{"uid":"cap_tK6Nn9Xwe4eXp-eSXBXBY","slug":"agentdiet-llm-guard-context-window-distiller-token-reducer-69a38403","name":"AgentDiet LLM Guard — Context Window Distiller & Token Reducer","description":"Deterministic B2A/A2A/MCP/x402/MPP/L402 execution and intelligence node at https://rag-diet.agentdiet.dev settling in USDC on Base.","url":"https://rag-diet.agentdiet.dev/v1/llm-guard?utm_source=zero.xyz","method":"GET","headers":{},"bodySchema":{"type":"object","$schema":"https://json-schema.org/draft/2020-12/schema","required":["input"],"properties":{"input":{"type":"object","required":["type","method"],"properties":{"type":{"type":"string","const":"http"},"method":{"enum":["GET","POST"],"type":"string"},"queryParams":{"type":"object","properties":{"text":{"type":"string"}}}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"example":{"type":"object"}}}}},"responseSchema":{"type":"json","example":{"data":{},"status":"ok","roi_proof":{"compression_ratio_pct":91.4}}},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.005","displayCostAsset":"USDC","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":"$0.005/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.005","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.005","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_Z0mAOFpTCzWA0CG3EN8sX","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.005","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Compresses and guards LLM context windows by stripping bloat from input text, returning a distilled version with up to 91%+ compression ratio","exampleAgentPrompt":"Run this wall of text through AgentDiet's LLM Guard to strip the bloat and give me back a compressed version — I want to see the compression ratio proof too.","exampleUseCases":[{"title":"RAG chunk compression before LLM call","prompt":"Before I send these retrieved document chunks to Claude, can you compress them with AgentDiet LLM Guard so I'm not wasting tokens on filler text?"},{"title":"Reduce prompt size to cut API costs","prompt":"This system prompt is getting expensive — run it through the AgentDiet context distiller and show me how much it shrinks the token count."},{"title":"Guard agent memory from context bloat","prompt":"My agent's conversation history is getting huge and slowing things down. Can you pass it through AgentDiet LLM Guard to distill it down before the next turn?"}],"resultDescription":"Returns a JSON object with a 'data' field containing the compressed/distilled text, a 'status' field ('ok'), and a 'roi_proof' object that includes 'compression_ratio_pct' — the percentage of tokens removed (e.g. 91.4%).","failureModes":["Missing 'input' field or malformed schema returns a validation error","'text' query param absent may result in empty or error response","Payment not settled in USDC on Base may result in 402 rejection","Extremely short or already-minimal text may yield low or zero compression ratio"],"whenToPreferThis":"Choose this endpoint when you need to reduce token consumption before calling an LLM, especially in RAG pipelines or multi-turn agent conversations where context windows are large and costly. It is particularly useful when you need a deterministic, measurable compression result with a verifiable ROI proof (compression_ratio_pct). Prefer this over manual prompt trimming or generic summarization when you want guaranteed, reproducible compression and a quantified output.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-22T12:42:49.509Z","isFirstParty":false,"canonicalSlug":"agentdiet-llm-guard-context-window-distiller-token-reducer-69a38403"}