Models with Caching

LLMs with Prompt Caching: Save on Repeated API Calls

Compare LLMs that offer prompt caching. Cache your system prompt, few-shot examples, or conversation history to dramatically cut costs on subsequent requests. Essential for AI agents and chatbots that make many calls with shared context.

3 models·1 providers·$0.2600 to $0.7000/1M input

Top Picks

Compare Models

vs
Compare

Related Categories

Cost per 1M Tokens / Flagship Models

Input
Output

All Models with Caching

3 models
ProviderModelInput $/1MOutput $/1MContextQuality
DeepSeekDeepseek V3.2$0.2600$0.3800163.8K
84.8Frontier
DeepSeekDeepseek Chat$0.3200$0.8900163.8K
83.4Frontier
DeepSeekDeepseek R1$0.7000$2.5064K
64.6Strong

Deploy your AI agent for $33/mo flat.

Managed Telegram bot hosting. We handle the infrastructure.

Any model. Any channel. Zero infrastructure.