OpenRouter Caching Strategy Overview OpenRouter charges per token, so caching identical or similar requests can dramatically cut costs. Deterministic requests ( ) with the same model and messages produce identical outputs -- these are safe to cache. This skill covers in-memory caching, persistent caching with TTL, and Anthropic prompt caching via OpenRouter. In-Memory Cache Persistent Cache with Redis Anthropic Prompt Caching via OpenRouter Anthropic models on OpenRouter support prompt caching -- large system prompts are cached server-side, reducing input cost by 90% on cache hits. Cache Key…