{"uid":"cap_m9t3a512ySGfn25LSpPUg","slug":"json-repair-agentdiet-dev-web-url-to-markdown-distiller-with-bm25-38a240a0","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://json-repair.agentdiet.dev/v1/spa-markdown-reader)","url":"https://json-repair.agentdiet.dev/v1/spa-markdown-reader?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__yPj07UvAA8qurU248jb9","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 accepts raw HTML) and distills it into compact, agent-ready Markdown, structured JSON, skeleton outline, or BM25-focused token-budgeted excerpts","exampleAgentPrompt":"Fetch https://stripe.com/docs/api and distill it into compact markdown using budget mode with a 2000-token ceiling, focused on 'payment intents'.","exampleUseCases":[{"title":"Stripe docs for agent pipeline","prompt":"Distill the Stripe API docs at https://stripe.com/docs/api into compact markdown so I can feed it to my coding agent — use budget mode with a max of 3000 tokens focused on 'webhooks'."},{"title":"Extract competitor pricing page","prompt":"Fetch https://www.notion.so/pricing and give me a structured JSON extraction of all the pricing tiers and features listed on that page."},{"title":"Skeleton outline of a long article","prompt":"Can you pull https://en.wikipedia.org/wiki/Large_language_model and return just a skeleton outline of the page's headings so I can navigate the content without reading the whole thing?"}],"resultDescription":"Returns a JSON object with a 'data' field containing the distilled content (Markdown text, structured tables/metadata, skeleton outline, or BM25-ranked excerpt depending on mode), plus an 'roi_proof' object showing raw vs. distilled token counts, compression ratio, tokens saved, and estimated LLM cost savings. Optionally includes billing info and cache hit/miss status.","failureModes":["Invalid or unreachable URL returns an error status","max_tokens below minimum of 20 rejected with validation error","BM25 query mode (budget) with no query string may return unfiltered excerpt","Raw HTML too large may exceed processing limits","Paywalled or JavaScript-heavy SPAs may return incomplete content","x402 payment failure if agent lacks sufficient USDC balance"],"whenToPreferThis":"Choose this endpoint when you need to feed live web content to an LLM but want to minimize token usage and cost — especially when the raw HTML is bloated with navigation, ads, or boilerplate. Ideal for agentic pipelines that need to read documentation, competitor pages, or news articles within strict token budgets. The BM25 budget mode is especially useful when you have a specific question and want only the most relevant passages. Prefer this over generic scrapers when you need both content extraction and token-cost optimization in a single call.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T12:49:35.294Z","isFirstParty":false,"canonicalSlug":"json-repair-agentdiet-dev-web-url-to-markdown-distiller-with-bm25-5a045dbc"}