Per-Model Prompt Caching Control

What: Fine-grained control over prompt caching for individual model families How to use:

# Disable caching for Haiku models only
export DISABLE_PROMPT_CACHING_HAIKU=true

# Disable caching for Sonnet models only
export DISABLE_PROMPT_CACHING_SONNET=true

# Disable caching for Opus models only
export DISABLE_PROMPT_CACHING_OPUS=true

# Or disable globally for all models (existing behavior)
export DISABLE_PROMPT_CACHING=true

Details:

• Allows optimization strategies per model tier (e.g., disable for cheaper Haiku, enable for expensive Opus)
• The global DISABLE_PROMPT_CACHING variable still works as before
• Enables cost and performance tuning based on your specific use cases
• Evidence: Sd(A) function at line 395280 replaces Pd() at line 394932 in v1.0.112