Prompt caching by provider

The mechanism is the same everywhere — an exact-prefix match, cached reads at a fraction of base price. The minimums, the pricing and the failure modes are not.

ProviderMin tokensReadWriteBase $/MTok
Anthropic Claude 1,0240.1×1.25×$3.00
OpenAI 1,0240.1×1.25×$5.00
Google Gemini 2,0480.1×$1.25
DeepSeek 1,0240.1×$0.28

The minimum is often per model, not per provider. On Anthropic it ranges from 512 to 4,096 tokens and runs backwards from price — see the Anthropic page for the full table.