{"uid":"cap_9NcSbaDb0hEKQrupev05q","slug":"company-enrich-agentdiet-dev-rag-token-diet-bm25-budget-controlled-6153568e","name":"RAG Token Diet — BM25 Budget-Controlled Web Distiller","description":"Distill a URL or raw HTML payload with BM25 budget control (Live x402 v2, IETF MPP & MCP endpoint at https://company-enrich.agentdiet.dev/v1/rag-token-diet)","url":"https://company-enrich.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_dhDgI2zc68CIr3eEmf2M5","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"company-enrich.agentdiet.dev","brandSlug":"company-enrich-agentdiet-dev-mpp","brandBaseUrl":"https://company-enrich.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches and distills a URL or raw HTML into compact Markdown, structured JSON, a skeleton outline, or a BM25-ranked token-budget excerpt for RAG pipelines","exampleAgentPrompt":"Distill the page at https://stripe.com/docs/payments into clean Markdown with a strict 1500-token budget, focused on the query 'how does payment intent work', using budget mode.","exampleUseCases":[{"title":"RAG pipeline cost reduction","prompt":"Fetch https://openai.com/research/gpt-4 and compress it down to 800 tokens max using BM25 budget mode with the query 'training data and architecture' — I want to pass only the relevant bits to my LLM without wasting tokens."},{"title":"Structured data extraction from product page","prompt":"Pull the page at https://aws.amazon.com/ec2/pricing/ and distill it into structured JSON tables so I can compare EC2 instance pricing without all the HTML noise."},{"title":"Documentation skeleton for agent context","prompt":"Take the raw HTML I'm sending you for our internal docs portal and give me a skeleton outline of its sections — I need a lightweight map of what's in there before I dive deeper."}],"resultDescription":"Returns a 'data' object containing the distilled content in the requested format (Markdown, structured JSON, skeleton, or BM25 excerpt), plus an 'roi_proof' block showing raw vs distilled token counts, tokens saved, compression ratio percentage, ROI multiplier, and estimated LLM cost saved in USD. Optionally includes cache hit/miss status and billing details.","failureModes":["URL is unreachable or returns non-200 — distillation cannot proceed","HTML payload is empty or malformed — returns error status","mode=budget with no query or max_tokens — BM25 ranking cannot be applied","Target page is behind a login wall or CAPTCHA — content cannot be fetched","Token budget too low (below 20) — rejected by schema validation","Payment not authorized via x402 — 402 response before distillation begins"],"whenToPreferThis":"Choose this endpoint when you need to feed web content into an LLM but want to minimize token spend and noise. It is especially valuable in RAG workflows where you need BM25-ranked, query-focused excerpts under a strict token budget. Prefer it over generic scrapers when compression ratio and cost-savings proof matter, or when you need structured JSON tables and metadata rather than raw HTML dumps.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T06:31:07.345Z","isFirstParty":false,"canonicalSlug":"company-enrich-agentdiet-dev-rag-token-diet-bm25-budget-controlled-6153568e"}