{"uid":"cap_wduPSjrJMeGYbHnMObQyz","slug":"agentdiet-clean-html-semantic-distillation-f0c0a9d8","name":"AgentDiet Clean HTML — Semantic Distillation","description":"Distill a URL or raw HTML payload with BM25 budget control (Live x402 v2, IETF MPP & MCP endpoint at https://agentdiet.dev/v1/clean-html)","url":"https://agentdiet.dev/v1/clean-html?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_gk0qWN_5G0UIhoqyulZQO","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null},{"uid":"pm_OhRV72J6cDVJWvIiO4utF","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 given URL, returning semantically dense, agent-readable content","exampleAgentPrompt":"Can you fetch https://techcrunch.com/2024/05/15/openai-gpt5/ and strip out all the HTML bloat — nav, ads, scripts, the works — so I just get the clean readable content without wasting tokens?","exampleUseCases":[{"title":"LLM summarization preprocessing","prompt":"Grab https://en.wikipedia.org/wiki/Large_language_model and strip all the HTML noise so I can summarize the article without blowing my context window."},{"title":"Agent web research pipeline","prompt":"Before you analyze this page for me — https://stripe.com/docs/api — clean the HTML first so you're only reading the actual documentation text, not all the sidebar and nav junk."},{"title":"Competitive pricing page extraction","prompt":"Pull the pricing page at https://vercel.com/pricing and distill it down to just the meaningful content — remove all the template HTML so we can compare their tiers efficiently."}],"resultDescription":"Returns a semantically distilled version of the target webpage with 85-97% of HTML token bloat removed, leaving clean, meaningful content suitable for LLM ingestion, summarization, or downstream agent processing.","failureModes":["Target URL is unreachable or returns a non-200 status — endpoint may return an error or empty result","JavaScript-rendered single-page apps may not yield meaningful content since static HTML is fetched","Rate limiting or bot-blocking on the target site may result in incomplete or blocked content","Malformed or extremely non-standard HTML may survive distillation with residual noise","Missing required 'url' query parameter results in a validation error"],"whenToPreferThis":"Choose this endpoint when you need to pass web page content to an LLM and are concerned about token limits or cost — it removes 85-97% of non-semantic markup. Prefer it over raw fetch-and-parse approaches when the target page is content-heavy with significant templating, navigation, advertising, or script bloat. Ideal as a preprocessing step before summarization, classification, or RAG ingestion pipelines.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-20T12:48:21.772Z","isFirstParty":false,"canonicalSlug":"agentdiet-clean-html-semantic-distillation-f0c0a9d8"}