{"uid":"cap_3CILF4PlwjFpAKxzCwR0A","slug":"x402broker-com-rag-diet-url-html-distillation-with-bm25-budget-control-e0767a00","name":"RAG-Diet: 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://x402broker.com/v1/rag-diet)","url":"https://x402broker.com/v1/rag-diet?utm_source=zero.xyz","method":"POST","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_IxvLoOFr8UJOcW1jmuFT4","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"x402broker.com","brandSlug":"x402broker-com-mpp","brandBaseUrl":"https://x402broker.com","brandDocsUrl":null,"whatItDoes":"Fetches and distills a URL or raw HTML into compressed Markdown, structured JSON, skeleton outlines, or BM25-scored token-budgeted excerpts for LLM-efficient retrieval.","exampleAgentPrompt":"Can you distill https://stripe.com/docs/api into compact markdown using BM25 budget mode focused on 'webhook events', keeping it under 500 tokens so I can feed it into my pipeline cheaply?","exampleUseCases":[{"title":"RAG pipeline token budget control","prompt":"Distill this URL https://docs.openai.com/api-reference into BM25 budget mode focused on 'function calling', capped at 300 tokens — I want just the most relevant chunk for my retrieval pipeline."},{"title":"Structured data extraction from documentation","prompt":"Fetch https://stripe.com/docs/api and distill it into structured mode so I get clean JSON tables and metadata I can use in my agent workflow."},{"title":"Compressing raw HTML for LLM ingestion","prompt":"I've got this raw HTML from a competitor's pricing page — can you distill it into clean markdown and tell me how many tokens you saved compared to the original?"}],"resultDescription":"Returns a 'data' object containing the distilled content (Markdown, structured JSON, skeleton outline, or BM25-scored excerpt depending on mode), plus an 'roi_proof' block showing raw_tokens, distilled_tokens, tokens_saved, compression_ratio_pct, and llm_cost_saved_usd. Also includes cache status (HIT/MISS) and billing details.","failureModes":["URL is unreachable or returns non-200 status — endpoint may return an error status","Raw HTML payload is malformed or empty — distillation may fail or return minimal output","BM25 query not provided when mode=budget — may default or error","max_tokens set below minimum of 20 — validation error","Rate limiting or payment failure via x402 — 402 response requiring payment","Target URL returns non-HTML content (PDF, binary) — unexpected distillation results"],"whenToPreferThis":"Choose this endpoint when you need to compress web content or HTML for LLM pipelines with strict token budgets, especially when you want BM25-ranked relevance filtering, ROI/cost-savings telemetry, or multiple distillation modes (markdown, structured, skeleton, budget). Prefer over generic scrapers when token efficiency and LLM cost reduction are primary concerns, or when you need structured JSON extraction from HTML rather than raw text.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:35:52.740Z","isFirstParty":false,"canonicalSlug":"x402broker-com-rag-diet-url-html-distillation-with-bm25-budget-control-e0767a00"}