{"uid":"cap_2jt9w4X2_X53tN3xWpypX","slug":"workflows-agentdiet-dev-web-url-to-markdown-distiller-with-bm25-b0189ffb","name":"Web URL to Markdown Distiller with BM25 Budget Control","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/docs-to-markdown)","url":"https://workflows.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_D_w0B-pyJGc_brQOXTNzU","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 Markdown, structured JSON, skeleton outline, or BM25-focused token-budgeted excerpts","exampleAgentPrompt":"Distill the Stripe documentation page at https://stripe.com/docs/api/charges into compact markdown using budget mode, focused on 'charge creation parameters', and keep it under 500 tokens.","exampleUseCases":[{"title":"Compress docs page for LLM context","prompt":"Fetch the OpenAI API reference at https://platform.openai.com/docs/api-reference and distill it into compact markdown so I can include it in my agent's context without blowing my token budget."},{"title":"BM25-focused answer extraction from webpage","prompt":"Go to https://docs.aws.amazon.com/lambda/latest/dg/welcome.html and pull out only the parts relevant to 'cold start latency' using budget mode with a max of 300 tokens."},{"title":"Structured data extraction from product page","prompt":"Distill https://stripe.com/docs/api/payment_intents into structured JSON tables so I can see the key fields and metadata at a glance."}],"resultDescription":"Returns a JSON object with a 'data' field containing the distilled content (Markdown, structured JSON, skeleton, or BM25 excerpt depending on mode), plus an 'roi_proof' block showing raw token count, distilled token count, tokens saved, compression ratio percentage, ROI multiplier, and estimated LLM cost saved in USD. Optionally includes cache hit/miss status and billing details.","failureModes":["URL is unreachable or returns non-200 status — endpoint may return an error status","Invalid or malformed URL string — validation error on the url parameter","max_tokens set below minimum of 20 — schema validation failure","mode=budget used without a query parameter — may return unfiltered or empty excerpt","Raw HTML provided but also a URL — ambiguous input, behavior may default to URL fetch","Payment not processed (402) — request blocked until x402 micropayment is completed","Webpage with heavy JavaScript rendering may not be fully captured by server-side fetch"],"whenToPreferThis":"Choose this endpoint when your AI agent needs to read and process web pages or documentation but must stay within a token budget or minimize LLM input costs. It is especially valuable when working with large documentation sites, API references, or any HTML-heavy content where only a portion is relevant. The BM25 budget mode makes it uniquely suited for targeted Q&A over web content. Prefer this over generic scrapers when you need both compression metrics (ROI proof) and multiple extraction modes (markdown, structured, skeleton, budget) in a single call.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:25:24.745Z","isFirstParty":false,"canonicalSlug":"workflows-agentdiet-dev-web-url-to-markdown-distiller-with-bm25-b0189ffb"}