{"uid":"cap_eBX9Zdfq5CpXUCrUzjR_H","slug":"json-repair-agentdiet-dev-web-url-html-distillation-with-bm25-budget-f80b20bd","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/clean-html)","url":"https://json-repair.agentdiet.dev/v1/clean-html?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_YNodcgG9Iq_r04PO-IaVz","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 distills it into compact, agent-ready tokens using markdown, structured, skeleton, or BM25-focused budget modes","exampleAgentPrompt":"Can you distill https://stripe.com/docs/payments into compact markdown, using budget mode focused on 'payment intents' and keeping it under 500 tokens?","exampleUseCases":[{"title":"LLM-ready doc extraction under token budget","prompt":"Distill https://docs.openai.com/api-reference into budget mode with the query 'function calling' and cap it at 800 tokens so I can feed it straight to my agent without blowing the context window."},{"title":"Structured table extraction from a pricing page","prompt":"Fetch https://vercel.com/pricing and convert it into structured mode so I get the pricing tiers as JSON tables I can compare programmatically."},{"title":"Raw HTML cleanup for scraped content","prompt":"I've got a raw HTML blob from a scraped news article — can you distill it into clean markdown so my agent can read it without all the nav and footer noise?"}],"resultDescription":"Returns a 'data' object containing distilled content (markdown text, structured JSON tables/metadata, skeleton outline, or BM25-focused excerpt depending on mode), alongside an 'roi_proof' block showing raw token count, distilled token count, tokens saved, compression ratio percentage, estimated LLM cost saved in USD, and ROI multiplier. Also includes cache status (HIT/MISS) and billing details.","failureModes":["URL unreachable or returns non-200 status — endpoint cannot fetch content","HTML payload too large for processing within token constraints","Invalid mode enum value provided — falls back to markdown or returns error","max_tokens set below minimum of 20 — validation error returned","BM25 query provided without mode=budget — query may be silently ignored","Payment not completed (HTTP 402) — response blocked until x402 payment fulfilled","Malformed URL string that fails minLength or format validation"],"whenToPreferThis":"Choose this endpoint when you need to feed web content to an LLM and want to minimize token consumption with measurable ROI metrics. It is especially valuable when you have a strict token budget (use mode=budget with a query and max_tokens), need structured table/metadata extraction from HTML (mode=structured), or want a fast outline of page structure (mode=skeleton). Prefer it over generic scrapers when you need built-in BM25 relevance filtering, compression ratio reporting, and LLM cost savings quantification. It also accepts raw HTML directly, making it useful when you already have scraped content and just need distillation without an extra fetch.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:23:47.538Z","isFirstParty":false,"canonicalSlug":"json-repair-agentdiet-dev-web-url-html-distillation-with-bm25-budget-f80b20bd"}