"Cost reduction playbook:
- (1)Model tiering — use Flash/Haiku for 80% of tasks (classification, simple Q&A), Pro/Opus only for complex reasoning. That alone cuts 60-70%.
- (2)Prompt caching — system prompt + tool definitions are identical across calls. Cache them. Saves 80% on input tokens for repeated calls.
- (3)Semantic caching — if someone asked a similar question in the last 24h, serve from cache. Expected 30-40% hit rate for support use cases.
- (4)Context trimming — summarize old tool observations instead of keeping full text.
- (5)Batch API — for non-urgent tasks, use the batch endpoint at 50% discount. Combined, these typically achieve 5-8x cost reduction."