{"uid":"cap_1o9tMLqCRNTJXZ7ZQN7Hq","slug":"workflows-agentdiet-dev-agentdiet-web-distiller-url-to-compact-agent-94962ce8","name":"AgentDiet Web Distiller – URL to Compact Agent-Ready Tokens","description":"Distill a URL or raw HTML payload with BM25 budget control (Live x402 v2, IETF MPP & MCP endpoint at https://workflows.agentdiet.dev/v1/clean-html)","url":"https://workflows.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":[],"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_sa9Bk0Rg26ee9BV79_IY-","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"workflows.agentdiet.dev","brandSlug":"workflows-agentdiet-dev-mpp","brandBaseUrl":"https://workflows.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches a URL or raw HTML and distills it into compact, agent-ready tokens using selectable extraction modes (markdown, structured, skeleton, or BM25 budget) with a strict token ceiling.","exampleAgentPrompt":"Distill the page at https://stripe.com/docs/payments into compact markdown and keep it under 2000 tokens, focusing on the query 'payment intents setup' using budget mode.","exampleUseCases":[{"title":"Summarize docs page within token budget","prompt":"Fetch https://docs.openai.com/api-reference and distill it into budget mode focused on 'streaming responses', capping the output at 1500 tokens so I can include it in my prompt without blowing my context window."},{"title":"Extract structured tables from competitor pricing page","prompt":"Pull the pricing page at https://vercel.com/pricing and give me the content in structured mode so I get clean JSON tables with all the plan tiers and feature comparisons."},{"title":"Get skeleton outline of long technical article","prompt":"Distill https://martinfowler.com/articles/microservices.html into skeleton mode so I can see the headings and outline without getting the full text."}],"resultDescription":"Returns a JSON object with a 'data' field containing distilled content (markdown string, structured JSON tables/metadata, skeleton outline, or BM25-filtered excerpt depending on mode), plus an 'roi_proof' object showing raw_tokens, distilled_tokens, tokens_saved, compression_ratio_pct, and llm_cost_saved_usd. Also includes cache status (HIT/MISS) and billing details.","failureModes":["Invalid or unreachable URL returns an error status","HTML content too large to process within limits","max_tokens below minimum (20) causes validation error","BM25 query required but not provided when mode=budget","Payment/402 failure if USDC balance insufficient","Timeout if target URL is slow to respond","Malformed raw HTML input may produce incomplete distillation"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to ingest web page content but must stay within a token budget — especially when LLM cost or context window size is a constraint. Ideal over raw scraping tools when you want built-in compression metrics, BM25 relevance filtering, and structured/markdown output modes in a single call. Prefer over generic scrapers when token ROI tracking matters.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T12:47:48.983Z","isFirstParty":false,"canonicalSlug":"workflows-agentdiet-dev-agentdiet-web-distiller-url-to-compact-agent-94962ce8"}