Skip to content

Models with Prompt caching

Models supporting cached prompt prefixes for cost reduction.

76 models

OpenAI

gpt-5.5-2026-04-23

73%
Prompt cachingTier A

OpenAI

gpt-5.1

73%
Prompt cachingTier B

OpenAI

gpt-4.1-mini

72%
Prompt caching1.047576M ctxTier C

OpenAI

gpt-4.1-2025-04-14

71%
Prompt cachingTier C

OpenAI

gpt-5.5

70%
Prompt cachingTier C

OpenAI

gpt-5.2-2025-12-11

70%
Prompt cachingTier B

OpenAI

gpt-4.1

70%
Prompt caching1.047576M ctxTier B

OpenAI

gpt-5.2

70%
Prompt cachingTier B

OpenAI

gpt-5.4-mini

69%
Prompt cachingTier A

Anthropic

Claude Opus 4.6

69%
Prompt caching200K ctxTier Barchived

OpenAI

gpt-4.1-mini-2025-04-14

69%
Prompt cachingTier C

OpenAI

gpt-5.4-2026-03-05

68%
Prompt cachingTier B

OpenAI

gpt-5.4

68%
Prompt cachingTier A

OpenAI

gpt-5.1-2025-11-13

67%
Prompt cachingTier B

OpenAI

gpt-4o-2024-05-13

66%
Prompt cachingTier Carchived

OpenAI

gpt-4o

65%
Prompt caching128K ctxTier C

OpenAI

gpt-5.4-mini-2026-03-17

65%
Prompt cachingTier A

OpenAI

gpt-5-search-api

65%
Prompt cachingTier C

OpenAI

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

64%
Prompt cachingTier B

Anthropic

Claude Opus 4.5

64%
Prompt caching200K ctxTier Barchived

Anthropic

Claude Sonnet 5

63%
Prompt caching1M ctxTier Aarchived

Anthropic

Claude Opus 4.7

63%
Prompt caching1M ctxTier Barchived

Google Gemini

Gemini Flash-Lite Latest

62%
Prompt caching1.048576M ctxTier C

Google Gemini

Nano Banana

62%
Prompt caching33K ctxTier Barchived

OpenAI

gpt-4o-mini

62%
Prompt caching128K ctxTier C

OpenAI

gpt-4.1-nano-2025-04-14

62%
Prompt cachingTier Carchived

OpenAI

o1

62%
Prompt caching200K ctxTier Carchived

Anthropic

Claude Sonnet 4.6

62%
Prompt caching1M ctxTier Aarchived

OpenAI

o1-2024-12-17

61%
Prompt cachingTier Carchived

Anthropic

Claude Fable 5

61%
Prompt caching1M ctxTier Aarchived

OpenAI

gpt-4o-2024-11-20

61%
Prompt cachingTier C

OpenAI

o4-mini

61%
Prompt cachingTier Carchived

OpenAI

gpt-4o-2024-08-06

60%
Prompt cachingTier C

OpenAI

gpt-4-turbo-2024-04-09

60%
Prompt cachingTier Carchived

Anthropic

Claude Sonnet 4.5

60%
Prompt caching200K ctxTier Barchived

OpenAI

o3

60%
Prompt caching200K ctxTier C

Google Gemini

Nano Banana 2

60%
Prompt caching66K ctxTier B

OpenAI

o3-mini-2025-01-31

60%
Prompt cachingTier Carchived

OpenAI

gpt-4-turbo

59%
Prompt caching128K ctxTier Carchived

OpenAI

o4-mini-2025-04-16

59%
Prompt cachingTier Barchived

OpenAI

gpt-5.4-nano-2026-03-17

59%
Prompt cachingTier A

OpenAI

o3-2025-04-16

58%
Prompt cachingTier Barchived

Google Gemini

Gemini 3.1 Flash Lite

58%
Prompt caching1.048576M ctxTier Barchived

Anthropic

Claude Opus 4.8

58%
Prompt caching1M ctxTier Aarchived

OpenAI

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

58%
Prompt cachingTier C

OpenAI

gpt-4.1-nano

57%
Prompt caching1.047576M ctxTier Carchived

Anthropic

Claude Haiku 4.5

55%
Prompt caching200K ctxTier Aarchived

OpenAI

gpt-5.4-nano

52%
Prompt cachingTier C

Google Gemini

Gemini 2.5 Flash-Lite

50%
Prompt caching1.048576M ctxTier Barchived

OpenAI

o3-mini

50%
Prompt caching200K ctxTier Carchived

OpenAI

gpt-5-mini

49%
Prompt cachingTier C

Anthropic

Claude Opus 5

49%
Prompt caching1M ctxTier Aarchived

OpenAI

gpt-4

49%
Prompt cachingTier Carchived

OpenAI

gpt-4-0613

48%
Prompt cachingTier Carchived

OpenAI

gpt-3.5-turbo-1106

46%
Prompt cachingTier Carchived

OpenAI

gpt-5-mini-2025-08-07

45%
Prompt cachingTier Barchived

OpenAI

gpt-3.5-turbo-0125

45%
Prompt cachingTier Carchived

OpenAI

gpt-3.5-turbo-16k

42%
Prompt cachingTier Carchived

OpenAI

gpt-3.5-turbo

40%
Prompt cachingTier Carchived

OpenAI

gpt-5

40%
Prompt cachingTier C

Google Gemini

Gemini 3 Flash Preview

40%
Prompt caching1.048576M ctxTier C

OpenAI

gpt-5-2025-08-07

39%
Prompt cachingTier Barchived

Google Gemini

Gemini Flash Latest

34%
Prompt caching1.048576M ctxTier B

OpenAI

gpt-5-nano-2025-08-07

28%
Prompt cachingTier Barchived

Google Gemini

Gemini 3.5 Flash

24%
Prompt caching1.048576M ctxTier Aarchived

OpenAI

gpt-5-nano

24%
Prompt cachingTier C

Google Gemini

Nano Banana Pro

23%
Prompt caching131K ctxTier A

Google Gemini

Gemini 3.1 Pro Preview Custom Tools

22%
Prompt caching1.048576M ctxTier C

Google Gemini

Gemini 3.1 Pro Preview

21%
Prompt caching1.048576M ctxTier C

Google Gemini

Gemini Pro Latest

19%
Prompt caching1.048576M ctxTier C

Google Gemini

Gemini 2.5 Pro

17%
Prompt caching1.048576M ctxTier Aarchived

Google Gemini

Gemini 2.5 Flash

15%
Prompt caching1.048576M ctxTier Aarchived

Google Gemini

Deep Research Pro Preview (Dec-12-2025)

no data
Prompt caching131K ctxTier B

OpenRouter

DeepSeek v3.2

no data
Prompt caching131K ctxTier A

Google Gemini

Gemini 2.5 Pro Preview TTS

no data
Prompt caching8K ctxTier B

OpenRouter

MiniMax M2.5

no data
Prompt caching256K ctxTier A