{"uid":"cap_h-Iq7f91rzD6pafhXcX2f","slug":"agentdiet-llm-guard-context-window-distiller-token-diet-03a6158b","name":"AgentDiet LLM Guard — Context Window Distiller & Token Diet","description":"Deterministic B2A/A2A/MCP/x402/MPP/L402 execution and intelligence node at https://status.agentdiet.dev settling in USDC on Base.","url":"https://status.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_5XAXSsY0LFefZ3mPPDNGJ","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":"Scans and compresses LLM context/text input to strip bloat, achieving up to 85-91% token reduction while preserving semantic content","exampleAgentPrompt":"Run this context through AgentDiet's LLM Guard to strip it down — it's getting too long and expensive to send to the model as-is: 'You are a helpful assistant. The user has asked about the history of the Roman Empire...' Give me the compressed version and tell me the compression ratio.","exampleUseCases":[{"title":"Cut inference costs before GPT-4 call","prompt":"This system prompt and conversation history is huge — can you run it through AgentDiet's token diet before we send it to GPT-4? I want to see how much we can compress it and what the compression ratio ends up being."},{"title":"Reduce context for agent memory retrieval","prompt":"My agent's memory context has ballooned to thousands of tokens. Run it through the LLM Guard to distill it down to the essentials so I'm not burning tokens on every retrieval step."},{"title":"Validate prompt efficiency in CI pipeline","prompt":"Before we deploy this new system prompt, can you send it through AgentDiet's LLM Guard and confirm the compression ratio? I want to make sure we're not shipping a bloated prompt into production."}],"resultDescription":"Returns a JSON object with status 'ok', a data field containing the distilled/compressed output, and an roi_proof object showing the compression_ratio_pct (e.g. 91.4%), confirming how much token reduction was achieved.","failureModes":["Missing required 'input' field returns validation error","Invalid HTTP method enum value rejected","Text too short to compress meaningfully may return low or zero compression ratio","Payment failure via x402/USDC blocks execution","Empty or null text query param may return error or no-op result"],"whenToPreferThis":"Choose this endpoint when you need deterministic, measurable token compression with a verifiable ROI proof (compression_ratio_pct) before sending context to an LLM. Ideal for cost-sensitive agentic pipelines on x402/USDC pay-per-call infrastructure where you want to minimize inference spend per call. Prefer over generic summarization when you need a compression ratio metric rather than a human-readable summary.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-22T12:40:42.994Z","isFirstParty":false,"canonicalSlug":"agentdiet-llm-guard-context-window-distiller-token-diet-03a6158b"}