85-97% of HTML token bloat removed, returning only meaningful text content suitable for LLM ingestion. Response includes the extracted semantic text and optionally structured example output depending on the mode selected.","failureModes":["URL is unreachable or returns non-200 status — endpoint may return an error or empty content","JavaScript-rendered pages may not be fully captured if no headless browser is used","Very large pages may still exceed context limits even after distillation","Paywalled or auth-required pages will return login/error HTML rather than content","Invalid or malformed URL input returns a validation error","Rate limiting or blocking by target website may result in empty or partial responses"],"whenToPreferThis":"Choose this endpoint when you need to fetch and process web pages for LLM consumption and want to minimize token usage — ideal when context window cost is a concern, when building agent research pipelines, or when you need clean readable text from HTML-heavy pages. Prefer over raw HTTP fetch when the goal is to pass page content into an AI model. Best for single-URL distillation where you need fast, cheap ($0.001 USDC) semantic extraction without running your own headless browser infrastructure.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-20T12:44:28.183Z","isFirstParty":false,"canonicalSlug":"x402broker-dom-stripper-36f3977c"}