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
Google
Google
Google
Models with this Capability
Gemini 2.0 Flash
Google · Gemini
Current
Input
1M tokens
Output
0 tokens
Input Cost
$0.10/1M
Output Cost
$0.40/1M
Exceptional at:
instruction following
multimodal input
long context
vision
+14
Gemini 1.5 Flash-8B
Google · Gemini
Current
Input
1M tokens
Output
0 tokens
Input Cost
$0.04/1M
Output Cost
$0.15/1M
multimodal input
long context
vision
+4
Gemini 1.5 Flash
Google · Gemini
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
multimodal input
long context
context caching
+2
Similar Capabilities
Multimodal Input
Found in 4 models with Context Caching
40 total models
Long Context
Found in 4 models with Context Caching
23 total models
Vision
Found in 3 models with Context Caching
18 total models
Thinking
Found in 2 models with Context Caching
4 total models
Tuning
Found in 3 models with Context Caching
3 total models
Grounding With Google Search
Found in 2 models with Context Caching
3 total models