Aller au contenu

Models with Prompt caching

Models supporting cached prompt prefixes for cost reduction.

85 models

Google Gemini

Gemini 3.1 Flash Lite

99.1
Prompt caching1.048576M ctx

Google Gemini

Gemini Flash-Lite Latest

99.0
Prompt caching1.048576M ctxTier C

OpenAI

gpt-5-chat-latest

98.9
Prompt cachingTier C

Anthropic

Claude Opus 4.7

98.8
Prompt caching1M ctxTier B

Anthropic

Claude Opus 4.5

98.8
Prompt caching200K ctxTier B

Anthropic

Claude Opus 4.6

98.4
Prompt caching200K ctxTier B

Anthropic

Claude Opus 4.8

98.0
Prompt caching1M ctxTier A

Google Gemini

Nano Banana 2

97.7
Prompt caching66K ctx

Anthropic

Claude Opus 4

97.6
Prompt caching200K ctxTier C

Anthropic

Claude Opus 4.1

97.6
Prompt caching200K ctxTier C

OpenAI

gpt-4.1

97.4
Prompt caching1.047576M ctxTier B

OpenAI

gpt-4.1-mini

97.1
Prompt caching1.047576M ctxTier C

OpenAI

gpt-4.1-nano

96.9
Prompt caching1.047576M ctxTier C

Anthropic

Claude Sonnet 4.6

96.8
Prompt caching1M ctxTier A

Anthropic

Claude Sonnet 4

96.6
Prompt caching200K ctxTier C

OpenAI

gpt-4o-2024-11-20

96.1
Prompt cachingTier C

Google Gemini

Nano Banana

95.8
Prompt caching33K ctx

OpenAI

gpt-4.1-mini-2025-04-14

95.6
Prompt caching

OpenAI

gpt-4o-2024-08-06

95.6
Prompt cachingTier C

OpenAI

gpt-4o

95.6
Prompt caching128K ctxTier C

OpenAI

gpt-4.1-2025-04-14

95.6
Prompt caching

OpenAI

gpt-4.1-nano-2025-04-14

95.6
Prompt caching

Google Gemini

Gemini 3 Flash Preview

95.4
Prompt caching1.048576M ctxTier C

OpenAI

gpt-4o-2024-05-13

95.3
Prompt cachingTier C

OpenAI

gpt-4o-mini

93.9
Prompt caching128K ctxTier C

OpenAI

gpt-4o-mini-2024-07-18

93.9
Prompt cachingTier C

OpenAI

gpt-4-turbo

93.8
Prompt caching128K ctxTier C

OpenAI

gpt-4-0613

93.3
Prompt caching

Anthropic

Claude Sonnet 4.5

92.9
Prompt caching200K ctxTier B

Anthropic

Claude Haiku 4.5

92.9
Prompt caching200K ctxTier A

OpenAI

gpt-4-turbo-2024-04-09

92.8
Prompt cachingTier C

OpenAI

gpt-3.5-turbo-1106

92.3
Prompt caching

OpenAI

gpt-4o-search-preview-2025-03-11

92.1
Prompt caching

OpenAI

gpt-5-search-api-2025-10-14

91.5
Prompt caching

Google Gemini

Gemini 2.5 Flash-Lite

91.5
Prompt caching1.048576M ctxTier B

OpenAI

gpt-5-search-api

91.3
Prompt cachingTier C

OpenAI

gpt-4o-mini-search-preview-2025-03-11

90.8
Prompt caching

OpenAI

gpt-3.5-turbo

90.3
Prompt cachingTier C

OpenAI

gpt-4o-mini-search-preview

88.9
Prompt cachingTier C

OpenAI

gpt-3.5-turbo-0125

88.8
Prompt caching

OpenAI

gpt-4o-search-preview

84.9
Prompt cachingTier C

OpenAI

gpt-4

81.9
Prompt cachingTier C

Google Gemini

Nano Banana Pro

80.8
Prompt caching131K ctx

OpenAI

gpt-3.5-turbo-16k

76.8
Prompt caching

Google Gemini

Gemini 3.5 Flash

62.3
Prompt caching1.048576M ctxTier A

Google Gemini

Gemini Flash Latest

62.0
Prompt caching1.048576M ctxTier B

Google Gemini

Gemini 2.5 Flash

53.6
Prompt caching1.048576M ctxTier A

Google Gemini

Gemini 3.1 Pro Preview

53.1
Prompt caching1.048576M ctxTier C

Google Gemini

Gemini Pro Latest

50.6
Prompt caching1.048576M ctxTier C

Google Gemini

Gemini 3.1 Pro Preview Custom Tools

50.0
Prompt caching1.048576M ctxTier C

Google Gemini

Gemini 2.5 Pro

45.6
Prompt caching1.048576M ctxTier A

Anthropic

Claude Fable 5

no data
Prompt caching1M ctxTier A

Google Gemini

Deep Research Pro Preview (Dec-12-2025)

no data
Prompt caching131K ctx

OpenRouter

DeepSeek v3.2

no data
Prompt caching131K ctxTier A

Google Gemini

Gemini 2.5 Pro Preview TTS

no data
Prompt caching8K ctx

OpenAI

gpt-5

no data
Prompt cachingTier C

OpenAI

gpt-5-2025-08-07

no data
Prompt caching

OpenAI

gpt-5-mini

no data
Prompt cachingTier C

OpenAI

gpt-5-mini-2025-08-07

no data
Prompt caching

OpenAI

gpt-5-nano

no data
Prompt cachingTier C

OpenAI

gpt-5-nano-2025-08-07

no data
Prompt caching

OpenAI

gpt-5.1

no data
Prompt cachingTier B

OpenAI

gpt-5.1-2025-11-13

no data
Prompt caching

OpenAI

gpt-5.1-chat-latest

no data
Prompt cachingTier C

OpenAI

gpt-5.2

no data
Prompt cachingTier B

OpenAI

gpt-5.2-2025-12-11

no data
Prompt caching

OpenAI

gpt-5.2-chat-latest

no data
Prompt cachingTier C

OpenAI

gpt-5.3-chat-latest

no data
Prompt cachingTier C

OpenAI

gpt-5.4

no data
Prompt cachingTier A

OpenAI

gpt-5.4-2026-03-05

no data
Prompt caching

OpenAI

gpt-5.4-mini

no data
Prompt cachingTier A

OpenAI

gpt-5.4-mini-2026-03-17

no data
Prompt caching

OpenAI

gpt-5.4-nano

no data
Prompt cachingTier C

OpenAI

gpt-5.4-nano-2026-03-17

no data
Prompt caching

OpenAI

gpt-5.5

no data
Prompt cachingTier C

OpenAI

gpt-5.5-2026-04-23

no data
Prompt caching

OpenRouter

MiniMax M2.5

no data
Prompt caching256K ctxTier A

OpenAI

o1

no data
Prompt caching200K ctxTier C

OpenAI

o1-2024-12-17

no data
Prompt cachingTier C

OpenAI

o3

no data
Prompt caching200K ctxTier C

OpenAI

o3-2025-04-16

no data
Prompt caching

OpenAI

o3-mini

no data
Prompt caching200K ctxTier C

OpenAI

o3-mini-2025-01-31

no data
Prompt caching

OpenAI

o4-mini

no data
Prompt cachingTier C

OpenAI

o4-mini-2025-04-16

no data
Prompt caching