AI Models with Prompt Caching Support
This page lists Large Language Models that offer Prompt Caching. Compare models, see how they implement this feature, and find the best option for projects requiring robust Prompt Caching.
Providers
Models with this Capability
Claude Sonnet 3.7
Anthropic · Claude 3
ID: claude-3-7-sonnet-20250219
Input
200K tokens
Output
64K tokens
Input Cost
$3.00/1M
Output Cost
$15.00/1M
Exceptional at:
Claude Haiku 3.5
Anthropic · Claude 3.5
ID: claude-3-5-haiku-20241022
Input
200K tokens
Output
8.2K tokens
Input Cost
$0.80/1M
Output Cost
$4.00/1M
Exceptional at:
Claude 3.5 Haiku
Anthropic · Claude 3.5
ID: anthropic-claude-3-5-haiku
Input
200K tokens
Output
8.2K tokens
Input Cost
$0.80/1M
Output Cost
$4.00/1M
Exceptional at:
Claude 3.5 Sonnet
Anthropic · Claude
ID: anthropic-claude-3-5-sonnet
Input
200K tokens
Output
4.1K tokens
Input Cost
$3.00/1M
Output Cost
$15.00/1M
Exceptional at:
Claude 3.5 Sonnet
Anthropic · Claude
ID: claude-3-5-sonnet-20241022
Input
200K tokens
Output
8.2K tokens
Input Cost
$3.00/1M
Output Cost
$15.00/1M
Claude Sonnet 3.5
Anthropic · Claude 3.5
ID: claude-3-5-sonnet-20240620
Input
200K tokens
Output
8.2K tokens
Input Cost
$3.00/1M
Output Cost
$15.00/1M
Claude Opus 4
Anthropic · Claude
ID: claude-opus-4-20250514
Input
200K tokens
Output
32K tokens
Input Cost
$15.00/1M
Output Cost
$75.00/1M
Exceptional at:
Claude Opus 3
Anthropic · Claude 3
ID: claude-3-opus-20240229
Input
200K tokens
Output
4.1K tokens
Input Cost
$15.00/1M
Output Cost
$75.00/1M
Exceptional at:
Claude 3.5 Sonnet
Anthropic · Claude
ID: claude-3-5-sonnet-latest
Input
200K tokens
Output
8.2K tokens
Input Cost
$3.00/1M
Output Cost
$15.00/1M
Claude 3.7 Sonnet
Anthropic · Claude 3
ID: anthropic-claude-3-7-sonnet
Input
200K tokens
Output
4.1K tokens
Input Cost
$3.00/1M
Output Cost
$15.00/1M
Exceptional at:
Claude Haiku 3.5
Anthropic · Claude
ID: claude-3-5-haiku-latest
Input
200K tokens
Output
8.2K tokens
Input Cost
$0.80/1M
Output Cost
$4.00/1M
Exceptional at:
Claude Opus 3
Anthropic · Claude 3
ID: claude-3-opus-latest
Input
200K tokens
Output
4.1K tokens
Input Cost
$15.00/1M
Output Cost
$75.00/1M
Exceptional at: