{"uid":"cap_ujMHAYPYyqqI-j_Z32mJF","slug":"llms-generator-agentdiet-dev-web-url-distiller-with-bm25-budget-control-ef21b312","name":"Web URL 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://llms-generator.agentdiet.dev/v1/docs-to-markdown)","url":"https://llms-generator.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_pctOfMJebP6xy3nJdO98H","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"llms-generator.agentdiet.dev","brandSlug":"llms-generator-agentdiet-dev-mpp","brandBaseUrl":"https://llms-generator.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches a web URL or raw HTML and distills it into compact, agent-ready Markdown, structured JSON, skeleton outlines, or BM25-focused token-budget excerpts","exampleAgentPrompt":"Distill the Stripe docs page at https://stripe.com/docs/api into compact markdown using budget mode, focused on 'payment intents', and keep it under 800 tokens.","exampleUseCases":[{"title":"Compress API docs for agent context","prompt":"Take the OpenAI API reference at https://platform.openai.com/docs/api-reference and distill it into clean markdown so I can include it in my agent's context without blowing up the token limit."},{"title":"BM25-focused excerpt from long page","prompt":"Fetch https://docs.aws.amazon.com/lambda/latest/dg/welcome.html and extract only the parts relevant to 'cold start latency' in budget mode, capped at 500 tokens."},{"title":"Structured data extraction from webpage","prompt":"Pull the pricing table from https://vercel.com/pricing and distill it into structured JSON so I can compare plans programmatically."}],"resultDescription":"Returns a JSON object with a 'data' field containing the distilled content (Markdown text, structured JSON tables/metadata, skeleton outline, or BM25-focused excerpt depending on mode), plus an 'roi_proof' object showing raw_tokens, distilled_tokens, tokens_saved, compression_ratio_pct, and llm_cost_saved_usd, and an optional 'cache' object indicating whether the result was a cache HIT or MISS with latency.","failureModes":["Invalid or unreachable URL returns an error status","Missing required 'url' parameter causes a 400-style validation error","mode=budget without a 'query' or 'max_tokens' may return unfiltered content","Raw HTML too large may hit processing limits","Paywalled or bot-protected pages may return empty or partial content","x402 payment failure halts the request before distillation"],"whenToPreferThis":"Use this endpoint when an AI agent needs to read or reference a live web page or documentation but must stay within a tight token budget. It is especially valuable over generic scraping tools because it offers BM25-ranked excerpt mode (returning only the most query-relevant tokens), multiple output modes (markdown, structured, skeleton, budget), and built-in ROI reporting showing exactly how many tokens were saved. Prefer it when you need to inject third-party documentation, pricing pages, or technical references into an LLM prompt without overwhelming the context window.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T12:51:26.273Z","isFirstParty":false,"canonicalSlug":"llms-generator-agentdiet-dev-web-url-distiller-with-bm25-budget-control-ef21b312"}