Cache Read Price

Artificial Analysis · 50 models

Rank	Model	Score
1	MiMo-V2.5	0.0028
1	MiMo-V2.6-Flash	0.0028
3	MiMo-V2.6-Pro	0.0036
4	GPT-5 nano (High)	0.005
4	GPT-5 nano (Medium)	0.005
4	GPT-5 nano (Minimal)	0.005
7	DeepSeek V4.1 Flash (Max)	0.006
7	DeepSeek V4.1 Flash 1017 (High)	0.006
7	DeepSeek V4.1 Flash 1017 (Max)	0.006
7	DeepSeek V4.1 Flash 1017 (Non-reasoning)	0.006
11	Nova Micro	0.0088
12	Quasar 438B (Max, Based on GLM-5.2)	0.0099
13	Agnes 2.5 Pro Beta	0.01
13	Claude Haiku 5.5 (High)	0.01
13	Claude Haiku 5.5 (Low)	0.01
13	Claude Haiku 5.5 (Max)	0.01
13	Claude Haiku 5.5 (Medium)	0.01
13	Claude Haiku 5.5 (Xhigh)	0.01
13	GLM-4.7-Flash (Reasoning)	0.01
13	GPT-6 Luna (High)	0.01
13	GPT-6 Luna (Low)	0.01
13	GPT-6 Luna (Max)	0.01
13	GPT-6 Luna (Medium)	0.01
13	GPT-6 Luna (Non-reasoning)	0.01
13	GPT-6 Luna (Xhigh)	0.01
13	Gemini 2.5 Flash-Lite (Non-reasoning)	0.01
13	Gemini 2.5 Flash-Lite (Reasoning)	0.01
13	Gemini 2.5 Flash-Lite Preview (Sep '25) (Non-reasoning)	0.01
13	Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning)	0.01
13	Ministral 3 3B	0.01
13	Solar Mini 4	0.01
32	DeepSeek V4.1 Flash (Non-reasoning)	0.0105
33	MiMo-V2.5-Pro (Reasoning)	0.0118
34	DeepSeek V3.2 (Reasoning)	0.014
34	DeepSeek V4 Flash Vision (Max)	0.014
36	Granite 4.2 8B	0.015
36	Ling 3.0 Flash	0.015
36	LongCat 2.0	0.015
36	MiniMax-M3.1-Flash	0.015
36	Ministral 3 8B	0.015
36	Mistral Small 4 (Non-reasoning)	0.015
36	Mistral Small 4 (Reasoning)	0.015
36	Nova Lite	0.015
36	Solar Pro 3	0.015
45	Qwen3.8-Flash-Next	0.016
46	DeepSeek V4 Flash 0420 (Non-reasoning)	0.019
47	Celeris-1	0.02
47	GPT-5.4 nano (Medium)	0.02
47	GPT-5.4 nano (Non-reasoning)	0.02
47	GPT-5.4 nano (Xhigh)	0.02