Naar inhoud

Models with Prompt caching

Models supporting cached prompt prefixes for cost reduction.

89 models

OpenAI

gpt-6-astra

87%
Prompt caching ✓1.05M ctxTier A

OpenAI

gpt-6-luna

87%
Prompt caching ✓1.05M ctxTier B

Google Gemini

Gemini 3.5 Flash-Lite

84%
Prompt caching ✓1.048576M ctxTier B

Google Gemini

Gemini 3.7 Flash

72%
Prompt caching ✓1.048576M ctxTier B

OpenAI

gpt-5.5-2026-04-23

71%
Prompt caching ✓Tier A

OpenAI

gpt-4.1-mini

71%
Prompt caching ✓1.047576M ctxTier C

OpenAI

gpt-5.5

70%
Prompt caching ✓Tier C

OpenAI

gpt-5.1

70%
Prompt caching ✓Tier B

OpenAI

gpt-4.1-2025-04-14

69%
Prompt caching ✓Tier C

OpenAI

gpt-5.2

69%
Prompt caching ✓Tier B

OpenAI

gpt-4.1-mini-2025-04-14

69%
Prompt caching ✓Tier C

OpenAI

gpt-5.2-2025-12-11

67%
Prompt caching ✓Tier B

OpenAI

gpt-5.1-2025-11-13

67%
Prompt caching ✓Tier B

OpenAI

gpt-6.1-sol

67%
Prompt caching ✓1.05M ctxTier A

OpenAI

gpt-5.4-2026-03-05

67%
Prompt caching ✓Tier B

Anthropic

Claude Opus 4.6

66%
Prompt caching ✓200K ctxTier B

OpenAI

gpt-5.4

66%
Prompt caching ✓Tier A

OpenAI

gpt-4.1

66%
Prompt caching ✓1.047576M ctxTier B

OpenAI

gpt-5.4-mini-2026-03-17

65%
Prompt caching ✓Tier A

OpenAI

gpt-4o-2024-05-13

63%
Prompt caching ✓Tier C

OpenAI

gpt-5.4-mini

63%
Prompt caching ✓Tier A

OpenAI

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

63%
Prompt caching ✓Tier B

OpenAI

o1

63%
Prompt caching ✓200K ctxTier C

Anthropic

Claude Opus 4.7

63%
Prompt caching ✓1M ctxTier B

Google Gemini

Gemini Flash-Lite Latest

63%
Prompt caching ✓1.048576M ctxTier C

OpenAI

gpt-4o

63%
Prompt caching ✓128K ctxTier C

OpenAI

o3-2025-04-16

62%
Prompt caching ✓Tier B

OpenAI

o3

61%
Prompt caching ✓200K ctxTier C

Anthropic

Claude Opus 4.5

61%
Prompt caching ✓200K ctxTier B

OpenAI

gpt-5-search-api

61%
Prompt caching ✓Tier C

OpenAI

gpt-5.6-sol

61%
Prompt caching ✓1.05M ctxTier B

Google Gemini

Gemini 3.1 Flash Lite

60%
Prompt caching ✓1.048576M ctxTier B

OpenAI

o1-2024-12-17

60%
Prompt caching ✓Tier C

Anthropic

Claude Fable 5

60%
Prompt caching ✓1M ctxTier A

Google Gemini

Nano Banana

60%
Prompt caching ✓33K ctxTier Barchived

Google Gemini

Gemini 3.8 Flash

60%
Prompt caching ✓1.048576M ctxTier A

OpenAI

o4-mini-2025-04-16

59%
Prompt caching ✓Tier B

OpenAI

gpt-4o-2024-08-06

59%
Prompt caching ✓Tier C

Anthropic

Claude Sonnet 4.5

59%
Prompt caching ✓200K ctxTier B

OpenAI

o3-mini-2025-01-31

58%
Prompt caching ✓Tier C

OpenAI

gpt-4.1-nano-2025-04-14

58%
Prompt caching ✓Tier C

Anthropic

Claude Opus 4.8

58%
Prompt caching ✓1M ctxTier A

OpenAI

gpt-4o-2024-11-20

58%
Prompt caching ✓Tier C

OpenAI

gpt-4-turbo-2024-04-09

57%
Prompt caching ✓Tier C

Google Gemini

Nano Banana 2 (preview)

57%
Prompt caching ✓66K ctxTier B

Anthropic

Claude Sonnet 4.6

57%
Prompt caching ✓1M ctxTier A

OpenAI

o4-mini

57%
Prompt caching ✓Tier C

OpenAI

gpt-4o-mini

57%
Prompt caching ✓128K ctxTier C

OpenAI

gpt-4-turbo

57%
Prompt caching ✓128K ctxTier C

OpenAI

gpt-4.1-nano

57%
Prompt caching ✓1.047576M ctxTier C

OpenAI

gpt-5.4-nano-2026-03-17

56%
Prompt caching ✓Tier A

OpenAI

gpt-5.6-luna

56%
Prompt caching ✓1.05M ctxTier B

OpenAI

gpt-6-sol

56%
Prompt caching ✓1.05M ctxTier A

Anthropic

Claude Sonnet 5

55%
Prompt caching ✓1M ctxTier A

OpenAI

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

53%
Prompt caching ✓Tier C

OpenAI

gpt-5-mini

52%
Prompt caching ✓Tier C

Anthropic

Claude Haiku 4.5

50%
Prompt caching ✓200K ctxTier A

OpenAI

gpt-5.4-nano

50%
Prompt caching ✓Tier C

Anthropic

Claude Opus 5

50%
Prompt caching ✓1M ctxTier A

OpenAI

o3-mini

50%
Prompt caching ✓200K ctxTier C

OpenAI

gpt-5.6-terra

49%
Prompt caching ✓1.05M ctxTier B

OpenAI

gpt-5-mini-2025-08-07

48%
Prompt caching ✓Tier B

Google Gemini

Gemini 2.5 Flash-Lite

48%
Prompt caching ✓1.048576M ctxTier B

OpenAI

gpt-4

44%
Prompt caching ✓Tier C

OpenAI

gpt-4-0613

44%
Prompt caching ✓Tier Carchived

Google Gemini

Gemini 3 Flash Preview

40%
Prompt caching ✓1.048576M ctxTier C

OpenAI

gpt-3.5-turbo-0125

40%
Prompt caching ✓Tier C

OpenAI

gpt-3.5-turbo

39%
Prompt caching ✓Tier C

OpenAI

gpt-5

39%
Prompt caching ✓Tier C

OpenAI

gpt-3.5-turbo-16k

38%
Prompt caching ✓Tier C

OpenAI

gpt-5-2025-08-07

38%
Prompt caching ✓Tier B

Google Gemini

Gemini Flash Latest

33%
Prompt caching ✓1.048576M ctxTier B

OpenAI

gpt-5-nano-2025-08-07

32%
Prompt caching ✓Tier B

Google Gemini

Gemini 3.5 Flash

25%
Prompt caching ✓1.048576M ctxTier A

OpenAI

gpt-5-nano

23%
Prompt caching ✓Tier C

Google Gemini

Nano Banana Pro (preview)

22%
Prompt caching ✓131K ctxTier A

Google Gemini

Gemini 3.1 Pro Preview

21%
Prompt caching ✓1.048576M ctxTier C

Google Gemini

Gemini 3.6 Flash

21%
Prompt caching ✓1.048576M ctxTier B

Google Gemini

Gemini 3.1 Pro Preview Custom Tools

21%
Prompt caching ✓1.048576M ctxTier C

Google Gemini

Gemini Pro Latest

19%
Prompt caching ✓1.048576M ctxTier C

Google Gemini

Gemini 2.5 Pro

17%
Prompt caching ✓1.048576M ctxTier A

Google Gemini

Gemini 2.5 Flash

13%
Prompt caching ✓1.048576M ctxTier A

Anthropic

Claude Fable 5.1

no data
Prompt caching ✓1M ctxTier A

Anthropic

Claude Opus 5.5

no data
Prompt caching ✓1M ctxTier A

Anthropic

Claude Sonnet 5.5

no data
Prompt caching ✓1M ctxTier A

Google Gemini

Deep Research Pro Preview (Dec-12-2025)

no data
Prompt caching ✓131K ctxTier B

OpenRouter

DeepSeek v3.2

no data
Prompt caching ✓131K ctxTier A

Google Gemini

Gemini 2.5 Pro Preview TTS

no data
Prompt caching ✓8K ctxTier B

OpenRouter

MiniMax M2.5

no data
Prompt caching ✓256K ctxTier A