Prompt caching can cut costs by ~90% for workloads with repeated system prompts (RAG, long-context chat, structured workflows). Ranked by cached-input price ascending so you can see the actual savings rate per model.
Methodology
How this ranking is built
Active models offering prompt caching with a published cached-input price. Ranked from cheapest cached-input cost upward — that's the rate you actually pay on cache hits, which is where the savings live.
#
Model
Provider
Cached input price
Lifecycle
Verified
1
Gemini 2.5 Flash-Lite
Google Gemini · Active
GGGoogle Gemini
$0.01/M cached
Active
· 51m ago
2
Gemini 3.1 Flash-Lite
Google Gemini · Active
GGGoogle Gemini
$0.0125/M cached
Active
· 51m ago
3
GPT-5.4 Nano
OpenAI · Active
OPOpenAI
$0.02/M cached
Active
· 45m ago
4
GPT-5 Mini
OpenAI · Active
OPOpenAI
$0.025/M cached
Active
· 46m ago
5
Gemini 3.1 Flash Image 🍌
Google Gemini · Active
GGGoogle Gemini
$0.025/M cached
Active
· 51m ago
6
Gemini 2.5 Flash
Google Gemini · Active
GGGoogle Gemini
$0.03/M cached
Active
· 51m ago
7
GPT-4o Mini
OpenAI · Active
OPOpenAI
$0.075/M cached
Active
· 46m ago
8
GPT-5.4 Mini
OpenAI · Active
OPOpenAI
$0.075/M cached
Active
· 45m ago
9
Claude Haiku 3.5
Anthropic · Active
ANAnthropic
$0.08/M cached
Active
· 55m ago
10
GPT-4.1 Mini
OpenAI · Active
OPOpenAI
$0.1/M cached
Active
· 46m ago
11
Claude Haiku 4.5
Anthropic · Active
ANAnthropic
$0.1/M cached
Active
· 55m ago
12
GPT-5
OpenAI · Active
OPOpenAI
$0.125/M cached
Active
· 46m ago
13
GPT-5.1
OpenAI · Active
OPOpenAI
$0.125/M cached
Active
· 46m ago
14
Gemini 2.5 Pro
Google Gemini · Active
GGGoogle Gemini
$0.125/M cached
Active
· 51m ago
15
Gemini 3.5 Flash
Google Gemini · Active
GGGoogle Gemini
$0.15/M cached
Active
· 50m ago
16
Gemini 3.1 Flash Image Preview 🍌
Google Gemini · Active
GGGoogle Gemini
$0.151/M cached
Active
· 51m ago
17
GPT-5.2
OpenAI · Active
OPOpenAI
$0.175/M cached
Active
· 45m ago
18
Grok 4.20
xAI · Active
XAxAI
$0.2/M cached
Active
· 43m ago
19
Grok 4.3
xAI · Active
XAxAI
$0.2/M cached
Active
· 43m ago
20
Grok Build 0.1
xAI · Active
XAxAI
$0.2/M cached
Active
· 43m ago
21
GPT-5.4
OpenAI · Active
OPOpenAI
$0.25/M cached
Active
· 45m ago
22
o4-mini
OpenAI · Active
OPOpenAI
$0.275/M cached
Active
· 43m ago
23
Claude Sonnet 4
Anthropic · Active
ANAnthropic
$0.3/M cached
Active
· 54m ago
24
Claude Sonnet 4.5
Anthropic · Active
ANAnthropic
$0.3/M cached
Active
· 54m ago
25
Claude Sonnet 4.6
Anthropic · Active
ANAnthropic
$0.3/M cached
Active
· 54m ago
Showing top 25 of 34 matches. Refreshed as we re-verify each model against its provider's official docs. Every value links to the page it came from.
Last updated Jun 15, 2026 08:56 UTC.
We use cookies to enhance your browsing experience and analyze site traffic.
By continuing to use our site, you consent to our use of cookies.
Learn more