06:26
2026-08-23
gojiberries.io
large-language-models
Cache-Control for LLMs
Anthropic's Claude Sonnet 5 charges $2.00 per million fresh input tokens, $2.50 to write into a five-minute cache, and $0.20 per read, making two identical calls cost $2.70 with caching versus $4.00 wโฆ