{"uid":"cap_N874kwmH6YqIxhmO2csBX","slug":"json-repair-agentdiet-dev-web-url-distillation-context-bloat-eliminator-d2e72199","name":"Web URL Distillation & Context Bloat Eliminator","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/context-bloat-eliminator)","url":"https://json-repair.agentdiet.dev/v1/context-bloat-eliminator?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_chOQe4qqKMjhUPCx7dHZ7","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 (or accepts raw HTML) and compresses it into compact, agent-ready tokens using BM25 budget control and multiple distillation modes","exampleAgentPrompt":"Can you distill https://stripe.com/docs/payments into compact markdown, keeping it under 2000 tokens and focusing on the query 'payment intents API'?","exampleUseCases":[{"title":"Trim docs page for LLM context","prompt":"Fetch https://docs.openai.com/api-reference and distill it into clean markdown under 1500 tokens — I need to fit it in my agent's context without burning through my budget."},{"title":"Extract structured data from landing page","prompt":"Pull https://www.competitor.com/pricing and give me a structured breakdown of their pricing tiers and features — use structured mode so I get it as tables I can actually parse."},{"title":"BM25 budget-focused research snippet","prompt":"Distill https://en.wikipedia.org/wiki/Transformer_(machine_learning_model) in budget mode with a max of 800 tokens, focused on the query 'attention mechanism self-attention'."}],"resultDescription":"Returns a JSON object with a 'data' field containing the distilled content (Markdown, structured JSON tables/metadata, skeleton outline, or BM25-ranked excerpt depending on mode), plus an 'roi_proof' object showing raw vs. distilled token counts, compression ratio percentage, tokens saved, and estimated LLM cost saved in USD. Also includes optional cache hit/miss status and billing details.","failureModes":["Invalid or unreachable URL returns an error status","mode=budget requires both 'query' and 'max_tokens' to be meaningful — omitting them may yield unfiltered output","Very large pages may hit internal processing limits","HTML-only input (no URL) requires the 'html' parameter instead of 'url'","Payment failure via x402 protocol returns HTTP 402 with payment details","Paywalled or JavaScript-rendered pages may return incomplete content"],"whenToPreferThis":"Choose this endpoint when your agent needs to read web pages without blowing up its context window — especially when you need token-budget enforcement via BM25 scoring to keep only the most relevant content. It is better than raw HTML fetchers when you want clean Markdown or structured JSON output. Prefer it over generic scrapers when you need the ROI proof (compression ratio, tokens saved) to justify the cost, or when you want skeleton outlines for navigation before deep-reading.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:20:55.539Z","isFirstParty":false,"canonicalSlug":"json-repair-agentdiet-dev-web-url-distillation-context-bloat-eliminator-d2e72199"}