{"uid":"cap_ebytwoUchU5nak_dQJyV-","slug":"mesh-agentdiet-dev-agentdiet-clean-html-bm25-budget-web-distiller-514daf51","name":"AgentDiet Clean HTML – BM25 Budget Web Distiller","description":"Distill a URL or raw HTML payload with BM25 budget control (Live x402 v2, IETF MPP & MCP endpoint at https://mesh.agentdiet.dev/v1/clean-html)","url":"https://mesh.agentdiet.dev/v1/clean-html?utm_source=zero.xyz","method":"POST","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_csLsV6NjhAi9BccBICrMZ","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"mesh.agentdiet.dev","brandSlug":"mesh-agentdiet-dev-mpp","brandBaseUrl":"https://mesh.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches a URL or accepts raw HTML and distills it into clean Markdown, structured JSON, a skeleton outline, or a BM25-ranked token-budget excerpt","exampleAgentPrompt":"Distill the content at https://stripe.com/docs/api into clean Markdown with a strict budget of 2000 tokens, focusing on the query 'authentication and API keys' using budget mode.","exampleUseCases":[{"title":"LLM-ready documentation extraction","prompt":"Fetch the React documentation page at https://react.dev/reference/react/useState and distill it into clean Markdown so I can feed it directly to my AI assistant without all the nav and footer noise."},{"title":"Token-budget excerpt for a research agent","prompt":"I need the most relevant 500 tokens from https://en.wikipedia.org/wiki/Transformer_(deep_learning_architecture) focused on the query 'attention mechanism' — use budget mode so my agent doesn't blow its context window."},{"title":"Structured data extraction from a webpage","prompt":"Pull the page at https://news.ycombinator.com and return it in structured mode so I get clean JSON tables and metadata rather than raw HTML."}],"resultDescription":"Returns a JSON object with a 'data' field containing the distilled content (Markdown string, structured JSON, skeleton outline, or BM25-ranked excerpt depending on mode), plus an 'roi_proof' object showing raw_tokens, distilled_tokens, tokens_saved, compression_ratio_pct, roi_multiplier, and llm_cost_saved_usd, along with optional billing and cache metadata.","failureModes":["URL unreachable or returns non-200 status — endpoint cannot fetch and distill the target","Invalid or missing 'url' field — required parameter not provided","max_tokens below minimum of 20 — budget ceiling too low","mode=budget used without a 'query' parameter — BM25 ranking has no focus term","Raw HTML too large or malformed — distillation may fail or truncate","Payment not included or insufficient — x402 payment required at $0.001 per call","Idempotency key reuse with different parameters — may return cached result unexpectedly"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to ingest web page content without wasting context-window tokens on boilerplate HTML, navigation, or ads. It is especially valuable when you need BM25-ranked budget control to stay within a strict token ceiling, or when you want structured JSON extraction rather than raw HTML. Prefer it over generic scrapers when LLM cost reduction and ROI tracking (compression ratio, tokens saved) matter to your workflow.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:37:27.852Z","isFirstParty":false,"canonicalSlug":"mesh-agentdiet-dev-agentdiet-clean-html-bm25-budget-web-distiller-514daf51"}