{"uid":"cap_M3FW34vb4OccfgRD0xw08","slug":"json-repair-agentdiet-dev-web-url-html-distillation-with-bm25-budget-f73be5b4","name":"Web URL & HTML Distillation 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/markdown-distill)","url":"https://json-repair.agentdiet.dev/v1/markdown-distill?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_YWog_YU2AbpfSUuCJSgAG","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 URL or accepts raw HTML and converts it into compact, agent-ready Markdown, structured JSON, skeleton outline, or BM25-ranked token-budgeted excerpts","exampleAgentPrompt":"Distill the webpage at https://stripe.com/docs/payments into compact markdown, using budget mode focused on the query 'payment intents API' with a max of 500 tokens, so I can read only the most relevant content.","exampleUseCases":[{"title":"Research page distillation for agent pipeline","prompt":"Fetch https://openai.com/blog/gpt-4 and distill it into clean markdown so I can pass just the key content to my next agent step without blowing my token budget."},{"title":"BM25 budget excerpt for targeted research","prompt":"Pull the content from https://docs.anthropic.com/claude/reference and give me only the parts about 'tool use and function calling' in budget mode, keeping it under 300 tokens."},{"title":"Structured data extraction from raw HTML","prompt":"I have this raw HTML from a product page — can you distill it into structured JSON tables pulling out the pricing tiers, features, and metadata?"}],"resultDescription":"Returns a JSON object with a 'data' field containing the distilled content in the requested format (Markdown, structured JSON tables/metadata, skeleton outline, or BM25-ranked excerpt), plus an 'roi_proof' object showing raw vs distilled token counts, compression ratio, tokens saved, and estimated LLM cost saved in USD. Optionally includes cache status (HIT/MISS) and billing details.","failureModes":["Invalid or unreachable URL returns an error status instead of distilled content","Missing required 'url' parameter causes a validation error","mode=budget without a 'query' parameter may produce degraded or fallback output","Very large pages or slow-loading URLs may increase latency or time out","Raw HTML passed via 'html' that is malformed or empty may yield sparse output","Token budget too low (below 20) is rejected by schema validation"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to read web pages or HTML content while minimizing LLM token consumption. It is especially valuable when you need BM25-ranked relevance filtering (budget mode) to extract only the content matching a specific query, or when you want structured JSON tables/metadata rather than raw HTML. Prefer it over generic scrapers when token cost reduction and ROI proof are important, or when you need multiple distillation modes (markdown, structured, skeleton, budget) from a single API.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:22:40.638Z","isFirstParty":false,"canonicalSlug":"json-repair-agentdiet-dev-web-url-html-distillation-with-bm25-budget-f80b20bd"}