{"uid":"cap_RY3h8Fz9x0LosvMRSAely","slug":"token-intel-agentdiet-dev-rag-token-diet-bm25-budget-controlled-web-0efd58af","name":"RAG Token Diet – BM25 Budget-Controlled Web Distillation","description":"Distill a URL or raw HTML payload with BM25 budget control (Live x402 v2, IETF MPP & MCP endpoint at https://token-intel.agentdiet.dev/v1/rag-token-diet)","url":"https://token-intel.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_WwAX3DS0t1hhBHCG_TH86","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"token-intel.agentdiet.dev","brandSlug":"token-intel-agentdiet-dev-mpp","brandBaseUrl":"https://token-intel.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches and distills a URL or raw HTML into compressed Markdown, structured JSON, skeleton outline, or BM25-focused excerpt within a strict token budget","exampleAgentPrompt":"Distill the content at https://stripe.com/docs/payments into clean Markdown using budget mode, focused on 'payment intents', and keep it under 500 tokens — I want to see how many tokens you saved me.","exampleUseCases":[{"title":"RAG pipeline cost reduction","prompt":"Fetch the page at https://openai.com/research/gpt-4 and distill it down to at most 300 tokens using budget mode, with the query 'multimodal capabilities', so I can feed it cheaply into my retrieval pipeline."},{"title":"Structured data extraction from docs","prompt":"Take the HTML from this Stripe documentation page and distill it into structured JSON tables — I need the pricing tiers and feature comparisons pulled out cleanly."},{"title":"Skeleton outline for long article","prompt":"Grab the article at https://en.wikipedia.org/wiki/Transformer_(machine_learning_model) and give me a skeleton outline of its sections so I can quickly navigate what's covered without reading the whole thing."}],"resultDescription":"Returns a 'data' object containing the distilled content (Markdown string, structured JSON, skeleton outline, or BM25-ranked excerpt depending on mode), plus an 'roi_proof' object with 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 metadata.","failureModes":["Invalid or unreachable URL returns fetch error","HTML payload too large may exceed processing limits","mode=budget without a query may produce suboptimal BM25 ranking","max_tokens set below minimum (20) returns validation error","Paywalled or JavaScript-heavy pages may yield incomplete distillation","Payment not included or invalid returns HTTP 402"],"whenToPreferThis":"Choose this endpoint when you need to feed web content into an LLM pipeline and want to minimize token usage — especially when you have a specific query focus (BM25 mode) or a strict token budget ceiling. It is better than generic scrapers when token efficiency and cost savings are measurable requirements, and better than raw HTML fetchers when you need clean Markdown or structured output ready for downstream LLM consumption. Ideal for RAG pipelines, document Q&A systems, and any agent that repeatedly ingests live web content.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:31:58.021Z","isFirstParty":false,"canonicalSlug":"token-intel-agentdiet-dev-rag-token-diet-bm25-budget-controlled-web-0efd58af"}