AI Models Directory

Browse all 700 language models from 52 providers — benchmarks, pricing, speed and rankings in one place.

Anthropic66OpenAI107Moonshot AI16Alibaba95Google68xAI33DeepSeek34Z.ai24Baidu5LongCat3Amazon25NVIDIA17Tencent13MiniMax9Mistral35StepFun6Meta42Cohere12AI27Ling5AI9Stars2IBM10Inception2Kwai1Liquid AI3Multiverse1Zhipu AI1Microsoft9Sarvam AI3Agnes3Xiaomi4Nex AGI1Thinking Machines2Upstage4ByteDance2WeRide1K21ServiceNow2North1Trinity1Celeris1Reka2AI21 Labs2Swiss AI2Async3Cogito1Independent1Muse1Ocat1Open Source1TII1
Interactive Analysis

Quality vs Cost Trade-off Matrix

Frontier evaluation: explore Pareto efficiency frontier, latency and pricing quadrants

Y-Axis:
X-Axis:
Pareto Optimal Frontier
Optimal Zone (High Quality, Low Cost)
High Performance / Premium
Claude Mythos Preview
1
Anthropic1.0M ctx80 t/s$15/M out
97.4
preview
Claude Fable 5
2
Anthropic1.0M ctx71 t/s$50/M out
93.4
Claude Fable 5.1
3
Anthropic500K ctx85 t/s$15/M out
88.4
GPT-6 Astra
4
OpenAI1.1M ctx82 t/s$50/M out
86.2
Kimi K3
5
Moonshot AI1.0M ctx37 t/s$15/M out
83.3
Open
Claude Opus 5
6
Anthropic1.0M ctx60 t/s$25/M out
81.4
GPT-5.6 Sol
7
OpenAI1.1M ctx72 t/s$30/M out
80.8
Qwen3.8 Max
8
Alibaba1M ctx55 t/s$2/M out
79.8
Claude Opus 4.8
9
Anthropic1M ctx50 t/s$15/M out
76.0
Claude Opus 4 6 Thinking
10
Anthropic128K ctx50 t/s$15/M out
75.0
Claude Opus 4 7 Thinking
11
Anthropic128K ctx50 t/s$15/M out
75.0
Claude Opus 5 Max
12
Anthropic128K ctx50 t/s$15/M out
75.0
Gemini 3.1 Pro Preview
13
Google128K ctx50 t/s$5/M out
74.0
Kimi K3 Max
14
Moonshot AI128K ctx50 t/s$3/M out
74.0
Claude Opus 4 8 Thinking
15
Anthropic128K ctx50 t/s$15/M out
74.0
GPT 5.6 Sol Xhigh
16
OpenAI128K ctx50 t/s$10/M out
74.0
GPT 5.5 High
17
OpenAI128K ctx50 t/s$10/M out
74.0
GPT 5.4 High
18
OpenAI128K ctx50 t/s$10/M out
74.0
Gemini 3.5 Flash High
19
Google128K ctx50 t/s$5/M out
74.0
GPT 5.2 Chat Latest 20260210
20
OpenAI128K ctx50 t/s$10/M out
74.0
Qwen3.7 Max Preview
21
Alibaba128K ctx50 t/s$2/M out
74.0
Grok 4.20 Beta1
22
xAI128K ctx50 t/s$15/M out
74.0
Gemini 3.5 Flash Medium
23
Google128K ctx50 t/s$5/M out
74.0
GPT 5.5 Instant
24
OpenAI128K ctx50 t/s$10/M out
74.0
Claude Opus 4 5 20251101 Thinking 32k
25
Anthropic128K ctx50 t/s$15/M out
74.0
Grok 4.20 Beta 0309 Reasoning
26
xAI128K ctx50 t/s$15/M out
74.0
Grok 4.20 Multi Agent Beta 0309
27
xAI128K ctx50 t/s$15/M out
74.0
Glm 5.2 Max
28
Z.ai128K ctx50 t/s$3/M out
73.0
Claude Opus 4 5 20251101
29
Anthropic128K ctx50 t/s$15/M out
73.0
GPT 5.6 Terra Xhigh
30
OpenAI128K ctx50 t/s$10/M out
73.0
Grok 4.1 Thinking
31
xAI128K ctx50 t/s$15/M out
73.0
Qwen3.5 Max Preview
32
Alibaba128K ctx50 t/s$2/M out
73.0
Qwen3.6 Max Preview
33
Alibaba128K ctx50 t/s$2/M out
73.0
Grok 4.1
34
xAI128K ctx50 t/s$15/M out
73.0
Dola Seed 2.0 Pro
35
Unknown128K ctx50 t/s$3/M out
73.0
Claude Sonnet 4 5 20250929 Thinking 32k
36
Anthropic128K ctx50 t/s$15/M out
73.0
Claude Sonnet 4 5 20250929
37
Anthropic128K ctx50 t/s$15/M out
73.0
GPT 5.1 High
38
OpenAI128K ctx50 t/s$10/M out
73.0
Deepseek V4 Pro High Preview
39
DeepSeek128K ctx50 t/s$1.1/M out
73.0
GPT 5.6 Luna Xhigh
40
OpenAI128K ctx50 t/s$10/M out
73.0
Kimi K2.5 Thinking
41
Moonshot AI128K ctx50 t/s$3/M out
73.0
Claude Opus 4 1 20250805 Thinking 16k
42
Anthropic128K ctx50 t/s$15/M out
72.0
Ernie 5.0 Preview 1203
43
Baidu128K ctx50 t/s$3/M out
72.0
GPT 5.3 Chat Latest
44
OpenAI128K ctx50 t/s$10/M out
72.0
GPT 5.4 Mini High
45
OpenAI128K ctx50 t/s$10/M out
72.0
Mimo V2 Pro
46
Unknown128K ctx50 t/s$3/M out
72.0
Claude Opus 4 1 20250805
47
Anthropic128K ctx50 t/s$15/M out
72.0
Ernie 5.0 0110
48
Baidu128K ctx50 t/s$3/M out
72.0
GPT 4.5 Preview 2025 02 27
49
OpenAI128K ctx50 t/s$10/M out
72.0
Chatgpt 4o Latest 20250326
50
OpenAI128K ctx50 t/s$10/M out
72.0
Glm 4.7
51
Z.ai128K ctx50 t/s$3/M out
72.0
Qwen3.5 397b A17b
52
Alibaba128K ctx50 t/s$2/M out
72.0
Deepseek V4 Flash High Preview
53
DeepSeek128K ctx50 t/s$1.1/M out
72.0
GPT 5.2 High
54
OpenAI128K ctx50 t/s$10/M out
72.0
Longcat Flash Chat 2602 Exp
55
LongCat128K ctx50 t/s$3/M out
72.0
GPT 5 High
56
OpenAI128K ctx50 t/s$10/M out
72.0
Mimo V2.5
57
Unknown128K ctx50 t/s$3/M out
72.0
Glm 5v Turbo
58
Z.ai128K ctx50 t/s$3/M out
72.0
Gemini 3.1 Flash Lite Preview
59
Google128K ctx50 t/s$5/M out
72.0
Kimi K2.5 Instant
60
Moonshot AI128K ctx50 t/s$3/M out
72.0
Grok 4 1 Fast Reasoning
61
xAI128K ctx50 t/s$15/M out
72.0
O3 2025 04 16
62
OpenAI128K ctx50 t/s$10/M out
72.0
Mimo V2 Omni
63
Unknown128K ctx50 t/s$3/M out
72.0
Kimi K2 Thinking Turbo
64
Moonshot AI128K ctx50 t/s$3/M out
72.0
GPT 5 Chat
65
OpenAI128K ctx50 t/s$10/M out
71.0
Nvidia Nemotron 3 Ultra 550b A55b Nvfp4
66
NVIDIA128K ctx50 t/s$3/M out
71.0
Amazon Nova Experimental Chat 26 02 10
67
Amazon128K ctx50 t/s$3/M out
71.0
Glm 4.6
68
Z.ai128K ctx50 t/s$3/M out
71.0
Deepseek V3.2 Exp Thinking
69
DeepSeek128K ctx50 t/s$1.1/M out
71.0
Claude Opus 4 20250514 Thinking 16k
70
Anthropic128K ctx50 t/s$15/M out
71.0
Qwen3 Max 2025 09 23
71
Alibaba128K ctx50 t/s$2/M out
71.0
Deepseek V3.2 Thinking
72
DeepSeek128K ctx50 t/s$1.1/M out
71.0
Deepseek V3.2 Exp
73
DeepSeek128K ctx50 t/s$1.1/M out
71.0
Deepseek R1 0528
74
DeepSeek128K ctx50 t/s$1.1/M out
71.0
Grok 4 Fast Chat
75
xAI128K ctx50 t/s$15/M out
71.0
Ernie 5.0 Preview 1022
76
Baidu128K ctx50 t/s$3/M out
71.0
Kimi K2 0905 Preview
77
Moonshot AI128K ctx50 t/s$3/M out
71.0
Kimi K2 0711 Preview
78
Moonshot AI128K ctx50 t/s$3/M out
71.0
Deepseek V3.1
79
DeepSeek128K ctx50 t/s$1.1/M out
71.0
Deepseek V3.1 Terminus Thinking
80
DeepSeek128K ctx50 t/s$1.1/M out
71.0
Deepseek V3.1 Thinking
81
DeepSeek128K ctx50 t/s$1.1/M out
71.0
Qwen3.5 122b A10b
82
Alibaba128K ctx50 t/s$2/M out
71.0
Amazon Nova Experimental Chat 26 01 10
83
Amazon128K ctx50 t/s$3/M out
71.0
Deepseek V3.1 Terminus
84
DeepSeek128K ctx50 t/s$1.1/M out
71.0
GPT 4.1 2025 04 14
85
OpenAI128K ctx50 t/s$10/M out
71.0
Claude Opus 4 20250514
86
Anthropic128K ctx50 t/s$15/M out
71.0
Claude Haiku 4 5 20251001
87
Anthropic128K ctx50 t/s$15/M out
71.0
Hunyuan Hy3 Preview
88
Tencent128K ctx50 t/s$3/M out
71.0
Grok 3 Preview 02 24
89
xAI128K ctx50 t/s$15/M out
71.0
Glm 4.5
90
Z.ai128K ctx50 t/s$3/M out
71.0
Grok 4 0709
91
xAI128K ctx50 t/s$15/M out
70.0
Mistral Medium 2508
92
Mistral128K ctx50 t/s$6/M out
70.0
Qwen3.5 27b
93
Alibaba128K ctx50 t/s$2/M out
70.0
Gemini 2.5 Flash Preview 09 2025
94
Google128K ctx50 t/s$5/M out
70.0
Qwen3 235b A22b No Thinking
95
Alibaba128K ctx50 t/s$2/M out
70.0
GPT 5.4 Nano High
96
OpenAI128K ctx50 t/s$10/M out
70.0
O1 2024 12 17
97
OpenAI128K ctx50 t/s$10/M out
70.0
Longcat Flash Chat
98
LongCat128K ctx50 t/s$3/M out
70.0
Claude Sonnet 4 20250514 Thinking 32k
99
Anthropic128K ctx50 t/s$15/M out
70.0
Qwen3 235b A22b Thinking 2507
100
Alibaba128K ctx50 t/s$2/M out
70.0
Qwen3.5 Flash
101
Alibaba128K ctx50 t/s$2/M out
70.0
Qwen3.5 35b A3b
102
Alibaba128K ctx50 t/s$2/M out
70.0
Qwen3 VL 235b A22b Thinking
103
Alibaba128K ctx50 t/s$2/M out
70.0
Hunyuan Vision 1.5 Thinking
104
Tencent128K ctx50 t/s$3/M out
70.0
Step 3.5 Flash
105
StepFun128K ctx50 t/s$3/M out
70.0
Amazon Nova Experimental Chat 12 10
106
Amazon128K ctx50 t/s$3/M out
70.0
GPT 5 Mini High
107
OpenAI128K ctx50 t/s$10/M out
70.0
O4 Mini 2025 04 16
108
OpenAI128K ctx50 t/s$10/M out
70.0
Minimax M2.5
109
MiniMax128K ctx50 t/s$3/M out
70.0
Muse Spark 1.1
110
Meta1.0M ctx208 t/s$4.25/M out
69.9
Claude Sonnet 4 20250514
111
Anthropic128K ctx50 t/s$15/M out
69.0
Claude 3 7 Sonnet 20250219 Thinking 32k
112
Anthropic128K ctx50 t/s$15/M out
69.0
Mistral Medium 2505
113
Mistral128K ctx50 t/s$6/M out
69.0
Hunyuan T1 20250711
114
Tencent128K ctx50 t/s$3/M out
69.0
Minimax M2.1 Preview
115
MiniMax128K ctx50 t/s$3/M out
69.0
Qwen3 30b A3b Instruct 2507
116
Alibaba128K ctx50 t/s$2/M out
69.0
GPT 4.1 Mini 2025 04 14
117
OpenAI128K ctx50 t/s$10/M out
69.0
Hunyuan Turbos 20250416
118
Tencent128K ctx50 t/s$3/M out
69.0
Gemini 2.5 Flash Lite Preview 09 2025 No Thinking
119
Google128K ctx50 t/s$5/M out
69.0
Glm 4.6v
120
Z.ai128K ctx50 t/s$3/M out
69.0
Qwen3 235b A22b
121
Alibaba128K ctx50 t/s$2/M out
69.0
Gemini 2.5 Flash Lite Preview 06 17 Thinking
122
Google128K ctx50 t/s$5/M out
69.0
Qwen2.5 Max
123
Alibaba128K ctx50 t/s$2/M out
69.0
Claude 3 5 Sonnet 20241022
124
Anthropic128K ctx50 t/s$15/M out
69.0
Glm 4.5 Air
125
Z.ai128K ctx50 t/s$3/M out
69.0
Claude 3 7 Sonnet 20250219
126
Anthropic128K ctx50 t/s$15/M out
69.0
Gemini 3.8 Flash
127
Google1M ctx302 t/s$3.75/M out
68.5
Qwen3 Next 80b A3b Thinking
128
Alibaba128K ctx50 t/s$2/M out
68.0
Glm 4.7 Flash
129
Z.ai128K ctx50 t/s$3/M out
68.0
Gemma 3 27b It
130
Google128K ctx50 t/s$5/M out
68.0
Amazon Nova Experimental Chat 11 10
131
Amazon128K ctx50 t/s$3/M out
68.0
Minimax M1
132
MiniMax128K ctx50 t/s$3/M out
68.0
Grok 3 Mini High
133
xAI128K ctx50 t/s$15/M out
68.0
Gemini 2.0 Flash 001
134
Google128K ctx50 t/s$5/M out
68.0
Mistral Small 2506
135
Mistral128K ctx50 t/s$6/M out
68.0
Grok 3 Mini Beta
136
xAI128K ctx50 t/s$15/M out
68.0
Command A 03 2025
137
Cohere128K ctx50 t/s$3/M out
68.0
Gemini 2.0 Flash Lite Preview 02 05
138
Google128K ctx50 t/s$5/M out
68.0
Glm 4.5v
139
Z.ai128K ctx50 t/s$3/M out
68.0
Gemini 1.5 Pro 002
140
Google128K ctx50 t/s$5/M out
68.0
Amazon Nova Experimental Chat 10 20
141
Amazon128K ctx50 t/s$3/M out
67.0
Hunyuan Turbos 20250226
142
Tencent128K ctx50 t/s$3/M out
67.0
Step 3
143
StepFun128K ctx50 t/s$3/M out
67.0
Llama 3.1 Nemotron Ultra 253b V1
144
Meta128K ctx50 t/s$0/M out
67.0
Amazon Nova Experimental Chat 10 09
145
Amazon128K ctx50 t/s$3/M out
67.0
Qwen3 32b
146
Alibaba128K ctx50 t/s$2/M out
67.0
Qwen Plus 0125
147
Alibaba128K ctx50 t/s$2/M out
67.0
Ling Flash 2.0
148
Ling128K ctx50 t/s$3/M out
67.0
Nvidia Llama 3.3 Nemotron Super 49b V1.5
149
NVIDIA128K ctx50 t/s$3/M out
67.0
Glm 4 Plus 0111
150
Z.ai128K ctx50 t/s$3/M out
67.0
Claude 3 5 Sonnet 20240620
151
Anthropic128K ctx50 t/s$15/M out
67.0
Gemma 3 12b It
152
Google128K ctx50 t/s$5/M out
67.0
Hunyuan Turbo 0110
153
Tencent128K ctx50 t/s$3/M out
67.0
GPT 5 Nano High
154
OpenAI128K ctx50 t/s$10/M out
67.0
O1 Mini
155
OpenAI128K ctx50 t/s$10/M out
67.0
Nova 2 Lite
156
Amazon128K ctx50 t/s$3/M out
67.0
Grok 2 2024 08 13
157
xAI128K ctx50 t/s$15/M out
67.0
Gemini Advanced 0514
158
Google128K ctx50 t/s$5/M out
67.0
Llama 3.1 405b Instruct Bf16
159
Meta128K ctx50 t/s$0/M out
67.0
Step 2 16k Exp 202412
160
StepFun128K ctx50 t/s$3/M out
67.0
Llama 3.1 405b Instruct Fp8
161
Meta128K ctx50 t/s$0/M out
67.0
Olmo 3.1 32b Instruct
162
AI2128K ctx50 t/s$3/M out
67.0
Qwen3.8 Flash Next
163
Alibaba260K ctx168 t/s$0.4/M out
66.8
Open
GPT-5.6 Terra
164
OpenAI1.1M ctx127 t/s$12/M out
66.4
Molmo 2 8b
165
AI2128K ctx50 t/s$3/M out
66.0
Llama 3.3 Nemotron 49b Super V1
166
Meta128K ctx50 t/s$0/M out
66.0
Qwen3 30b A3b
167
Alibaba128K ctx50 t/s$2/M out
66.0
Llama 4 Maverick 17b 128e Instruct
168
Meta128K ctx50 t/s$0/M out
66.0
Hunyuan Large 2025 02 10
169
Tencent128K ctx50 t/s$3/M out
66.0
GPT 4 Turbo 2024 04 09
170
OpenAI128K ctx50 t/s$10/M out
66.0
Claude 3 5 Haiku 20241022
171
Anthropic128K ctx50 t/s$15/M out
66.0
Gemini 1.5 Pro 001
172
Google128K ctx50 t/s$5/M out
66.0
Deepseek V2.5 1210
173
DeepSeek128K ctx50 t/s$1.1/M out
66.0
Llama 4 Scout 17b 16e Instruct
174
Meta128K ctx50 t/s$0/M out
66.0
GPT 4.1 Nano 2025 04 14
175
OpenAI128K ctx50 t/s$10/M out
66.0
Claude 3 Opus 20240229
176
Anthropic128K ctx50 t/s$15/M out
66.0
Ring Flash 2.0
177
Unknown128K ctx50 t/s$3/M out
66.0
Step 1o Turbo 202506
178
StepFun128K ctx50 t/s$3/M out
66.0
Glm 4 Plus
179
Z.ai128K ctx50 t/s$3/M out
66.0
Llama 3.3 70b Instruct
180
Meta128K ctx50 t/s$0/M out
66.0
Gemma 3n E4b It
181
Google128K ctx50 t/s$5/M out
66.0
Qwen Max 0919
182
Alibaba128K ctx50 t/s$2/M out
66.0
GPT 4o Mini 2024 07 18
183
OpenAI128K ctx50 t/s$10/M out
66.0
Nvidia Nemotron 3 Nano 30b A3b Bf16
184
NVIDIA128K ctx50 t/s$3/M out
66.0
Qwen2.5 Plus 1127
185
Alibaba128K ctx50 t/s$2/M out
66.0
GPT 4 0125 Preview
186
OpenAI128K ctx50 t/s$10/M out
66.0
GPT 4 1106 Preview
187
OpenAI128K ctx50 t/s$10/M out
66.0
Hunyuan Standard 2025 02 10
188
Tencent128K ctx50 t/s$3/M out
66.0
Gemini 3.6 Flash
189
Google1.0M ctx233 t/s$7.5/M out
65.9
Gemini 3.8 Flash (Medium Reasoning)
190
Google1M ctx315 t/s$3.75/M out
65.2
Gemini 1.5 Flash 002
191
Google128K ctx50 t/s$5/M out
65.0
Grok 2 Mini 2024 08 13
192
xAI128K ctx50 t/s$15/M out
65.0
Deepseek V2.5
193
DeepSeek128K ctx50 t/s$1.1/M out
65.0
Granite 4.1 8b
194
IBM128K ctx50 t/s$3/M out
65.0
Mercury
195
Inception128K ctx50 t/s$3/M out
65.0
Olmo 3 32b Think
196
AI2128K ctx50 t/s$3/M out
65.0
Mistral Large 2411
197
Mistral128K ctx50 t/s$6/M out
65.0
Magistral Medium 2506
198
Mistral128K ctx50 t/s$6/M out
65.0
Gemma 3 4b It
199
Google128K ctx50 t/s$5/M out
65.0
Mistral Small 3.1 24b Instruct 2503
200
Mistral128K ctx50 t/s$6/M out
65.0
Qwen2.5 72b Instruct
201
Alibaba128K ctx50 t/s$2/M out
65.0
Llama 3.1 Nemotron 70b Instruct
202
Meta128K ctx50 t/s$0/M out
65.0
Hunyuan Large Vision
203
Tencent128K ctx50 t/s$3/M out
65.0
Llama 3.1 70b Instruct
204
Meta128K ctx50 t/s$0/M out
65.0
Amazon Nova Pro V1.0
205
Amazon128K ctx50 t/s$3/M out
65.0
DeepSeek V4 Flash Vision
206
DeepSeek1.0M ctx120 t/s$1.32/M out
65.0
G9v3-39A5B
207
AI9Stars130K ctx60 t/s$2/M out
65.0
Open
G9v3-3B
208
AI9Stars130K ctx60 t/s$2/M out
65.0
Open
GLM-5.3
209
Zhipu AI1.0M ctx90 t/s$4.4/M out
65.0
Grok 4.6 (low)
210
xAI500K ctx59 t/s$6/M out
65.0
Grok 4.6 (medium)
211
xAI500K ctx59 t/s$6/M out
65.0
Grok 4.6 (xhigh)
212
xAI500K ctx62 t/s$6/M out
65.0
HyperNova 60B
213
Multiverse130K ctx367 t/s$0.14/M out
65.0
Open
KAT-Coder-Pro V2
214
Kwai260K ctx103 t/s$1.2/M out
65.0
LFM2.5-2.6B
215
Liquid AI130K ctx60 t/s$2/M out
65.0
Open
LFM2.5-8B-A1B
216
Liquid AI33K ctx338 t/s$2/M out
65.0
Open
LFM2.5-VL-1.6B
217
Liquid AI32K ctx395 t/s$2/M out
65.0
Open
LongCat 2.0
218
LongCat1.0M ctx42 t/s$2.95/M out
65.0
Open
Magistral Small 1.2
219
Mistral130K ctx60 t/s$1.5/M out
65.0
Open
Qwen3.8 27B (xhigh)
220
Alibaba260K ctx53 t/s$3/M out
65.0
Open
Qwen3.8 27B (low)
221
Alibaba260K ctx64 t/s$3/M out
65.0
Open
Qwen3.8 27B (medium)
222
Alibaba260K ctx62 t/s$3/M out
65.0
Open
Qwen3.8 27B (Non-reasoning)
223
Alibaba260K ctx62 t/s$3/M out
65.0
Open
GLM-5.3 Flash
224
Z.ai262K ctx182 t/s$0.3/M out
64.2
Open
Gemma 2 27b It
225
Google128K ctx50 t/s$5/M out
64.0
Ibm Granite H Small
226
Unknown128K ctx50 t/s$3/M out
64.0
GPT 4 0314
227
OpenAI128K ctx50 t/s$10/M out
64.0
Gemini 1.5 Flash 001
228
Google128K ctx50 t/s$5/M out
64.0
Llama 3.1 Nemotron 51b Instruct
229
Meta128K ctx50 t/s$0/M out
64.0
Llama 3.1 Tulu 3 70b
230
Meta128K ctx50 t/s$0/M out
64.0
Olmo 3.1 32b Think
231
AI2128K ctx50 t/s$3/M out
64.0
Claude 3 Sonnet 20240229
232
Anthropic128K ctx50 t/s$15/M out
64.0
Nemotron 4 340b Instruct
233
NVIDIA128K ctx50 t/s$3/M out
64.0
Llama 3 70b Instruct
234
Meta128K ctx50 t/s$0/M out
64.0
Command R Plus 08 2024
235
Cohere128K ctx50 t/s$3/M out
64.0
GPT 4 0613
236
OpenAI128K ctx50 t/s$10/M out
64.0
Mistral Small 24b Instruct 2501
237
Mistral128K ctx50 t/s$6/M out
64.0
Glm 4 0520
238
Z.ai128K ctx50 t/s$3/M out
64.0
Qwen2.5 Coder 32b Instruct
239
Alibaba128K ctx50 t/s$2/M out
64.0
C4ai Aya Expanse 32b
240
Cohere128K ctx50 t/s$3/M out
63.0
Gemma 2 9b It
241
Google128K ctx50 t/s$5/M out
63.0
Deepseek Coder V2
242
DeepSeek128K ctx50 t/s$1.1/M out
63.0
Qwen2 72b Instruct
243
Alibaba128K ctx50 t/s$2/M out
63.0
Command R Plus
244
Cohere128K ctx50 t/s$3/M out
63.0
Claude 3 Haiku 20240307
245
Anthropic128K ctx50 t/s$15/M out
63.0
Amazon Nova Lite V1.0
246
Amazon128K ctx50 t/s$3/M out
63.0
Gemini 1.5 Flash 8b 001
247
Google128K ctx50 t/s$5/M out
63.0
Olmo 2 0325 32b Instruct
248
AI2128K ctx50 t/s$3/M out
63.0
Command R 08 2024
249
Cohere128K ctx50 t/s$3/M out
63.0
Claude Opus 5 Xhigh
250
Anthropic131K ctx80 t/s$15/M out
62.5
Mistral Large 2402
251
Mistral128K ctx50 t/s$6/M out
62.0
Amazon Nova Micro V1.0
252
Amazon128K ctx50 t/s$3/M out
62.0
Ministral 8b 2410
253
Mistral128K ctx50 t/s$6/M out
62.0
Gemini Pro Dev API
254
Google128K ctx50 t/s$5/M out
62.0
Qwen1.5 110b Chat
255
Alibaba128K ctx50 t/s$2/M out
62.0
Hunyuan Standard 256k
256
Tencent128K ctx50 t/s$3/M out
62.0
Qwen1.5 72b Chat
257
Alibaba128K ctx50 t/s$2/M out
62.0
Gemini 3.8 Flash (Low Reasoning)
258
Google1M ctx340 t/s$3.75/M out
62.0
Claude Opus 5 High
259
Anthropic131K ctx80 t/s$15/M out
61.5
Grok 4.5
260
xAI500K ctx59 t/s$6/M out
61.3
Claude Opus 4.6
261
Anthropic1M ctx50 t/s$15/M out
61.2
legacy
Mixtral 8x22b Instruct V0.1
262
Mistral128K ctx50 t/s$6/M out
61.0
Command R
263
Cohere128K ctx50 t/s$3/M out
61.0
GPT 3.5 Turbo 0125
264
OpenAI128K ctx50 t/s$10/M out
61.0
Llama 3 8b Instruct
265
Meta128K ctx50 t/s$0/M out
61.0
C4ai Aya Expanse 8b
266
Cohere128K ctx50 t/s$3/M out
61.0
Gemini Pro
267
Google128K ctx50 t/s$5/M out
61.0
Llama 3.1 Tulu 3 8b
268
Meta128K ctx50 t/s$0/M out
61.0
Llama 3.1 8b Instruct
269
Meta128K ctx50 t/s$0/M out
61.0
Grok 4
270
xAI131K ctx80 t/s$15/M out
60.9
Grok 4 6
271
xAI131K ctx80 t/s$15/M out
60.9
Gemini 3.1 Pro
272
Google1.0M ctx136 t/s$12/M out
60.6
Granite 3.1 8b Instruct
273
IBM128K ctx50 t/s$3/M out
60.0
Qwen1.5 32b Chat
274
Alibaba128K ctx50 t/s$2/M out
60.0
GPT 3.5 Turbo 1106
275
OpenAI128K ctx50 t/s$10/M out
60.0
Gemma 2 2b It
276
Google128K ctx50 t/s$5/M out
60.0
Phi 3 Medium 4k Instruct
277
Microsoft128K ctx50 t/s$3/M out
60.0
Mixtral 8x7b Instruct V0.1
278
Mistral128K ctx50 t/s$6/M out
60.0
Qwen1.5 14b Chat
279
Alibaba128K ctx50 t/s$2/M out
60.0
GLM-5.2
280
Z.ai262K ctx164 t/s$4.29/M out
59.1
Open
Deepseek LLM 67b Chat
281
DeepSeek128K ctx50 t/s$1.1/M out
59.0
Wizardlm 70b
282
Microsoft128K ctx50 t/s$3/M out
59.0
Granite 3.0 8b Instruct
283
IBM128K ctx50 t/s$3/M out
59.0
Gemma 1.1 7b It
284
Google128K ctx50 t/s$5/M out
59.0
Granite 3.1 2b Instruct
285
IBM128K ctx50 t/s$3/M out
59.0
Phi 3 Small 8k Instruct
286
Microsoft128K ctx50 t/s$3/M out
59.0
Llama 2 70b Chat
287
Meta128K ctx50 t/s$0/M out
59.0
Claude Opus 5 Medium
288
Anthropic131K ctx80 t/s$15/M out
58.6
Granite 4.2 30B Instruct
289
IBM128K ctx78 t/s$1.2/M out
58.6
Open
Llama 3.2 3b Instruct
290
Meta128K ctx50 t/s$0/M out
58.0
Granite 3.0 2b Instruct
291
IBM128K ctx50 t/s$3/M out
58.0
Qwq 32b Preview
292
Alibaba128K ctx50 t/s$2/M out
58.0
Llama2 70b Steerlm Chat
293
Meta128K ctx50 t/s$0/M out
58.0
Qwen3 8 2 4t A95b
294
Alibaba131K ctx85 t/s$2/M out
57.7
Open
Gpt 5 6 Sol High
295
OpenAI131K ctx90 t/s$10/M out
57.3
Wizardlm 13b
296
Microsoft128K ctx50 t/s$3/M out
57.0
Mistral 7b Instruct V0.2
297
Mistral128K ctx50 t/s$6/M out
57.0
Qwen1.5 7b Chat
298
Alibaba128K ctx50 t/s$2/M out
57.0
Phi 3 Mini 4k Instruct June 2024
299
Microsoft128K ctx50 t/s$3/M out
57.0
Llama 2 13b Chat
300
Meta128K ctx50 t/s$0/M out
57.0
Qwen 14b Chat
301
Alibaba128K ctx50 t/s$2/M out
57.0
Palm 2
302
Google128K ctx50 t/s$5/M out
57.0
Gemma 7b It
303
Google128K ctx50 t/s$5/M out
57.0
Codellama 34b Instruct
304
Unknown128K ctx50 t/s$3/M out
57.0
Muse Spark 1 2
305
Meta131K ctx80 t/s$0/M out
56.8
Gemini 3 7 Flash
306
Google131K ctx120 t/s$5/M out
56.0
Phi 3 Mini 128k Instruct
307
Microsoft128K ctx50 t/s$3/M out
56.0
Phi 3 Mini 4k Instruct
308
Microsoft128K ctx50 t/s$3/M out
56.0
Codellama 70b Instruct
309
Unknown128K ctx50 t/s$3/M out
56.0
Gemma 1.1 2b It
310
Google128K ctx50 t/s$5/M out
56.0
Llama 3.2 1b Instruct
311
Meta128K ctx50 t/s$0/M out
56.0
Gpt 5 6 Sol Medium
312
OpenAI131K ctx90 t/s$10/M out
55.6
Llama 2 7b Chat
313
Meta128K ctx50 t/s$0/M out
55.0
Gemma 2b It
314
Google128K ctx50 t/s$5/M out
55.0
Qwen1.5 4b Chat
315
Alibaba128K ctx50 t/s$2/M out
55.0
Grok 4 Heavy
316
xAI256k ctx50 t/s$15/M out
54.5
preview
DeepSeek V4.1 Flash
317
DeepSeek1.0M ctx214 t/s$1.2/M out
54.5
Open
GPT-5.5
318
OpenAI1.1M ctx60 t/s$10/M out
54.0
Olmo 7b Instruct
319
AI2128K ctx50 t/s$3/M out
54.0
Gemini 3 7 Flash Medium
320
Google131K ctx120 t/s$5/M out
53.4
Glm 5
321
Z.ai131K ctx60 t/s$3/M out
52.6
Open
Claude Opus 5 Low
322
Anthropic131K ctx80 t/s$15/M out
52.5
GPT-5.3 Codex
323
OpenAI400K ctx118 t/s$14/M out
52.4
Claude Opus 4.5
324
Anthropic200K ctx50 t/s$15/M out
52.1
legacy
Claude Opus 4.7
325
Anthropic1M ctx80 t/s$15/M out
52.0
Phi-4 Multimodal
326
Microsoft128K ctx85 t/s$0.32/M out
52.0
Gemini 3 Pro
327
Google1M ctx120 t/s$5/M out
51.9
Gpt 5 5 Medium
328
OpenAI131K ctx90 t/s$10/M out
51.4
GPT-5.4
329
OpenAI1.1M ctx60 t/s$10/M out
51.0
legacy
Qwen3.7 Max
330
Alibaba1.0M ctx203 t/s$7.5/M out
51.0
Gemini 3 7 Flash Low
331
Google131K ctx120 t/s$5/M out
50.9
Gpt 5 6 Sol Low
332
OpenAI131K ctx90 t/s$10/M out
50.7
Gpt 5 6 Terra High
333
OpenAI131K ctx90 t/s$10/M out
50.1
Gemini 3.5 Flash
334
Google1.0M ctx267 t/s$9/M out
50.0
Sarvam 105B
335
Sarvam AI128K ctx60 t/s$3/M out
50.0
Open
Sarvam 30B
336
Sarvam AI128K ctx60 t/s$3/M out
50.0
Open
GPT-5.2
337
OpenAI128K ctx90 t/s$10/M out
49.2
legacy
Granite 4.2 8B Instruct
338
IBM128K ctx115 t/s$0.45/M out
49.2
Open
GPT-5.6 Luna
339
OpenAI1.1M ctx175 t/s$1.2/M out
49.1
ERNIE 5.1
340
Baidu131K ctx60 t/s$3/M out
49.1
Kimi K2.6
341
Moonshot AI262.1K ctx40 t/s$4/M out
49.0
Open
Sarvam M Reasoning
342
Sarvam AI128K ctx40 t/s$3/M out
49.0
Open
Kimi K3 Low
343
Moonshot AI131K ctx60 t/s$4/M out
48.3
Agnes 3.0 Flash
344
Agnes1.0M ctx235 t/s$0.15/M out
48.2
Grok 4.3
345
xAI500K ctx129 t/s$2.5/M out
48.0
MiMo V2.5 Pro
346
Xiaomi1.0M ctx65 t/s$0.87/M out
48.0
Open
Muse Spark
347
Meta1.0M ctx80 t/s$0/M out
47.0
Claude Sonnet 4 6 Adaptive
348
Anthropic131K ctx80 t/s$15/M out
47.0
Gpt 5 6 Luna High
349
OpenAI131K ctx90 t/s$10/M out
47.0
Gpt 5 6 Terra Medium
350
OpenAI131K ctx90 t/s$10/M out
46.8
DeepSeek V4 Pro
351
DeepSeek1.0M ctx66 t/s$0.87/M out
46.0
Open
GLM-5.1
352
Z.ai262K ctx74 t/s$4.4/M out
46.0
Open
Claude Sonnet 5
353
Anthropic1.0M ctx96 t/s$10/M out
45.4
Deepseek V4 Pro 0424
354
DeepSeek131K ctx60 t/s$1.1/M out
45.3
Open
MiniMax-M2.7
355
MiniMax1.0M ctx40 t/s$2/M out
45.0
Claude Opus 4 6 Adaptive
356
Anthropic131K ctx80 t/s$15/M out
44.9
Gpt 5 5 Low
357
OpenAI131K ctx90 t/s$10/M out
44.5
Nex N2 Pro
358
Nex AGI262K ctx138 t/s$2.5/M out
44.4
Gpt 5 4 Mini
359
OpenAI131K ctx90 t/s$10/M out
44.0
Claude Opus 4 7 Non Reasoning
360
Anthropic131K ctx50 t/s$15/M out
43.9
Deepseek V4 Pro 0424 High
361
DeepSeek131K ctx60 t/s$1.1/M out
43.7
Open
Claude Sonnet 5 Non Reasoning
362
Anthropic131K ctx50 t/s$15/M out
42.6
Agnes 2.5 Pro Beta
363
Agnes131K ctx65 t/s$3/M out
42.5
Claude Sonnet 4.5
364
Anthropic200K ctx80 t/s$15/M out
42.4
legacy
Gemini 3 Flash
365
Google1M ctx120 t/s$5/M out
42.4
GPT-5.1
366
OpenAI400K ctx60 t/s$10/M out
42.3
legacy
Qwen3.7 Plus
367
Alibaba1.0M ctx54 t/s$1.6/M out
42.2
Deepseek V4 Flash 0420
368
DeepSeek131K ctx60 t/s$1.1/M out
42.1
Open
DeepSeek V4 Flash
369
DeepSeek1.0M ctx113 t/s$0.28/M out
42.0
Open
Granite 4.2 3B Instruct
370
IBM128K ctx148 t/s$0.2/M out
42.0
Open
Claude Opus 4 5 Thinking
371
Anthropic131K ctx50 t/s$15/M out
41.9
Gpt 5 6 Sol Non Reasoning
372
OpenAI131K ctx60 t/s$10/M out
41.9
Kimi K2.7 Code
373
Moonshot AI262K ctx39 t/s$4/M out
41.8
Open
Inkling Small
374
Thinking Machines524K ctx130 t/s$1.2/M out
41.7
Solar Pro4
375
Upstage131K ctx40 t/s$3/M out
41.6
Gpt 5 6 Terra Low
376
OpenAI131K ctx90 t/s$10/M out
41.3
Gpt 5 2 Codex
377
OpenAI131K ctx90 t/s$10/M out
41.2
Qwen3 6 Max
378
Alibaba131K ctx85 t/s$2/M out
41.1
Open
Grok Build 0 1 06 16
379
xAI131K ctx80 t/s$15/M out
40.7
Gpt 5 4 Low
380
OpenAI131K ctx90 t/s$10/M out
40.2
Seed 2.0 Pro
381
ByteDance131K ctx40 t/s$3/M out
40.0
Agnes 2 5 Pro Alpha
382
Agnes131K ctx60 t/s$3/M out
39.7
Gpt 5 4 Nano
383
OpenAI131K ctx90 t/s$10/M out
39.7
MiniMax M3
384
MiniMax524K ctx93 t/s$1.2/M out
39.6
Deepseek V4 Flash 0420 High
385
DeepSeek131K ctx60 t/s$1.1/M out
39.0
Open
Hunyuan Hy3
386
Tencent262K ctx69 t/s$0.56/M out
38.9
Gpt 5 2 Medium
387
OpenAI131K ctx90 t/s$10/M out
38.9
Gpt 5 6 Luna Medium
388
OpenAI131K ctx90 t/s$10/M out
38.9
Gemini 3.5 Flash-Lite
389
Google1.0M ctx389 t/s$2.5/M out
38.8
Gemini 3 Flash Reasoning
390
Google131K ctx80 t/s$5/M out
38.7
Nvidia Nemotron 3 Ultra 550b A55b
391
NVIDIA131K ctx150 t/s$1/M out
38.3
Claude Sonnet 4.6
392
Anthropic1M ctx50 t/s$15/M out
38.1
Deepseek V3 2 Reasoning
393
DeepSeek131K ctx40 t/s$1.1/M out
38.0
Open
Grok 4 20
394
xAI131K ctx80 t/s$15/M out
38.0
Mimo V2 5 0424
395
Xiaomi131K ctx60 t/s$3/M out
38.0
Open
Ling 3 0 Flash
396
Ling131K ctx60 t/s$3/M out
37.8
Qwen3 6 27b
397
Alibaba131K ctx85 t/s$2/M out
37.7
Open
Claude 4 5 Sonnet Thinking
398
Anthropic131K ctx50 t/s$15/M out
37.4
Grok 4 20 0309
399
xAI131K ctx80 t/s$15/M out
37.4
Gpt 5 Codex
400
OpenAI131K ctx90 t/s$10/M out
37.0
Grok 4 3 Medium
401
xAI131K ctx80 t/s$15/M out
36.9
Glm 5 1 Non Reasoning
402
Z.ai131K ctx40 t/s$3/M out
36.3
Open
Grok 4 3 Low
403
xAI131K ctx80 t/s$15/M out
36.3
Kimi K2 5
404
Moonshot AI131K ctx60 t/s$4/M out
36.0
Gemini 3 5 Flash Minimal
405
Google131K ctx120 t/s$5/M out
35.8
Gpt 5 5 Non Reasoning
406
OpenAI131K ctx60 t/s$10/M out
35.8
Gpt 5 1 Codex
407
OpenAI131K ctx90 t/s$10/M out
35.6
Kimi K2 6 Non Reasoning
408
Moonshot AI131K ctx40 t/s$4/M out
35.4
Claude Sonnet 4 6 Non Reasoning Low Effort
409
Anthropic131K ctx50 t/s$15/M out
35.1
Muse Glimmer
410
Meta131K ctx80 t/s$0/M out
35.1
Gemma 4 31B
411
Google262.1K ctx35 t/s$0.3/M out
35.0
Open
Mistral Medium 3.5
412
Mistral131K ctx60 t/s$6/M out
35.0
Glm 5 2 Non Reasoning
413
Z.ai131K ctx40 t/s$3/M out
34.8
Open
Gpt 5 6 Terra Non Reasoning
414
OpenAI131K ctx60 t/s$10/M out
34.6
Gpt 5 Medium
415
OpenAI131K ctx90 t/s$10/M out
34.6
Claude 4 1 Opus Thinking
416
Anthropic131K ctx50 t/s$15/M out
34.5
Hy3 Preview
417
Tencent131K ctx60 t/s$3/M out
34.4
Gpt 5 5 Instant 05 26
418
OpenAI131K ctx90 t/s$10/M out
34.3
Gemini 3 Pro Low
419
Google131K ctx120 t/s$5/M out
33.9
Gpt 5 6 Luna Low
420
OpenAI131K ctx90 t/s$10/M out
33.9
Kimi K2 Thinking
421
Moonshot AI131K ctx40 t/s$4/M out
33.5
O3 Pro
422
OpenAI131K ctx60 t/s$10/M out
33.3
Glm 5 Non Reasoning
423
Z.ai131K ctx40 t/s$3/M out
33.2
Open
Claude 4 5 Haiku Reasoning
424
Anthropic131K ctx50 t/s$15/M out
33.0
Qwen3 5 397b A17b Non Reasoning
425
Alibaba131K ctx55 t/s$2/M out
32.7
Open
Qwen3.6 Plus
426
Alibaba1.0M ctx55 t/s$3/M out
32.4
Minimax M2 1
427
MiniMax131K ctx60 t/s$2/M out
32.1
Open
Qwen3 6 35b A3b
428
Alibaba131K ctx85 t/s$2/M out
32.1
Open
o3
429
OpenAI200K ctx90 t/s$10/M out
32.0
legacy
Nova 2 0 Pro Reasoning Medium
430
Amazon131K ctx40 t/s$3.2/M out
32.0
Nvidia Nemotron 3 Super 120b A12b
431
NVIDIA131K ctx150 t/s$1/M out
32.0
Deepseek V4 Pro 0424 Non Reasoning
432
DeepSeek131K ctx40 t/s$1.1/M out
31.9
Open
Gpt 5 Low
433
OpenAI131K ctx90 t/s$10/M out
31.9
Mimo V2 Flash Reasoning
434
Xiaomi131K ctx40 t/s$3/M out
31.9
Open
Inkling
435
Thinking Machines524K ctx81 t/s$4.05/M out
31.7
Claude 4 Opus Thinking
436
Anthropic131K ctx50 t/s$15/M out
31.7
Gpt 5 Mini Medium
437
OpenAI131K ctx90 t/s$10/M out
31.6
Gpt 5 1 Codex Mini
438
OpenAI131K ctx90 t/s$10/M out
31.3
Qwen3 5 Omni Plus
439
Alibaba131K ctx85 t/s$2/M out
31.3
Open
Qwen3 6 27b Non Reasoning
440
Alibaba131K ctx55 t/s$2/M out
31.3
Open
Ring 2 6 1t
441
WeRide131K ctx60 t/s$3/M out
31.3
Deepseek V3 1 Terminus Reasoning
442
DeepSeek131K ctx40 t/s$1.1/M out
31.1
Open
Step 3 7 Flash
443
StepFun131K ctx60 t/s$3/M out
30.9
Gpt 5 4 Nano Medium
444
OpenAI131K ctx90 t/s$10/M out
30.8
Gpt 5 4 Mini Medium
445
OpenAI131K ctx90 t/s$10/M out
30.5
Kimi K2 5 Non Reasoning
446
Moonshot AI131K ctx40 t/s$4/M out
30.1
GPT-oss-120B
447
OpenAI131K ctx240 t/s$0.4/M out
30.0
Open
Qwen3 5 27b Non Reasoning
448
Alibaba131K ctx55 t/s$2/M out
30.0
Open
Claude 4 5 Sonnet
449
Anthropic131K ctx80 t/s$15/M out
29.9
Claude 4 Sonnet Thinking
450
Anthropic131K ctx50 t/s$15/M out
29.8
Deepseek V4 Flash Non Reasoning
451
DeepSeek131K ctx40 t/s$1.1/M out
29.3
Open
Glm 4 6 Reasoning
452
Z.ai131K ctx40 t/s$3/M out
29.3
Open
Gpt 5 5 Instant 06 26
453
OpenAI131K ctx90 t/s$10/M out
29.2
Minimax M2
454
MiniMax131K ctx60 t/s$2/M out
28.9
Open
Claude 4 1 Opus
455
Anthropic131K ctx80 t/s$15/M out
28.8
Mimo V2 5 Pro Non Reasoning
456
Xiaomi131K ctx40 t/s$3/M out
28.4
Open
Gpt 5 4 Non Reasoning
457
OpenAI131K ctx60 t/s$10/M out
28.3
Qwen3 5 122b A10b Non Reasoning
458
Alibaba131K ctx55 t/s$2/M out
28.2
Open
Grok 4 Fast Reasoning
459
xAI131K ctx50 t/s$15/M out
27.9
Glm 4 7 Non Reasoning
460
Z.ai131K ctx40 t/s$3/M out
27.1
Open
Gpt 5 6 Luna Non Reasoning
461
OpenAI131K ctx60 t/s$10/M out
26.8
Hy3 Non Reasoning
462
Tencent131K ctx40 t/s$3/M out
26.6
Ling 2 6 1t
463
Ling131K ctx60 t/s$3/M out
26.6
Gpt 5 2 Non Reasoning
464
OpenAI131K ctx60 t/s$10/M out
26.5
Gemma 4 26b A4b
465
Google131K ctx120 t/s$5/M out
26.1
Open
Claude 4 Opus
466
Anthropic131K ctx80 t/s$15/M out
26.0
Claude 4 Sonnet
467
Anthropic131K ctx80 t/s$15/M out
26.0
Step 3 5 Flash 0202
468
StepFun131K ctx60 t/s$3/M out
26.0
Deepseek V3 2 Reasoning 0925
469
DeepSeek131K ctx40 t/s$1.1/M out
25.9
Open
Gpt 5 Mini
470
OpenAI131K ctx90 t/s$10/M out
25.8
Qwen3 Max Thinking Preview
471
Alibaba131K ctx55 t/s$2/M out
25.5
Open
Grok 4 3 Non Reasoning
472
xAI131K ctx50 t/s$15/M out
25.0
Qwen3 6 35b A3b Non Reasoning
473
Alibaba131K ctx55 t/s$2/M out
24.6
Open
Ling 3 0 Tiny
474
Ling131K ctx60 t/s$3/M out
24.5
Qwen3 5 35b A3b Non Reasoning
475
Alibaba131K ctx55 t/s$2/M out
24.3
Open
Claude 4.5 Haiku
476
Anthropic200K ctx80 t/s$15/M out
24.1
Kimi K2 0905
477
Moonshot AI131K ctx60 t/s$4/M out
24.0
Qwen3.5 397B-A17B
478
Alibaba262.1K ctx71 t/s$2/M out
23.9
Open
Claude 3 7 Sonnet
479
Anthropic131K ctx80 t/s$15/M out
23.9
O1
480
OpenAI131K ctx60 t/s$10/M out
23.9
Nemotron 3 5 Lightning
481
NVIDIA131K ctx150 t/s$1/M out
23.6
GPT-5
482
OpenAI400K ctx60 t/s$10/M out
23.0
legacy
Solar Pro 3
483
Upstage131K ctx40 t/s$3/M out
23.0
Grok 3 Mini Reasoning
484
xAI131K ctx50 t/s$15/M out
22.9
Grok 4 20 0309 Non Reasoning
485
xAI131K ctx50 t/s$15/M out
22.9
Command A Plus
486
Cohere131K ctx60 t/s$10/M out
22.8
Gemini 2 5 Pro 05 06
487
Google131K ctx120 t/s$5/M out
22.7
Gemma 4 31b Non Reasoning
488
Google131K ctx80 t/s$5/M out
22.3
Open
Gemma 4 12b
489
Google131K ctx120 t/s$5/M out
22.2
Open
Grok 4 20 Non Reasoning
490
xAI131K ctx50 t/s$15/M out
22.2
Qwen3.5 122B-A10B
491
Alibaba262.1K ctx126 t/s$2/M out
22.0
Open
GPT-oss-20B
492
OpenAI131K ctx90 t/s$0.2/M out
22.0
Open
K2 Think V2
493
K2131K ctx40 t/s$3/M out
22.0
Mercury 2
494
Inception131K ctx60 t/s$3/M out
21.9
Qwen3 5 9b
495
Alibaba131K ctx85 t/s$2/M out
21.8
Open
Claude Opus 4.1
496
Anthropic200K ctx80 t/s$15/M out
21.7
legacy
Deepseek V3 2 0925
497
DeepSeek131K ctx60 t/s$1.1/M out
21.7
Open
Apriel V1 5 15b Thinker
498
ServiceNow131K ctx60 t/s$3/M out
21.6
Nova 2 0 Omni Reasoning Medium
499
Amazon131K ctx40 t/s$3.2/M out
21.3
Qwen3 Coder Next
500
Alibaba131K ctx85 t/s$2/M out
21.3
Open
Deepseek V3 1 Reasoning
501
DeepSeek131K ctx40 t/s$1.1/M out
21.0
Open
Qwen3 Vl 235b A22b Reasoning
502
Alibaba131K ctx55 t/s$2/M out
20.9
Open
Apriel V1 6 15b Thinker
503
ServiceNow131K ctx60 t/s$3/M out
20.8
Nova 2 0 Lite Reasoning
504
Amazon131K ctx40 t/s$3.2/M out
20.8
Gpt 5 1 Non Reasoning
505
OpenAI131K ctx60 t/s$10/M out
20.7
Qwen3 5 9b Non Reasoning
506
Alibaba131K ctx55 t/s$2/M out
20.6
Open
Gemma 4 26b A4b Non Reasoning
507
Google131K ctx80 t/s$5/M out
20.4
Open
Qwen3 5 4b
508
Alibaba131K ctx85 t/s$2/M out
20.4
Open
Gemini 2 5 Flash Reasoning
509
Google131K ctx80 t/s$5/M out
20.3
North Mini Code
510
North131K ctx60 t/s$3/M out
20.2
Gpt 5 Nano
511
OpenAI131K ctx90 t/s$10/M out
20.1
Qwen3 235b A22b Instruct 2507 Reasoning
512
Alibaba131K ctx55 t/s$2/M out
19.9
Open
Nova 2 0 Pro Reasoning Low
513
Amazon131K ctx40 t/s$3.2/M out
19.8
Kimi K2
514
Moonshot AI131K ctx60 t/s$4/M out
19.7
Mistral Small 4
515
Mistral131K ctx100 t/s$6/M out
19.7
Open
Qwen3 Max
516
Alibaba262.1K ctx85 t/s$2/M out
19.6
Openlegacy
Gpt 4 1
517
OpenAI131K ctx90 t/s$10/M out
19.6
Qwen3 Max Preview
518
Alibaba131K ctx85 t/s$2/M out
19.4
Open
Devstral 2
519
Mistral131K ctx100 t/s$6/M out
19.2
Gpt 5 Nano Medium
520
OpenAI131K ctx90 t/s$10/M out
19.2
Nova 2 0 Lite Reasoning Medium
521
Amazon131K ctx40 t/s$3.2/M out
19.2
O3 Mini
522
OpenAI131K ctx60 t/s$10/M out
19.2
Qwen3 5 Omni Flash
523
Alibaba131K ctx85 t/s$2/M out
19.2
Open
O1 Pro
524
OpenAI131K ctx60 t/s$10/M out
19.1
Nemotron 3 Ultra 550B
525
NVIDIA512K ctx142 t/s$2.75/M out
19.0
Open
Deepseek R1 0120
526
DeepSeek131K ctx40 t/s$1.1/M out
18.6
Open
Seed Oss 36b Instruct
527
ByteDance131K ctx60 t/s$3/M out
18.5
Qwen3 235b A22b Instruct 2507
528
Alibaba131K ctx85 t/s$2/M out
18.4
Open
Trinity Large Thinking
529
Trinity131K ctx40 t/s$3/M out
18.4
Qwen3 Coder 480b A35b Instruct
530
Alibaba131K ctx85 t/s$2/M out
18.2
Open
Qwen3 Vl 32b Reasoning
531
Alibaba131K ctx55 t/s$2/M out
18.1
Open
Nova 2 0 Lite Reasoning Low
532
Amazon131K ctx40 t/s$3.2/M out
18.0
Minimax M1 80k
533
MiniMax131K ctx60 t/s$2/M out
17.9
Open
Gpt 5 4 Nano Non Reasoning
534
OpenAI131K ctx60 t/s$10/M out
17.8
Devstral Small 2
535
Mistral131K ctx100 t/s$6/M out
17.7
Gpt 5 Minimal
536
OpenAI131K ctx90 t/s$10/M out
17.3
O1 Preview
537
OpenAI131K ctx60 t/s$10/M out
17.2
Glm 4 6v Reasoning
538
Z.ai131K ctx40 t/s$3/M out
16.9
Open
Qwen3 Next 80b A3b Reasoning
539
Alibaba131K ctx55 t/s$2/M out
16.9
Open
Gpt 5 4 Mini Non Reasoning
540
OpenAI131K ctx60 t/s$10/M out
16.8
Nova 2 0 Omni Reasoning Low
541
Amazon131K ctx40 t/s$3.2/M out
16.7
Grok 4 Fast
542
xAI131K ctx80 t/s$15/M out
16.6
Qwen3 5 4b Non Reasoning
543
Alibaba131K ctx55 t/s$2/M out
16.1
Open
Mistral Large 3
544
Mistral131K ctx100 t/s$6/M out
15.9
Open
O3 Mini High
545
OpenAI131K ctx60 t/s$10/M out
15.7
Glm 4 7 Flash Non Reasoning
546
Z.ai131K ctx40 t/s$3/M out
15.6
Open
Deepseek V3 0324
547
DeepSeek131K ctx60 t/s$1.1/M out
15.2
Open
Gemini 2 5 Flash Lite Preview 09 2025 Reasoning
548
Google131K ctx80 t/s$5/M out
15.2
Nemotron 3 Nano Omni 30b A3b
549
NVIDIA131K ctx150 t/s$1/M out
15.0
Gpt Oss 120b Low
550
OpenAI131K ctx90 t/s$10/M out
14.9
Mistral Small 3 1
551
Mistral131K ctx100 t/s$6/M out
14.9
Open
Gpt 4 1 Mini
552
OpenAI131K ctx90 t/s$10/M out
14.8
Mistral Medium 3 1
553
Mistral131K ctx100 t/s$6/M out
14.7
Open
Qwen3 30b A3b 2507 Reasoning
554
Alibaba131K ctx55 t/s$2/M out
14.6
Open
Nvidia Nemotron 3 Nano 30b A3b Reasoning
555
NVIDIA131K ctx100 t/s$1/M out
14.5
Nova 2.0 Pro Preview
556
Amazon1.0M ctx40 t/s$3.2/M out
14.4
preview
Gpt Oss 20b Low
557
OpenAI131K ctx90 t/s$10/M out
14.4
Qwen3 Vl 235b A22b Instruct
558
Alibaba131K ctx85 t/s$2/M out
14.4
Open
Gpt 5 Mini Minimal
559
OpenAI131K ctx90 t/s$10/M out
14.3
Ling 2 6 Flash
560
Ling131K ctx60 t/s$3/M out
14.2
Qwen3 Next 80b A3b Instruct
561
Alibaba131K ctx85 t/s$2/M out
13.8
Open
Qwen3 Coder 30b A3b Instruct
562
Alibaba131K ctx85 t/s$2/M out
13.6
Open
Qwen3 235b A22b Instruct Reasoning
563
Alibaba131K ctx55 t/s$2/M out
13.5
Open
Qwen3 Vl 30b A3b Reasoning
564
Alibaba131K ctx55 t/s$2/M out
13.4
Open
Qwq 32b
565
Alibaba131K ctx85 t/s$2/M out
13.4
Gemma 4 12b Non Reasoning
566
Google131K ctx80 t/s$5/M out
13.2
Open
Gemini 2 5 Flash Lite Preview 09 2025
567
Google131K ctx120 t/s$5/M out
13.1
DeepSeek V3.2
568
DeepSeek163.8K ctx60 t/s$1.1/M out
12.9
Openlegacy
Nova Premier
569
Amazon131K ctx60 t/s$3.2/M out
12.7
Mistral Medium 3
570
Mistral131K ctx100 t/s$6/M out
12.5
Open
Celeris 1
571
Celeris131K ctx60 t/s$3/M out
12.4
Llama Nemotron Super 49b V1 5 Reasoning
572
Meta131K ctx50 t/s$0/M out
12.4
Open
Mistral Small 4 Non Reasoning
573
Mistral131K ctx60 t/s$6/M out
12.3
Open
Gemma 4 E4b
574
Google131K ctx120 t/s$5/M out
12.2
Open
Claude 3 Opus
575
Anthropic131K ctx80 t/s$15/M out
11.8
Nova 2 0 Lite
576
Amazon131K ctx60 t/s$3.2/M out
11.8
Gemini 2 5 Flash Lite Reasoning
577
Google131K ctx80 t/s$5/M out
11.4
Qwen3 32b Instruct Reasoning
578
Alibaba131K ctx55 t/s$2/M out
11.4
Open
Ministral 3 14b
579
Mistral131K ctx100 t/s$6/M out
11.2
Qwen3 Vl 32b Instruct
580
Alibaba131K ctx85 t/s$2/M out
11.0
Open
Qwen3 235b A22b Instruct
581
Alibaba131K ctx85 t/s$2/M out
10.8
Open
Mistral Small 3 2
582
Mistral131K ctx100 t/s$6/M out
10.7
Open
Gemini 2 0 Flash Experimental
583
Google131K ctx120 t/s$5/M out
10.6
Qwen3 Vl 8b Reasoning
584
Alibaba131K ctx55 t/s$2/M out
10.5
Open
Nova 2 0 Omni
585
Amazon131K ctx60 t/s$3.2/M out
10.4
Qwen3 14b Instruct Reasoning
586
Alibaba131K ctx55 t/s$2/M out
10.4
Open
Llama 4 Scout
587
Meta131K ctx80 t/s$0/M out
10.3
Open
Hermes 4 Llama 3 1 70b Reasoning
588
Meta131K ctx50 t/s$0/M out
9.9
Open
Qwen3 Vl 30b A3b Instruct
589
Alibaba131K ctx85 t/s$2/M out
9.9
Open
Claude 35 Sonnet
590
Anthropic131K ctx80 t/s$15/M out
9.8
Deepseek R1 Distill Llama 70b
591
DeepSeek131K ctx40 t/s$1.1/M out
9.8
Open
Gpt 4 1 Nano
592
OpenAI131K ctx90 t/s$10/M out
9.6
Qwen3 Omni 30b A3b Reasoning
593
Alibaba131K ctx55 t/s$2/M out
9.5
Open
Gpt 4o 2024 08 06
594
OpenAI131K ctx90 t/s$10/M out
9.4
Llama 3 3 Instruct 70b
595
Meta131K ctx80 t/s$0/M out
9.3
Open
Qwen3 30b A3b Instruct Reasoning
596
Alibaba131K ctx55 t/s$2/M out
9.2
Open
Glm 4 5v Reasoning
597
Z.ai131K ctx40 t/s$3/M out
9.0
Open
Ministral 3 8b
598
Mistral131K ctx100 t/s$6/M out
9.0
Ernie 4 5 300b A47b
599
Baidu131K ctx60 t/s$3/M out
8.9
Llama 3 1 Nemotron Ultra 253b V1 Reasoning
600
Meta131K ctx50 t/s$0/M out
8.9
Open
Qwen3 30b A3b 2507
601
Alibaba131K ctx85 t/s$2/M out
8.9
Open
Hermes 4 Llama 3 1 405b Reasoning
602
Meta131K ctx50 t/s$0/M out
8.8
Open
Nvidia Nemotron Nano 12b V2 Vl Reasoning
603
NVIDIA131K ctx100 t/s$1/M out
8.8
Gemma 4 E4b Non Reasoning
604
Google131K ctx80 t/s$5/M out
8.7
Open
Nvidia Nemotron Nano 9b V2 Reasoning
605
NVIDIA131K ctx100 t/s$1/M out
8.7
Hermes 4 Llama 3 1 405b
606
Meta131K ctx80 t/s$0/M out
8.6
Open
Llama Nemotron Super 49b V1 5
607
Meta131K ctx80 t/s$0/M out
8.5
Open
Qwen3 32b Instruct
608
Alibaba131K ctx85 t/s$2/M out
8.5
Open
Gpt 4o 2024 05 13
609
OpenAI131K ctx90 t/s$10/M out
8.4
Qwen3 8b Instruct Reasoning
610
Alibaba131K ctx55 t/s$2/M out
8.3
Open
Qwen3 Vl 8b Instruct
611
Alibaba131K ctx85 t/s$2/M out
8.2
Open
Claude 35 Sonnet June 24
612
Anthropic131K ctx80 t/s$15/M out
8.1
Gpt 5 Nano Minimal
613
OpenAI131K ctx90 t/s$10/M out
7.8
Gpt 4 Turbo
614
OpenAI131K ctx90 t/s$10/M out
7.7
Command A
615
Cohere131K ctx60 t/s$10/M out
7.5
Nova Pro
616
Amazon131K ctx60 t/s$3.2/M out
7.5
Gemma 3 27b
617
Google131K ctx120 t/s$5/M out
7.4
Open
Llama 3 1 Instruct 8b
618
Meta131K ctx80 t/s$0/M out
7.4
Open
Llama 3 1 Nemotron Instruct 70b
619
Meta131K ctx80 t/s$0/M out
7.4
Open
Nvidia Nemotron 3 Nano 30b A3b
620
NVIDIA131K ctx150 t/s$1/M out
7.2
Nvidia Nemotron Nano 9b V2
621
NVIDIA131K ctx150 t/s$1/M out
7.2
Ministral 3 3b
622
Mistral131K ctx100 t/s$6/M out
7.1
Mistral Large 2407
623
Mistral131K ctx100 t/s$6/M out
7.0
Open
Gpt 4
624
OpenAI131K ctx90 t/s$10/M out
6.8
Qwen3 14b Instruct
625
Alibaba131K ctx85 t/s$2/M out
6.8
Open
Gemini 2 5 Flash Lite
626
Google131K ctx120 t/s$5/M out
6.7
Hermes 4 Llama 3 1 70b
627
Meta131K ctx80 t/s$0/M out
6.7
Open
Mistral Small 3
628
Mistral131K ctx100 t/s$6/M out
6.7
Open
Nova Lite
629
Amazon131K ctx60 t/s$3.2/M out
6.7
Qwen3 30b A3b Instruct
630
Alibaba131K ctx85 t/s$2/M out
6.6
Open
Llama 3 1 Instruct 70b
631
Meta131K ctx80 t/s$0/M out
6.5
Open
Qwen Turbo
632
Alibaba131K ctx85 t/s$2/M out
6.0
Open
Reka Flash
633
Reka131K ctx60 t/s$3/M out
6.0
Solar Mini
634
Upstage131K ctx60 t/s$3/M out
6.0
Phi 4 Mini
635
Microsoft131K ctx60 t/s$0.6/M out
5.7
Open
Gemma 3 12b
636
Google131K ctx120 t/s$5/M out
5.5
Open
DeepSeek R1
637
DeepSeek163.8K ctx60 t/s$1.1/M out
5.4
Openlegacy
Granite 4 0 H Small
638
IBM131K ctx60 t/s$3/M out
4.9
Open
Hermes 3 Llama 3 1 70b
639
Meta131K ctx80 t/s$0/M out
4.8
Open
Jamba 1 5 Large
640
AI21 Labs131K ctx60 t/s$3/M out
4.8
Qwen3 8b Instruct
641
Alibaba131K ctx85 t/s$2/M out
4.8
Open
Qwen3 Omni 30b A3b Instruct
642
Alibaba131K ctx85 t/s$2/M out
4.8
Open
Nova Micro
643
Amazon131K ctx60 t/s$3.2/M out
4.4
Mistral Small
644
Mistral131K ctx100 t/s$6/M out
4.3
Open
Nvidia Nemotron Nano 12b V2 Vl
645
NVIDIA131K ctx150 t/s$1/M out
4.2
Mistral Large
646
Mistral131K ctx100 t/s$6/M out
4.1
Open
Llama 2 Chat 7b
647
Meta131K ctx80 t/s$0/M out
3.9
Open
Reka Flash 3
648
Reka131K ctx60 t/s$3/M out
3.7
Claude 3 Haiku
649
Anthropic131K ctx80 t/s$15/M out
3.5
Gpt 35 Turbo
650
OpenAI131K ctx90 t/s$10/M out
3.2
Mistral Medium
651
Mistral131K ctx100 t/s$6/M out
3.2
Open
Mistral Small 2402
652
Mistral131K ctx100 t/s$6/M out
3.2
Open
Llama 3 Instruct 70b
653
Meta131K ctx80 t/s$0/M out
3.1
Open
Llama 3 2 Instruct 11b Vision
654
Meta131K ctx80 t/s$0/M out
3.0
Open
Command R Plus 04 2024
655
Cohere131K ctx60 t/s$10/M out
2.6
Olmo 3 7b Instruct
656
AI2131K ctx60 t/s$3/M out
2.4
Open
Jamba 1 5 Mini
657
AI21 Labs131K ctx60 t/s$3/M out
2.3
Apertus 70b Instruct
658
Swiss AI131K ctx60 t/s$3/M out
2.0
Mixtral 8x7b Instruct
659
Mistral131K ctx100 t/s$6/M out
2.0
Command R 03 2024
660
Cohere131K ctx60 t/s$10/M out
1.7
Mistral 7b Instruct
661
Mistral131K ctx100 t/s$6/M out
1.7
Open
Granite 3 3 8b Instruct
662
IBM131K ctx60 t/s$3/M out
1.3
Open
Apertus 8b Instruct
663
Swiss AI131K ctx60 t/s$3/M out
1.0
Gemma 3 1b
664
Google131K ctx120 t/s$5/M out
1.0
Open
Gemma 3 4b
665
Google131K ctx120 t/s$5/M out
1.0
Open
Gemma 3n E2b
666
Google131K ctx120 t/s$5/M out
1.0
Open
Gemma 3n E4b
667
Google131K ctx120 t/s$5/M out
1.0
Open
Llama 3 Instruct 8b
668
Meta131K ctx80 t/s$0/M out
1.0
Open
Tiny Aya Global
669
Cohere131K ctx60 t/s$10/M out
1.0
Claude Mythos 5
670
Anthropic1.0M ctx50 t/s$50/M out
0.0
preview
GPT-5.5 Pro
671
OpenAI1.1M ctx60 t/s$10/M out
0.0
Claude Sonnet 4.6 (max)
672
Anthropic1.0M ctx50 t/s$15/M out
0.0
Amazon Nova
673
Amazon131K ctx60 t/s$3.2/M out
0.0
Async Flash V1 5
674
Async131K ctx60 t/s$3/M out
0.0
Async Pro V1 0
675
Async131K ctx60 t/s$3/M out
0.0
Asyncflow V2
676
Async131K ctx60 t/s$3/M out
0.0
Claude Sonnet 5 High
677
Anthropic131K ctx80 t/s$15/M out
0.0
Claude Sonnet 5 Low
678
Anthropic131K ctx80 t/s$15/M out
0.0
Claude Sonnet 5 Medium
679
Anthropic131K ctx80 t/s$15/M out
0.0
Claude Sonnet 5 Xhigh
680
Anthropic131K ctx80 t/s$15/M out
0.0
Cogito V2 1 Reasoning
681
Cogito131K ctx40 t/s$3/M out
0.0
Falcon 2
682
TII131K ctx60 t/s$3/M out
0.0
Open
Gemini
683
Google131K ctx120 t/s$5/M out
0.0
Gemini 2 5 Flash Dec 2025
684
Google131K ctx120 t/s$5/M out
0.0
Gemini_nano Banana Pro
685
Google131K ctx120 t/s$5/M out
0.0
Gladia Solaria
686
Upstage131K ctx60 t/s$3/M out
0.0
Gpt 5 4 Pro
687
OpenAI131K ctx90 t/s$10/M out
0.0
Gpt Realtime 2
688
OpenAI131K ctx90 t/s$10/M out
0.0
Grok Stt
689
xAI131K ctx80 t/s$15/M out
0.0
Hidream O1 Image
690
OpenAI131K ctx60 t/s$10/M out
0.0
Minimax H3
691
MiniMax131K ctx60 t/s$2/M out
0.0
Open
Mistral
692
Mistral131K ctx100 t/s$6/M out
0.0
Open
Nvidia
693
NVIDIA131K ctx150 t/s$1/M out
0.0
Nvidia Nemotron Asr Streaming
694
NVIDIA131K ctx150 t/s$1/M out
0.0
Ocateve 2
695
Ocat131K ctx60 t/s$3/M out
0.0
Qwen Image
696
Alibaba131K ctx85 t/s$2/M out
0.0
Open
Qwen3 Asr
697
Alibaba131K ctx85 t/s$2/M out
0.0
Open
Apodex 1.1
698
Independent128K ctx145 t/s$0.8/M out
0.0
Open
Muse Spark 1.3 (xhigh)
699
Muse256K ctx65 t/s$10/M out
0.0
Quasar 438B
700
Open Source128K ctx95 t/s$1.6/M out
0.0
Open
0 / 4
Compare Now →