{"uid":"cap_Wz2v9BiMI0ZY5lARhCgHy","slug":"json-repair-agentdiet-dev-web-url-distillation-to-agent-ready-tokens-73d97902","name":"Web URL Distillation to Agent-Ready Tokens","description":"Distill a web URL into compact agent-ready tokens (Live x402 v2, IETF MPP & MCP endpoint at https://json-repair.agentdiet.dev/v1/rag-diet)","url":"https://json-repair.agentdiet.dev/v1/rag-diet?utm_source=zero.xyz","method":"GET","headers":{},"bodySchema":{"type":"object","required":["url"],"properties":{"url":{"type":"string","minLength":1,"description":"Target webpage URL to distill (or builtin://stripe-docs)"},"mode":{"enum":["markdown","structured","skeleton","budget"],"type":"string","default":"markdown","description":"Extraction mode: markdown, structured, skeleton, or budget"},"limit":{"type":"integer","default":20,"maximum":100,"minimum":1,"description":"Maximum number of items to return per page (1-100)"},"query":{"type":"string","description":"BM25 focus query when mode=budget"},"cursor":{"type":"string","description":"Opaque pagination cursor for fetching the next page"},"max_tokens":{"type":"integer","minimum":20,"description":"Strict token 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_NNrVfjchPm3GfMtoxl9JG","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 and compresses it into compact, token-efficient markdown, structured tables, skeleton outlines, or BM25-focused budget excerpts for LLM consumption.","exampleAgentPrompt":"Can you distill https://docs.stripe.com/payments/accept-a-payment into compact markdown for me — keep it under 2000 tokens using budget mode and focus the BM25 query on 'payment intents'?","exampleUseCases":[{"title":"Documentation page for RAG pipeline","prompt":"Distill the content at https://platform.openai.com/docs/guides/function-calling into structured mode so I can load it into my RAG index without wasting tokens."},{"title":"Token-budget excerpt for tight context window","prompt":"I need to pull the key parts of https://www.example.com/blog/ai-trends-2025 that are relevant to 'AI agents in enterprise' — use budget mode with a max of 500 tokens and focus the BM25 query on that phrase."},{"title":"Skeleton outline of a long article","prompt":"Grab https://en.wikipedia.org/wiki/Large_language_model and give me just the skeleton outline — I want to see the section structure without all the body text."}],"resultDescription":"Returns a JSON object with a 'data' field containing the distilled content (markdown text, structured tables/metadata, skeleton outline, or BM25-filtered 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 status (HIT/MISS) and billing metadata.","failureModes":["Invalid or unreachable URL returns an error status","Pages behind authentication or paywalls cannot be fetched","Very large pages may exceed processing limits","BM25 query with mode other than 'budget' is ignored","Invalid mode enum value causes request rejection","max_tokens below minimum of 20 is rejected","Cursor from a different session may be invalid, causing pagination errors","Rate limits or payment failures (x402) may block the request"],"whenToPreferThis":"Choose this endpoint when you need to feed web content into an LLM or RAG pipeline cost-effectively — especially when raw HTML or full page text would exceed your context window or inflate token costs. It is purpose-built for agentic workflows with multiple extraction modes (markdown, structured, skeleton, budget) and provides built-in ROI metrics. Prefer it over generic scrapers when token efficiency and LLM-readiness matter, or when you need BM25-focused excerpts at a strict token ceiling.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:34:56.346Z","isFirstParty":false,"canonicalSlug":"json-repair-agentdiet-dev-web-url-distillation-to-agent-ready-tokens-73d97902"}