Skip to content

🏆 AI Model Performance Leaderboard

Compare 253AI models by quality, cost & value

253 Models·60 GPUs·19 Providers
🥇#1Most Popular
Alibaba

Qwen 2.5 7B

Qwen 2.5 · 7.6B · 128K ctx

Quality
70
Cost $/M
$0.200
Value
350.0
Calculate ROI
🥈#2
Alibaba

Qwen 3 8B

Qwen 3 · 8.2B · 128K ctx

Quality
67
Cost $/M
$0.200
Value
335.0
Calculate ROI
🥉#3
Alibaba

Qwen 2.5 1.5B

Qwen 2.5 · 1.5B · 32K ctx

Quality
50
Cost $/M~
$0.027
Value
1862.0
Calculate ROI
#4
Alibaba

Qwen 2.5 3B

Qwen 2.5 · 3.1B · 32K ctx

Quality
58
Cost $/M
$0.100
Value
580.0
Calculate ROI
#5
Meta

Llama 3.1 8B

Llama 3.1 · 8B · 128K ctx

Quality
65
Cost $/M
$0.080
Value
812.5
Calculate ROI
#6
Alibaba

Qwen 3 4B

Qwen 3 · 4B · 128K ctx

Quality
57
Cost $/M
$0.100
Value
570.0
Calculate ROI
#7
Meta

Llama 3.2 3B

Llama 3.2 · 3.2B · 128K ctx

Quality
55
Cost $/M
$0.060
Value
916.7
Calculate ROI
#8
Alibaba

Qwen 3 32B

Qwen 3 · 32.8B · 128K ctx

Quality
80
Cost $/M
$0.800
Value
100.0
Calculate ROI
#9
Meta

Llama 3.2 1B

Llama 3.2 · 1.2B · 128K ctx

Quality
38
Cost $/M
$0.030
Value
1266.7
Calculate ROI
#10
Meta

Llama 3 8B

Llama 3 · 8B · 8K ctx

Quality
63
Cost $/M
$0.200
Value
315.0
Calculate ROI
#11
Meta

HelpSteer2 Llama 3.1 70B

Llama 3.1 · 70.6B · 128K ctx

Quality
82
Cost $/M
$0.500
Value
164.0
Calculate ROI
#12
Meta

Llama 3.1 70B

Llama 3.1 · 70.6B · 128K ctx

Quality
82
Cost $/M
$0.790
Value
103.8
Calculate ROI
#13
Meta

Llama 3.1 70B Turbo

Llama 3.1 · 70.6B · 128K ctx

Quality
50
Cost $/M
$0.880
Value
56.8
Calculate ROI
#14
Mistral

NV EmbedQA Mistral 7B

NV EmbedQA · 7.2B · 32K ctx

Quality
50
Cost $/M
$0.012
Value
4166.7
Calculate ROI
#15
Mistral

E5 Mistral 7B

E5 · 7.1B · 32K ctx

Quality
50
Cost $/M
$0.016
Value
3125.0
Calculate ROI
#16
Google

Gemma 3 1B

Gemma 3 · 1B · 32K ctx

Quality
35
Cost $/M~
$0.018
Value
1955.1
Calculate ROI
#17
Mistral

Mistral 7B

Mistral · 7.3B · 32K ctx

Quality
56
Cost $/M
$0.070
Value
800.0
Calculate ROI
#18
Mistral

BioMistral 7B

BioMistral · 7.2B · 32K ctx

Quality
50
Cost $/M~
$0.129
Value
387.9
Calculate ROI
#19
Meta

TinyLlama 1.1B

TinyLlama · 1.1B · 2K ctx

Quality
50
Cost $/M~
$0.021
Value
2412.1
Calculate ROI
#20
Meta

TinyLlama 1.1B Chat

TinyLlama · 1.1B · 2K ctx

Quality
50
Cost $/M~
$0.021
Value
2412.1
Calculate ROI
#21
Alibaba

Qwen 2.5 14B

Qwen 2.5 · 14.8B · 128K ctx

Quality
76
Cost $/M
$0.300
Value
253.3
Calculate ROI
#22
Alibaba

Qwen 2.5 72B

Qwen 2.5 · 72.7B · 128K ctx

Quality
84
Cost $/M
$0.900
Value
93.3
Calculate ROI
#23
Microsoft

Phi 2

Phi · 2.7B · 2K ctx

Quality
50
Cost $/M~
$0.054
Value
931.0
Calculate ROI
#24
Alibaba

Qwen 2.5 32B

Qwen 2.5 · 32.5B · 128K ctx

Quality
81
Cost $/M
$0.800
Value
101.3
Calculate ROI
#25
DeepSeek

DeepSeek R1 Distill 1.5B

DeepSeek R1 · 1.5B · 128K ctx

Quality
42
Cost $/M~
$0.027
Value
1564.1
Calculate ROI
#26
DeepSeek

DeepSeek R1 Distill 8B

DeepSeek R1 · 8B · 128K ctx

Quality
50
Cost $/M
$0.200
Value
250.0
Calculate ROI
#27
DeepSeek

DeepSeek R1 Distill 14B

DeepSeek R1 · 14.8B · 128K ctx

Quality
50
Cost $/M
$0.300
Value
166.7
Calculate ROI
#28
DeepSeek

DeepSeek R1 Distill 32B

DeepSeek R1 · 32.8B · 128K ctx

Quality
50
Cost $/M
$0.500
Value
100.0
Calculate ROI
#29
DeepSeek

DeepSeek R1 Distill 70B

DeepSeek R1 · 70.6B · 128K ctx

Quality
50
Cost $/M
$0.880
Value
56.8
Calculate ROI
#30
DeepSeek

DeepSeek R1

DeepSeek R1 · 671B MoE (37B active) · 128K ctx

Quality
92
Cost $/M
$2.19
Value
42.0
Calculate ROI
#31
DeepSeek

DeepSeek V3

DeepSeek V3 · 671B MoE (37B active) · 128K ctx

Quality
86
Cost $/M
$0.420
Value
204.8
Calculate ROI
#32
Meta

Llama 3 70B

Llama 3 · 70.6B · 8K ctx

Quality
80
Cost $/M
$0.880
Value
90.9
Calculate ROI
#33
Meta

Llama 3 70B 1M Context

Llama 3 · 70.6B · 1024K ctx

Quality
50
Cost $/M
$1.50
Value
33.3
Calculate ROI
#34
Mistral

Mixtral 8x7B

Mixtral · 46.7B MoE (12.9B active) · 32K ctx

Quality
67
Cost $/M
$0.500
Value
134.0
Calculate ROI
#35
Mistral

Mixtral 8x7B Instruct

Mixtral · 46.7B MoE (12.9B active) · 32K ctx

Quality
69
Cost $/M
$0.600
Value
115.0
Calculate ROI
#36
Google

Gemma 2 9B

Gemma 2 · 9.2B · 8K ctx

Quality
68
Cost $/M
$0.100
Value
680.0
Calculate ROI
#37
Microsoft

Phi 4 Mini

Phi · 3.8B · 128K ctx

Quality
70
Cost $/M~
$0.068
Value
1029.0
Calculate ROI
#38
Microsoft

Phi-4

Phi · 14.7B · 16K ctx

Quality
83
Cost $/M
$0.140
Value
592.9
Calculate ROI
#39
Meta

Llama 2 7B

Llama 2 · 7B · 4K ctx

Quality
40
Cost $/M~
$0.125
Value
319.2
Calculate ROI
#40
Meta

Llama 2 13B

Llama 2 · 13B · 4K ctx

Quality
47
Cost $/M~
$0.233
Value
202.0
Calculate ROI
#41
Meta

Llama 2 70B

Llama 2 · 70B · 4K ctx

Quality
62
Cost $/M
$0.900
Value
68.9
Calculate ROI
#42
Meta

Llama Guard 3 1B

Llama Guard · 1B · 128K ctx

Quality
50
Cost $/M~
$0.019
Value
2653.3
Calculate ROI
#43
Meta

Llama 3.2 11B Vision

Llama 3.2 · 11B · 128K ctx

Quality
50
Cost $/M
$0.180
Value
277.8
Calculate ROI
#44
Meta

Llama 3.3 8B

Llama 3.3 · 8B · 128K ctx

Quality
50
Cost $/M
$0.180
Value
277.8
Calculate ROI
#45
Meta

Llama 4 Scout

Llama 4 · 109B MoE (17B active) · 10240K ctx

Quality
76
Cost $/M
$0.300
Value
253.3
Calculate ROI
#46
Meta

Llama Guard 3 8B

Llama Guard · 8B · 128K ctx

Quality
50
Cost $/M
$0.200
Value
250.0
Calculate ROI
#47
Meta

Code Llama 13B

Code Llama · 13B · 16K ctx

Quality
44
Cost $/M
$0.220
Value
200.0
Calculate ROI
#48
Meta

Code Llama 7B

Code Llama · 7B · 16K ctx

Quality
39
Cost $/M
$0.200
Value
195.0
Calculate ROI
#49
Meta

Llama 3.1 Nemotron 51B

Llama 3.1 · 51B · 128K ctx

Quality
78
Cost $/M
$0.400
Value
195.0
Calculate ROI
#50
Meta

Llama 3.1 Nemotron 70B Reward

Llama 3.1 · 70.6B · 128K ctx

Quality
80
Cost $/M
$0.500
Value
160.0
Calculate ROI
#51
Meta

Llama 3.3 70B

Llama 3.3 · 70.6B · 128K ctx

Quality
84
Cost $/M
$0.790
Value
106.3
Calculate ROI
#52
Meta

Llama 3.1 Nemotron 70B Instruct

Llama 3.1 · 70.6B · 128K ctx

Quality
83
Cost $/M
$0.880
Value
94.3
Calculate ROI
#53
Meta

Code Llama 34B

Code Llama · 34B · 98K ctx

Quality
55
Cost $/M
$0.780
Value
70.5
Calculate ROI
#54
Meta

Llama 3.2 90B Vision Instruct

Llama 3.2 · 88.8B · 128K ctx

Quality
84
Cost $/M
$1.20
Value
70.0
Calculate ROI
#55
Meta

Code Llama 70B

Code Llama · 70B · 16K ctx

Quality
60
Cost $/M
$0.900
Value
66.7
Calculate ROI
#56
Meta

Llama 3.2 90B Vision

Llama 3.2 · 90B · 128K ctx

Quality
50
Cost $/M
$0.900
Value
55.6
Calculate ROI
#57
Meta

Llama 4 Maverick

Llama 4 · 400B MoE (17B active) · 1024K ctx

Quality
89
Cost $/M
$1.80
Value
49.4
Calculate ROI
#58
Meta

Llama 3.1 405B

Llama 3.1 · 405B · 128K ctx

Quality
88
Cost $/M
$3.00
Value
29.3
Calculate ROI
#59
Meta

Llama 4 Behemoth

Llama 4 · 2000B MoE (400B active) · 1024K ctx

Quality
93
Cost $/M
$16.00
Value
5.8
Calculate ROI
#60
Alibaba

Qwen 2.5 0.5B

Qwen 2.5 · 500M · 32K ctx

Quality
50
Cost $/M~
$0.0094
Value
5306.6
Calculate ROI
#61
Alibaba

Qwen 3 0.6B

Qwen 3 · 600M · 128K ctx

Quality
50
Cost $/M~
$0.011
Value
4654.9
Calculate ROI
#62
Alibaba

GTE Qwen2 7B

GTE · 7.6B · 32K ctx

Quality
50
Cost $/M
$0.016
Value
3125.0
Calculate ROI
#63
Alibaba

Qwen 3 1.7B

Qwen 3 · 1.7B · 128K ctx

Quality
50
Cost $/M~
$0.030
Value
1642.9
Calculate ROI
#64
Alibaba

Qwen 2.5 Coder 1.5B

Qwen 2.5 Coder · 1.5B · 32K ctx

Quality
40
Cost $/M~
$0.027
Value
1489.6
Calculate ROI
#65
Alibaba

Qwen 2 VL 2B

Qwen 2 VL · 2.2B · 32K ctx

Quality
50
Cost $/M~
$0.039
Value
1269.5
Calculate ROI
#66
Alibaba

Qwen 3 30B-A3B

Qwen 3 · 30.5B MoE (3.3B active) · 128K ctx

Quality
70
Cost $/M~
$0.059
Value
1184.9
Calculate ROI
#67
Alibaba

Qwen 1.5 MoE A2.7B

Qwen 1.5 · 14.3B MoE (2.7B active) · 32K ctx

Quality
50
Cost $/M~
$0.048
Value
1034.4
Calculate ROI
#68
Alibaba

Qwen 2.5 Coder 3B

Qwen 2.5 Coder · 3.1B · 32K ctx

Quality
50
Cost $/M~
$0.055
Value
901.0
Calculate ROI
#69
Alibaba

Qwen 2 Audio 7B

Qwen 2 · 7.6B · 32K ctx

Quality
50
Cost $/M~
$0.136
Value
367.5
Calculate ROI
#70
Alibaba

Qwen 2.5 Coder 7B

Qwen 2.5 Coder · 7.6B · 128K ctx

Quality
50
Cost $/M
$0.200
Value
250.0
Calculate ROI
#71
Alibaba

Qwen 2.5 Math 7B

Qwen 2.5 Math · 7.6B · 4K ctx

Quality
50
Cost $/M
$0.200
Value
250.0
Calculate ROI
#72
Alibaba

Qwen 2.5 VL 7B

Qwen 2.5 VL · 7.6B · 128K ctx

Quality
50
Cost $/M
$0.200
Value
250.0
Calculate ROI
#73
Alibaba

Qwen 2.5 Coder 14B

Qwen 2.5 Coder · 14.7B · 128K ctx

Quality
50
Cost $/M
$0.300
Value
166.7
Calculate ROI
#74
Alibaba

Qwen 2.5 Coder 32B

Qwen 2.5 · 32.5B · 128K ctx

Quality
50
Cost $/M
$0.800
Value
62.5
Calculate ROI
#75
Alibaba

Qwen 2.5 Math 72B

Qwen 2.5 Math · 72.7B · 4K ctx

Quality
50
Cost $/M
$0.900
Value
55.6
Calculate ROI
#76
Alibaba

Qwen 2.5 VL 72B

Qwen 2.5 VL · 72.7B · 128K ctx

Quality
50
Cost $/M
$0.900
Value
55.6
Calculate ROI
#77
Alibaba

Qwen 3 235B

Qwen 3 · 235B MoE (22B active) · 128K ctx

Quality
88
Cost $/M
$3.00
Value
29.3
Calculate ROI
#78
Mistral

Ministral 8B

Ministral · 8B · 128K ctx

Quality
50
Cost $/M
$0.100
Value
500.0
Calculate ROI
#79
Mistral

Mistral Nemo 12B

Mistral Nemo · 12B · 128K ctx

Quality
62
Cost $/M
$0.130
Value
476.9
Calculate ROI
#80
Mistral

Pixtral 12B

Pixtral · 12B · 128K ctx

Quality
50
Cost $/M
$0.150
Value
333.3
Calculate ROI
#81
Mistral

Mistral Small 24B

Mistral Small · 24B · 32K ctx

Quality
68
Cost $/M
$0.300
Value
226.7
Calculate ROI
#82
Mistral

Mistral Small 3.1 24B

Mistral Small · 24B · 128K ctx

Quality
50
Cost $/M
$0.300
Value
166.7
Calculate ROI
#83
Mistral

Codestral Mamba 7B

Codestral · 7.3B · 256K ctx

Quality
50
Cost $/M
$0.600
Value
83.3
Calculate ROI
#84
Mistral

Codestral 22B

Codestral · 22B · 32K ctx

Quality
63
Cost $/M
$0.900
Value
70.0
Calculate ROI
#85
Mistral

Mixtral 8x22B

Mixtral · 141B MoE (39B active) · 64K ctx

Quality
73
Cost $/M
$1.20
Value
60.8
Calculate ROI
#86
Mistral

Mistral Large 2

Mistral Large · 123B · 128K ctx

Quality
82
Cost $/M
$2.50
Value
32.8
Calculate ROI
#87
Mistral

Mistral Medium 3

Mistral · 70B · 128K ctx

Quality
80
Cost $/M
$6.00
Value
13.3
Calculate ROI
#88
Mistral

Mistral Large 2411

Mistral Large · 123B · 128K ctx

Quality
50
Cost $/M
$6.00
Value
8.3
Calculate ROI
#89
DeepSeek

DeepSeek V2 Lite

DeepSeek V2 · 15.7B MoE (2.4B active) · 32K ctx

Quality
50
Cost $/M~
$0.043
Value
1163.7
Calculate ROI
#90
DeepSeek

DeepSeek MoE 16B

DeepSeek MoE · 16.4B MoE (2.8B active) · 4K ctx

Quality
50
Cost $/M~
$0.050
Value
997.5
Calculate ROI
#91
DeepSeek

DeepSeek Math 7B

DeepSeek Math · 7.2B · 4K ctx

Quality
50
Cost $/M~
$0.130
Value
385.8
Calculate ROI
#92
DeepSeek

DeepSeek V2.5

DeepSeek V2 · 236B MoE (21B active) · 128K ctx

Quality
78
Cost $/M
$0.280
Value
278.6
Calculate ROI
#93
DeepSeek

DeepSeek Coder 6.7B

DeepSeek Coder · 6.7B · 16K ctx

Quality
50
Cost $/M
$0.200
Value
250.0
Calculate ROI
#94
DeepSeek

DeepSeek Coder V2 236B

DeepSeek Coder V2 · 236B MoE (21B active) · 128K ctx

Quality
50
Cost $/M
$0.280
Value
178.6
Calculate ROI
#95
DeepSeek

DeepSeek Coder 33B

DeepSeek Coder · 33B · 16K ctx

Quality
50
Cost $/M
$0.800
Value
62.5
Calculate ROI
#96
DeepSeek

DeepSeek LLM 67B

DeepSeek LLM · 67B · 4K ctx

Quality
66
Cost $/M~
$1.21
Value
54.7
Calculate ROI
#97
Microsoft

Phi 1.5

Phi · 1.3B · 2K ctx

Quality
50
Cost $/M~
$0.024
Value
2041.0
Calculate ROI
#98
Microsoft

Phi 1

Phi · 1.3B · 2K ctx

Quality
38
Cost $/M~
$0.024
Value
1551.2
Calculate ROI
#99
Google

Gemma 3 2B

Gemma 3 · 2B · 8K ctx

Quality
42
Cost $/M~
$0.040
Value
1055.7
Calculate ROI
#100
Google

Gemma 1.1 2B

Gemma · 2.5B · 8K ctx

Quality
50
Cost $/M~
$0.050
Value
1005.5
Calculate ROI
#101
Google

RecurrentGemma 2B

RecurrentGemma · 2.7B · 8K ctx

Quality
50
Cost $/M~
$0.054
Value
931.0
Calculate ROI
#102
Google

PaLI-Gemma 3B

PaLI-Gemma · 2.9B · 8K ctx

Quality
50
Cost $/M~
$0.058
Value
866.8
Calculate ROI
#103
Google

Gemma 2 2B

Gemma 2 · 2.6B · 8K ctx

Quality
44
Cost $/M~
$0.052
Value
850.8
Calculate ROI
#104
Microsoft

Phi 3 Mini 3.8B

Phi 3 · 3.8B · 128K ctx

Quality
64
Cost $/M~
$0.076
Value
846.7
Calculate ROI
#105
Google

Gemma 3 12B

Gemma 3 · 12B · 128K ctx

Quality
71
Cost $/M
$0.100
Value
710.0
Calculate ROI
#106
Microsoft

Phi 3.5 MoE

Phi · 41.9B MoE (6.6B active) · 128K ctx

Quality
74
Cost $/M~
$0.121
Value
613.0
Calculate ROI
#107
Microsoft

Phi 3.5 Vision

Phi 3.5 · 4.2B · 128K ctx

Quality
50
Cost $/M~
$0.084
Value
598.5
Calculate ROI
#108
Microsoft

Phi 3 Small 7B

Phi 3 · 7B · 128K ctx

Quality
72
Cost $/M~
$0.125
Value
574.6
Calculate ROI
#109
Google

Gemma 3 4B

Gemma 3 · 4.3B · 128K ctx

Quality
54
Cost $/M
$0.100
Value
540.0
Calculate ROI
#110
Google

Gemma 3 27B

Gemma 3 · 27B · 128K ctx

Quality
76
Cost $/M
$0.200
Value
380.0
Calculate ROI
#111
Google

CodeGemma 7B

Gemma · 8.5B · 8K ctx

Quality
52
Cost $/M~
$0.169
Value
307.6
Calculate ROI
#112
Microsoft

Phi 3 Medium 14B

Phi 3 · 14B · 128K ctx

Quality
76
Cost $/M~
$0.251
Value
303.2
Calculate ROI
#113
Google

Gemma 2 27B

Gemma 2 · 27B · 8K ctx

Quality
73
Cost $/M
$0.270
Value
270.4
Calculate ROI
#114
Microsoft

Dolphin 2.9 72B

Dolphin · 72B · 32K ctx

Quality
50
Cost $/M~
$1.30
Value
38.5
Calculate ROI
#115
OpenAI

FinGPT 7B

FinGPT · 7.2B · 4K ctx

Quality
50
Cost $/M~
$0.129
Value
387.9
Calculate ROI
#116
OpenAI

Cerebras GPT 13B

Cerebras GPT · 13B · 2K ctx

Quality
50
Cost $/M~
$0.233
Value
214.8
Calculate ROI
#117
OpenAI

GPT-4o Mini

GPT-4 · 8B · 125K ctx

Quality
80
Cost $/M
$0.600
Value
133.3
Calculate ROI
#118
OpenAI

GPT-3.5 Turbo

GPT-3.5 · 20B · 16K ctx

Quality
67
Cost $/M
$1.50
Value
44.7
Calculate ROI
#119
Anthropic

Claude 3.5 Haiku

Claude · 20B · 195K ctx

Quality
77
Cost $/M
$4.00
Value
19.3
Calculate ROI
#120
OpenAI

GPT-4o

GPT-4 · 200B MoE (50B active) · 125K ctx

Quality
91
Cost $/M
$10.00
Value
9.1
Calculate ROI
#121
Anthropic

Claude Sonnet 4

Claude · 70B · 195K ctx

Quality
90
Cost $/M
$15.00
Value
6.0
Calculate ROI
#122
Anthropic

Claude 3 Sonnet

Claude · 70B · 195K ctx

Quality
78
Cost $/M
$15.00
Value
5.2
Calculate ROI
#123
OpenAI

GPT-4 Turbo

GPT-4 · 200B MoE (50B active) · 125K ctx

Quality
86
Cost $/M
$30.00
Value
2.9
Calculate ROI
#124
Anthropic

Claude Opus 4

Claude · 200B · 195K ctx

Quality
94
Cost $/M
$75.00
Value
1.3
Calculate ROI
#125
Anthropic

Claude 3 Opus

Claude · 175B · 195K ctx

Quality
88
Cost $/M
$75.00
Value
1.2
Calculate ROI
#126
OpenAI

GPT-4.5 Preview

GPT · 1500B MoE (300B active) · 125K ctx

Quality
93
Cost $/M
$150.00
Value
0.6
Calculate ROI
#127
BAAI

BGE Small EN v1.5

BGE · 33M · 1K ctx

Quality
50
Cost $/M~
$0.0007
Value
76171.8
Calculate ROI
#128
OpenAI

Whisper Base

Whisper · 74M · 0K ctx

Quality
50
Cost $/M~
$0.0014
Value
35855.6
Calculate ROI
#129
BAAI

BGE Base EN v1.5

BGE · 110M · 1K ctx

Quality
50
Cost $/M~
$0.0021
Value
24121.1
Calculate ROI
#130
HuggingFace

SmolLM 135M

SmolLM · 135M · 2K ctx

Quality
50
Cost $/M~
$0.0025
Value
19654.2
Calculate ROI
#131
OpenAI

Whisper Small

Whisper · 244M · 0K ctx

Quality
50
Cost $/M~
$0.0046
Value
10874.3
Calculate ROI
#132
SentenceTransformers

All MiniLM L6 v2

MiniLM · 23M · 0K ctx

Quality
50
Cost $/M
$0.0050
Value
10000.0
Calculate ROI
#133
NVIDIA

NV EmbedQA E5 v5

NV EmbedQA · 330M · 1K ctx

Quality
50
Cost $/M
$0.0060
Value
8333.3
Calculate ROI
#134
NVIDIA

NV Retriever v1

NV Retriever · 330M · 1K ctx

Quality
50
Cost $/M
$0.0060
Value
8333.3
Calculate ROI
#135
OpenAI

Whisper Large V3

Whisper · 1.6B · 0K ctx

Quality
50
Cost $/M
$0.0060
Value
8333.3
Calculate ROI
#136
HuggingFace

SmolLM 360M

SmolLM · 360M · 2K ctx

Quality
50
Cost $/M~
$0.0068
Value
7370.3
Calculate ROI
#137
BAAI

BGE Large EN v1.5

BGE · 335M · 1K ctx

Quality
50
Cost $/M
$0.0080
Value
6250.0
Calculate ROI
#138
BAAI

BGE M3

BGE · 568M · 8K ctx

Quality
50
Cost $/M
$0.0080
Value
6250.0
Calculate ROI
#139
Jina

Jina Embeddings v3

Jina Embeddings · 570M · 8K ctx

Quality
50
Cost $/M
$0.0080
Value
6250.0
Calculate ROI
#140
Nomic

Nomic Embed Text v1.5

Nomic Embed · 137M · 8K ctx

Quality
50
Cost $/M
$0.0080
Value
6250.0
Calculate ROI
#141
H2O.ai

H2O Danube3 500M

H2O Danube · 500M · 8K ctx

Quality
50
Cost $/M~
$0.0094
Value
5306.6
Calculate ROI
#142
SentenceTransformers

InfoXLM Large

InfoXLM · 550M · 1K ctx

Quality
50
Cost $/M~
$0.010
Value
4824.2
Calculate ROI
#143
SentenceTransformers

Multilingual E5 Large

E5 · 560M · 1K ctx

Quality
50
Cost $/M~
$0.011
Value
4738.1
Calculate ROI
#144
NVIDIA

NV Embed v2

NV Embed · 7.8B · 32K ctx

Quality
50
Cost $/M
$0.012
Value
4166.7
Calculate ROI
#145
OpenAI

Whisper Medium

Whisper · 769M · 0K ctx

Quality
50
Cost $/M~
$0.014
Value
3450.3
Calculate ROI
#146
NVIDIA

Florence 2 Large

Florence · 770M · 2K ctx

Quality
50
Cost $/M~
$0.015
Value
3445.9
Calculate ROI
#147
BigCode

SantaCoder 1.1B

SantaCoder · 1.1B · 2K ctx

Quality
50
Cost $/M~
$0.020
Value
2539.1
Calculate ROI
#148
NVIDIA

Parakeet CTC 0.6B

Parakeet · 600M · 4K ctx

Quality
50
Cost $/M
$0.030
Value
1666.7
Calculate ROI
#149
HuggingFace

SmolLM2 1.7B

SmolLM2 · 1.7B · 8K ctx

Quality
50
Cost $/M~
$0.032
Value
1560.8
Calculate ROI
#150
NVIDIA

Canary 1B

Canary · 1B · 4K ctx

Quality
50
Cost $/M
$0.040
Value
1250.0
Calculate ROI
#151
NVIDIA

Parakeet TDT 1.1B

Parakeet · 1.1B · 4K ctx

Quality
50
Cost $/M
$0.040
Value
1250.0
Calculate ROI
#152
Meta

SeamlessM4T v2 Large

SeamlessM4T · 2.3B · 4K ctx

Quality
50
Cost $/M~
$0.043
Value
1153.6
Calculate ROI
#153
Apple

OpenELM 3B

OpenELM · 3B · 2K ctx

Quality
50
Cost $/M~
$0.054
Value
931.0
Calculate ROI
#154
Stability

StableLM Zephyr 3B

StableLM · 3B · 4K ctx

Quality
50
Cost $/M~
$0.060
Value
837.9
Calculate ROI
#155
Cerebras

BTLM 3B

BTLM · 3B · 8K ctx

Quality
50
Cost $/M~
$0.060
Value
837.9
Calculate ROI
#156
NVIDIA

Minitron 4B

Nemotron · 4B · 8K ctx

Quality
50
Cost $/M
$0.060
Value
833.3
Calculate ROI
#157
NVIDIA

Nemotron Mini 4B

Nemotron · 4B · 8K ctx

Quality
48
Cost $/M
$0.060
Value
800.0
Calculate ROI
#158
Replit

Replit Code v1.5 3B

Replit Code · 3.3B · 4K ctx

Quality
50
Cost $/M~
$0.066
Value
761.7
Calculate ROI
#159
Stability

Stable Diffusion XL 1.0

Stable Diffusion · 3.5B · 0K ctx

Quality
50
Cost $/M~
$0.070
Value
718.2
Calculate ROI
#160
NVIDIA

Minitron 8B

Nemotron · 8B · 8K ctx

Quality
62
Cost $/M
$0.100
Value
620.0
Calculate ROI
#161
NVIDIA

VILA 1.5 3B

VILA · 3B · 4K ctx

Quality
44
Cost $/M
$0.080
Value
550.0
Calculate ROI
#162
Embedding

Cohere Embed English v3

Embed · 500M · 1K ctx

Quality
50
Cost $/M
$0.100
Value
500.0
Calculate ROI
#163
Zhipu

ChatGLM3 6B

ChatGLM3 · 6B · 128K ctx

Quality
50
Cost $/M~
$0.107
Value
465.5
Calculate ROI
#164
01.AI

Yi 6B 200K

Yi · 6B · 195K ctx

Quality
50
Cost $/M~
$0.107
Value
465.5
Calculate ROI
#165
Scientific AI

SciGLM 6B

SciGLM · 6.2B · 8K ctx

Quality
50
Cost $/M~
$0.111
Value
450.5
Calculate ROI
#166
Allen AI

OLMo 2 7B

OLMo 2 · 7B · 4K ctx

Quality
50
Cost $/M~
$0.125
Value
399.0
Calculate ROI
#167
HuggingFace

Zephyr 7B

Zephyr · 7B · 32K ctx

Quality
50
Cost $/M~
$0.125
Value
399.0
Calculate ROI
#168
LMSYS

Vicuna 7B

Vicuna · 7B · 4K ctx

Quality
50
Cost $/M~
$0.125
Value
399.0
Calculate ROI
#169
Baichuan

Baichuan 2 7B

Baichuan 2 · 7B · 4K ctx

Quality
50
Cost $/M~
$0.125
Value
399.0
Calculate ROI
#170
Legal AI

SaulLM 7B

SaulLM · 7.2B · 8K ctx

Quality
50
Cost $/M~
$0.129
Value
387.9
Calculate ROI
#171
Prometheus

Prometheus 2 7B

Prometheus · 7.2B · 8K ctx

Quality
50
Cost $/M~
$0.130
Value
385.8
Calculate ROI
#172
OpenAI

Marco O1

Marco · 7.6B · 64K ctx

Quality
50
Cost $/M~
$0.136
Value
367.5
Calculate ROI
#173
Cohere

Command R 7B

Command R · 7B · 128K ctx

Quality
50
Cost $/M
$0.150
Value
333.3
Calculate ROI
#174
TII

Falcon Mamba 7B

Falcon Mamba · 7.3B · 8K ctx

Quality
50
Cost $/M
$0.150
Value
333.3
Calculate ROI
#175
Zhipu

GLM-4 9B

GLM-4 · 9.4B · 128K ctx

Quality
50
Cost $/M
$0.150
Value
333.3
Calculate ROI
#176
01.AI

Yi Coder 9B

Yi Coder · 8.8B · 128K ctx

Quality
50
Cost $/M~
$0.158
Value
317.4
Calculate ROI
#177
01.AI

Yi 1.5 9B

Yi 1.5 · 8.8B · 4K ctx

Quality
62
Cost $/M
$0.200
Value
310.0
Calculate ROI
#178
MosaicML

MPT 7B

MPT · 6.7B · 64K ctx

Quality
36
Cost $/M~
$0.120
Value
300.1
Calculate ROI
#179
Zhipu

ChatGLM4 9B

ChatGLM · 9.4B · 128K ctx

Quality
50
Cost $/M~
$0.168
Value
297.1
Calculate ROI
#180
BigCode

StarCoder2 3B

StarCoder2 · 3B · 16K ctx

Quality
29
Cost $/M
$0.100
Value
290.0
Calculate ROI
#181
NousResearch

Hermes 3 8B

Hermes 3 · 8B · 128K ctx

Quality
50
Cost $/M
$0.180
Value
277.8
Calculate ROI
#182
TII

Falcon 11B

Falcon · 11B · 8K ctx

Quality
50
Cost $/M~
$0.197
Value
253.9
Calculate ROI
#183
InternLM

InternLM 2.5 7B

InternLM 2.5 · 7.7B · 1024K ctx

Quality
50
Cost $/M
$0.200
Value
250.0
Calculate ROI
#184
RWKV

RWKV-6 14B

RWKV · 14.1B · 32K ctx

Quality
50
Cost $/M
$0.200
Value
250.0
Calculate ROI
#185
NousResearch

OpenHermes 2.5 7B

OpenHermes · 7B · 32K ctx

Quality
50
Cost $/M
$0.200
Value
250.0
Calculate ROI
#186
Google

Gemini 1.5 Flash

Gemini · 50B MoE (12B active) · 1024K ctx

Quality
75
Cost $/M
$0.300
Value
250.0
Calculate ROI
#187
TII

Falcon 7B

Falcon · 7B · 2K ctx

Quality
37
Cost $/M
$0.150
Value
246.7
Calculate ROI
#188
NVIDIA

Nemotron 15B

Nemotron · 15B · 4K ctx

Quality
72
Cost $/M
$0.300
Value
240.0
Calculate ROI
#189
BigCode

StarCoder2 7B

StarCoder2 · 6.7B · 16K ctx

Quality
35
Cost $/M
$0.150
Value
233.3
Calculate ROI
#190
Korean AI

KULLM 12.8B

KULLM · 12.8B · 4K ctx

Quality
50
Cost $/M~
$0.229
Value
218.2
Calculate ROI
#191
Allen AI

OLMo 2 13B

OLMo 2 · 13B · 4K ctx

Quality
50
Cost $/M~
$0.233
Value
214.8
Calculate ROI
#192
LMSYS

Vicuna 13B

Vicuna · 13B · 4K ctx

Quality
50
Cost $/M~
$0.233
Value
214.8
Calculate ROI
#193
Microsoft

Orca 2 13B

Orca · 13B · 4K ctx

Quality
50
Cost $/M~
$0.233
Value
214.8
Calculate ROI
#194
Japanese AI

ELYZA 13B

ELYZA · 13B · 4K ctx

Quality
50
Cost $/M~
$0.233
Value
214.8
Calculate ROI
#195
Amazon

Amazon Nova Lite

Nova · 12B · 293K ctx

Quality
50
Cost $/M
$0.240
Value
208.3
Calculate ROI
#196
Google

Gemini 2.0 Flash

Gemini · 50B MoE (15B active) · 1024K ctx

Quality
83
Cost $/M
$0.400
Value
207.5
Calculate ROI
#197
NVIDIA

VILA 1.5 13B

VILA · 13B · 4K ctx

Quality
62
Cost $/M
$0.300
Value
206.7
Calculate ROI
#198
Baichuan

Baichuan 2 13B

Baichuan 2 · 13B · 4K ctx

Quality
50
Cost $/M
$0.250
Value
200.0
Calculate ROI
#199
Stability

StableLM 2 12B

StableLM 2 · 12.1B · 4K ctx

Quality
50
Cost $/M
$0.250
Value
200.0
Calculate ROI
#200
Rinna

Nekomata 14B

Nekomata · 14B · 4K ctx

Quality
50
Cost $/M~
$0.251
Value
199.5
Calculate ROI
#201
BigCode

OctoCoder 15B

OctoCoder · 15.5B · 8K ctx

Quality
50
Cost $/M~
$0.277
Value
180.2
Calculate ROI
#202
Salesforce

CodeGen2 16B

CodeGen2 · 16B · 2K ctx

Quality
50
Cost $/M~
$0.286
Value
174.6
Calculate ROI
#203
Upstage

SOLAR 10.7B

SOLAR · 10.7B · 4K ctx

Quality
50
Cost $/M
$0.300
Value
166.7
Calculate ROI
#204
Snowflake

Snowflake Arctic 128x3B

Arctic · 395B MoE (17B active) · 4K ctx

Quality
50
Cost $/M~
$0.312
Value
160.3
Calculate ROI
#205
Zhipu

CogVLM2 19B

CogVLM2 · 19B · 8K ctx

Quality
50
Cost $/M~
$0.340
Value
147.0
Calculate ROI
#206
BigCode

StarCoder2 15B

StarCoder2 · 15.5B · 16K ctx

Quality
42
Cost $/M
$0.300
Value
140.0
Calculate ROI
#207
Sber

GigaChat 20B

GigaChat · 20B · 8K ctx

Quality
50
Cost $/M~
$0.358
Value
139.6
Calculate ROI
#208
InternLM

InternLM 20B

InternLM · 20B · 16K ctx

Quality
50
Cost $/M~
$0.358
Value
139.6
Calculate ROI
#209
Cohere

Command R

Command R · 35B · 128K ctx

Quality
68
Cost $/M
$0.500
Value
136.0
Calculate ROI
#210
AI21

Jamba 1.5 Mini

Jamba · 52B · 250K ctx

Quality
50
Cost $/M
$0.400
Value
125.0
Calculate ROI
#211
InternLM

InternVL2 26B

InternVL2 · 26B · 32K ctx

Quality
50
Cost $/M~
$0.465
Value
107.4
Calculate ROI
#212
InternLM

InternLM 2.5 20B

InternLM 2.5 · 19.9B · 256K ctx

Quality
50
Cost $/M
$0.500
Value
100.0
Calculate ROI
#213
Upstage

Solar Pro 22B

Solar · 22B · 4K ctx

Quality
50
Cost $/M
$0.500
Value
100.0
Calculate ROI
#214
NVIDIA

Nemotron 70B

Nemotron · 70.6B · 128K ctx

Quality
83
Cost $/M
$0.880
Value
94.3
Calculate ROI
#215
AI21

Jamba Instruct

Jamba · 52B MoE (12B active) · 250K ctx

Quality
66
Cost $/M
$0.700
Value
94.3
Calculate ROI
#216
Arabic AI

JAIS 30B

JAIS · 30B · 8K ctx

Quality
50
Cost $/M~
$0.537
Value
93.1
Calculate ROI
#217
01.AI

Yi 1.5 34B

Yi 1.5 · 34.4B · 195K ctx

Quality
72
Cost $/M
$0.800
Value
90.0
Calculate ROI
#218
LMSYS

Vicuna 33B

Vicuna · 33B · 2K ctx

Quality
50
Cost $/M~
$0.591
Value
84.6
Calculate ROI
#219
WizardLM

WizardCoder 33B

WizardCoder · 33B · 16K ctx

Quality
50
Cost $/M~
$0.591
Value
84.6
Calculate ROI
#220
Cohere

Aya 23 8B

Aya · 8B · 8K ctx

Quality
50
Cost $/M
$0.600
Value
83.3
Calculate ROI
#221
Cohere

Command R (August 2024)

Command R · 35B · 125K ctx

Quality
50
Cost $/M
$0.600
Value
83.3
Calculate ROI
#222
MosaicML

MPT 30B

MPT · 30B · 8K ctx

Quality
48
Cost $/M~
$0.597
Value
80.4
Calculate ROI
#223
NVIDIA

VILA 1.5 40B

VILA · 40B · 8K ctx

Quality
73
Cost $/M
$1.00
Value
73.0
Calculate ROI
#224
TII

Falcon 40B

Falcon · 40B · 2K ctx

Quality
48
Cost $/M
$0.800
Value
60.0
Calculate ROI
#225
NousResearch

Hermes 3 70B

Hermes 3 · 70.6B · 128K ctx

Quality
50
Cost $/M
$0.880
Value
56.8
Calculate ROI
#226
Databricks

DBRX Instruct

DBRX · 132B MoE (36B active) · 32K ctx

Quality
50
Cost $/M
$1.20
Value
41.7
Calculate ROI
#227
WizardLM

WizardMath 70B

WizardMath · 70B · 4K ctx

Quality
50
Cost $/M~
$1.26
Value
39.5
Calculate ROI
#228
Medical AI

Meditron 70B

Meditron · 70B · 4K ctx

Quality
50
Cost $/M~
$1.26
Value
39.5
Calculate ROI
#229
Stability

Japanese StableLM 70B

StableLM · 70B · 8K ctx

Quality
50
Cost $/M~
$1.26
Value
39.5
Calculate ROI
#230
Cohere

Command R+

Command R · 104B · 128K ctx

Quality
78
Cost $/M
$2.00
Value
39.0
Calculate ROI
#231
Cohere

Aya 23 35B

Aya · 35B · 128K ctx

Quality
50
Cost $/M
$1.50
Value
33.3
Calculate ROI
#232
Snowflake

Snowflake Arctic 480B

Arctic · 480B MoE (17B active) · 4K ctx

Quality
50
Cost $/M
$1.50
Value
33.3
Calculate ROI
#233
Yandex

YaLM 100B

YaLM · 100B · 2K ctx

Quality
50
Cost $/M~
$1.80
Value
27.7
Calculate ROI
#234
TII

Falcon 180B

Falcon · 180B · 2K ctx

Quality
60
Cost $/M
$2.40
Value
25.0
Calculate ROI
#235
01.AI

Yi-Large

Yi · 103B MoE (24B active) · 32K ctx

Quality
74
Cost $/M
$3.00
Value
24.7
Calculate ROI
#236
Databricks

DBRX Base

DBRX · 132B MoE (36B active) · 32K ctx

Quality
50
Cost $/M
$2.25
Value
22.2
Calculate ROI
#237
Google

Gemini 2.0 Pro

Gemini · 600B MoE (150B active) · 1953K ctx

Quality
88
Cost $/M
$4.00
Value
22.0
Calculate ROI
#238
Moonshot

Kimi K2.5

Kimi · 1000B MoE (32B active) · 128K ctx

Quality
50
Cost $/M
$2.40
Value
20.8
Calculate ROI
#239
NVIDIA

Nemotron 340B

Nemotron · 340B · 128K ctx

Quality
85
Cost $/M
$4.20
Value
20.2
Calculate ROI
#240
OpenAI

o3-mini

o3 · 70B · 195K ctx

Quality
89
Cost $/M
$4.40
Value
20.2
Calculate ROI
#241
Google

Gemini 1.5 Pro

Gemini · 175B MoE (40B active) · 2048K ctx

Quality
86
Cost $/M
$5.00
Value
17.2
Calculate ROI
#242
Amazon

Amazon Nova Pro

Nova · 50B · 293K ctx

Quality
50
Cost $/M
$3.20
Value
15.6
Calculate ROI
#243
xAI

Grok-2

Grok · 314B MoE (50B active) · 128K ctx

Quality
87
Cost $/M
$10.00
Value
8.7
Calculate ROI
#244
Cohere

Command A

Command · 111B · 250K ctx

Quality
81
Cost $/M
$10.00
Value
8.1
Calculate ROI
#245
OpenAI

o1-mini

o1 · 70B · 125K ctx

Quality
86
Cost $/M
$12.00
Value
7.2
Calculate ROI
#246
AI21

Jamba 1.5 Large

Jamba · 398B · 250K ctx

Quality
50
Cost $/M
$8.00
Value
6.3
Calculate ROI
#247
xAI

Grok 3

Grok · 600B MoE (120B active) · 128K ctx

Quality
90
Cost $/M
$15.00
Value
6.0
Calculate ROI
#248
NVIDIA

Megatron-Turing NLG 530B

Megatron-Turing · 530B · 2K ctx

Quality
58
Cost $/M~
$10.59
Value
5.5
Calculate ROI
#249
Reka

Reka Core

Reka · 70B · 125K ctx

Quality
76
Cost $/M
$15.00
Value
5.1
Calculate ROI
#250
Inflection

Inflection 3

Inflection · 100B · 8K ctx

Quality
74
Cost $/M
$15.00
Value
4.9
Calculate ROI
#251
Black Forest Labs

FLUX.1 Dev

FLUX · 12B · 1K ctx

Quality
50
Cost $/M
$25.00
Value
2.0
Calculate ROI
#252
OpenAI

o1

o1 · 200B MoE (50B active) · 195K ctx

Quality
95
Cost $/M
$60.00
Value
1.6
Calculate ROI
#253
OpenAI

DALL-E 3

DALL-E · 3.5B · 4K ctx

Quality
50
Cost $/M
$40.00
Value
1.3
Calculate ROI

Showing 253 of 253 models

Ready to calculate your inference costs?

Open the Calculator

Built with care · Open Source · Inference Bench