{"uid":"cap_l5VW88NN1xqC57-TtmXV6","slug":"agentdiet-dev-rag-token-diet-url-html-distillation-with-bm25-budget-2c7adc45","name":"RAG Token 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://agentdiet.dev/v1/rag-token-diet)","url":"https://agentdiet.dev/v1/rag-token-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_-4AODcGw-faYiDYs5TZyN","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"agentdiet.dev","brandSlug":"agentdiet-dev-mpp","brandBaseUrl":"https://agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches and distills a URL or raw HTML into Markdown, structured JSON, skeleton outline, or a BM25-ranked token-budget excerpt, returning compression ROI metrics.","exampleAgentPrompt":"Distill https://stripe.com/docs/payments/payment-intents into clean Markdown using budget mode, focused on the query 'payment intent lifecycle', with a max of 500 tokens — and show me how many tokens you saved.","exampleUseCases":[{"title":"RAG pipeline web preprocessing","prompt":"Fetch https://openai.com/research/gpt-4 and distill it into clean Markdown so I can feed it into my RAG pipeline without wasting tokens."},{"title":"Query-focused budget extraction","prompt":"Pull this URL https://docs.aws.amazon.com/lambda/latest/dg/welcome.html and extract only the parts relevant to 'cold start latency' using budget mode with a max of 300 tokens."},{"title":"Structured page summarization","prompt":"Take the raw HTML I'm pasting here and convert it into a structured JSON summary with tables and metadata extracted — I want to index this in my database."}],"resultDescription":"Returns a JSON object with a 'data' field containing the distilled content (Markdown text, structured JSON, skeleton outline, or BM25-ranked excerpt depending on mode), an 'roi_proof' object showing raw_tokens, distilled_tokens, tokens_saved, compression_ratio_pct, roi_multiplier, and llm_cost_saved_usd, plus optional cache hit/miss status and billing details.","failureModes":["URL is unreachable or returns non-200 HTTP status — endpoint may return an error status","HTML payload is empty or malformed — distillation may produce empty output","max_tokens set too low (below 20) — rejected by schema validation","BM25 query provided without mode=budget — query may be ignored","Rate limit or payment failure via x402 — request blocked with 402 status","Target page is JavaScript-rendered and content not in static HTML — distillation may be incomplete"],"whenToPreferThis":"Choose this endpoint when you need to feed web content into an LLM or RAG pipeline and want to minimize token usage and cost. It is ideal when you have a specific query focus (BM25 mode) and need only the relevant chunks within a strict token budget, or when you need clean Markdown/structured JSON from raw HTML without building your own parser. Prefer it over generic scrapers when compression ratio and token-cost ROI metrics matter to your pipeline.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:30:17.373Z","isFirstParty":false,"canonicalSlug":"agentdiet-dev-rag-token-diet-url-html-distillation-with-bm25-budget-2c7adc45"}