Who caches what

Same idea. Different knobs.

LayerHow a hit happensYou see it asTypical save
OpenAI Automatic longest identical prefix, usually 1,024+ tokens. Explicit breakpoints on GPT-5.6+. cached_tokens ~50–90% off cached input; writes extra on newest models
Claude Automatic top-level cache_control, or up to 4 explicit breakpoints. Writes only at markers. cache_read_input_tokens Reads at 10% of input; 5-minute TTL, optional 1 hour
Self-hosted vLLM / SGLang prefix KV cache on GPU. Hash of the token prefix. Same left-edge rule. Faster prefill, not a bill Latency, not an API discount
Your app Semantic cache: embed the query, return a previous answer if close enough. Zero model call 100% — but it is a different product

This talk is about the first three — KV prefix reuse. Do not mix them up with “we cached the chatbot reply.”