{"uid":"cap__rtbn7h_FrjYEFuzldVPN","slug":"json-repair-agentdiet-dev-url-to-markdown-distiller-with-bm25-budget-48939b44","name":"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://json-repair.agentdiet.dev/v1/url-to-markdown)","url":"https://json-repair.agentdiet.dev/v1/url-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_68usthlXyR36uPDbxYTMQ","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"json-repair.agentdiet.dev","brandSlug":"json-repair-agentdiet-dev-mpp","brandBaseUrl":"https://json-repair.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches a webpage URL or raw HTML and converts it into compact, agent-ready Markdown with optional BM25-ranked token budget control","exampleAgentPrompt":"Can you distill https://stripe.com/docs/payments into compact markdown using budget mode, focused on 'payment intents', and keep it under 500 tokens?","exampleUseCases":[{"title":"Research page distillation for agent","prompt":"Fetch https://openai.com/research/gpt-4 and convert it to clean markdown so I can read it without all the navigation noise and ads."},{"title":"Token-budget excerpt for RAG pipeline","prompt":"Distill https://docs.anthropic.com/claude/reference/getting-started-with-the-api using budget mode with the query 'rate limits' and a max of 300 tokens — I only want the most relevant chunk."},{"title":"Structured data extraction from landing page","prompt":"Pull https://linear.app and return the content in structured mode so I can get the tables and metadata in JSON format for my lead research."}],"resultDescription":"Returns a JSON object with a 'data' field containing the distilled content (Markdown, structured JSON, skeleton outline, or BM25 excerpt depending on mode), plus an 'roi_proof' object showing raw vs distilled token counts, compression ratio, tokens saved, and estimated LLM cost saved in USD. Also includes optional cache status and billing details.","failureModes":["Invalid or unreachable URL returns an error status","Target site blocks scraping or returns non-HTML content causing empty output","max_tokens set below minimum of 20 causes validation error","mode=budget without a query may return unfiltered or degraded output","Payment/402 failure if agent lacks sufficient USDC balance","HTML too large or timeout causes partial or failed distillation"],"whenToPreferThis":"Choose this endpoint when you need to fetch and compress web content into token-efficient format for an AI agent pipeline, especially when you have a strict token budget or want BM25-ranked relevance filtering. It is preferable over generic scrapers when LLM cost savings and compression ratio matter, or when you need multiple output modes (markdown, structured, skeleton, budget) from a single endpoint with native x402 micropayment support.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T12:48:11.575Z","isFirstParty":false,"canonicalSlug":"json-repair-agentdiet-dev-url-to-markdown-distiller-with-bm25-budget-48939b44"}