{"uid":"cap_Yl3LymlGJCqb8CWXOANPJ","slug":"agentdiet-dev-agentdiet-web-url-distiller-47b37abc","name":"AgentDiet Web URL Distiller","description":"Distill a URL or raw HTML payload with BM25 budget control (Live x402 v2, IETF MPP & MCP endpoint at https://agentdiet.dev/v1/docs-to-markdown)","url":"https://agentdiet.dev/v1/docs-to-markdown?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_X9CkZKomPX7q7hNV1YLXL","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"agentdiet.dev","brandSlug":"agentdiet-dev-mpp","brandBaseUrl":"https://agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches and compresses a web page or raw HTML into compact, agent-ready Markdown or structured data with BM25 token-budget control","exampleAgentPrompt":"Fetch https://stripe.com/docs/api/charges and distill it into compact markdown — use budget mode with the query 'charge creation parameters' and keep it under 1500 tokens.","exampleUseCases":[{"title":"LLM context window trimming","prompt":"Pull https://docs.openai.com/api-reference/chat and compress it into budget mode focused on 'streaming response format', capped at 800 tokens — I need to fit it into a prompt without blowing my context limit."},{"title":"Agent-readable docs pipeline","prompt":"Distill the raw HTML from our internal wiki page into structured JSON tables so my agent can parse the pricing tiers and feature flags without processing the whole page."},{"title":"Skeleton outline extraction","prompt":"Fetch https://developer.mozilla.org/en-US/docs/Web/API/Fetch_API and give me a skeleton outline of the page — just the headings and section structure, nothing else."}],"resultDescription":"Returns a 'data' object containing the distilled content (Markdown text, structured JSON tables/metadata, 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. Also includes optional cache hit/miss status and billing details.","failureModes":["URL unreachable or returns non-200 status — distillation fails with error status","HTML payload too large or malformed — may produce incomplete distillation","mode=budget without query or max_tokens — defaults may not match intent","Token ceiling too low (below 20) — rejected by schema validation","Rate limiting or payment failure via x402 — call not executed"],"whenToPreferThis":"Choose this endpoint when an agent needs to fetch a live webpage and reduce its token footprint before passing content to an LLM — especially when working within strict context windows. The BM25 budget mode is uniquely suited for targeted excerpt extraction from long documents. Prefer over generic scrapers when token-cost ROI tracking and structured output modes (tables, skeleton, markdown) are needed simultaneously.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:22:55.802Z","isFirstParty":false,"canonicalSlug":"agentdiet-dev-agentdiet-web-url-distiller-47b37abc"}