{"uid":"cap_EmUo1MP4j-T99PqVP-Xuu","slug":"x402broker-context-diet-html-semantic-distillation-94a9526d","name":"x402broker Context Diet — HTML Semantic Distillation","description":"Distill a URL or raw HTML payload with BM25 budget control (Live x402 v2, IETF MPP & MCP endpoint at https://x402broker.com/v1/context-diet)","url":"https://x402broker.com/v1/context-diet?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_BPMoqtGm-UCP5AicFJLMO","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null},{"uid":"pm_fHC7HG6_W-bVGnNQ-TIVQ","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 web page URL, returning a semantically distilled version optimized for LLM context windows","exampleAgentPrompt":"Can you fetch https://example.com/blog/ai-agents and distill it down — strip all the HTML noise so I just get the clean semantic content that fits in my context window?","exampleUseCases":[{"title":"Webpage summarization pipeline prep","prompt":"I need to summarize this news article at https://techcrunch.com/2024/01/15/openai-new-model but the raw HTML is massive — can you distill it to just the meaningful text so we can summarize it without blowing the context limit?"},{"title":"Agent research without token waste","prompt":"My agent needs to read https://docs.anthropic.com/en/docs/about-claude/models to find the latest Claude model names — can you run context-diet on that URL to strip the HTML bloat and give me just the semantic content?"},{"title":"Competitive intelligence extraction","prompt":"Pull https://stripe.com/pricing using context-diet mode and give me the distilled version — I want just the pricing info without all the nav, footer, and HTML cruft eating my tokens."}],"resultDescription":"A semantically distilled version of the target webpage with 85-97% of HTML token bloat removed, leaving only meaningful content suitable for direct injection into an LLM context window. The response is a compact, clean representation of the page's core information.","failureModes":["Invalid or unreachable URL returns an error with HTTP status","Paywalled or bot-blocked pages may return incomplete or empty content","Very large or JavaScript-heavy single-page apps may not fully render","Missing required 'input' field with type and method returns a 400 validation error","Payment not fulfilled returns HTTP 402 requiring x402 payment flow"],"whenToPreferThis":"Choose this endpoint when you need to feed web page content into an LLM context window and the raw HTML is too large or noisy. Ideal for agentic pipelines that scrape URLs and must stay within token budgets. Prefer over raw HTTP fetches or general scrapers when the primary concern is token efficiency and semantic fidelity for LLM consumption.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-20T12:48:21.461Z","isFirstParty":false,"canonicalSlug":"x402broker-context-diet-html-semantic-distillation-94a9526d"}