AI Models Directory

Browse all 767 language models from 56 providers — benchmarks, pricing, speed and rankings in one place.

Anthropic77Moonshot AI18ElevenLabs2Black Forest Labs4Google69OpenAI125xAI36Cartesia1Mistral37Alibaba98Independent5Lightricks2StepFun8Zhipu AI3Kwai2Ling8Xiaomi6NVIDIA18DeepSeek36Z.ai23Baidu5LongCat3Amazon25Tencent13MiniMax9Meta42Cohere12AI27AI9Stars2IBM10Inception3Liquid AI3Multiverse1Muse2Microsoft9Sarvam AI3Agnes3Nex AGI1Thinking Machines2Upstage4ByteDance2WeRide1K21ServiceNow2North1Trinity1Celeris1Reka2AI21 Labs2Swiss AI2Async3Cogito1Ocat1Open 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/M out
97.4
preview
Claude 5.5 Sonnet
2
Anthropic1M ctx94 t/s$15/M/M out
94.8
Kimi K3.1 Pro
3
Moonshot AI1.0M ctx45 t/s$20/M/M out
94.2
Open
Eleven Multilingual v3
4
ElevenLabs32K ctx200 t/s$0.05/M/M out
94.0
FLUX.2 Pro
5
Black Forest Labs128K ctx30 t/s$0.08/M/M out
93.8
Gemini 4 Argon
6
Google2M ctx88 t/s$10/M/M out
93.6
preview
Claude Fable 5
7
Anthropic1.0M ctx71 t/s$50/M/M out
93.4
GPT-Image 2
8
OpenAI128K ctx25 t/s$0.09/M/M out
93.1
Grok Imagine Quality
9
xAI128K ctx34 t/s$0.06/M/M out
92.6
ElevenLabs Scribe v2
10
ElevenLabs64K ctx240 t/s$0.016/M/M out
92.5
GPT-6.1 Sol
11
OpenAI1M ctx75 t/s$20/M/M out
92.4
Cartesia Ink Whisper
12
Cartesia64K ctx260 t/s$0.012/M/M out
91.8
Kimi K3.1 Highspeed
13
Moonshot AI1.0M ctx130 t/s$8/M/M out
91.5
Open
Gemini 3.1 Pro Preview
14
Google1M ctx105 t/s$5/M/M out
90.8
preview
FLUX.2 Dev
15
Black Forest Labs128K ctx28 t/s$0.03/M/M out
90.4
Open
Voxtral 3 TTS
16
Mistral32K ctx165 t/s$0.03/M/M out
90.2
Mistral Large 4
17
Mistral256K ctx92 t/s$6/M/M out
89.8
Qwen Audio 3.1 TTS+
18
Alibaba32K ctx140 t/s$0.02/M/M out
89.4
Open
FLUX.2 Max
19
Independent128K ctx35 t/s$0.05/M/M out
89.2
LTX-2.3 Pro
20
Lightricks64K ctx18 t/s$0.12/M/M out
89.1
Claude Fable 5.1 (XHigh)
21
Anthropic500K ctx78 t/s$15/M/M out
89.0
Step Audio 2
22
StepFun64K ctx150 t/s$0.024/M/M out
89.0
GLM-4.5 Air
23
Zhipu AI131K ctx96 t/s$1.1/M/M out
88.9
Open
Kling 3.0 Pro
24
Kwai64K ctx25 t/s$0.1/M/M out
88.6
Ling 3.1 Flash
25
Ling131K ctx175 t/s$0.8/M/M out
88.5
Claude Fable 5.1
26
Anthropic500K ctx85 t/s$15/M/M out
88.4
MiMo v2.6 Flash
27
Xiaomi1M ctx118 t/s$0.3/M/M out
88.4
Open
FLUX.2 Klein 9B
28
Black Forest Labs64K ctx55 t/s$0.02/M/M out
88.2
Open
Qwen3 TTS Flash
29
Alibaba32K ctx230 t/s$0.01/M/M out
88.1
NVIDIA Nemotron 3.5 Super-VL
30
NVIDIA512K ctx110 t/s$1.2/M/M out
87.8
Open
Simba 3.2
31
Independent262K ctx62 t/s$10/M/M out
87.8
Claude 5.5 Haiku
32
Anthropic500K ctx145 t/s$4/M/M out
87.5
Wan 2.2 A14B
33
Alibaba64K ctx15 t/s$0.06/M/M out
87.4
Open
ElevenLabs v4 Turbo
34
Independent32K ctx220 t/s$0.03/M/M out
87.1
GPT-6 Astra (xhigh)
35
OpenAI1.1M ctx76 t/s$50/M/M out
87.0
Claude Fable 5.1 (High)
36
Anthropic500K ctx92 t/s$15/M/M out
86.5
Deepgram Flux
37
Independent64K ctx260 t/s$0.015/M/M out
86.5
FLUX.2 Klein 4B
38
Black Forest Labs32K ctx90 t/s$0.01/M/M out
86.5
Open
GPT-6 Astra
39
OpenAI1.1M ctx82 t/s$50/M/M out
86.2
LTX-2.3 Fast
40
Lightricks64K ctx60 t/s$0.05/M/M out
86.2
Gemini 3.1 Flash Lite Preview
41
Google1M ctx210 t/s$0.3/M/M out
85.4
preview
GPT-6 Astra (high)
42
OpenAI1.1M ctx90 t/s$50/M/M out
85.0
GPT-6 Luna
43
OpenAI1.0M ctx120 t/s$20/M/M out
84.5
Claude Opus 5.5 (XHigh)
44
Anthropic1.0M ctx62 t/s$25/M/M out
84.5
GPT-6 Luna (xhigh)
45
OpenAI1.0M ctx118 t/s$20/M/M out
84.0
Claude Opus 5.5
46
Anthropic1.0M ctx68 t/s$25/M/M out
84.0
Claude Fable 5.1 (Medium)
47
Anthropic500K ctx104 t/s$15/M/M out
84.0
Kimi K3
48
Moonshot AI1.0M ctx37 t/s$15/M/M out
83.3
Open
Claude Opus 5.5 (High)
49
Anthropic1.0M ctx74 t/s$25/M/M out
82.5
GPT-6 Luna (high)
50
OpenAI1.0M ctx128 t/s$20/M/M out
82.0
GPT-6 Astra (medium)
51
OpenAI1.1M ctx98 t/s$50/M/M out
81.5
Claude Opus 5
52
Anthropic1.0M ctx60 t/s$25/M/M out
81.4
GPT-5.6 Sol
53
OpenAI1.1M ctx72 t/s$30/M/M out
80.8
Claude Fable 5.1 (Low)
54
Anthropic500K ctx118 t/s$15/M/M out
80.0
Qwen3.8 Max
55
Alibaba1M ctx55 t/s$2/M/M out
79.8
Claude Opus 5.5 (Medium)
56
Anthropic1.0M ctx82 t/s$25/M/M out
79.5
GPT-6 Luna (medium)
57
OpenAI1.0M ctx138 t/s$20/M/M out
78.5
GPT-6 Sol (xhigh)
58
OpenAI400K ctx210 t/s$4/M/M out
78.5
GPT-6 Sol
59
OpenAI400K ctx220 t/s$4/M/M out
78.0
GPT-6 Astra (low)
60
OpenAI1.1M ctx110 t/s$50/M/M out
78.0
GPT-6 Sol (high)
61
OpenAI400K ctx226 t/s$4/M/M out
77.0
Claude Opus 4.8
62
Anthropic1M ctx50 t/s$15/M/M out
76.0
Claude Opus 5.5 (Low)
63
Anthropic1.0M ctx92 t/s$25/M/M out
75.5
Claude Opus 4 6 Thinking
64
Anthropic128K ctx50 t/s$15/M/M out
75.0
Claude Opus 4 7 Thinking
65
Anthropic128K ctx50 t/s$15/M/M out
75.0
Claude Opus 5 Max
66
Anthropic128K ctx50 t/s$15/M/M out
75.0
GPT-6 Luna (low)
67
OpenAI1.0M ctx150 t/s$20/M/M out
74.5
Kimi K3 Max
68
Moonshot AI128K ctx50 t/s$3/M/M out
74.0
Claude Opus 4 8 Thinking
69
Anthropic128K ctx50 t/s$15/M/M out
74.0
GPT 5.6 Sol Xhigh
70
OpenAI128K ctx50 t/s$10/M/M out
74.0
GPT 5.5 High
71
OpenAI128K ctx50 t/s$10/M/M out
74.0
GPT 5.4 High
72
OpenAI128K ctx50 t/s$10/M/M out
74.0
Gemini 3.5 Flash High
73
Google128K ctx50 t/s$5/M/M out
74.0
GPT 5.2 Chat Latest 20260210
74
OpenAI128K ctx50 t/s$10/M/M out
74.0
Qwen3.7 Max Preview
75
Alibaba128K ctx50 t/s$2/M/M out
74.0
Grok 4.20 Beta1
76
xAI128K ctx50 t/s$15/M/M out
74.0
Gemini 3.5 Flash Medium
77
Google128K ctx50 t/s$5/M/M out
74.0
GPT 5.5 Instant
78
OpenAI128K ctx50 t/s$10/M/M out
74.0
Claude Opus 4 5 20251101 Thinking 32k
79
Anthropic128K ctx50 t/s$15/M/M out
74.0
Grok 4.20 Beta 0309 Reasoning
80
xAI128K ctx50 t/s$15/M/M out
74.0
Grok 4.20 Multi Agent Beta 0309
81
xAI128K ctx50 t/s$15/M/M out
74.0
GPT-6 Sol (medium)
82
OpenAI400K ctx238 t/s$4/M/M out
74.0
Glm 5.2 Max
83
Z.ai128K ctx50 t/s$3/M/M out
73.0
Claude Opus 4 5 20251101
84
Anthropic128K ctx50 t/s$15/M/M out
73.0
GPT 5.6 Terra Xhigh
85
OpenAI128K ctx50 t/s$10/M/M out
73.0
Grok 4.1 Thinking
86
xAI128K ctx50 t/s$15/M/M out
73.0
Qwen3.5 Max Preview
87
Alibaba128K ctx50 t/s$2/M/M out
73.0
Qwen3.6 Max Preview
88
Alibaba128K ctx50 t/s$2/M/M out
73.0
Grok 4.1
89
xAI128K ctx50 t/s$15/M/M out
73.0
Dola Seed 2.0 Pro
90
Unknown128K ctx50 t/s$3/M/M out
73.0
Claude Sonnet 4 5 20250929 Thinking 32k
91
Anthropic128K ctx50 t/s$15/M/M out
73.0
Claude Sonnet 4 5 20250929
92
Anthropic128K ctx50 t/s$15/M/M out
73.0
GPT 5.1 High
93
OpenAI128K ctx50 t/s$10/M/M out
73.0
Deepseek V4 Pro High Preview
94
DeepSeek128K ctx50 t/s$1.1/M/M out
73.0
GPT 5.6 Luna Xhigh
95
OpenAI128K ctx50 t/s$10/M/M out
73.0
Kimi K2.5 Thinking
96
Moonshot AI128K ctx50 t/s$3/M/M out
73.0
Claude Opus 4 1 20250805 Thinking 16k
97
Anthropic128K ctx50 t/s$15/M/M out
72.0
Ernie 5.0 Preview 1203
98
Baidu128K ctx50 t/s$3/M/M out
72.0
GPT 5.3 Chat Latest
99
OpenAI128K ctx50 t/s$10/M/M out
72.0
GPT 5.4 Mini High
100
OpenAI128K ctx50 t/s$10/M/M out
72.0
Mimo V2 Pro
101
Unknown128K ctx50 t/s$3/M/M out
72.0
Claude Opus 4 1 20250805
102
Anthropic128K ctx50 t/s$15/M/M out
72.0
Ernie 5.0 0110
103
Baidu128K ctx50 t/s$3/M/M out
72.0
GPT 4.5 Preview 2025 02 27
104
OpenAI128K ctx50 t/s$10/M/M out
72.0
Chatgpt 4o Latest 20250326
105
OpenAI128K ctx50 t/s$10/M/M out
72.0
Glm 4.7
106
Z.ai128K ctx50 t/s$3/M/M out
72.0
Qwen3.5 397b A17b
107
Alibaba128K ctx50 t/s$2/M/M out
72.0
Deepseek V4 Flash High Preview
108
DeepSeek128K ctx50 t/s$1.1/M/M out
72.0
GPT 5.2 High
109
OpenAI128K ctx50 t/s$10/M/M out
72.0
Longcat Flash Chat 2602 Exp
110
LongCat128K ctx50 t/s$3/M/M out
72.0
GPT 5 High
111
OpenAI128K ctx50 t/s$10/M/M out
72.0
Mimo V2.5
112
Unknown128K ctx50 t/s$3/M/M out
72.0
Glm 5v Turbo
113
Z.ai128K ctx50 t/s$3/M/M out
72.0
Kimi K2.5 Instant
114
Moonshot AI128K ctx50 t/s$3/M/M out
72.0
Grok 4 1 Fast Reasoning
115
xAI128K ctx50 t/s$15/M/M out
72.0
O3 2025 04 16
116
OpenAI128K ctx50 t/s$10/M/M out
72.0
Mimo V2 Omni
117
Unknown128K ctx50 t/s$3/M/M out
72.0
Kimi K2 Thinking Turbo
118
Moonshot AI128K ctx50 t/s$3/M/M out
72.0
GPT-6 Luna (Non-reasoning)
119
OpenAI1.0M ctx165 t/s$20/M/M out
71.5
GPT 5 Chat
120
OpenAI128K ctx50 t/s$10/M/M out
71.0
Nvidia Nemotron 3 Ultra 550b A55b Nvfp4
121
NVIDIA128K ctx50 t/s$3/M/M out
71.0
Amazon Nova Experimental Chat 26 02 10
122
Amazon128K ctx50 t/s$3/M/M out
71.0
Glm 4.6
123
Z.ai128K ctx50 t/s$3/M/M out
71.0
Deepseek V3.2 Exp Thinking
124
DeepSeek128K ctx50 t/s$1.1/M/M out
71.0
Claude Opus 4 20250514 Thinking 16k
125
Anthropic128K ctx50 t/s$15/M/M out
71.0
Qwen3 Max 2025 09 23
126
Alibaba128K ctx50 t/s$2/M/M out
71.0
Deepseek V3.2 Thinking
127
DeepSeek128K ctx50 t/s$1.1/M/M out
71.0
Deepseek V3.2 Exp
128
DeepSeek128K ctx50 t/s$1.1/M/M out
71.0
Deepseek R1 0528
129
DeepSeek128K ctx50 t/s$1.1/M/M out
71.0
Grok 4 Fast Chat
130
xAI128K ctx50 t/s$15/M/M out
71.0
Ernie 5.0 Preview 1022
131
Baidu128K ctx50 t/s$3/M/M out
71.0
Kimi K2 0905 Preview
132
Moonshot AI128K ctx50 t/s$3/M/M out
71.0
Kimi K2 0711 Preview
133
Moonshot AI128K ctx50 t/s$3/M/M out
71.0
Deepseek V3.1
134
DeepSeek128K ctx50 t/s$1.1/M/M out
71.0
Deepseek V3.1 Terminus Thinking
135
DeepSeek128K ctx50 t/s$1.1/M/M out
71.0
Deepseek V3.1 Thinking
136
DeepSeek128K ctx50 t/s$1.1/M/M out
71.0
Qwen3.5 122b A10b
137
Alibaba128K ctx50 t/s$2/M/M out
71.0
Amazon Nova Experimental Chat 26 01 10
138
Amazon128K ctx50 t/s$3/M/M out
71.0
Deepseek V3.1 Terminus
139
DeepSeek128K ctx50 t/s$1.1/M/M out
71.0
GPT 4.1 2025 04 14
140
OpenAI128K ctx50 t/s$10/M/M out
71.0
Claude Opus 4 20250514
141
Anthropic128K ctx50 t/s$15/M/M out
71.0
Claude Haiku 4 5 20251001
142
Anthropic128K ctx50 t/s$15/M/M out
71.0
Hunyuan Hy3 Preview
143
Tencent128K ctx50 t/s$3/M/M out
71.0
Grok 3 Preview 02 24
144
xAI128K ctx50 t/s$15/M/M out
71.0
Glm 4.5
145
Z.ai128K ctx50 t/s$3/M/M out
71.0
Grok 4.7 (high)
146
xAI1.0M ctx80 t/s$15/M/M out
71.0
Grok 4 0709
147
xAI128K ctx50 t/s$15/M/M out
70.0
Mistral Medium 2508
148
Mistral128K ctx50 t/s$6/M/M out
70.0
Qwen3.5 27b
149
Alibaba128K ctx50 t/s$2/M/M out
70.0
Gemini 2.5 Flash Preview 09 2025
150
Google128K ctx50 t/s$5/M/M out
70.0
Qwen3 235b A22b No Thinking
151
Alibaba128K ctx50 t/s$2/M/M out
70.0
GPT 5.4 Nano High
152
OpenAI128K ctx50 t/s$10/M/M out
70.0
O1 2024 12 17
153
OpenAI128K ctx50 t/s$10/M/M out
70.0
Longcat Flash Chat
154
LongCat128K ctx50 t/s$3/M/M out
70.0
Claude Sonnet 4 20250514 Thinking 32k
155
Anthropic128K ctx50 t/s$15/M/M out
70.0
Qwen3 235b A22b Thinking 2507
156
Alibaba128K ctx50 t/s$2/M/M out
70.0
Qwen3.5 Flash
157
Alibaba128K ctx50 t/s$2/M/M out
70.0
Qwen3.5 35b A3b
158
Alibaba128K ctx50 t/s$2/M/M out
70.0
Qwen3 VL 235b A22b Thinking
159
Alibaba128K ctx50 t/s$2/M/M out
70.0
Hunyuan Vision 1.5 Thinking
160
Tencent128K ctx50 t/s$3/M/M out
70.0
Step 3.5 Flash
161
StepFun128K ctx50 t/s$3/M/M out
70.0
Amazon Nova Experimental Chat 12 10
162
Amazon128K ctx50 t/s$3/M/M out
70.0
GPT 5 Mini High
163
OpenAI128K ctx50 t/s$10/M/M out
70.0
O4 Mini 2025 04 16
164
OpenAI128K ctx50 t/s$10/M/M out
70.0
Minimax M2.5
165
MiniMax128K ctx50 t/s$3/M/M out
70.0
GPT-6 Sol (low)
166
OpenAI400K ctx250 t/s$4/M/M out
70.0
Muse Spark 1.1
167
Meta1.0M ctx208 t/s$4.25/M/M out
69.9
Claude Sonnet 4 20250514
168
Anthropic128K ctx50 t/s$15/M/M out
69.0
Claude 3 7 Sonnet 20250219 Thinking 32k
169
Anthropic128K ctx50 t/s$15/M/M out
69.0
Mistral Medium 2505
170
Mistral128K ctx50 t/s$6/M/M out
69.0
Hunyuan T1 20250711
171
Tencent128K ctx50 t/s$3/M/M out
69.0
Minimax M2.1 Preview
172
MiniMax128K ctx50 t/s$3/M/M out
69.0
Qwen3 30b A3b Instruct 2507
173
Alibaba128K ctx50 t/s$2/M/M out
69.0
GPT 4.1 Mini 2025 04 14
174
OpenAI128K ctx50 t/s$10/M/M out
69.0
Hunyuan Turbos 20250416
175
Tencent128K ctx50 t/s$3/M/M out
69.0
Gemini 2.5 Flash Lite Preview 09 2025 No Thinking
176
Google128K ctx50 t/s$5/M/M out
69.0
Glm 4.6v
177
Z.ai128K ctx50 t/s$3/M/M out
69.0
Qwen3 235b A22b
178
Alibaba128K ctx50 t/s$2/M/M out
69.0
Gemini 2.5 Flash Lite Preview 06 17 Thinking
179
Google128K ctx50 t/s$5/M/M out
69.0
Qwen2.5 Max
180
Alibaba128K ctx50 t/s$2/M/M out
69.0
Claude 3 5 Sonnet 20241022
181
Anthropic128K ctx50 t/s$15/M/M out
69.0
Claude 3 7 Sonnet 20250219
182
Anthropic128K ctx50 t/s$15/M/M out
69.0
Gemini 3.8 Flash
183
Google1M ctx302 t/s$3.75/M/M out
68.5
Grok 4.7
184
xAI1.0M ctx95 t/s$15/M/M out
68.5
Qwen3 Next 80b A3b Thinking
185
Alibaba128K ctx50 t/s$2/M/M out
68.0
Glm 4.7 Flash
186
Z.ai128K ctx50 t/s$3/M/M out
68.0
Gemma 3 27b It
187
Google128K ctx50 t/s$5/M/M out
68.0
Amazon Nova Experimental Chat 11 10
188
Amazon128K ctx50 t/s$3/M/M out
68.0
Minimax M1
189
MiniMax128K ctx50 t/s$3/M/M out
68.0
Grok 3 Mini High
190
xAI128K ctx50 t/s$15/M/M out
68.0
Gemini 2.0 Flash 001
191
Google128K ctx50 t/s$5/M/M out
68.0
Mistral Small 2506
192
Mistral128K ctx50 t/s$6/M/M out
68.0
Grok 3 Mini Beta
193
xAI128K ctx50 t/s$15/M/M out
68.0
Command A 03 2025
194
Cohere128K ctx50 t/s$3/M/M out
68.0
Gemini 2.0 Flash Lite Preview 02 05
195
Google128K ctx50 t/s$5/M/M out
68.0
Glm 4.5v
196
Z.ai128K ctx50 t/s$3/M/M out
68.0
Gemini 1.5 Pro 002
197
Google128K ctx50 t/s$5/M/M out
68.0
GPT-6 Sol (Non-reasoning)
198
OpenAI400K ctx265 t/s$4/M/M out
68.0
Amazon Nova Experimental Chat 10 20
199
Amazon128K ctx50 t/s$3/M/M out
67.0
Hunyuan Turbos 20250226
200
Tencent128K ctx50 t/s$3/M/M out
67.0
Step 3
201
StepFun128K ctx50 t/s$3/M/M out
67.0
Llama 3.1 Nemotron Ultra 253b V1
202
Meta128K ctx50 t/s$0/M/M out
67.0
Amazon Nova Experimental Chat 10 09
203
Amazon128K ctx50 t/s$3/M/M out
67.0
Qwen3 32b
204
Alibaba128K ctx50 t/s$2/M/M out
67.0
Qwen Plus 0125
205
Alibaba128K ctx50 t/s$2/M/M out
67.0
Ling Flash 2.0
206
Ling128K ctx50 t/s$3/M/M out
67.0
Nvidia Llama 3.3 Nemotron Super 49b V1.5
207
NVIDIA128K ctx50 t/s$3/M/M out
67.0
Glm 4 Plus 0111
208
Z.ai128K ctx50 t/s$3/M/M out
67.0
Claude 3 5 Sonnet 20240620
209
Anthropic128K ctx50 t/s$15/M/M out
67.0
Gemma 3 12b It
210
Google128K ctx50 t/s$5/M/M out
67.0
Hunyuan Turbo 0110
211
Tencent128K ctx50 t/s$3/M/M out
67.0
GPT 5 Nano High
212
OpenAI128K ctx50 t/s$10/M/M out
67.0
O1 Mini
213
OpenAI128K ctx50 t/s$10/M/M out
67.0
Nova 2 Lite
214
Amazon128K ctx50 t/s$3/M/M out
67.0
Grok 2 2024 08 13
215
xAI128K ctx50 t/s$15/M/M out
67.0
Gemini Advanced 0514
216
Google128K ctx50 t/s$5/M/M out
67.0
Llama 3.1 405b Instruct Bf16
217
Meta128K ctx50 t/s$0/M/M out
67.0
Step 2 16k Exp 202412
218
StepFun128K ctx50 t/s$3/M/M out
67.0
Llama 3.1 405b Instruct Fp8
219
Meta128K ctx50 t/s$0/M/M out
67.0
Olmo 3.1 32b Instruct
220
AI2128K ctx50 t/s$3/M/M out
67.0
Qwen3.8 Flash Next
221
Alibaba260K ctx168 t/s$0.4/M/M out
66.8
Open
GPT-5.6 Terra
222
OpenAI1.1M ctx127 t/s$12/M/M out
66.4
Molmo 2 8b
223
AI2128K ctx50 t/s$3/M/M out
66.0
Llama 3.3 Nemotron 49b Super V1
224
Meta128K ctx50 t/s$0/M/M out
66.0
Qwen3 30b A3b
225
Alibaba128K ctx50 t/s$2/M/M out
66.0
Llama 4 Maverick 17b 128e Instruct
226
Meta128K ctx50 t/s$0/M/M out
66.0
Hunyuan Large 2025 02 10
227
Tencent128K ctx50 t/s$3/M/M out
66.0
GPT 4 Turbo 2024 04 09
228
OpenAI128K ctx50 t/s$10/M/M out
66.0
Claude 3 5 Haiku 20241022
229
Anthropic128K ctx50 t/s$15/M/M out
66.0
Gemini 1.5 Pro 001
230
Google128K ctx50 t/s$5/M/M out
66.0
Deepseek V2.5 1210
231
DeepSeek128K ctx50 t/s$1.1/M/M out
66.0
Llama 4 Scout 17b 16e Instruct
232
Meta128K ctx50 t/s$0/M/M out
66.0
GPT 4.1 Nano 2025 04 14
233
OpenAI128K ctx50 t/s$10/M/M out
66.0
Claude 3 Opus 20240229
234
Anthropic128K ctx50 t/s$15/M/M out
66.0
Ring Flash 2.0
235
Unknown128K ctx50 t/s$3/M/M out
66.0
Step 1o Turbo 202506
236
StepFun128K ctx50 t/s$3/M/M out
66.0
Glm 4 Plus
237
Z.ai128K ctx50 t/s$3/M/M out
66.0
Llama 3.3 70b Instruct
238
Meta128K ctx50 t/s$0/M/M out
66.0
Gemma 3n E4b It
239
Google128K ctx50 t/s$5/M/M out
66.0
Qwen Max 0919
240
Alibaba128K ctx50 t/s$2/M/M out
66.0
GPT 4o Mini 2024 07 18
241
OpenAI128K ctx50 t/s$10/M/M out
66.0
Nvidia Nemotron 3 Nano 30b A3b Bf16
242
NVIDIA128K ctx50 t/s$3/M/M out
66.0
Qwen2.5 Plus 1127
243
Alibaba128K ctx50 t/s$2/M/M out
66.0
GPT 4 0125 Preview
244
OpenAI128K ctx50 t/s$10/M/M out
66.0
GPT 4 1106 Preview
245
OpenAI128K ctx50 t/s$10/M/M out
66.0
Hunyuan Standard 2025 02 10
246
Tencent128K ctx50 t/s$3/M/M out
66.0
Gemini 3.6 Flash
247
Google1.0M ctx233 t/s$7.5/M/M out
65.9
Gemini 3.8 Flash (Medium Reasoning)
248
Google1M ctx315 t/s$3.75/M/M out
65.2
Gemini 1.5 Flash 002
249
Google128K ctx50 t/s$5/M/M out
65.0
Grok 2 Mini 2024 08 13
250
xAI128K ctx50 t/s$15/M/M out
65.0
Deepseek V2.5
251
DeepSeek128K ctx50 t/s$1.1/M/M out
65.0
Granite 4.1 8b
252
IBM128K ctx50 t/s$3/M/M out
65.0
Mercury
253
Inception128K ctx50 t/s$3/M/M out
65.0
Olmo 3 32b Think
254
AI2128K ctx50 t/s$3/M/M out
65.0
Mistral Large 2411
255
Mistral128K ctx50 t/s$6/M/M out
65.0
Magistral Medium 2506
256
Mistral128K ctx50 t/s$6/M/M out
65.0
Gemma 3 4b It
257
Google128K ctx50 t/s$5/M/M out
65.0
Mistral Small 3.1 24b Instruct 2503
258
Mistral128K ctx50 t/s$6/M/M out
65.0
Qwen2.5 72b Instruct
259
Alibaba128K ctx50 t/s$2/M/M out
65.0
Llama 3.1 Nemotron 70b Instruct
260
Meta128K ctx50 t/s$0/M/M out
65.0
Hunyuan Large Vision
261
Tencent128K ctx50 t/s$3/M/M out
65.0
Llama 3.1 70b Instruct
262
Meta128K ctx50 t/s$0/M/M out
65.0
Amazon Nova Pro V1.0
263
Amazon128K ctx50 t/s$3/M/M out
65.0
DeepSeek V4 Flash Vision
264
DeepSeek1.0M ctx120 t/s$1.32/M/M out
65.0
G9v3-39A5B
265
AI9Stars130K ctx60 t/s$2/M/M out
65.0
Open
G9v3-3B
266
AI9Stars130K ctx60 t/s$2/M/M out
65.0
Open
GLM-5.3
267
Zhipu AI1.0M ctx90 t/s$4.4/M/M out
65.0
Grok 4.6 (low)
268
xAI500K ctx59 t/s$6/M/M out
65.0
Grok 4.6 (medium)
269
xAI500K ctx59 t/s$6/M/M out
65.0
Grok 4.6 (xhigh)
270
xAI500K ctx62 t/s$6/M/M out
65.0
HyperNova 60B
271
Multiverse130K ctx367 t/s$0.14/M/M out
65.0
Open
KAT-Coder-Pro V2
272
Kwai260K ctx103 t/s$1.2/M/M out
65.0
LFM2.5-2.6B
273
Liquid AI130K ctx60 t/s$2/M/M out
65.0
Open
LFM2.5-8B-A1B
274
Liquid AI33K ctx338 t/s$2/M/M out
65.0
Open
LFM2.5-VL-1.6B
275
Liquid AI32K ctx395 t/s$2/M/M out
65.0
Open
LongCat 2.0
276
LongCat1.0M ctx42 t/s$2.95/M/M out
65.0
Open
Magistral Small 1.2
277
Mistral130K ctx60 t/s$1.5/M/M out
65.0
Open
Qwen3.8 27B (xhigh)
278
Alibaba260K ctx53 t/s$3/M/M out
65.0
Open
Qwen3.8 27B (low)
279
Alibaba260K ctx64 t/s$3/M/M out
65.0
Open
Qwen3.8 27B (medium)
280
Alibaba260K ctx62 t/s$3/M/M out
65.0
Open
Qwen3.8 27B (Non-reasoning)
281
Alibaba260K ctx62 t/s$3/M/M out
65.0
Open
GLM-5.3 Flash
282
Z.ai262K ctx182 t/s$0.3/M/M out
64.2
Open
Gemma 2 27b It
283
Google128K ctx50 t/s$5/M/M out
64.0
Ibm Granite H Small
284
Unknown128K ctx50 t/s$3/M/M out
64.0
GPT 4 0314
285
OpenAI128K ctx50 t/s$10/M/M out
64.0
Gemini 1.5 Flash 001
286
Google128K ctx50 t/s$5/M/M out
64.0
Llama 3.1 Nemotron 51b Instruct
287
Meta128K ctx50 t/s$0/M/M out
64.0
Llama 3.1 Tulu 3 70b
288
Meta128K ctx50 t/s$0/M/M out
64.0
Olmo 3.1 32b Think
289
AI2128K ctx50 t/s$3/M/M out
64.0
Claude 3 Sonnet 20240229
290
Anthropic128K ctx50 t/s$15/M/M out
64.0
Nemotron 4 340b Instruct
291
NVIDIA128K ctx50 t/s$3/M/M out
64.0
Llama 3 70b Instruct
292
Meta128K ctx50 t/s$0/M/M out
64.0
Command R Plus 08 2024
293
Cohere128K ctx50 t/s$3/M/M out
64.0
GPT 4 0613
294
OpenAI128K ctx50 t/s$10/M/M out
64.0
Mistral Small 24b Instruct 2501
295
Mistral128K ctx50 t/s$6/M/M out
64.0
Glm 4 0520
296
Z.ai128K ctx50 t/s$3/M/M out
64.0
Qwen2.5 Coder 32b Instruct
297
Alibaba128K ctx50 t/s$2/M/M out
64.0
Muse Spark 1.3
298
Muse256K ctx75 t/s$10/M/M out
63.5
C4ai Aya Expanse 32b
299
Cohere128K ctx50 t/s$3/M/M out
63.0
Gemma 2 9b It
300
Google128K ctx50 t/s$5/M/M out
63.0
Deepseek Coder V2
301
DeepSeek128K ctx50 t/s$1.1/M/M out
63.0
Qwen2 72b Instruct
302
Alibaba128K ctx50 t/s$2/M/M out
63.0
Command R Plus
303
Cohere128K ctx50 t/s$3/M/M out
63.0
Claude 3 Haiku 20240307
304
Anthropic128K ctx50 t/s$15/M/M out
63.0
Amazon Nova Lite V1.0
305
Amazon128K ctx50 t/s$3/M/M out
63.0
Gemini 1.5 Flash 8b 001
306
Google128K ctx50 t/s$5/M/M out
63.0
Olmo 2 0325 32b Instruct
307
AI2128K ctx50 t/s$3/M/M out
63.0
Command R 08 2024
308
Cohere128K ctx50 t/s$3/M/M out
63.0
Step-5
309
StepFun512K ctx110 t/s$6/M/M out
63.0
Claude Opus 5 Xhigh
310
Anthropic131K ctx80 t/s$15/M/M out
62.5
Mistral Large 2402
311
Mistral128K ctx50 t/s$6/M/M out
62.0
Amazon Nova Micro V1.0
312
Amazon128K ctx50 t/s$3/M/M out
62.0
Ministral 8b 2410
313
Mistral128K ctx50 t/s$6/M/M out
62.0
Gemini Pro Dev API
314
Google128K ctx50 t/s$5/M/M out
62.0
Qwen1.5 110b Chat
315
Alibaba128K ctx50 t/s$2/M/M out
62.0
Hunyuan Standard 256k
316
Tencent128K ctx50 t/s$3/M/M out
62.0
Qwen1.5 72b Chat
317
Alibaba128K ctx50 t/s$2/M/M out
62.0
Gemini 3.8 Flash (Low Reasoning)
318
Google1M ctx340 t/s$3.75/M/M out
62.0
Claude Opus 5 High
319
Anthropic131K ctx80 t/s$15/M/M out
61.5
Grok 4.5
320
xAI500K ctx59 t/s$6/M/M out
61.3
Claude Opus 4.6
321
Anthropic1M ctx50 t/s$15/M/M out
61.2
legacy
Mixtral 8x22b Instruct V0.1
322
Mistral128K ctx50 t/s$6/M/M out
61.0
Command R
323
Cohere128K ctx50 t/s$3/M/M out
61.0
GPT 3.5 Turbo 0125
324
OpenAI128K ctx50 t/s$10/M/M out
61.0
Llama 3 8b Instruct
325
Meta128K ctx50 t/s$0/M/M out
61.0
C4ai Aya Expanse 8b
326
Cohere128K ctx50 t/s$3/M/M out
61.0
Gemini Pro
327
Google128K ctx50 t/s$5/M/M out
61.0
Llama 3.1 Tulu 3 8b
328
Meta128K ctx50 t/s$0/M/M out
61.0
Llama 3.1 8b Instruct
329
Meta128K ctx50 t/s$0/M/M out
61.0
Grok 4
330
xAI131K ctx80 t/s$15/M/M out
60.9
Grok 4 6
331
xAI131K ctx80 t/s$15/M/M out
60.9
Gemini 3.1 Pro
332
Google1.0M ctx136 t/s$12/M/M out
60.6
Granite 3.1 8b Instruct
333
IBM128K ctx50 t/s$3/M/M out
60.0
Qwen1.5 32b Chat
334
Alibaba128K ctx50 t/s$2/M/M out
60.0
GPT 3.5 Turbo 1106
335
OpenAI128K ctx50 t/s$10/M/M out
60.0
Gemma 2 2b It
336
Google128K ctx50 t/s$5/M/M out
60.0
Phi 3 Medium 4k Instruct
337
Microsoft128K ctx50 t/s$3/M/M out
60.0
Mixtral 8x7b Instruct V0.1
338
Mistral128K ctx50 t/s$6/M/M out
60.0
Qwen1.5 14b Chat
339
Alibaba128K ctx50 t/s$2/M/M out
60.0
GLM-5.3 (low)
340
Zhipu AI1.0M ctx100 t/s$4.4/M/M out
60.0
GLM-5.2
341
Z.ai262K ctx164 t/s$4.29/M/M out
59.1
Open
Deepseek LLM 67b Chat
342
DeepSeek128K ctx50 t/s$1.1/M/M out
59.0
Wizardlm 70b
343
Microsoft128K ctx50 t/s$3/M/M out
59.0
Granite 3.0 8b Instruct
344
IBM128K ctx50 t/s$3/M/M out
59.0
Gemma 1.1 7b It
345
Google128K ctx50 t/s$5/M/M out
59.0
Granite 3.1 2b Instruct
346
IBM128K ctx50 t/s$3/M/M out
59.0
Phi 3 Small 8k Instruct
347
Microsoft128K ctx50 t/s$3/M/M out
59.0
Llama 2 70b Chat
348
Meta128K ctx50 t/s$0/M/M out
59.0
Claude Opus 5 Medium
349
Anthropic131K ctx80 t/s$15/M/M out
58.6
Granite 4.2 30B Instruct
350
IBM128K ctx78 t/s$1.2/M/M out
58.6
Open
Llama 3.2 3b Instruct
351
Meta128K ctx50 t/s$0/M/M out
58.0
Granite 3.0 2b Instruct
352
IBM128K ctx50 t/s$3/M/M out
58.0
Qwq 32b Preview
353
Alibaba128K ctx50 t/s$2/M/M out
58.0
Llama2 70b Steerlm Chat
354
Meta128K ctx50 t/s$0/M/M out
58.0
Qwen3 8 2 4t A95b
355
Alibaba131K ctx85 t/s$2/M/M out
57.7
Open
Gpt 5 6 Sol High
356
OpenAI131K ctx90 t/s$10/M/M out
57.3
Wizardlm 13b
357
Microsoft128K ctx50 t/s$3/M/M out
57.0
Mistral 7b Instruct V0.2
358
Mistral128K ctx50 t/s$6/M/M out
57.0
Qwen1.5 7b Chat
359
Alibaba128K ctx50 t/s$2/M/M out
57.0
Phi 3 Mini 4k Instruct June 2024
360
Microsoft128K ctx50 t/s$3/M/M out
57.0
Llama 2 13b Chat
361
Meta128K ctx50 t/s$0/M/M out
57.0
Qwen 14b Chat
362
Alibaba128K ctx50 t/s$2/M/M out
57.0
Palm 2
363
Google128K ctx50 t/s$5/M/M out
57.0
Gemma 7b It
364
Google128K ctx50 t/s$5/M/M out
57.0
Codellama 34b Instruct
365
Unknown128K ctx50 t/s$3/M/M out
57.0
Muse Spark 1 2
366
Meta131K ctx80 t/s$0/M/M out
56.8
Gemini 3 7 Flash
367
Google131K ctx120 t/s$5/M/M out
56.0
Phi 3 Mini 128k Instruct
368
Microsoft128K ctx50 t/s$3/M/M out
56.0
Phi 3 Mini 4k Instruct
369
Microsoft128K ctx50 t/s$3/M/M out
56.0
Codellama 70b Instruct
370
Unknown128K ctx50 t/s$3/M/M out
56.0
Gemma 1.1 2b It
371
Google128K ctx50 t/s$5/M/M out
56.0
Llama 3.2 1b Instruct
372
Meta128K ctx50 t/s$0/M/M out
56.0
Gpt 5 6 Sol Medium
373
OpenAI131K ctx90 t/s$10/M/M out
55.6
Llama 2 7b Chat
374
Meta128K ctx50 t/s$0/M/M out
55.0
Gemma 2b It
375
Google128K ctx50 t/s$5/M/M out
55.0
Qwen1.5 4b Chat
376
Alibaba128K ctx50 t/s$2/M/M out
55.0
Mercury 2.5
377
Inception128K ctx105 t/s$3/M/M out
55.0
Grok 4 Heavy
378
xAI256k ctx50 t/s$15/M/M out
54.5
preview
DeepSeek V4.1 Flash
379
DeepSeek1.0M ctx214 t/s$1.2/M/M out
54.5
Open
GPT-5.5
380
OpenAI1.1M ctx60 t/s$10/M/M out
54.0
Olmo 7b Instruct
381
AI2128K ctx50 t/s$3/M/M out
54.0
Gemini 3 7 Flash Medium
382
Google131K ctx120 t/s$5/M/M out
53.4
Glm 5
383
Z.ai131K ctx60 t/s$3/M/M out
52.6
Open
Claude Opus 5 Low
384
Anthropic131K ctx80 t/s$15/M/M out
52.5
MiMo V2.6 Pro
385
Xiaomi1.0M ctx72 t/s$0.95/M/M out
52.5
Open
GPT-5.3 Codex
386
OpenAI400K ctx118 t/s$14/M/M out
52.4
Claude Opus 4.5
387
Anthropic200K ctx50 t/s$15/M/M out
52.1
legacy
Claude Opus 4.7
388
Anthropic1M ctx80 t/s$15/M/M out
52.0
Phi-4 Multimodal
389
Microsoft128K ctx85 t/s$0.32/M/M out
52.0
Gemini 3 Pro
390
Google1M ctx120 t/s$5/M/M out
51.9
Gpt 5 5 Medium
391
OpenAI131K ctx90 t/s$10/M/M out
51.4
GPT-5.4
392
OpenAI1.1M ctx60 t/s$10/M/M out
51.0
legacy
Qwen3.7 Max
393
Alibaba1.0M ctx203 t/s$7.5/M/M out
51.0
Gemini 3 7 Flash Low
394
Google131K ctx120 t/s$5/M/M out
50.9
Gpt 5 6 Sol Low
395
OpenAI131K ctx90 t/s$10/M/M out
50.7
Gpt 5 6 Terra High
396
OpenAI131K ctx90 t/s$10/M/M out
50.1
Gemini 3.5 Flash
397
Google1.0M ctx267 t/s$9/M/M out
50.0
Sarvam 105B
398
Sarvam AI128K ctx60 t/s$3/M/M out
50.0
Open
Sarvam 30B
399
Sarvam AI128K ctx60 t/s$3/M/M out
50.0
Open
DeepSeek V4.1 Flash (Non-reasoning)
400
DeepSeek1.0M ctx240 t/s$1.2/M/M out
50.0
Open
GPT-5.2
401
OpenAI128K ctx90 t/s$10/M/M out
49.2
legacy
Granite 4.2 8B Instruct
402
IBM128K ctx115 t/s$0.45/M/M out
49.2
Open
GPT-5.6 Luna
403
OpenAI1.1M ctx175 t/s$1.2/M/M out
49.1
ERNIE 5.1
404
Baidu131K ctx60 t/s$3/M/M out
49.1
Kimi K2.6
405
Moonshot AI262.1K ctx40 t/s$4/M/M out
49.0
Open
Sarvam M Reasoning
406
Sarvam AI128K ctx40 t/s$3/M/M out
49.0
Open
Kimi K3 Low
407
Moonshot AI131K ctx60 t/s$4/M/M out
48.3
Agnes 3.0 Flash
408
Agnes1.0M ctx235 t/s$0.15/M/M out
48.2
Grok 4.3
409
xAI500K ctx129 t/s$2.5/M/M out
48.0
MiMo V2.5 Pro
410
Xiaomi1.0M ctx65 t/s$0.87/M/M out
48.0
Open
Muse Spark
411
Meta1.0M ctx80 t/s$0/M/M out
47.0
Claude Sonnet 4 6 Adaptive
412
Anthropic131K ctx80 t/s$15/M/M out
47.0
Gpt 5 6 Luna High
413
OpenAI131K ctx90 t/s$10/M/M out
47.0
Gpt 5 6 Terra Medium
414
OpenAI131K ctx90 t/s$10/M/M out
46.8
DeepSeek V4 Pro
415
DeepSeek1.0M ctx66 t/s$0.87/M/M out
46.0
Open
GLM-5.1
416
Z.ai262K ctx74 t/s$4.4/M/M out
46.0
Open
DeepSeek V4 Flash 0420 (Non-reasoning)
417
DeepSeek1.0M ctx210 t/s$1.1/M/M out
46.0
Open
Claude Sonnet 5
418
Anthropic1.0M ctx96 t/s$10/M/M out
45.4
Deepseek V4 Pro 0424
419
DeepSeek131K ctx60 t/s$1.1/M/M out
45.3
Open
MiniMax-M2.7
420
MiniMax1.0M ctx40 t/s$2/M/M out
45.0
Claude Opus 4 6 Adaptive
421
Anthropic131K ctx80 t/s$15/M/M out
44.9
Gpt 5 5 Low
422
OpenAI131K ctx90 t/s$10/M/M out
44.5
Nex N2 Pro
423
Nex AGI262K ctx138 t/s$2.5/M/M out
44.4
Gpt 5 4 Mini
424
OpenAI131K ctx90 t/s$10/M/M out
44.0
Claude Opus 4 7 Non Reasoning
425
Anthropic131K ctx50 t/s$15/M/M out
43.9
Deepseek V4 Pro 0424 High
426
DeepSeek131K ctx60 t/s$1.1/M/M out
43.7
Open
Claude Sonnet 5 Non Reasoning
427
Anthropic131K ctx50 t/s$15/M/M out
42.6
Agnes 2.5 Pro Beta
428
Agnes131K ctx65 t/s$3/M/M out
42.5
Claude Sonnet 4.5
429
Anthropic200K ctx80 t/s$15/M/M out
42.4
legacy
Gemini 3 Flash
430
Google1M ctx120 t/s$5/M/M out
42.4
GPT-5.1
431
OpenAI400K ctx60 t/s$10/M/M out
42.3
legacy
Qwen3.7 Plus
432
Alibaba1.0M ctx54 t/s$1.6/M/M out
42.2
Deepseek V4 Flash 0420
433
DeepSeek131K ctx60 t/s$1.1/M/M out
42.1
Open
DeepSeek V4 Flash
434
DeepSeek1.0M ctx113 t/s$0.28/M/M out
42.0
Open
Granite 4.2 3B Instruct
435
IBM128K ctx148 t/s$0.2/M/M out
42.0
Open
Ling 3.0 Flash Fin
436
Ling131K ctx65 t/s$3/M/M out
42.0
Claude Opus 4 5 Thinking
437
Anthropic131K ctx50 t/s$15/M/M out
41.9
Gpt 5 6 Sol Non Reasoning
438
OpenAI131K ctx60 t/s$10/M/M out
41.9
Kimi K2.7 Code
439
Moonshot AI262K ctx39 t/s$4/M/M out
41.8
Open
Inkling Small
440
Thinking Machines524K ctx130 t/s$1.2/M/M out
41.7
Solar Pro4
441
Upstage131K ctx40 t/s$3/M/M out
41.6
Gpt 5 6 Terra Low
442
OpenAI131K ctx90 t/s$10/M/M out
41.3
Gpt 5 2 Codex
443
OpenAI131K ctx90 t/s$10/M/M out
41.2
Qwen3 6 Max
444
Alibaba131K ctx85 t/s$2/M/M out
41.1
Open
Grok Build 0 1 06 16
445
xAI131K ctx80 t/s$15/M/M out
40.7
Ling 3.0 Flash VL
446
Ling131K ctx60 t/s$3/M/M out
40.5
Gpt 5 4 Low
447
OpenAI131K ctx90 t/s$10/M/M out
40.2
Seed 2.0 Pro
448
ByteDance131K ctx40 t/s$3/M/M out
40.0
Agnes 2 5 Pro Alpha
449
Agnes131K ctx60 t/s$3/M/M out
39.7
Gpt 5 4 Nano
450
OpenAI131K ctx90 t/s$10/M/M out
39.7
MiniMax M3
451
MiniMax524K ctx93 t/s$1.2/M/M out
39.6
Deepseek V4 Flash 0420 High
452
DeepSeek131K ctx60 t/s$1.1/M/M out
39.0
Open
Hunyuan Hy3
453
Tencent262K ctx69 t/s$0.56/M/M out
38.9
Gpt 5 2 Medium
454
OpenAI131K ctx90 t/s$10/M/M out
38.9
Gpt 5 6 Luna Medium
455
OpenAI131K ctx90 t/s$10/M/M out
38.9
Gemini 3.5 Flash-Lite
456
Google1.0M ctx389 t/s$2.5/M/M out
38.8
Gemini 3 Flash Reasoning
457
Google131K ctx80 t/s$5/M/M out
38.7
Nvidia Nemotron 3 Ultra 550b A55b
458
NVIDIA131K ctx150 t/s$1/M/M out
38.3
Claude Sonnet 4.6
459
Anthropic1M ctx50 t/s$15/M/M out
38.1
Deepseek V3 2 Reasoning
460
DeepSeek131K ctx40 t/s$1.1/M/M out
38.0
Open
Grok 4 20
461
xAI131K ctx80 t/s$15/M/M out
38.0
Mimo V2 5 0424
462
Xiaomi131K ctx60 t/s$3/M/M out
38.0
Open
Ling 3 0 Flash
463
Ling131K ctx60 t/s$3/M/M out
37.8
Qwen3 6 27b
464
Alibaba131K ctx85 t/s$2/M/M out
37.7
Open
Claude 4 5 Sonnet Thinking
465
Anthropic131K ctx50 t/s$15/M/M out
37.4
Grok 4 20 0309
466
xAI131K ctx80 t/s$15/M/M out
37.4
Gpt 5 Codex
467
OpenAI131K ctx90 t/s$10/M/M out
37.0
Grok 4 3 Medium
468
xAI131K ctx80 t/s$15/M/M out
36.9
Glm 5 1 Non Reasoning
469
Z.ai131K ctx40 t/s$3/M/M out
36.3
Open
Grok 4 3 Low
470
xAI131K ctx80 t/s$15/M/M out
36.3
Kimi K2 5
471
Moonshot AI131K ctx60 t/s$4/M/M out
36.0
Gemini 3 5 Flash Minimal
472
Google131K ctx120 t/s$5/M/M out
35.8
Gpt 5 5 Non Reasoning
473
OpenAI131K ctx60 t/s$10/M/M out
35.8
Gpt 5 1 Codex
474
OpenAI131K ctx90 t/s$10/M/M out
35.6
Kimi K2 6 Non Reasoning
475
Moonshot AI131K ctx40 t/s$4/M/M out
35.4
Claude Sonnet 4 6 Non Reasoning Low Effort
476
Anthropic131K ctx50 t/s$15/M/M out
35.1
Muse Glimmer
477
Meta131K ctx80 t/s$0/M/M out
35.1
Gemma 4 31B
478
Google262.1K ctx35 t/s$0.3/M/M out
35.0
Open
Mistral Medium 3.5
479
Mistral131K ctx60 t/s$6/M/M out
35.0
Glm 5 2 Non Reasoning
480
Z.ai131K ctx40 t/s$3/M/M out
34.8
Open
Gpt 5 6 Terra Non Reasoning
481
OpenAI131K ctx60 t/s$10/M/M out
34.6
Gpt 5 Medium
482
OpenAI131K ctx90 t/s$10/M/M out
34.6
Claude 4 1 Opus Thinking
483
Anthropic131K ctx50 t/s$15/M/M out
34.5
Hy3 Preview
484
Tencent131K ctx60 t/s$3/M/M out
34.4
Gpt 5 5 Instant 05 26
485
OpenAI131K ctx90 t/s$10/M/M out
34.3
Gemini 3 Pro Low
486
Google131K ctx120 t/s$5/M/M out
33.9
Gpt 5 6 Luna Low
487
OpenAI131K ctx90 t/s$10/M/M out
33.9
Kimi K2 Thinking
488
Moonshot AI131K ctx40 t/s$4/M/M out
33.5
O3 Pro
489
OpenAI131K ctx60 t/s$10/M/M out
33.3
Glm 5 Non Reasoning
490
Z.ai131K ctx40 t/s$3/M/M out
33.2
Open
Claude 4 5 Haiku Reasoning
491
Anthropic131K ctx50 t/s$15/M/M out
33.0
Qwen3 5 397b A17b Non Reasoning
492
Alibaba131K ctx55 t/s$2/M/M out
32.7
Open
Qwen3.6 Plus
493
Alibaba1.0M ctx55 t/s$3/M/M out
32.4
Minimax M2 1
494
MiniMax131K ctx60 t/s$2/M/M out
32.1
Open
Qwen3 6 35b A3b
495
Alibaba131K ctx85 t/s$2/M/M out
32.1
Open
o3
496
OpenAI200K ctx90 t/s$10/M/M out
32.0
legacy
Nova 2 0 Pro Reasoning Medium
497
Amazon131K ctx40 t/s$3.2/M/M out
32.0
Nvidia Nemotron 3 Super 120b A12b
498
NVIDIA131K ctx150 t/s$1/M/M out
32.0
Deepseek V4 Pro 0424 Non Reasoning
499
DeepSeek131K ctx40 t/s$1.1/M/M out
31.9
Open
Gpt 5 Low
500
OpenAI131K ctx90 t/s$10/M/M out
31.9
Mimo V2 Flash Reasoning
501
Xiaomi131K ctx40 t/s$3/M/M out
31.9
Open
Inkling
502
Thinking Machines524K ctx81 t/s$4.05/M/M out
31.7
Claude 4 Opus Thinking
503
Anthropic131K ctx50 t/s$15/M/M out
31.7
Gpt 5 Mini Medium
504
OpenAI131K ctx90 t/s$10/M/M out
31.6
Gpt 5 1 Codex Mini
505
OpenAI131K ctx90 t/s$10/M/M out
31.3
Qwen3 5 Omni Plus
506
Alibaba131K ctx85 t/s$2/M/M out
31.3
Open
Qwen3 6 27b Non Reasoning
507
Alibaba131K ctx55 t/s$2/M/M out
31.3
Open
Ring 2 6 1t
508
WeRide131K ctx60 t/s$3/M/M out
31.3
Deepseek V3 1 Terminus Reasoning
509
DeepSeek131K ctx40 t/s$1.1/M/M out
31.1
Open
Step 3 7 Flash
510
StepFun131K ctx60 t/s$3/M/M out
30.9
Gpt 5 4 Nano Medium
511
OpenAI131K ctx90 t/s$10/M/M out
30.8
Gpt 5 4 Mini Medium
512
OpenAI131K ctx90 t/s$10/M/M out
30.5
Kimi K2 5 Non Reasoning
513
Moonshot AI131K ctx40 t/s$4/M/M out
30.1
GPT-oss-120B
514
OpenAI131K ctx240 t/s$0.4/M/M out
30.0
Open
Qwen3 5 27b Non Reasoning
515
Alibaba131K ctx55 t/s$2/M/M out
30.0
Open
Claude 4 5 Sonnet
516
Anthropic131K ctx80 t/s$15/M/M out
29.9
Claude 4 Sonnet Thinking
517
Anthropic131K ctx50 t/s$15/M/M out
29.8
Deepseek V4 Flash Non Reasoning
518
DeepSeek131K ctx40 t/s$1.1/M/M out
29.3
Open
Glm 4 6 Reasoning
519
Z.ai131K ctx40 t/s$3/M/M out
29.3
Open
Gpt 5 5 Instant 06 26
520
OpenAI131K ctx90 t/s$10/M/M out
29.2
Minimax M2
521
MiniMax131K ctx60 t/s$2/M/M out
28.9
Open
Claude 4 1 Opus
522
Anthropic131K ctx80 t/s$15/M/M out
28.8
Mimo V2 5 Pro Non Reasoning
523
Xiaomi131K ctx40 t/s$3/M/M out
28.4
Open
Gpt 5 4 Non Reasoning
524
OpenAI131K ctx60 t/s$10/M/M out
28.3
Qwen3 5 122b A10b Non Reasoning
525
Alibaba131K ctx55 t/s$2/M/M out
28.2
Open
Grok 4 Fast Reasoning
526
xAI131K ctx50 t/s$15/M/M out
27.9
Glm 4 7 Non Reasoning
527
Z.ai131K ctx40 t/s$3/M/M out
27.1
Open
Gpt 5 6 Luna Non Reasoning
528
OpenAI131K ctx60 t/s$10/M/M out
26.8
Hy3 Non Reasoning
529
Tencent131K ctx40 t/s$3/M/M out
26.6
Ling 2 6 1t
530
Ling131K ctx60 t/s$3/M/M out
26.6
Gpt 5 2 Non Reasoning
531
OpenAI131K ctx60 t/s$10/M/M out
26.5
Gemma 4 26b A4b
532
Google131K ctx120 t/s$5/M/M out
26.1
Open
Claude 4 Opus
533
Anthropic131K ctx80 t/s$15/M/M out
26.0
Claude 4 Sonnet
534
Anthropic131K ctx80 t/s$15/M/M out
26.0
Step 3 5 Flash 0202
535
StepFun131K ctx60 t/s$3/M/M out
26.0
Deepseek V3 2 Reasoning 0925
536
DeepSeek131K ctx40 t/s$1.1/M/M out
25.9
Open
Gpt 5 Mini
537
OpenAI131K ctx90 t/s$10/M/M out
25.8
Qwen3 Max Thinking Preview
538
Alibaba131K ctx55 t/s$2/M/M out
25.5
Open
Grok 4 3 Non Reasoning
539
xAI131K ctx50 t/s$15/M/M out
25.0
Qwen3 6 35b A3b Non Reasoning
540
Alibaba131K ctx55 t/s$2/M/M out
24.6
Open
Ling 3 0 Tiny
541
Ling131K ctx60 t/s$3/M/M out
24.5
Qwen3 5 35b A3b Non Reasoning
542
Alibaba131K ctx55 t/s$2/M/M out
24.3
Open
Claude 4.5 Haiku
543
Anthropic200K ctx80 t/s$15/M/M out
24.1
Kimi K2 0905
544
Moonshot AI131K ctx60 t/s$4/M/M out
24.0
Qwen3.5 397B-A17B
545
Alibaba262.1K ctx71 t/s$2/M/M out
23.9
Open
Claude 3 7 Sonnet
546
Anthropic131K ctx80 t/s$15/M/M out
23.9
O1
547
OpenAI131K ctx60 t/s$10/M/M out
23.9
Nemotron 3 5 Lightning
548
NVIDIA131K ctx150 t/s$1/M/M out
23.6
GPT-5
549
OpenAI400K ctx60 t/s$10/M/M out
23.0
legacy
Solar Pro 3
550
Upstage131K ctx40 t/s$3/M/M out
23.0
Grok 3 Mini Reasoning
551
xAI131K ctx50 t/s$15/M/M out
22.9
Grok 4 20 0309 Non Reasoning
552
xAI131K ctx50 t/s$15/M/M out
22.9
Command A Plus
553
Cohere131K ctx60 t/s$10/M/M out
22.8
Gemini 2 5 Pro 05 06
554
Google131K ctx120 t/s$5/M/M out
22.7
Gemma 4 31b Non Reasoning
555
Google131K ctx80 t/s$5/M/M out
22.3
Open
Gemma 4 12b
556
Google131K ctx120 t/s$5/M/M out
22.2
Open
Grok 4 20 Non Reasoning
557
xAI131K ctx50 t/s$15/M/M out
22.2
Qwen3.5 122B-A10B
558
Alibaba262.1K ctx126 t/s$2/M/M out
22.0
Open
GPT-oss-20B
559
OpenAI131K ctx90 t/s$0.2/M/M out
22.0
Open
K2 Think V2
560
K2131K ctx40 t/s$3/M/M out
22.0
Mercury 2
561
Inception131K ctx60 t/s$3/M/M out
21.9
Qwen3 5 9b
562
Alibaba131K ctx85 t/s$2/M/M out
21.8
Open
Claude Opus 4.1
563
Anthropic200K ctx80 t/s$15/M/M out
21.7
legacy
Deepseek V3 2 0925
564
DeepSeek131K ctx60 t/s$1.1/M/M out
21.7
Open
Apriel V1 5 15b Thinker
565
ServiceNow131K ctx60 t/s$3/M/M out
21.6
Nova 2 0 Omni Reasoning Medium
566
Amazon131K ctx40 t/s$3.2/M/M out
21.3
Qwen3 Coder Next
567
Alibaba131K ctx85 t/s$2/M/M out
21.3
Open
Deepseek V3 1 Reasoning
568
DeepSeek131K ctx40 t/s$1.1/M/M out
21.0
Open
Qwen3 Vl 235b A22b Reasoning
569
Alibaba131K ctx55 t/s$2/M/M out
20.9
Open
Apriel V1 6 15b Thinker
570
ServiceNow131K ctx60 t/s$3/M/M out
20.8
Nova 2 0 Lite Reasoning
571
Amazon131K ctx40 t/s$3.2/M/M out
20.8
Gpt 5 1 Non Reasoning
572
OpenAI131K ctx60 t/s$10/M/M out
20.7
Qwen3 5 9b Non Reasoning
573
Alibaba131K ctx55 t/s$2/M/M out
20.6
Open
Gemma 4 26b A4b Non Reasoning
574
Google131K ctx80 t/s$5/M/M out
20.4
Open
Qwen3 5 4b
575
Alibaba131K ctx85 t/s$2/M/M out
20.4
Open
Gemini 2 5 Flash Reasoning
576
Google131K ctx80 t/s$5/M/M out
20.3
North Mini Code
577
North131K ctx60 t/s$3/M/M out
20.2
Gpt 5 Nano
578
OpenAI131K ctx90 t/s$10/M/M out
20.1
Qwen3 235b A22b Instruct 2507 Reasoning
579
Alibaba131K ctx55 t/s$2/M/M out
19.9
Open
Nova 2 0 Pro Reasoning Low
580
Amazon131K ctx40 t/s$3.2/M/M out
19.8
Kimi K2
581
Moonshot AI131K ctx60 t/s$4/M/M out
19.7
Mistral Small 4
582
Mistral131K ctx100 t/s$6/M/M out
19.7
Open
Qwen3 Max
583
Alibaba262.1K ctx85 t/s$2/M/M out
19.6
Openlegacy
Gpt 4 1
584
OpenAI131K ctx90 t/s$10/M/M out
19.6
Qwen3 Max Preview
585
Alibaba131K ctx85 t/s$2/M/M out
19.4
Open
Devstral 2
586
Mistral131K ctx100 t/s$6/M/M out
19.2
Gpt 5 Nano Medium
587
OpenAI131K ctx90 t/s$10/M/M out
19.2
Nova 2 0 Lite Reasoning Medium
588
Amazon131K ctx40 t/s$3.2/M/M out
19.2
O3 Mini
589
OpenAI131K ctx60 t/s$10/M/M out
19.2
Qwen3 5 Omni Flash
590
Alibaba131K ctx85 t/s$2/M/M out
19.2
Open
O1 Pro
591
OpenAI131K ctx60 t/s$10/M/M out
19.1
Nemotron 3 Ultra 550B
592
NVIDIA512K ctx142 t/s$2.75/M/M out
19.0
Open
Deepseek R1 0120
593
DeepSeek131K ctx40 t/s$1.1/M/M out
18.6
Open
Seed Oss 36b Instruct
594
ByteDance131K ctx60 t/s$3/M/M out
18.5
Qwen3 235b A22b Instruct 2507
595
Alibaba131K ctx85 t/s$2/M/M out
18.4
Open
Trinity Large Thinking
596
Trinity131K ctx40 t/s$3/M/M out
18.4
Qwen3 Coder 480b A35b Instruct
597
Alibaba131K ctx85 t/s$2/M/M out
18.2
Open
Qwen3 Vl 32b Reasoning
598
Alibaba131K ctx55 t/s$2/M/M out
18.1
Open
Nova 2 0 Lite Reasoning Low
599
Amazon131K ctx40 t/s$3.2/M/M out
18.0
Minimax M1 80k
600
MiniMax131K ctx60 t/s$2/M/M out
17.9
Open
Gpt 5 4 Nano Non Reasoning
601
OpenAI131K ctx60 t/s$10/M/M out
17.8
Devstral Small 2
602
Mistral131K ctx100 t/s$6/M/M out
17.7
Gpt 5 Minimal
603
OpenAI131K ctx90 t/s$10/M/M out
17.3
O1 Preview
604
OpenAI131K ctx60 t/s$10/M/M out
17.2
Glm 4 6v Reasoning
605
Z.ai131K ctx40 t/s$3/M/M out
16.9
Open
Qwen3 Next 80b A3b Reasoning
606
Alibaba131K ctx55 t/s$2/M/M out
16.9
Open
Gpt 5 4 Mini Non Reasoning
607
OpenAI131K ctx60 t/s$10/M/M out
16.8
Nova 2 0 Omni Reasoning Low
608
Amazon131K ctx40 t/s$3.2/M/M out
16.7
Grok 4 Fast
609
xAI131K ctx80 t/s$15/M/M out
16.6
Qwen3 5 4b Non Reasoning
610
Alibaba131K ctx55 t/s$2/M/M out
16.1
Open
Mistral Large 3
611
Mistral131K ctx100 t/s$6/M/M out
15.9
Open
O3 Mini High
612
OpenAI131K ctx60 t/s$10/M/M out
15.7
Glm 4 7 Flash Non Reasoning
613
Z.ai131K ctx40 t/s$3/M/M out
15.6
Open
Deepseek V3 0324
614
DeepSeek131K ctx60 t/s$1.1/M/M out
15.2
Open
Gemini 2 5 Flash Lite Preview 09 2025 Reasoning
615
Google131K ctx80 t/s$5/M/M out
15.2
Nemotron 3 Nano Omni 30b A3b
616
NVIDIA131K ctx150 t/s$1/M/M out
15.0
Gpt Oss 120b Low
617
OpenAI131K ctx90 t/s$10/M/M out
14.9
Mistral Small 3 1
618
Mistral131K ctx100 t/s$6/M/M out
14.9
Open
Gpt 4 1 Mini
619
OpenAI131K ctx90 t/s$10/M/M out
14.8
Mistral Medium 3 1
620
Mistral131K ctx100 t/s$6/M/M out
14.7
Open
Qwen3 30b A3b 2507 Reasoning
621
Alibaba131K ctx55 t/s$2/M/M out
14.6
Open
Nvidia Nemotron 3 Nano 30b A3b Reasoning
622
NVIDIA131K ctx100 t/s$1/M/M out
14.5
Nova 2.0 Pro Preview
623
Amazon1.0M ctx40 t/s$3.2/M/M out
14.4
preview
Gpt Oss 20b Low
624
OpenAI131K ctx90 t/s$10/M/M out
14.4
Qwen3 Vl 235b A22b Instruct
625
Alibaba131K ctx85 t/s$2/M/M out
14.4
Open
Gpt 5 Mini Minimal
626
OpenAI131K ctx90 t/s$10/M/M out
14.3
Ling 2 6 Flash
627
Ling131K ctx60 t/s$3/M/M out
14.2
Qwen3 Next 80b A3b Instruct
628
Alibaba131K ctx85 t/s$2/M/M out
13.8
Open
Qwen3 Coder 30b A3b Instruct
629
Alibaba131K ctx85 t/s$2/M/M out
13.6
Open
Qwen3 235b A22b Instruct Reasoning
630
Alibaba131K ctx55 t/s$2/M/M out
13.5
Open
Qwen3 Vl 30b A3b Reasoning
631
Alibaba131K ctx55 t/s$2/M/M out
13.4
Open
Qwq 32b
632
Alibaba131K ctx85 t/s$2/M/M out
13.4
Gemma 4 12b Non Reasoning
633
Google131K ctx80 t/s$5/M/M out
13.2
Open
Gemini 2 5 Flash Lite Preview 09 2025
634
Google131K ctx120 t/s$5/M/M out
13.1
DeepSeek V3.2
635
DeepSeek163.8K ctx60 t/s$1.1/M/M out
12.9
Openlegacy
Nova Premier
636
Amazon131K ctx60 t/s$3.2/M/M out
12.7
Mistral Medium 3
637
Mistral131K ctx100 t/s$6/M/M out
12.5
Open
Celeris 1
638
Celeris131K ctx60 t/s$3/M/M out
12.4
Llama Nemotron Super 49b V1 5 Reasoning
639
Meta131K ctx50 t/s$0/M/M out
12.4
Open
Mistral Small 4 Non Reasoning
640
Mistral131K ctx60 t/s$6/M/M out
12.3
Open
Gemma 4 E4b
641
Google131K ctx120 t/s$5/M/M out
12.2
Open
Claude 3 Opus
642
Anthropic131K ctx80 t/s$15/M/M out
11.8
Nova 2 0 Lite
643
Amazon131K ctx60 t/s$3.2/M/M out
11.8
Gemini 2 5 Flash Lite Reasoning
644
Google131K ctx80 t/s$5/M/M out
11.4
Qwen3 32b Instruct Reasoning
645
Alibaba131K ctx55 t/s$2/M/M out
11.4
Open
Ministral 3 14b
646
Mistral131K ctx100 t/s$6/M/M out
11.2
Qwen3 Vl 32b Instruct
647
Alibaba131K ctx85 t/s$2/M/M out
11.0
Open
Qwen3 235b A22b Instruct
648
Alibaba131K ctx85 t/s$2/M/M out
10.8
Open
Mistral Small 3 2
649
Mistral131K ctx100 t/s$6/M/M out
10.7
Open
Gemini 2 0 Flash Experimental
650
Google131K ctx120 t/s$5/M/M out
10.6
Qwen3 Vl 8b Reasoning
651
Alibaba131K ctx55 t/s$2/M/M out
10.5
Open
Nova 2 0 Omni
652
Amazon131K ctx60 t/s$3.2/M/M out
10.4
Qwen3 14b Instruct Reasoning
653
Alibaba131K ctx55 t/s$2/M/M out
10.4
Open
Llama 4 Scout
654
Meta131K ctx80 t/s$0/M/M out
10.3
Open
Hermes 4 Llama 3 1 70b Reasoning
655
Meta131K ctx50 t/s$0/M/M out
9.9
Open
Qwen3 Vl 30b A3b Instruct
656
Alibaba131K ctx85 t/s$2/M/M out
9.9
Open
Claude 35 Sonnet
657
Anthropic131K ctx80 t/s$15/M/M out
9.8
Deepseek R1 Distill Llama 70b
658
DeepSeek131K ctx40 t/s$1.1/M/M out
9.8
Open
Gpt 4 1 Nano
659
OpenAI131K ctx90 t/s$10/M/M out
9.6
Qwen3 Omni 30b A3b Reasoning
660
Alibaba131K ctx55 t/s$2/M/M out
9.5
Open
Gpt 4o 2024 08 06
661
OpenAI131K ctx90 t/s$10/M/M out
9.4
Llama 3 3 Instruct 70b
662
Meta131K ctx80 t/s$0/M/M out
9.3
Open
Qwen3 30b A3b Instruct Reasoning
663
Alibaba131K ctx55 t/s$2/M/M out
9.2
Open
Glm 4 5v Reasoning
664
Z.ai131K ctx40 t/s$3/M/M out
9.0
Open
Ministral 3 8b
665
Mistral131K ctx100 t/s$6/M/M out
9.0
Ernie 4 5 300b A47b
666
Baidu131K ctx60 t/s$3/M/M out
8.9
Llama 3 1 Nemotron Ultra 253b V1 Reasoning
667
Meta131K ctx50 t/s$0/M/M out
8.9
Open
Qwen3 30b A3b 2507
668
Alibaba131K ctx85 t/s$2/M/M out
8.9
Open
Hermes 4 Llama 3 1 405b Reasoning
669
Meta131K ctx50 t/s$0/M/M out
8.8
Open
Nvidia Nemotron Nano 12b V2 Vl Reasoning
670
NVIDIA131K ctx100 t/s$1/M/M out
8.8
Gemma 4 E4b Non Reasoning
671
Google131K ctx80 t/s$5/M/M out
8.7
Open
Nvidia Nemotron Nano 9b V2 Reasoning
672
NVIDIA131K ctx100 t/s$1/M/M out
8.7
Hermes 4 Llama 3 1 405b
673
Meta131K ctx80 t/s$0/M/M out
8.6
Open
Llama Nemotron Super 49b V1 5
674
Meta131K ctx80 t/s$0/M/M out
8.5
Open
Qwen3 32b Instruct
675
Alibaba131K ctx85 t/s$2/M/M out
8.5
Open
Gpt 4o 2024 05 13
676
OpenAI131K ctx90 t/s$10/M/M out
8.4
Qwen3 8b Instruct Reasoning
677
Alibaba131K ctx55 t/s$2/M/M out
8.3
Open
Qwen3 Vl 8b Instruct
678
Alibaba131K ctx85 t/s$2/M/M out
8.2
Open
Claude 35 Sonnet June 24
679
Anthropic131K ctx80 t/s$15/M/M out
8.1
Gpt 5 Nano Minimal
680
OpenAI131K ctx90 t/s$10/M/M out
7.8
Gpt 4 Turbo
681
OpenAI131K ctx90 t/s$10/M/M out
7.7
Command A
682
Cohere131K ctx60 t/s$10/M/M out
7.5
Nova Pro
683
Amazon131K ctx60 t/s$3.2/M/M out
7.5
Gemma 3 27b
684
Google131K ctx120 t/s$5/M/M out
7.4
Open
Llama 3 1 Instruct 8b
685
Meta131K ctx80 t/s$0/M/M out
7.4
Open
Llama 3 1 Nemotron Instruct 70b
686
Meta131K ctx80 t/s$0/M/M out
7.4
Open
Nvidia Nemotron 3 Nano 30b A3b
687
NVIDIA131K ctx150 t/s$1/M/M out
7.2
Nvidia Nemotron Nano 9b V2
688
NVIDIA131K ctx150 t/s$1/M/M out
7.2
Ministral 3 3b
689
Mistral131K ctx100 t/s$6/M/M out
7.1
Mistral Large 2407
690
Mistral131K ctx100 t/s$6/M/M out
7.0
Open
Gpt 4
691
OpenAI131K ctx90 t/s$10/M/M out
6.8
Qwen3 14b Instruct
692
Alibaba131K ctx85 t/s$2/M/M out
6.8
Open
Gemini 2 5 Flash Lite
693
Google131K ctx120 t/s$5/M/M out
6.7
Hermes 4 Llama 3 1 70b
694
Meta131K ctx80 t/s$0/M/M out
6.7
Open
Mistral Small 3
695
Mistral131K ctx100 t/s$6/M/M out
6.7
Open
Nova Lite
696
Amazon131K ctx60 t/s$3.2/M/M out
6.7
Qwen3 30b A3b Instruct
697
Alibaba131K ctx85 t/s$2/M/M out
6.6
Open
Llama 3 1 Instruct 70b
698
Meta131K ctx80 t/s$0/M/M out
6.5
Open
Qwen Turbo
699
Alibaba131K ctx85 t/s$2/M/M out
6.0
Open
Reka Flash
700
Reka131K ctx60 t/s$3/M/M out
6.0
Solar Mini
701
Upstage131K ctx60 t/s$3/M/M out
6.0
Phi 4 Mini
702
Microsoft131K ctx60 t/s$0.6/M/M out
5.7
Open
Gemma 3 12b
703
Google131K ctx120 t/s$5/M/M out
5.5
Open
DeepSeek R1
704
DeepSeek163.8K ctx60 t/s$1.1/M/M out
5.4
Openlegacy
Granite 4 0 H Small
705
IBM131K ctx60 t/s$3/M/M out
4.9
Open
Hermes 3 Llama 3 1 70b
706
Meta131K ctx80 t/s$0/M/M out
4.8
Open
Jamba 1 5 Large
707
AI21 Labs131K ctx60 t/s$3/M/M out
4.8
Qwen3 8b Instruct
708
Alibaba131K ctx85 t/s$2/M/M out
4.8
Open
Qwen3 Omni 30b A3b Instruct
709
Alibaba131K ctx85 t/s$2/M/M out
4.8
Open
Nova Micro
710
Amazon131K ctx60 t/s$3.2/M/M out
4.4
Mistral Small
711
Mistral131K ctx100 t/s$6/M/M out
4.3
Open
Nvidia Nemotron Nano 12b V2 Vl
712
NVIDIA131K ctx150 t/s$1/M/M out
4.2
Mistral Large
713
Mistral131K ctx100 t/s$6/M/M out
4.1
Open
Llama 2 Chat 7b
714
Meta131K ctx80 t/s$0/M/M out
3.9
Open
Reka Flash 3
715
Reka131K ctx60 t/s$3/M/M out
3.7
Claude 3 Haiku
716
Anthropic131K ctx80 t/s$15/M/M out
3.5
Gpt 35 Turbo
717
OpenAI131K ctx90 t/s$10/M/M out
3.2
Mistral Medium
718
Mistral131K ctx100 t/s$6/M/M out
3.2
Open
Mistral Small 2402
719
Mistral131K ctx100 t/s$6/M/M out
3.2
Open
Llama 3 Instruct 70b
720
Meta131K ctx80 t/s$0/M/M out
3.1
Open
Llama 3 2 Instruct 11b Vision
721
Meta131K ctx80 t/s$0/M/M out
3.0
Open
Command R Plus 04 2024
722
Cohere131K ctx60 t/s$10/M/M out
2.6
Olmo 3 7b Instruct
723
AI2131K ctx60 t/s$3/M/M out
2.4
Open
Jamba 1 5 Mini
724
AI21 Labs131K ctx60 t/s$3/M/M out
2.3
Apertus 70b Instruct
725
Swiss AI131K ctx60 t/s$3/M/M out
2.0
Mixtral 8x7b Instruct
726
Mistral131K ctx100 t/s$6/M/M out
2.0
Command R 03 2024
727
Cohere131K ctx60 t/s$10/M/M out
1.7
Mistral 7b Instruct
728
Mistral131K ctx100 t/s$6/M/M out
1.7
Open
Granite 3 3 8b Instruct
729
IBM131K ctx60 t/s$3/M/M out
1.3
Open
Apertus 8b Instruct
730
Swiss AI131K ctx60 t/s$3/M/M out
1.0
Gemma 3 1b
731
Google131K ctx120 t/s$5/M/M out
1.0
Open
Gemma 3 4b
732
Google131K ctx120 t/s$5/M/M out
1.0
Open
Gemma 3n E2b
733
Google131K ctx120 t/s$5/M/M out
1.0
Open
Gemma 3n E4b
734
Google131K ctx120 t/s$5/M/M out
1.0
Open
Llama 3 Instruct 8b
735
Meta131K ctx80 t/s$0/M/M out
1.0
Open
Tiny Aya Global
736
Cohere131K ctx60 t/s$10/M/M out
1.0
Claude Mythos 5
737
Anthropic1.0M ctx50 t/s$50/M/M out
0.0
preview
GPT-5.5 Pro
738
OpenAI1.1M ctx60 t/s$10/M/M out
0.0
Claude Sonnet 4.6 (max)
739
Anthropic1.0M ctx50 t/s$15/M/M out
0.0
Amazon Nova
740
Amazon131K ctx60 t/s$3.2/M/M out
0.0
Async Flash V1 5
741
Async131K ctx60 t/s$3/M/M out
0.0
Async Pro V1 0
742
Async131K ctx60 t/s$3/M/M out
0.0
Asyncflow V2
743
Async131K ctx60 t/s$3/M/M out
0.0
Claude Sonnet 5 High
744
Anthropic131K ctx80 t/s$15/M/M out
0.0
Claude Sonnet 5 Low
745
Anthropic131K ctx80 t/s$15/M/M out
0.0
Claude Sonnet 5 Medium
746
Anthropic131K ctx80 t/s$15/M/M out
0.0
Claude Sonnet 5 Xhigh
747
Anthropic131K ctx80 t/s$15/M/M out
0.0
Cogito V2 1 Reasoning
748
Cogito131K ctx40 t/s$3/M/M out
0.0
Falcon 2
749
TII131K ctx60 t/s$3/M/M out
0.0
Open
Gemini
750
Google131K ctx120 t/s$5/M/M out
0.0
Gemini 2 5 Flash Dec 2025
751
Google131K ctx120 t/s$5/M/M out
0.0
Gemini_nano Banana Pro
752
Google131K ctx120 t/s$5/M/M out
0.0
Gladia Solaria
753
Upstage131K ctx60 t/s$3/M/M out
0.0
Gpt 5 4 Pro
754
OpenAI131K ctx90 t/s$10/M/M out
0.0
Gpt Realtime 2
755
OpenAI131K ctx90 t/s$10/M/M out
0.0
Grok Stt
756
xAI131K ctx80 t/s$15/M/M out
0.0
Hidream O1 Image
757
OpenAI131K ctx60 t/s$10/M/M out
0.0
Minimax H3
758
MiniMax131K ctx60 t/s$2/M/M out
0.0
Open
Mistral
759
Mistral131K ctx100 t/s$6/M/M out
0.0
Open
Nvidia
760
NVIDIA131K ctx150 t/s$1/M/M out
0.0
Nvidia Nemotron Asr Streaming
761
NVIDIA131K ctx150 t/s$1/M/M out
0.0
Ocateve 2
762
Ocat131K ctx60 t/s$3/M/M out
0.0
Qwen Image
763
Alibaba131K ctx85 t/s$2/M/M out
0.0
Open
Qwen3 Asr
764
Alibaba131K ctx85 t/s$2/M/M out
0.0
Open
Apodex 1.1
765
Independent128K ctx145 t/s$0.8/M/M out
0.0
Open
Muse Spark 1.3 (xhigh)
766
Muse256K ctx65 t/s$10/M/M out
0.0
Quasar 438B
767
Open Source128K ctx95 t/s$1.6/M/M out
0.0
Open
0 / 4
Compare Now →