Caching

Caching: Prompt caches, semantic caches, KV caches, and their taxes. 12 field notes from the engineers shipping Nadir's LLM routing layer.

Posts in Caching

• Watch the Wire (2026-10-24)
• Pay to Forget (2026-09-22)
• Compact Now, Pay Later (2026-09-10)
• The Embedding Tax (2026-08-18)
• The Overcaching Tax (2026-08-02)
• The Compression Trap (2026-07-27)
• The Cache Diet (2026-07-24)
• Your Router Is Fighting Your Prompt Cache (2026-07-16)
• The Cache Write Tax (2026-07-14)
• Cache-Blind Routing (2026-07-09)
• The Cache That Understands (2026-06-14)
• The Closest Thing to Free Money (2026-06-11)

Pages on this site

• Home
• Pricing
• Nadir Lens
• Benchmarks
• Techniques
• What is an LLM router?
• AI gateway vs model router
• Savings calculator
• Solutions
• Routing
• Provider fallback
• Analytics
• Prompt clustering
• Compare
• Nadir vs LiteLLM
• Nadir vs OpenRouter
• Nadir vs Requesty
• Nadir vs Ramp Router
• Nadir vs Not Diamond
• Nadir vs Weave Router
• Nadir vs Portkey
• Contact
• Self-host with NadirClaw
• On-prem
• Context Optimize
• Docs
• Blog
• Agent skill
• Claude Code receipt
• Coding agents
• Cookbooks
• FAQ
• How it works
• Terms of Service
• Privacy Policy
• Data Processing Agreement
• Security

Machine-readable summaries of this site: llms.txt and llms-full.txt.