{"uid":"cap_15hx4FIUC9XZX2Xsa3-pw","slug":"mesh-agentdiet-dev-web-url-dom-stripper-token-distiller-ceecd285","name":"Web URL DOM Stripper & Token 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/dom-stripper)","url":"https://mesh.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":[],"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_QxJygR957yZrOxjbdDE8v","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 raw HTML and distills it into compact, agent-ready tokens using BM25 budget control and multiple extraction modes.","exampleAgentPrompt":"Can you fetch https://stripe.com/docs/api and distill it into compact markdown, keeping it under 2000 tokens — I need just the key content without all the HTML bloat?","exampleUseCases":[{"title":"Docs page into agent context","prompt":"Pull https://docs.openai.com/api-reference and distill it into structured markdown so I can feed it into my agent without blowing my context window."},{"title":"Budget-focused query extraction","prompt":"Fetch https://news.ycombinator.com and give me only the parts relevant to 'AI funding rounds' using budget mode with a max of 500 tokens."},{"title":"Raw HTML cleanup for pipeline","prompt":"I have a raw HTML dump from a scraper — can you strip it down to clean skeleton outline so I can see just the page structure without all the noise?"}],"resultDescription":"Returns a data object containing the distilled content (markdown, structured JSON, skeleton, or BM25-filtered excerpt), plus an roi_proof block showing raw_tokens, distilled_tokens, tokens_saved, compression_ratio_pct, roi_multiplier, and llm_cost_saved_usd. Also includes cache status (HIT/MISS) and billing details.","failureModes":["Invalid or unreachable URL returns an error status","HTML too large may exceed processing limits","mode=budget without a query parameter may return unfiltered content","max_tokens below minimum (20) will be rejected","Rate limiting or payment failure via x402 protocol blocks the request","Paywalled or JavaScript-heavy pages may return incomplete content"],"whenToPreferThis":"Choose this endpoint when you need to feed web content into an LLM context window cost-efficiently — especially when raw HTML or full-page text would exceed token budgets. Ideal for agent pipelines that need to process documentation, news, or data pages without inflating LLM costs. The BM25 budget mode is uniquely useful when you only need the slice of a page relevant to a specific query. Prefer over generic scraping tools when token compression metrics and ROI proofs are needed.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:23:28.012Z","isFirstParty":false,"canonicalSlug":"mesh-agentdiet-dev-web-url-dom-stripper-token-distiller-ceecd285"}