Logo

AI Models with Context Caching Support

This page lists Large Language Models that offer Context Caching. Compare models, see how they implement this feature, and find the best option for projects requiring robust Context Caching.

Providers

Google

Models with this Capability

Gemini 2.0 Flash

Google · Gemini

ID: google-gemini-2.0-flash-live

Current

Input

1M tokens

Output

0 tokens

Input Cost

$0.10/1M

Output Cost

$0.40/1M

Exceptional at:

instruction following

Gemini 1.5 Flash-8B

Google · Gemini

ID: google-gemini-1.5-flash-8b

Current

Input

1M tokens

Output

0 tokens

Input Cost

$0.04/1M

Output Cost

$0.15/1M

Gemini 1.5 Flash

Google · Gemini

ID: google-gemini-1.5-flash

Current

Input

1M tokens

Output

1M tokens

Input Cost

$0.07/1M

Output Cost

$0.30/1M

Exceptional at:

long context processing
multimodal understanding
+3

Gemini 2.5 Pro Preview

Google · Gemini

ID: google-gemini-2.5-pro-preview

preview

Input

1M tokens

Output

0 tokens

Input Cost

$1.25/1M

Output Cost

$10.00/1M

Exceptional at:

complex reasoning
coding
+7

Similar Capabilities