Katalog model

Semua 738 model bahasa dari 52 penyedia — benchmark, harga, kecepatan, dan peringkat dalam satu tempat.

Anthropic75OpenAI123Moonshot AI16Alibaba95Google68xAI36DeepSeek36Z.ai24Baidu5LongCat3Amazon25NVIDIA17Tencent13MiniMax9Mistral35StepFun7Meta42Cohere12AI27Ling7AI9Stars2IBM10Inception3Kwai1Liquid AI3Multiverse1Zhipu AI2Muse2Microsoft10Xiaomi5Sarvam AI3Agnes3Nex AGI1Thinking Machines2Upstage4ByteDance2WeRide1K21ServiceNow2North1Trinity1Celeris1Reka2AI21 Labs2Swiss AI2Async3Cogito1Independent1Ocat1Open Source1TII1
Analisis Interaktif

Matriks Trade-off Kualitas vs Biaya

Evaluasi frontier: jelajahi frontier efisiensi Pareto, latensi, dan kuadran harga

Sumbu Y:
Sumbu X:
Frontier Optimal Pareto
Zona Optimal (Kualitas Tinggi, Biaya Rendah)
Performa Tinggi / Premium
Claude Mythos Preview
1
Anthropic1.0M ctx80 t/s$15/M/M output
97.4
pratinjau
Claude Fable 5
2
Anthropic1.0M ctx71 t/s$50/M/M output
93.4
Claude Fable 5.1 (XHigh)
3
Anthropic500K ctx78 t/s$15/M/M output
89.0
Claude Fable 5.1
4
Anthropic500K ctx85 t/s$15/M/M output
88.4
GPT-6 Astra (xhigh)
5
OpenAI1.1M ctx76 t/s$50/M/M output
87.0
Claude Fable 5.1 (High)
6
Anthropic500K ctx92 t/s$15/M/M output
86.5
GPT-6 Astra
7
OpenAI1.1M ctx82 t/s$50/M/M output
86.2
GPT-6 Astra (high)
8
OpenAI1.1M ctx90 t/s$50/M/M output
85.0
GPT-6 Luna
9
OpenAI1.0M ctx120 t/s$20/M/M output
84.5
Claude Opus 5.5 (XHigh)
10
Anthropic1.0M ctx62 t/s$25/M/M output
84.5
GPT-6 Luna (xhigh)
11
OpenAI1.0M ctx118 t/s$20/M/M output
84.0
Claude Opus 5.5
12
Anthropic1.0M ctx68 t/s$25/M/M output
84.0
Claude Fable 5.1 (Medium)
13
Anthropic500K ctx104 t/s$15/M/M output
84.0
Kimi K3
14
Moonshot AI1.0M ctx37 t/s$15/M/M output
83.3
Terbuka
Claude Opus 5.5 (High)
15
Anthropic1.0M ctx74 t/s$25/M/M output
82.5
GPT-6 Luna (high)
16
OpenAI1.0M ctx128 t/s$20/M/M output
82.0
GPT-6 Astra (medium)
17
OpenAI1.1M ctx98 t/s$50/M/M output
81.5
Claude Opus 5
18
Anthropic1.0M ctx60 t/s$25/M/M output
81.4
GPT-5.6 Sol
19
OpenAI1.1M ctx72 t/s$30/M/M output
80.8
Claude Fable 5.1 (Low)
20
Anthropic500K ctx118 t/s$15/M/M output
80.0
Qwen3.8 Max
21
Alibaba1M ctx55 t/s$2/M/M output
79.8
Claude Opus 5.5 (Medium)
22
Anthropic1.0M ctx82 t/s$25/M/M output
79.5
GPT-6 Luna (medium)
23
OpenAI1.0M ctx138 t/s$20/M/M output
78.5
GPT-6 Sol (xhigh)
24
OpenAI400K ctx210 t/s$4/M/M output
78.5
GPT-6 Sol
25
OpenAI400K ctx220 t/s$4/M/M output
78.0
GPT-6 Astra (low)
26
OpenAI1.1M ctx110 t/s$50/M/M output
78.0
GPT-6 Sol (high)
27
OpenAI400K ctx226 t/s$4/M/M output
77.0
Claude Opus 4.8
28
Anthropic1M ctx50 t/s$15/M/M output
76.0
Claude Opus 5.5 (Low)
29
Anthropic1.0M ctx92 t/s$25/M/M output
75.5
Claude Opus 4 6 Thinking
30
Anthropic128K ctx50 t/s$15/M/M output
75.0
Claude Opus 4 7 Thinking
31
Anthropic128K ctx50 t/s$15/M/M output
75.0
Claude Opus 5 Max
32
Anthropic128K ctx50 t/s$15/M/M output
75.0
GPT-6 Luna (low)
33
OpenAI1.0M ctx150 t/s$20/M/M output
74.5
Gemini 3.1 Pro Preview
34
Google128K ctx50 t/s$5/M/M output
74.0
Kimi K3 Max
35
Moonshot AI128K ctx50 t/s$3/M/M output
74.0
Claude Opus 4 8 Thinking
36
Anthropic128K ctx50 t/s$15/M/M output
74.0
GPT 5.6 Sol Xhigh
37
OpenAI128K ctx50 t/s$10/M/M output
74.0
GPT 5.5 High
38
OpenAI128K ctx50 t/s$10/M/M output
74.0
GPT 5.4 High
39
OpenAI128K ctx50 t/s$10/M/M output
74.0
Gemini 3.5 Flash High
40
Google128K ctx50 t/s$5/M/M output
74.0
GPT 5.2 Chat Latest 20260210
41
OpenAI128K ctx50 t/s$10/M/M output
74.0
Qwen3.7 Max Preview
42
Alibaba128K ctx50 t/s$2/M/M output
74.0
Grok 4.20 Beta1
43
xAI128K ctx50 t/s$15/M/M output
74.0
Gemini 3.5 Flash Medium
44
Google128K ctx50 t/s$5/M/M output
74.0
GPT 5.5 Instant
45
OpenAI128K ctx50 t/s$10/M/M output
74.0
Claude Opus 4 5 20251101 Thinking 32k
46
Anthropic128K ctx50 t/s$15/M/M output
74.0
Grok 4.20 Beta 0309 Reasoning
47
xAI128K ctx50 t/s$15/M/M output
74.0
Grok 4.20 Multi Agent Beta 0309
48
xAI128K ctx50 t/s$15/M/M output
74.0
GPT-6 Sol (medium)
49
OpenAI400K ctx238 t/s$4/M/M output
74.0
Glm 5.2 Max
50
Z.ai128K ctx50 t/s$3/M/M output
73.0
Claude Opus 4 5 20251101
51
Anthropic128K ctx50 t/s$15/M/M output
73.0
GPT 5.6 Terra Xhigh
52
OpenAI128K ctx50 t/s$10/M/M output
73.0
Grok 4.1 Thinking
53
xAI128K ctx50 t/s$15/M/M output
73.0
Qwen3.5 Max Preview
54
Alibaba128K ctx50 t/s$2/M/M output
73.0
Qwen3.6 Max Preview
55
Alibaba128K ctx50 t/s$2/M/M output
73.0
Grok 4.1
56
xAI128K ctx50 t/s$15/M/M output
73.0
Dola Seed 2.0 Pro
57
Unknown128K ctx50 t/s$3/M/M output
73.0
Claude Sonnet 4 5 20250929 Thinking 32k
58
Anthropic128K ctx50 t/s$15/M/M output
73.0
Claude Sonnet 4 5 20250929
59
Anthropic128K ctx50 t/s$15/M/M output
73.0
GPT 5.1 High
60
OpenAI128K ctx50 t/s$10/M/M output
73.0
Deepseek V4 Pro High Preview
61
DeepSeek128K ctx50 t/s$1.1/M/M output
73.0
GPT 5.6 Luna Xhigh
62
OpenAI128K ctx50 t/s$10/M/M output
73.0
Kimi K2.5 Thinking
63
Moonshot AI128K ctx50 t/s$3/M/M output
73.0
Claude Opus 4 1 20250805 Thinking 16k
64
Anthropic128K ctx50 t/s$15/M/M output
72.0
Ernie 5.0 Preview 1203
65
Baidu128K ctx50 t/s$3/M/M output
72.0
GPT 5.3 Chat Latest
66
OpenAI128K ctx50 t/s$10/M/M output
72.0
GPT 5.4 Mini High
67
OpenAI128K ctx50 t/s$10/M/M output
72.0
Mimo V2 Pro
68
Unknown128K ctx50 t/s$3/M/M output
72.0
Claude Opus 4 1 20250805
69
Anthropic128K ctx50 t/s$15/M/M output
72.0
Ernie 5.0 0110
70
Baidu128K ctx50 t/s$3/M/M output
72.0
GPT 4.5 Preview 2025 02 27
71
OpenAI128K ctx50 t/s$10/M/M output
72.0
Chatgpt 4o Latest 20250326
72
OpenAI128K ctx50 t/s$10/M/M output
72.0
Glm 4.7
73
Z.ai128K ctx50 t/s$3/M/M output
72.0
Qwen3.5 397b A17b
74
Alibaba128K ctx50 t/s$2/M/M output
72.0
Deepseek V4 Flash High Preview
75
DeepSeek128K ctx50 t/s$1.1/M/M output
72.0
GPT 5.2 High
76
OpenAI128K ctx50 t/s$10/M/M output
72.0
Longcat Flash Chat 2602 Exp
77
LongCat128K ctx50 t/s$3/M/M output
72.0
GPT 5 High
78
OpenAI128K ctx50 t/s$10/M/M output
72.0
Mimo V2.5
79
Unknown128K ctx50 t/s$3/M/M output
72.0
Glm 5v Turbo
80
Z.ai128K ctx50 t/s$3/M/M output
72.0
Gemini 3.1 Flash Lite Preview
81
Google128K ctx50 t/s$5/M/M output
72.0
Kimi K2.5 Instant
82
Moonshot AI128K ctx50 t/s$3/M/M output
72.0
Grok 4 1 Fast Reasoning
83
xAI128K ctx50 t/s$15/M/M output
72.0
O3 2025 04 16
84
OpenAI128K ctx50 t/s$10/M/M output
72.0
Mimo V2 Omni
85
Unknown128K ctx50 t/s$3/M/M output
72.0
Kimi K2 Thinking Turbo
86
Moonshot AI128K ctx50 t/s$3/M/M output
72.0
GPT-6 Luna (Non-reasoning)
87
OpenAI1.0M ctx165 t/s$20/M/M output
71.5
GPT 5 Chat
88
OpenAI128K ctx50 t/s$10/M/M output
71.0
Nvidia Nemotron 3 Ultra 550b A55b Nvfp4
89
NVIDIA128K ctx50 t/s$3/M/M output
71.0
Amazon Nova Experimental Chat 26 02 10
90
Amazon128K ctx50 t/s$3/M/M output
71.0
Glm 4.6
91
Z.ai128K ctx50 t/s$3/M/M output
71.0
Deepseek V3.2 Exp Thinking
92
DeepSeek128K ctx50 t/s$1.1/M/M output
71.0
Claude Opus 4 20250514 Thinking 16k
93
Anthropic128K ctx50 t/s$15/M/M output
71.0
Qwen3 Max 2025 09 23
94
Alibaba128K ctx50 t/s$2/M/M output
71.0
Deepseek V3.2 Thinking
95
DeepSeek128K ctx50 t/s$1.1/M/M output
71.0
Deepseek V3.2 Exp
96
DeepSeek128K ctx50 t/s$1.1/M/M output
71.0
Deepseek R1 0528
97
DeepSeek128K ctx50 t/s$1.1/M/M output
71.0
Grok 4 Fast Chat
98
xAI128K ctx50 t/s$15/M/M output
71.0
Ernie 5.0 Preview 1022
99
Baidu128K ctx50 t/s$3/M/M output
71.0
Kimi K2 0905 Preview
100
Moonshot AI128K ctx50 t/s$3/M/M output
71.0
Kimi K2 0711 Preview
101
Moonshot AI128K ctx50 t/s$3/M/M output
71.0
Deepseek V3.1
102
DeepSeek128K ctx50 t/s$1.1/M/M output
71.0
Deepseek V3.1 Terminus Thinking
103
DeepSeek128K ctx50 t/s$1.1/M/M output
71.0
Deepseek V3.1 Thinking
104
DeepSeek128K ctx50 t/s$1.1/M/M output
71.0
Qwen3.5 122b A10b
105
Alibaba128K ctx50 t/s$2/M/M output
71.0
Amazon Nova Experimental Chat 26 01 10
106
Amazon128K ctx50 t/s$3/M/M output
71.0
Deepseek V3.1 Terminus
107
DeepSeek128K ctx50 t/s$1.1/M/M output
71.0
GPT 4.1 2025 04 14
108
OpenAI128K ctx50 t/s$10/M/M output
71.0
Claude Opus 4 20250514
109
Anthropic128K ctx50 t/s$15/M/M output
71.0
Claude Haiku 4 5 20251001
110
Anthropic128K ctx50 t/s$15/M/M output
71.0
Hunyuan Hy3 Preview
111
Tencent128K ctx50 t/s$3/M/M output
71.0
Grok 3 Preview 02 24
112
xAI128K ctx50 t/s$15/M/M output
71.0
Glm 4.5
113
Z.ai128K ctx50 t/s$3/M/M output
71.0
Grok 4.7 (high)
114
xAI1.0M ctx80 t/s$15/M/M output
71.0
Grok 4 0709
115
xAI128K ctx50 t/s$15/M/M output
70.0
Mistral Medium 2508
116
Mistral128K ctx50 t/s$6/M/M output
70.0
Qwen3.5 27b
117
Alibaba128K ctx50 t/s$2/M/M output
70.0
Gemini 2.5 Flash Preview 09 2025
118
Google128K ctx50 t/s$5/M/M output
70.0
Qwen3 235b A22b No Thinking
119
Alibaba128K ctx50 t/s$2/M/M output
70.0
GPT 5.4 Nano High
120
OpenAI128K ctx50 t/s$10/M/M output
70.0
O1 2024 12 17
121
OpenAI128K ctx50 t/s$10/M/M output
70.0
Longcat Flash Chat
122
LongCat128K ctx50 t/s$3/M/M output
70.0
Claude Sonnet 4 20250514 Thinking 32k
123
Anthropic128K ctx50 t/s$15/M/M output
70.0
Qwen3 235b A22b Thinking 2507
124
Alibaba128K ctx50 t/s$2/M/M output
70.0
Qwen3.5 Flash
125
Alibaba128K ctx50 t/s$2/M/M output
70.0
Qwen3.5 35b A3b
126
Alibaba128K ctx50 t/s$2/M/M output
70.0
Qwen3 VL 235b A22b Thinking
127
Alibaba128K ctx50 t/s$2/M/M output
70.0
Hunyuan Vision 1.5 Thinking
128
Tencent128K ctx50 t/s$3/M/M output
70.0
Step 3.5 Flash
129
StepFun128K ctx50 t/s$3/M/M output
70.0
Amazon Nova Experimental Chat 12 10
130
Amazon128K ctx50 t/s$3/M/M output
70.0
GPT 5 Mini High
131
OpenAI128K ctx50 t/s$10/M/M output
70.0
O4 Mini 2025 04 16
132
OpenAI128K ctx50 t/s$10/M/M output
70.0
Minimax M2.5
133
MiniMax128K ctx50 t/s$3/M/M output
70.0
GPT-6 Sol (low)
134
OpenAI400K ctx250 t/s$4/M/M output
70.0
Muse Spark 1.1
135
Meta1.0M ctx208 t/s$4.25/M/M output
69.9
Claude Sonnet 4 20250514
136
Anthropic128K ctx50 t/s$15/M/M output
69.0
Claude 3 7 Sonnet 20250219 Thinking 32k
137
Anthropic128K ctx50 t/s$15/M/M output
69.0
Mistral Medium 2505
138
Mistral128K ctx50 t/s$6/M/M output
69.0
Hunyuan T1 20250711
139
Tencent128K ctx50 t/s$3/M/M output
69.0
Minimax M2.1 Preview
140
MiniMax128K ctx50 t/s$3/M/M output
69.0
Qwen3 30b A3b Instruct 2507
141
Alibaba128K ctx50 t/s$2/M/M output
69.0
GPT 4.1 Mini 2025 04 14
142
OpenAI128K ctx50 t/s$10/M/M output
69.0
Hunyuan Turbos 20250416
143
Tencent128K ctx50 t/s$3/M/M output
69.0
Gemini 2.5 Flash Lite Preview 09 2025 No Thinking
144
Google128K ctx50 t/s$5/M/M output
69.0
Glm 4.6v
145
Z.ai128K ctx50 t/s$3/M/M output
69.0
Qwen3 235b A22b
146
Alibaba128K ctx50 t/s$2/M/M output
69.0
Gemini 2.5 Flash Lite Preview 06 17 Thinking
147
Google128K ctx50 t/s$5/M/M output
69.0
Qwen2.5 Max
148
Alibaba128K ctx50 t/s$2/M/M output
69.0
Claude 3 5 Sonnet 20241022
149
Anthropic128K ctx50 t/s$15/M/M output
69.0
Glm 4.5 Air
150
Z.ai128K ctx50 t/s$3/M/M output
69.0
Claude 3 7 Sonnet 20250219
151
Anthropic128K ctx50 t/s$15/M/M output
69.0
Gemini 3.8 Flash
152
Google1M ctx302 t/s$3.75/M/M output
68.5
Grok 4.7
153
xAI1.0M ctx95 t/s$15/M/M output
68.5
Qwen3 Next 80b A3b Thinking
154
Alibaba128K ctx50 t/s$2/M/M output
68.0
Glm 4.7 Flash
155
Z.ai128K ctx50 t/s$3/M/M output
68.0
Gemma 3 27b It
156
Google128K ctx50 t/s$5/M/M output
68.0
Amazon Nova Experimental Chat 11 10
157
Amazon128K ctx50 t/s$3/M/M output
68.0
Minimax M1
158
MiniMax128K ctx50 t/s$3/M/M output
68.0
Grok 3 Mini High
159
xAI128K ctx50 t/s$15/M/M output
68.0
Gemini 2.0 Flash 001
160
Google128K ctx50 t/s$5/M/M output
68.0
Mistral Small 2506
161
Mistral128K ctx50 t/s$6/M/M output
68.0
Grok 3 Mini Beta
162
xAI128K ctx50 t/s$15/M/M output
68.0
Command A 03 2025
163
Cohere128K ctx50 t/s$3/M/M output
68.0
Gemini 2.0 Flash Lite Preview 02 05
164
Google128K ctx50 t/s$5/M/M output
68.0
Glm 4.5v
165
Z.ai128K ctx50 t/s$3/M/M output
68.0
Gemini 1.5 Pro 002
166
Google128K ctx50 t/s$5/M/M output
68.0
GPT-6 Sol (Non-reasoning)
167
OpenAI400K ctx265 t/s$4/M/M output
68.0
Amazon Nova Experimental Chat 10 20
168
Amazon128K ctx50 t/s$3/M/M output
67.0
Hunyuan Turbos 20250226
169
Tencent128K ctx50 t/s$3/M/M output
67.0
Step 3
170
StepFun128K ctx50 t/s$3/M/M output
67.0
Llama 3.1 Nemotron Ultra 253b V1
171
Meta128K ctx50 t/s$0/M/M output
67.0
Amazon Nova Experimental Chat 10 09
172
Amazon128K ctx50 t/s$3/M/M output
67.0
Qwen3 32b
173
Alibaba128K ctx50 t/s$2/M/M output
67.0
Qwen Plus 0125
174
Alibaba128K ctx50 t/s$2/M/M output
67.0
Ling Flash 2.0
175
Ling128K ctx50 t/s$3/M/M output
67.0
Nvidia Llama 3.3 Nemotron Super 49b V1.5
176
NVIDIA128K ctx50 t/s$3/M/M output
67.0
Glm 4 Plus 0111
177
Z.ai128K ctx50 t/s$3/M/M output
67.0
Claude 3 5 Sonnet 20240620
178
Anthropic128K ctx50 t/s$15/M/M output
67.0
Gemma 3 12b It
179
Google128K ctx50 t/s$5/M/M output
67.0
Hunyuan Turbo 0110
180
Tencent128K ctx50 t/s$3/M/M output
67.0
GPT 5 Nano High
181
OpenAI128K ctx50 t/s$10/M/M output
67.0
O1 Mini
182
OpenAI128K ctx50 t/s$10/M/M output
67.0
Nova 2 Lite
183
Amazon128K ctx50 t/s$3/M/M output
67.0
Grok 2 2024 08 13
184
xAI128K ctx50 t/s$15/M/M output
67.0
Gemini Advanced 0514
185
Google128K ctx50 t/s$5/M/M output
67.0
Llama 3.1 405b Instruct Bf16
186
Meta128K ctx50 t/s$0/M/M output
67.0
Step 2 16k Exp 202412
187
StepFun128K ctx50 t/s$3/M/M output
67.0
Llama 3.1 405b Instruct Fp8
188
Meta128K ctx50 t/s$0/M/M output
67.0
Olmo 3.1 32b Instruct
189
AI2128K ctx50 t/s$3/M/M output
67.0
Qwen3.8 Flash Next
190
Alibaba260K ctx168 t/s$0.4/M/M output
66.8
Terbuka
GPT-5.6 Terra
191
OpenAI1.1M ctx127 t/s$12/M/M output
66.4
Molmo 2 8b
192
AI2128K ctx50 t/s$3/M/M output
66.0
Llama 3.3 Nemotron 49b Super V1
193
Meta128K ctx50 t/s$0/M/M output
66.0
Qwen3 30b A3b
194
Alibaba128K ctx50 t/s$2/M/M output
66.0
Llama 4 Maverick 17b 128e Instruct
195
Meta128K ctx50 t/s$0/M/M output
66.0
Hunyuan Large 2025 02 10
196
Tencent128K ctx50 t/s$3/M/M output
66.0
GPT 4 Turbo 2024 04 09
197
OpenAI128K ctx50 t/s$10/M/M output
66.0
Claude 3 5 Haiku 20241022
198
Anthropic128K ctx50 t/s$15/M/M output
66.0
Gemini 1.5 Pro 001
199
Google128K ctx50 t/s$5/M/M output
66.0
Deepseek V2.5 1210
200
DeepSeek128K ctx50 t/s$1.1/M/M output
66.0
Llama 4 Scout 17b 16e Instruct
201
Meta128K ctx50 t/s$0/M/M output
66.0
GPT 4.1 Nano 2025 04 14
202
OpenAI128K ctx50 t/s$10/M/M output
66.0
Claude 3 Opus 20240229
203
Anthropic128K ctx50 t/s$15/M/M output
66.0
Ring Flash 2.0
204
Unknown128K ctx50 t/s$3/M/M output
66.0
Step 1o Turbo 202506
205
StepFun128K ctx50 t/s$3/M/M output
66.0
Glm 4 Plus
206
Z.ai128K ctx50 t/s$3/M/M output
66.0
Llama 3.3 70b Instruct
207
Meta128K ctx50 t/s$0/M/M output
66.0
Gemma 3n E4b It
208
Google128K ctx50 t/s$5/M/M output
66.0
Qwen Max 0919
209
Alibaba128K ctx50 t/s$2/M/M output
66.0
GPT 4o Mini 2024 07 18
210
OpenAI128K ctx50 t/s$10/M/M output
66.0
Nvidia Nemotron 3 Nano 30b A3b Bf16
211
NVIDIA128K ctx50 t/s$3/M/M output
66.0
Qwen2.5 Plus 1127
212
Alibaba128K ctx50 t/s$2/M/M output
66.0
GPT 4 0125 Preview
213
OpenAI128K ctx50 t/s$10/M/M output
66.0
GPT 4 1106 Preview
214
OpenAI128K ctx50 t/s$10/M/M output
66.0
Hunyuan Standard 2025 02 10
215
Tencent128K ctx50 t/s$3/M/M output
66.0
Gemini 3.6 Flash
216
Google1.0M ctx233 t/s$7.5/M/M output
65.9
Gemini 3.8 Flash (Medium Reasoning)
217
Google1M ctx315 t/s$3.75/M/M output
65.2
Gemini 1.5 Flash 002
218
Google128K ctx50 t/s$5/M/M output
65.0
Grok 2 Mini 2024 08 13
219
xAI128K ctx50 t/s$15/M/M output
65.0
Deepseek V2.5
220
DeepSeek128K ctx50 t/s$1.1/M/M output
65.0
Granite 4.1 8b
221
IBM128K ctx50 t/s$3/M/M output
65.0
Mercury
222
Inception128K ctx50 t/s$3/M/M output
65.0
Olmo 3 32b Think
223
AI2128K ctx50 t/s$3/M/M output
65.0
Mistral Large 2411
224
Mistral128K ctx50 t/s$6/M/M output
65.0
Magistral Medium 2506
225
Mistral128K ctx50 t/s$6/M/M output
65.0
Gemma 3 4b It
226
Google128K ctx50 t/s$5/M/M output
65.0
Mistral Small 3.1 24b Instruct 2503
227
Mistral128K ctx50 t/s$6/M/M output
65.0
Qwen2.5 72b Instruct
228
Alibaba128K ctx50 t/s$2/M/M output
65.0
Llama 3.1 Nemotron 70b Instruct
229
Meta128K ctx50 t/s$0/M/M output
65.0
Hunyuan Large Vision
230
Tencent128K ctx50 t/s$3/M/M output
65.0
Llama 3.1 70b Instruct
231
Meta128K ctx50 t/s$0/M/M output
65.0
Amazon Nova Pro V1.0
232
Amazon128K ctx50 t/s$3/M/M output
65.0
DeepSeek V4 Flash Vision
233
DeepSeek1.0M ctx120 t/s$1.32/M/M output
65.0
G9v3-39A5B
234
AI9Stars130K ctx60 t/s$2/M/M output
65.0
Terbuka
G9v3-3B
235
AI9Stars130K ctx60 t/s$2/M/M output
65.0
Terbuka
GLM-5.3
236
Zhipu AI1.0M ctx90 t/s$4.4/M/M output
65.0
Grok 4.6 (low)
237
xAI500K ctx59 t/s$6/M/M output
65.0
Grok 4.6 (medium)
238
xAI500K ctx59 t/s$6/M/M output
65.0
Grok 4.6 (xhigh)
239
xAI500K ctx62 t/s$6/M/M output
65.0
HyperNova 60B
240
Multiverse130K ctx367 t/s$0.14/M/M output
65.0
Terbuka
KAT-Coder-Pro V2
241
Kwai260K ctx103 t/s$1.2/M/M output
65.0
LFM2.5-2.6B
242
Liquid AI130K ctx60 t/s$2/M/M output
65.0
Terbuka
LFM2.5-8B-A1B
243
Liquid AI33K ctx338 t/s$2/M/M output
65.0
Terbuka
LFM2.5-VL-1.6B
244
Liquid AI32K ctx395 t/s$2/M/M output
65.0
Terbuka
LongCat 2.0
245
LongCat1.0M ctx42 t/s$2.95/M/M output
65.0
Terbuka
Magistral Small 1.2
246
Mistral130K ctx60 t/s$1.5/M/M output
65.0
Terbuka
Qwen3.8 27B (xhigh)
247
Alibaba260K ctx53 t/s$3/M/M output
65.0
Terbuka
Qwen3.8 27B (low)
248
Alibaba260K ctx64 t/s$3/M/M output
65.0
Terbuka
Qwen3.8 27B (medium)
249
Alibaba260K ctx62 t/s$3/M/M output
65.0
Terbuka
Qwen3.8 27B (Non-reasoning)
250
Alibaba260K ctx62 t/s$3/M/M output
65.0
Terbuka
GLM-5.3 Flash
251
Z.ai262K ctx182 t/s$0.3/M/M output
64.2
Terbuka
Gemma 2 27b It
252
Google128K ctx50 t/s$5/M/M output
64.0
Ibm Granite H Small
253
Unknown128K ctx50 t/s$3/M/M output
64.0
GPT 4 0314
254
OpenAI128K ctx50 t/s$10/M/M output
64.0
Gemini 1.5 Flash 001
255
Google128K ctx50 t/s$5/M/M output
64.0
Llama 3.1 Nemotron 51b Instruct
256
Meta128K ctx50 t/s$0/M/M output
64.0
Llama 3.1 Tulu 3 70b
257
Meta128K ctx50 t/s$0/M/M output
64.0
Olmo 3.1 32b Think
258
AI2128K ctx50 t/s$3/M/M output
64.0
Claude 3 Sonnet 20240229
259
Anthropic128K ctx50 t/s$15/M/M output
64.0
Nemotron 4 340b Instruct
260
NVIDIA128K ctx50 t/s$3/M/M output
64.0
Llama 3 70b Instruct
261
Meta128K ctx50 t/s$0/M/M output
64.0
Command R Plus 08 2024
262
Cohere128K ctx50 t/s$3/M/M output
64.0
GPT 4 0613
263
OpenAI128K ctx50 t/s$10/M/M output
64.0
Mistral Small 24b Instruct 2501
264
Mistral128K ctx50 t/s$6/M/M output
64.0
Glm 4 0520
265
Z.ai128K ctx50 t/s$3/M/M output
64.0
Qwen2.5 Coder 32b Instruct
266
Alibaba128K ctx50 t/s$2/M/M output
64.0
Muse Spark 1.3
267
Muse256K ctx75 t/s$10/M/M output
63.5
C4ai Aya Expanse 32b
268
Cohere128K ctx50 t/s$3/M/M output
63.0
Gemma 2 9b It
269
Google128K ctx50 t/s$5/M/M output
63.0
Deepseek Coder V2
270
DeepSeek128K ctx50 t/s$1.1/M/M output
63.0
Qwen2 72b Instruct
271
Alibaba128K ctx50 t/s$2/M/M output
63.0
Command R Plus
272
Cohere128K ctx50 t/s$3/M/M output
63.0
Claude 3 Haiku 20240307
273
Anthropic128K ctx50 t/s$15/M/M output
63.0
Amazon Nova Lite V1.0
274
Amazon128K ctx50 t/s$3/M/M output
63.0
Gemini 1.5 Flash 8b 001
275
Google128K ctx50 t/s$5/M/M output
63.0
Olmo 2 0325 32b Instruct
276
AI2128K ctx50 t/s$3/M/M output
63.0
Command R 08 2024
277
Cohere128K ctx50 t/s$3/M/M output
63.0
Step-5
278
StepFun512K ctx110 t/s$6/M/M output
63.0
Claude Opus 5 Xhigh
279
Anthropic131K ctx80 t/s$15/M/M output
62.5
Mistral Large 2402
280
Mistral128K ctx50 t/s$6/M/M output
62.0
Amazon Nova Micro V1.0
281
Amazon128K ctx50 t/s$3/M/M output
62.0
Ministral 8b 2410
282
Mistral128K ctx50 t/s$6/M/M output
62.0
Gemini Pro Dev API
283
Google128K ctx50 t/s$5/M/M output
62.0
Qwen1.5 110b Chat
284
Alibaba128K ctx50 t/s$2/M/M output
62.0
Hunyuan Standard 256k
285
Tencent128K ctx50 t/s$3/M/M output
62.0
Qwen1.5 72b Chat
286
Alibaba128K ctx50 t/s$2/M/M output
62.0
Gemini 3.8 Flash (Low Reasoning)
287
Google1M ctx340 t/s$3.75/M/M output
62.0
Claude Opus 5 High
288
Anthropic131K ctx80 t/s$15/M/M output
61.5
Grok 4.5
289
xAI500K ctx59 t/s$6/M/M output
61.3
Claude Opus 4.6
290
Anthropic1M ctx50 t/s$15/M/M output
61.2
lawas
Mixtral 8x22b Instruct V0.1
291
Mistral128K ctx50 t/s$6/M/M output
61.0
Command R
292
Cohere128K ctx50 t/s$3/M/M output
61.0
GPT 3.5 Turbo 0125
293
OpenAI128K ctx50 t/s$10/M/M output
61.0
Llama 3 8b Instruct
294
Meta128K ctx50 t/s$0/M/M output
61.0
C4ai Aya Expanse 8b
295
Cohere128K ctx50 t/s$3/M/M output
61.0
Gemini Pro
296
Google128K ctx50 t/s$5/M/M output
61.0
Llama 3.1 Tulu 3 8b
297
Meta128K ctx50 t/s$0/M/M output
61.0
Llama 3.1 8b Instruct
298
Meta128K ctx50 t/s$0/M/M output
61.0
Grok 4
299
xAI131K ctx80 t/s$15/M/M output
60.9
Grok 4 6
300
xAI131K ctx80 t/s$15/M/M output
60.9
Gemini 3.1 Pro
301
Google1.0M ctx136 t/s$12/M/M output
60.6
Granite 3.1 8b Instruct
302
IBM128K ctx50 t/s$3/M/M output
60.0
Qwen1.5 32b Chat
303
Alibaba128K ctx50 t/s$2/M/M output
60.0
GPT 3.5 Turbo 1106
304
OpenAI128K ctx50 t/s$10/M/M output
60.0
Gemma 2 2b It
305
Google128K ctx50 t/s$5/M/M output
60.0
Phi 3 Medium 4k Instruct
306
Microsoft128K ctx50 t/s$3/M/M output
60.0
Mixtral 8x7b Instruct V0.1
307
Mistral128K ctx50 t/s$6/M/M output
60.0
Qwen1.5 14b Chat
308
Alibaba128K ctx50 t/s$2/M/M output
60.0
GLM-5.3 (low)
309
Zhipu AI1.0M ctx100 t/s$4.4/M/M output
60.0
GLM-5.2
310
Z.ai262K ctx164 t/s$4.29/M/M output
59.1
Terbuka
Deepseek LLM 67b Chat
311
DeepSeek128K ctx50 t/s$1.1/M/M output
59.0
Wizardlm 70b
312
Microsoft128K ctx50 t/s$3/M/M output
59.0
Granite 3.0 8b Instruct
313
IBM128K ctx50 t/s$3/M/M output
59.0
Gemma 1.1 7b It
314
Google128K ctx50 t/s$5/M/M output
59.0
Granite 3.1 2b Instruct
315
IBM128K ctx50 t/s$3/M/M output
59.0
Phi 3 Small 8k Instruct
316
Microsoft128K ctx50 t/s$3/M/M output
59.0
Llama 2 70b Chat
317
Meta128K ctx50 t/s$0/M/M output
59.0
Claude Opus 5 Medium
318
Anthropic131K ctx80 t/s$15/M/M output
58.6
Granite 4.2 30B Instruct
319
IBM128K ctx78 t/s$1.2/M/M output
58.6
Terbuka
Llama 3.2 3b Instruct
320
Meta128K ctx50 t/s$0/M/M output
58.0
Granite 3.0 2b Instruct
321
IBM128K ctx50 t/s$3/M/M output
58.0
Qwq 32b Preview
322
Alibaba128K ctx50 t/s$2/M/M output
58.0
Llama2 70b Steerlm Chat
323
Meta128K ctx50 t/s$0/M/M output
58.0
Qwen3 8 2 4t A95b
324
Alibaba131K ctx85 t/s$2/M/M output
57.7
Terbuka
Gpt 5 6 Sol High
325
OpenAI131K ctx90 t/s$10/M/M output
57.3
Wizardlm 13b
326
Microsoft128K ctx50 t/s$3/M/M output
57.0
Mistral 7b Instruct V0.2
327
Mistral128K ctx50 t/s$6/M/M output
57.0
Qwen1.5 7b Chat
328
Alibaba128K ctx50 t/s$2/M/M output
57.0
Phi 3 Mini 4k Instruct June 2024
329
Microsoft128K ctx50 t/s$3/M/M output
57.0
Llama 2 13b Chat
330
Meta128K ctx50 t/s$0/M/M output
57.0
Qwen 14b Chat
331
Alibaba128K ctx50 t/s$2/M/M output
57.0
Palm 2
332
Google128K ctx50 t/s$5/M/M output
57.0
Gemma 7b It
333
Google128K ctx50 t/s$5/M/M output
57.0
Codellama 34b Instruct
334
Unknown128K ctx50 t/s$3/M/M output
57.0
Muse Spark 1 2
335
Meta131K ctx80 t/s$0/M/M output
56.8
Gemini 3 7 Flash
336
Google131K ctx120 t/s$5/M/M output
56.0
Phi 3 Mini 128k Instruct
337
Microsoft128K ctx50 t/s$3/M/M output
56.0
Phi 3 Mini 4k Instruct
338
Microsoft128K ctx50 t/s$3/M/M output
56.0
Codellama 70b Instruct
339
Unknown128K ctx50 t/s$3/M/M output
56.0
Gemma 1.1 2b It
340
Google128K ctx50 t/s$5/M/M output
56.0
Llama 3.2 1b Instruct
341
Meta128K ctx50 t/s$0/M/M output
56.0
Gpt 5 6 Sol Medium
342
OpenAI131K ctx90 t/s$10/M/M output
55.6
Llama 2 7b Chat
343
Meta128K ctx50 t/s$0/M/M output
55.0
Gemma 2b It
344
Google128K ctx50 t/s$5/M/M output
55.0
Qwen1.5 4b Chat
345
Alibaba128K ctx50 t/s$2/M/M output
55.0
Mercury 2.5
346
Inception128K ctx105 t/s$3/M/M output
55.0
Grok 4 Heavy
347
xAI256k ctx50 t/s$15/M/M output
54.5
pratinjau
DeepSeek V4.1 Flash
348
DeepSeek1.0M ctx214 t/s$1.2/M/M output
54.5
Terbuka
GPT-5.5
349
OpenAI1.1M ctx60 t/s$10/M/M output
54.0
Olmo 7b Instruct
350
AI2128K ctx50 t/s$3/M/M output
54.0
Gemini 3 7 Flash Medium
351
Google131K ctx120 t/s$5/M/M output
53.4
Glm 5
352
Z.ai131K ctx60 t/s$3/M/M output
52.6
Terbuka
Claude Opus 5 Low
353
Anthropic131K ctx80 t/s$15/M/M output
52.5
MiMo V2.6 Pro
354
Xiaomi1.0M ctx72 t/s$0.95/M/M output
52.5
Terbuka
GPT-5.3 Codex
355
OpenAI400K ctx118 t/s$14/M/M output
52.4
Claude Opus 4.5
356
Anthropic200K ctx50 t/s$15/M/M output
52.1
lawas
Claude Opus 4.7
357
Anthropic1M ctx80 t/s$15/M/M output
52.0
Phi-4 Multimodal
358
Microsoft128K ctx85 t/s$0.32/M/M output
52.0
Gemini 3 Pro
359
Google1M ctx120 t/s$5/M/M output
51.9
Gpt 5 5 Medium
360
OpenAI131K ctx90 t/s$10/M/M output
51.4
GPT-5.4
361
OpenAI1.1M ctx60 t/s$10/M/M output
51.0
lawas
Qwen3.7 Max
362
Alibaba1.0M ctx203 t/s$7.5/M/M output
51.0
Gemini 3 7 Flash Low
363
Google131K ctx120 t/s$5/M/M output
50.9
Gpt 5 6 Sol Low
364
OpenAI131K ctx90 t/s$10/M/M output
50.7
Gpt 5 6 Terra High
365
OpenAI131K ctx90 t/s$10/M/M output
50.1
Gemini 3.5 Flash
366
Google1.0M ctx267 t/s$9/M/M output
50.0
Sarvam 105B
367
Sarvam AI128K ctx60 t/s$3/M/M output
50.0
Terbuka
Sarvam 30B
368
Sarvam AI128K ctx60 t/s$3/M/M output
50.0
Terbuka
DeepSeek V4.1 Flash (Non-reasoning)
369
DeepSeek1.0M ctx240 t/s$1.2/M/M output
50.0
Terbuka
GPT-5.2
370
OpenAI128K ctx90 t/s$10/M/M output
49.2
lawas
Granite 4.2 8B Instruct
371
IBM128K ctx115 t/s$0.45/M/M output
49.2
Terbuka
GPT-5.6 Luna
372
OpenAI1.1M ctx175 t/s$1.2/M/M output
49.1
ERNIE 5.1
373
Baidu131K ctx60 t/s$3/M/M output
49.1
Kimi K2.6
374
Moonshot AI262.1K ctx40 t/s$4/M/M output
49.0
Terbuka
Sarvam M Reasoning
375
Sarvam AI128K ctx40 t/s$3/M/M output
49.0
Terbuka
Kimi K3 Low
376
Moonshot AI131K ctx60 t/s$4/M/M output
48.3
Agnes 3.0 Flash
377
Agnes1.0M ctx235 t/s$0.15/M/M output
48.2
Grok 4.3
378
xAI500K ctx129 t/s$2.5/M/M output
48.0
MiMo V2.5 Pro
379
Xiaomi1.0M ctx65 t/s$0.87/M/M output
48.0
Terbuka
Muse Spark
380
Meta1.0M ctx80 t/s$0/M/M output
47.0
Claude Sonnet 4 6 Adaptive
381
Anthropic131K ctx80 t/s$15/M/M output
47.0
Gpt 5 6 Luna High
382
OpenAI131K ctx90 t/s$10/M/M output
47.0
Gpt 5 6 Terra Medium
383
OpenAI131K ctx90 t/s$10/M/M output
46.8
DeepSeek V4 Pro
384
DeepSeek1.0M ctx66 t/s$0.87/M/M output
46.0
Terbuka
GLM-5.1
385
Z.ai262K ctx74 t/s$4.4/M/M output
46.0
Terbuka
DeepSeek V4 Flash 0420 (Non-reasoning)
386
DeepSeek1.0M ctx210 t/s$1.1/M/M output
46.0
Terbuka
Claude Sonnet 5
387
Anthropic1.0M ctx96 t/s$10/M/M output
45.4
Deepseek V4 Pro 0424
388
DeepSeek131K ctx60 t/s$1.1/M/M output
45.3
Terbuka
MiniMax-M2.7
389
MiniMax1.0M ctx40 t/s$2/M/M output
45.0
Claude Opus 4 6 Adaptive
390
Anthropic131K ctx80 t/s$15/M/M output
44.9
Gpt 5 5 Low
391
OpenAI131K ctx90 t/s$10/M/M output
44.5
Nex N2 Pro
392
Nex AGI262K ctx138 t/s$2.5/M/M output
44.4
Gpt 5 4 Mini
393
OpenAI131K ctx90 t/s$10/M/M output
44.0
Claude Opus 4 7 Non Reasoning
394
Anthropic131K ctx50 t/s$15/M/M output
43.9
Deepseek V4 Pro 0424 High
395
DeepSeek131K ctx60 t/s$1.1/M/M output
43.7
Terbuka
Claude Sonnet 5 Non Reasoning
396
Anthropic131K ctx50 t/s$15/M/M output
42.6
Agnes 2.5 Pro Beta
397
Agnes131K ctx65 t/s$3/M/M output
42.5
Claude Sonnet 4.5
398
Anthropic200K ctx80 t/s$15/M/M output
42.4
lawas
Gemini 3 Flash
399
Google1M ctx120 t/s$5/M/M output
42.4
GPT-5.1
400
OpenAI400K ctx60 t/s$10/M/M output
42.3
lawas
Qwen3.7 Plus
401
Alibaba1.0M ctx54 t/s$1.6/M/M output
42.2
Deepseek V4 Flash 0420
402
DeepSeek131K ctx60 t/s$1.1/M/M output
42.1
Terbuka
DeepSeek V4 Flash
403
DeepSeek1.0M ctx113 t/s$0.28/M/M output
42.0
Terbuka
Granite 4.2 3B Instruct
404
IBM128K ctx148 t/s$0.2/M/M output
42.0
Terbuka
Ling 3.0 Flash Fin
405
Ling131K ctx65 t/s$3/M/M output
42.0
Claude Opus 4 5 Thinking
406
Anthropic131K ctx50 t/s$15/M/M output
41.9
Gpt 5 6 Sol Non Reasoning
407
OpenAI131K ctx60 t/s$10/M/M output
41.9
Kimi K2.7 Code
408
Moonshot AI262K ctx39 t/s$4/M/M output
41.8
Terbuka
Inkling Small
409
Thinking Machines524K ctx130 t/s$1.2/M/M output
41.7
Solar Pro4
410
Upstage131K ctx40 t/s$3/M/M output
41.6
Gpt 5 6 Terra Low
411
OpenAI131K ctx90 t/s$10/M/M output
41.3
Gpt 5 2 Codex
412
OpenAI131K ctx90 t/s$10/M/M output
41.2
Qwen3 6 Max
413
Alibaba131K ctx85 t/s$2/M/M output
41.1
Terbuka
Grok Build 0 1 06 16
414
xAI131K ctx80 t/s$15/M/M output
40.7
Ling 3.0 Flash VL
415
Ling131K ctx60 t/s$3/M/M output
40.5
Gpt 5 4 Low
416
OpenAI131K ctx90 t/s$10/M/M output
40.2
Seed 2.0 Pro
417
ByteDance131K ctx40 t/s$3/M/M output
40.0
Agnes 2 5 Pro Alpha
418
Agnes131K ctx60 t/s$3/M/M output
39.7
Gpt 5 4 Nano
419
OpenAI131K ctx90 t/s$10/M/M output
39.7
MiniMax M3
420
MiniMax524K ctx93 t/s$1.2/M/M output
39.6
Deepseek V4 Flash 0420 High
421
DeepSeek131K ctx60 t/s$1.1/M/M output
39.0
Terbuka
Hunyuan Hy3
422
Tencent262K ctx69 t/s$0.56/M/M output
38.9
Gpt 5 2 Medium
423
OpenAI131K ctx90 t/s$10/M/M output
38.9
Gpt 5 6 Luna Medium
424
OpenAI131K ctx90 t/s$10/M/M output
38.9
Gemini 3.5 Flash-Lite
425
Google1.0M ctx389 t/s$2.5/M/M output
38.8
Gemini 3 Flash Reasoning
426
Google131K ctx80 t/s$5/M/M output
38.7
Nvidia Nemotron 3 Ultra 550b A55b
427
NVIDIA131K ctx150 t/s$1/M/M output
38.3
Claude Sonnet 4.6
428
Anthropic1M ctx50 t/s$15/M/M output
38.1
Deepseek V3 2 Reasoning
429
DeepSeek131K ctx40 t/s$1.1/M/M output
38.0
Terbuka
Grok 4 20
430
xAI131K ctx80 t/s$15/M/M output
38.0
Mimo V2 5 0424
431
Xiaomi131K ctx60 t/s$3/M/M output
38.0
Terbuka
Ling 3 0 Flash
432
Ling131K ctx60 t/s$3/M/M output
37.8
Qwen3 6 27b
433
Alibaba131K ctx85 t/s$2/M/M output
37.7
Terbuka
Claude 4 5 Sonnet Thinking
434
Anthropic131K ctx50 t/s$15/M/M output
37.4
Grok 4 20 0309
435
xAI131K ctx80 t/s$15/M/M output
37.4
Gpt 5 Codex
436
OpenAI131K ctx90 t/s$10/M/M output
37.0
Grok 4 3 Medium
437
xAI131K ctx80 t/s$15/M/M output
36.9
Glm 5 1 Non Reasoning
438
Z.ai131K ctx40 t/s$3/M/M output
36.3
Terbuka
Grok 4 3 Low
439
xAI131K ctx80 t/s$15/M/M output
36.3
Kimi K2 5
440
Moonshot AI131K ctx60 t/s$4/M/M output
36.0
Gemini 3 5 Flash Minimal
441
Google131K ctx120 t/s$5/M/M output
35.8
Gpt 5 5 Non Reasoning
442
OpenAI131K ctx60 t/s$10/M/M output
35.8
Gpt 5 1 Codex
443
OpenAI131K ctx90 t/s$10/M/M output
35.6
Kimi K2 6 Non Reasoning
444
Moonshot AI131K ctx40 t/s$4/M/M output
35.4
Claude Sonnet 4 6 Non Reasoning Low Effort
445
Anthropic131K ctx50 t/s$15/M/M output
35.1
Muse Glimmer
446
Meta131K ctx80 t/s$0/M/M output
35.1
Gemma 4 31B
447
Google262.1K ctx35 t/s$0.3/M/M output
35.0
Terbuka
Mistral Medium 3.5
448
Mistral131K ctx60 t/s$6/M/M output
35.0
Glm 5 2 Non Reasoning
449
Z.ai131K ctx40 t/s$3/M/M output
34.8
Terbuka
Gpt 5 6 Terra Non Reasoning
450
OpenAI131K ctx60 t/s$10/M/M output
34.6
Gpt 5 Medium
451
OpenAI131K ctx90 t/s$10/M/M output
34.6
Claude 4 1 Opus Thinking
452
Anthropic131K ctx50 t/s$15/M/M output
34.5
Hy3 Preview
453
Tencent131K ctx60 t/s$3/M/M output
34.4
Gpt 5 5 Instant 05 26
454
OpenAI131K ctx90 t/s$10/M/M output
34.3
Gemini 3 Pro Low
455
Google131K ctx120 t/s$5/M/M output
33.9
Gpt 5 6 Luna Low
456
OpenAI131K ctx90 t/s$10/M/M output
33.9
Kimi K2 Thinking
457
Moonshot AI131K ctx40 t/s$4/M/M output
33.5
O3 Pro
458
OpenAI131K ctx60 t/s$10/M/M output
33.3
Glm 5 Non Reasoning
459
Z.ai131K ctx40 t/s$3/M/M output
33.2
Terbuka
Claude 4 5 Haiku Reasoning
460
Anthropic131K ctx50 t/s$15/M/M output
33.0
Qwen3 5 397b A17b Non Reasoning
461
Alibaba131K ctx55 t/s$2/M/M output
32.7
Terbuka
Qwen3.6 Plus
462
Alibaba1.0M ctx55 t/s$3/M/M output
32.4
Minimax M2 1
463
MiniMax131K ctx60 t/s$2/M/M output
32.1
Terbuka
Qwen3 6 35b A3b
464
Alibaba131K ctx85 t/s$2/M/M output
32.1
Terbuka
o3
465
OpenAI200K ctx90 t/s$10/M/M output
32.0
lawas
Nova 2 0 Pro Reasoning Medium
466
Amazon131K ctx40 t/s$3.2/M/M output
32.0
Nvidia Nemotron 3 Super 120b A12b
467
NVIDIA131K ctx150 t/s$1/M/M output
32.0
Deepseek V4 Pro 0424 Non Reasoning
468
DeepSeek131K ctx40 t/s$1.1/M/M output
31.9
Terbuka
Gpt 5 Low
469
OpenAI131K ctx90 t/s$10/M/M output
31.9
Mimo V2 Flash Reasoning
470
Xiaomi131K ctx40 t/s$3/M/M output
31.9
Terbuka
Inkling
471
Thinking Machines524K ctx81 t/s$4.05/M/M output
31.7
Claude 4 Opus Thinking
472
Anthropic131K ctx50 t/s$15/M/M output
31.7
Gpt 5 Mini Medium
473
OpenAI131K ctx90 t/s$10/M/M output
31.6
Gpt 5 1 Codex Mini
474
OpenAI131K ctx90 t/s$10/M/M output
31.3
Qwen3 5 Omni Plus
475
Alibaba131K ctx85 t/s$2/M/M output
31.3
Terbuka
Qwen3 6 27b Non Reasoning
476
Alibaba131K ctx55 t/s$2/M/M output
31.3
Terbuka
Ring 2 6 1t
477
WeRide131K ctx60 t/s$3/M/M output
31.3
Deepseek V3 1 Terminus Reasoning
478
DeepSeek131K ctx40 t/s$1.1/M/M output
31.1
Terbuka
Step 3 7 Flash
479
StepFun131K ctx60 t/s$3/M/M output
30.9
Gpt 5 4 Nano Medium
480
OpenAI131K ctx90 t/s$10/M/M output
30.8
Gpt 5 4 Mini Medium
481
OpenAI131K ctx90 t/s$10/M/M output
30.5
Kimi K2 5 Non Reasoning
482
Moonshot AI131K ctx40 t/s$4/M/M output
30.1
GPT-oss-120B
483
OpenAI131K ctx240 t/s$0.4/M/M output
30.0
Terbuka
Qwen3 5 27b Non Reasoning
484
Alibaba131K ctx55 t/s$2/M/M output
30.0
Terbuka
Claude 4 5 Sonnet
485
Anthropic131K ctx80 t/s$15/M/M output
29.9
Claude 4 Sonnet Thinking
486
Anthropic131K ctx50 t/s$15/M/M output
29.8
Deepseek V4 Flash Non Reasoning
487
DeepSeek131K ctx40 t/s$1.1/M/M output
29.3
Terbuka
Glm 4 6 Reasoning
488
Z.ai131K ctx40 t/s$3/M/M output
29.3
Terbuka
Gpt 5 5 Instant 06 26
489
OpenAI131K ctx90 t/s$10/M/M output
29.2
Minimax M2
490
MiniMax131K ctx60 t/s$2/M/M output
28.9
Terbuka
Claude 4 1 Opus
491
Anthropic131K ctx80 t/s$15/M/M output
28.8
Mimo V2 5 Pro Non Reasoning
492
Xiaomi131K ctx40 t/s$3/M/M output
28.4
Terbuka
Gpt 5 4 Non Reasoning
493
OpenAI131K ctx60 t/s$10/M/M output
28.3
Qwen3 5 122b A10b Non Reasoning
494
Alibaba131K ctx55 t/s$2/M/M output
28.2
Terbuka
Grok 4 Fast Reasoning
495
xAI131K ctx50 t/s$15/M/M output
27.9
Glm 4 7 Non Reasoning
496
Z.ai131K ctx40 t/s$3/M/M output
27.1
Terbuka
Gpt 5 6 Luna Non Reasoning
497
OpenAI131K ctx60 t/s$10/M/M output
26.8
Hy3 Non Reasoning
498
Tencent131K ctx40 t/s$3/M/M output
26.6
Ling 2 6 1t
499
Ling131K ctx60 t/s$3/M/M output
26.6
Gpt 5 2 Non Reasoning
500
OpenAI131K ctx60 t/s$10/M/M output
26.5
Gemma 4 26b A4b
501
Google131K ctx120 t/s$5/M/M output
26.1
Terbuka
Claude 4 Opus
502
Anthropic131K ctx80 t/s$15/M/M output
26.0
Claude 4 Sonnet
503
Anthropic131K ctx80 t/s$15/M/M output
26.0
Step 3 5 Flash 0202
504
StepFun131K ctx60 t/s$3/M/M output
26.0
Deepseek V3 2 Reasoning 0925
505
DeepSeek131K ctx40 t/s$1.1/M/M output
25.9
Terbuka
Gpt 5 Mini
506
OpenAI131K ctx90 t/s$10/M/M output
25.8
Qwen3 Max Thinking Preview
507
Alibaba131K ctx55 t/s$2/M/M output
25.5
Terbuka
Grok 4 3 Non Reasoning
508
xAI131K ctx50 t/s$15/M/M output
25.0
Qwen3 6 35b A3b Non Reasoning
509
Alibaba131K ctx55 t/s$2/M/M output
24.6
Terbuka
Ling 3 0 Tiny
510
Ling131K ctx60 t/s$3/M/M output
24.5
Qwen3 5 35b A3b Non Reasoning
511
Alibaba131K ctx55 t/s$2/M/M output
24.3
Terbuka
Claude 4.5 Haiku
512
Anthropic200K ctx80 t/s$15/M/M output
24.1
Kimi K2 0905
513
Moonshot AI131K ctx60 t/s$4/M/M output
24.0
Qwen3.5 397B-A17B
514
Alibaba262.1K ctx71 t/s$2/M/M output
23.9
Terbuka
Claude 3 7 Sonnet
515
Anthropic131K ctx80 t/s$15/M/M output
23.9
O1
516
OpenAI131K ctx60 t/s$10/M/M output
23.9
Nemotron 3 5 Lightning
517
NVIDIA131K ctx150 t/s$1/M/M output
23.6
GPT-5
518
OpenAI400K ctx60 t/s$10/M/M output
23.0
lawas
Solar Pro 3
519
Upstage131K ctx40 t/s$3/M/M output
23.0
Grok 3 Mini Reasoning
520
xAI131K ctx50 t/s$15/M/M output
22.9
Grok 4 20 0309 Non Reasoning
521
xAI131K ctx50 t/s$15/M/M output
22.9
Command A Plus
522
Cohere131K ctx60 t/s$10/M/M output
22.8
Gemini 2 5 Pro 05 06
523
Google131K ctx120 t/s$5/M/M output
22.7
Gemma 4 31b Non Reasoning
524
Google131K ctx80 t/s$5/M/M output
22.3
Terbuka
Gemma 4 12b
525
Google131K ctx120 t/s$5/M/M output
22.2
Terbuka
Grok 4 20 Non Reasoning
526
xAI131K ctx50 t/s$15/M/M output
22.2
Qwen3.5 122B-A10B
527
Alibaba262.1K ctx126 t/s$2/M/M output
22.0
Terbuka
GPT-oss-20B
528
OpenAI131K ctx90 t/s$0.2/M/M output
22.0
Terbuka
K2 Think V2
529
K2131K ctx40 t/s$3/M/M output
22.0
Mercury 2
530
Inception131K ctx60 t/s$3/M/M output
21.9
Qwen3 5 9b
531
Alibaba131K ctx85 t/s$2/M/M output
21.8
Terbuka
Claude Opus 4.1
532
Anthropic200K ctx80 t/s$15/M/M output
21.7
lawas
Deepseek V3 2 0925
533
DeepSeek131K ctx60 t/s$1.1/M/M output
21.7
Terbuka
Apriel V1 5 15b Thinker
534
ServiceNow131K ctx60 t/s$3/M/M output
21.6
Nova 2 0 Omni Reasoning Medium
535
Amazon131K ctx40 t/s$3.2/M/M output
21.3
Qwen3 Coder Next
536
Alibaba131K ctx85 t/s$2/M/M output
21.3
Terbuka
Deepseek V3 1 Reasoning
537
DeepSeek131K ctx40 t/s$1.1/M/M output
21.0
Terbuka
Qwen3 Vl 235b A22b Reasoning
538
Alibaba131K ctx55 t/s$2/M/M output
20.9
Terbuka
Apriel V1 6 15b Thinker
539
ServiceNow131K ctx60 t/s$3/M/M output
20.8
Nova 2 0 Lite Reasoning
540
Amazon131K ctx40 t/s$3.2/M/M output
20.8
Gpt 5 1 Non Reasoning
541
OpenAI131K ctx60 t/s$10/M/M output
20.7
Qwen3 5 9b Non Reasoning
542
Alibaba131K ctx55 t/s$2/M/M output
20.6
Terbuka
Gemma 4 26b A4b Non Reasoning
543
Google131K ctx80 t/s$5/M/M output
20.4
Terbuka
Qwen3 5 4b
544
Alibaba131K ctx85 t/s$2/M/M output
20.4
Terbuka
Gemini 2 5 Flash Reasoning
545
Google131K ctx80 t/s$5/M/M output
20.3
North Mini Code
546
North131K ctx60 t/s$3/M/M output
20.2
Gpt 5 Nano
547
OpenAI131K ctx90 t/s$10/M/M output
20.1
Qwen3 235b A22b Instruct 2507 Reasoning
548
Alibaba131K ctx55 t/s$2/M/M output
19.9
Terbuka
Nova 2 0 Pro Reasoning Low
549
Amazon131K ctx40 t/s$3.2/M/M output
19.8
Kimi K2
550
Moonshot AI131K ctx60 t/s$4/M/M output
19.7
Mistral Small 4
551
Mistral131K ctx100 t/s$6/M/M output
19.7
Terbuka
Qwen3 Max
552
Alibaba262.1K ctx85 t/s$2/M/M output
19.6
Terbukalawas
Gpt 4 1
553
OpenAI131K ctx90 t/s$10/M/M output
19.6
Qwen3 Max Preview
554
Alibaba131K ctx85 t/s$2/M/M output
19.4
Terbuka
Devstral 2
555
Mistral131K ctx100 t/s$6/M/M output
19.2
Gpt 5 Nano Medium
556
OpenAI131K ctx90 t/s$10/M/M output
19.2
Nova 2 0 Lite Reasoning Medium
557
Amazon131K ctx40 t/s$3.2/M/M output
19.2
O3 Mini
558
OpenAI131K ctx60 t/s$10/M/M output
19.2
Qwen3 5 Omni Flash
559
Alibaba131K ctx85 t/s$2/M/M output
19.2
Terbuka
O1 Pro
560
OpenAI131K ctx60 t/s$10/M/M output
19.1
Nemotron 3 Ultra 550B
561
NVIDIA512K ctx142 t/s$2.75/M/M output
19.0
Terbuka
Deepseek R1 0120
562
DeepSeek131K ctx40 t/s$1.1/M/M output
18.6
Terbuka
Grok 3
563
xAI131K ctx75 t/s$15/M/M output
18.6
Seed Oss 36b Instruct
564
ByteDance131K ctx60 t/s$3/M/M output
18.5
Qwen3 235b A22b Instruct 2507
565
Alibaba131K ctx85 t/s$2/M/M output
18.4
Terbuka
Trinity Large Thinking
566
Trinity131K ctx40 t/s$3/M/M output
18.4
Qwen3 Coder 480b A35b Instruct
567
Alibaba131K ctx85 t/s$2/M/M output
18.2
Terbuka
Qwen3 Vl 32b Reasoning
568
Alibaba131K ctx55 t/s$2/M/M output
18.1
Terbuka
Nova 2 0 Lite Reasoning Low
569
Amazon131K ctx40 t/s$3.2/M/M output
18.0
Minimax M1 80k
570
MiniMax131K ctx60 t/s$2/M/M output
17.9
Terbuka
Gpt 5 4 Nano Non Reasoning
571
OpenAI131K ctx60 t/s$10/M/M output
17.8
Devstral Small 2
572
Mistral131K ctx100 t/s$6/M/M output
17.7
Gpt 5 Minimal
573
OpenAI131K ctx90 t/s$10/M/M output
17.3
O1 Preview
574
OpenAI131K ctx60 t/s$10/M/M output
17.2
Glm 4 6v Reasoning
575
Z.ai131K ctx40 t/s$3/M/M output
16.9
Terbuka
Qwen3 Next 80b A3b Reasoning
576
Alibaba131K ctx55 t/s$2/M/M output
16.9
Terbuka
Gpt 5 4 Mini Non Reasoning
577
OpenAI131K ctx60 t/s$10/M/M output
16.8
Nova 2 0 Omni Reasoning Low
578
Amazon131K ctx40 t/s$3.2/M/M output
16.7
Grok 4 Fast
579
xAI131K ctx80 t/s$15/M/M output
16.6
Qwen3 5 4b Non Reasoning
580
Alibaba131K ctx55 t/s$2/M/M output
16.1
Terbuka
Mistral Large 3
581
Mistral131K ctx100 t/s$6/M/M output
15.9
Terbuka
O3 Mini High
582
OpenAI131K ctx60 t/s$10/M/M output
15.7
Glm 4 7 Flash Non Reasoning
583
Z.ai131K ctx40 t/s$3/M/M output
15.6
Terbuka
Deepseek V3 0324
584
DeepSeek131K ctx60 t/s$1.1/M/M output
15.2
Terbuka
Gemini 2 5 Flash Lite Preview 09 2025 Reasoning
585
Google131K ctx80 t/s$5/M/M output
15.2
Nemotron 3 Nano Omni 30b A3b
586
NVIDIA131K ctx150 t/s$1/M/M output
15.0
Gpt Oss 120b Low
587
OpenAI131K ctx90 t/s$10/M/M output
14.9
Mistral Small 3 1
588
Mistral131K ctx100 t/s$6/M/M output
14.9
Terbuka
Gpt 4 1 Mini
589
OpenAI131K ctx90 t/s$10/M/M output
14.8
Mistral Medium 3 1
590
Mistral131K ctx100 t/s$6/M/M output
14.7
Terbuka
Qwen3 30b A3b 2507 Reasoning
591
Alibaba131K ctx55 t/s$2/M/M output
14.6
Terbuka
Nvidia Nemotron 3 Nano 30b A3b Reasoning
592
NVIDIA131K ctx100 t/s$1/M/M output
14.5
Nova 2.0 Pro Preview
593
Amazon1.0M ctx40 t/s$3.2/M/M output
14.4
pratinjau
Gpt Oss 20b Low
594
OpenAI131K ctx90 t/s$10/M/M output
14.4
Qwen3 Vl 235b A22b Instruct
595
Alibaba131K ctx85 t/s$2/M/M output
14.4
Terbuka
Gpt 5 Mini Minimal
596
OpenAI131K ctx90 t/s$10/M/M output
14.3
Ling 2 6 Flash
597
Ling131K ctx60 t/s$3/M/M output
14.2
Qwen3 Next 80b A3b Instruct
598
Alibaba131K ctx85 t/s$2/M/M output
13.8
Terbuka
Qwen3 Coder 30b A3b Instruct
599
Alibaba131K ctx85 t/s$2/M/M output
13.6
Terbuka
Qwen3 235b A22b Instruct Reasoning
600
Alibaba131K ctx55 t/s$2/M/M output
13.5
Terbuka
Qwen3 Vl 30b A3b Reasoning
601
Alibaba131K ctx55 t/s$2/M/M output
13.4
Terbuka
Qwq 32b
602
Alibaba131K ctx85 t/s$2/M/M output
13.4
Gemma 4 12b Non Reasoning
603
Google131K ctx80 t/s$5/M/M output
13.2
Terbuka
Gemini 2 5 Flash Lite Preview 09 2025
604
Google131K ctx120 t/s$5/M/M output
13.1
DeepSeek V3.2
605
DeepSeek163.8K ctx60 t/s$1.1/M/M output
12.9
Terbukalawas
Nova Premier
606
Amazon131K ctx60 t/s$3.2/M/M output
12.7
Mistral Medium 3
607
Mistral131K ctx100 t/s$6/M/M output
12.5
Terbuka
Celeris 1
608
Celeris131K ctx60 t/s$3/M/M output
12.4
Llama Nemotron Super 49b V1 5 Reasoning
609
Meta131K ctx50 t/s$0/M/M output
12.4
Terbuka
Mistral Small 4 Non Reasoning
610
Mistral131K ctx60 t/s$6/M/M output
12.3
Terbuka
Gemma 4 E4b
611
Google131K ctx120 t/s$5/M/M output
12.2
Terbuka
Claude 3 Opus
612
Anthropic131K ctx80 t/s$15/M/M output
11.8
Nova 2 0 Lite
613
Amazon131K ctx60 t/s$3.2/M/M output
11.8
Gemini 2 5 Flash Lite Reasoning
614
Google131K ctx80 t/s$5/M/M output
11.4
Qwen3 32b Instruct Reasoning
615
Alibaba131K ctx55 t/s$2/M/M output
11.4
Terbuka
Ministral 3 14b
616
Mistral131K ctx100 t/s$6/M/M output
11.2
Qwen3 Vl 32b Instruct
617
Alibaba131K ctx85 t/s$2/M/M output
11.0
Terbuka
Qwen3 235b A22b Instruct
618
Alibaba131K ctx85 t/s$2/M/M output
10.8
Terbuka
Mistral Small 3 2
619
Mistral131K ctx100 t/s$6/M/M output
10.7
Terbuka
Gemini 2 0 Flash Experimental
620
Google131K ctx120 t/s$5/M/M output
10.6
Qwen3 Vl 8b Reasoning
621
Alibaba131K ctx55 t/s$2/M/M output
10.5
Terbuka
Nova 2 0 Omni
622
Amazon131K ctx60 t/s$3.2/M/M output
10.4
Qwen3 14b Instruct Reasoning
623
Alibaba131K ctx55 t/s$2/M/M output
10.4
Terbuka
Llama 4 Scout
624
Meta131K ctx80 t/s$0/M/M output
10.3
Terbuka
Hermes 4 Llama 3 1 70b Reasoning
625
Meta131K ctx50 t/s$0/M/M output
9.9
Terbuka
Qwen3 Vl 30b A3b Instruct
626
Alibaba131K ctx85 t/s$2/M/M output
9.9
Terbuka
Claude 35 Sonnet
627
Anthropic131K ctx80 t/s$15/M/M output
9.8
Deepseek R1 Distill Llama 70b
628
DeepSeek131K ctx40 t/s$1.1/M/M output
9.8
Terbuka
Gpt 4 1 Nano
629
OpenAI131K ctx90 t/s$10/M/M output
9.6
Qwen3 Omni 30b A3b Reasoning
630
Alibaba131K ctx55 t/s$2/M/M output
9.5
Terbuka
Gpt 4o 2024 08 06
631
OpenAI131K ctx90 t/s$10/M/M output
9.4
Llama 3 3 Instruct 70b
632
Meta131K ctx80 t/s$0/M/M output
9.3
Terbuka
Qwen3 30b A3b Instruct Reasoning
633
Alibaba131K ctx55 t/s$2/M/M output
9.2
Terbuka
Glm 4 5v Reasoning
634
Z.ai131K ctx40 t/s$3/M/M output
9.0
Terbuka
Ministral 3 8b
635
Mistral131K ctx100 t/s$6/M/M output
9.0
Ernie 4 5 300b A47b
636
Baidu131K ctx60 t/s$3/M/M output
8.9
Llama 3 1 Nemotron Ultra 253b V1 Reasoning
637
Meta131K ctx50 t/s$0/M/M output
8.9
Terbuka
Qwen3 30b A3b 2507
638
Alibaba131K ctx85 t/s$2/M/M output
8.9
Terbuka
Hermes 4 Llama 3 1 405b Reasoning
639
Meta131K ctx50 t/s$0/M/M output
8.8
Terbuka
Nvidia Nemotron Nano 12b V2 Vl Reasoning
640
NVIDIA131K ctx100 t/s$1/M/M output
8.8
Gemma 4 E4b Non Reasoning
641
Google131K ctx80 t/s$5/M/M output
8.7
Terbuka
Nvidia Nemotron Nano 9b V2 Reasoning
642
NVIDIA131K ctx100 t/s$1/M/M output
8.7
Hermes 4 Llama 3 1 405b
643
Meta131K ctx80 t/s$0/M/M output
8.6
Terbuka
Llama Nemotron Super 49b V1 5
644
Meta131K ctx80 t/s$0/M/M output
8.5
Terbuka
Qwen3 32b Instruct
645
Alibaba131K ctx85 t/s$2/M/M output
8.5
Terbuka
Gpt 4o 2024 05 13
646
OpenAI131K ctx90 t/s$10/M/M output
8.4
Qwen3 8b Instruct Reasoning
647
Alibaba131K ctx55 t/s$2/M/M output
8.3
Terbuka
Qwen3 Vl 8b Instruct
648
Alibaba131K ctx85 t/s$2/M/M output
8.2
Terbuka
Claude 35 Sonnet June 24
649
Anthropic131K ctx80 t/s$15/M/M output
8.1
Gpt 5 Nano Minimal
650
OpenAI131K ctx90 t/s$10/M/M output
7.8
Gpt 4 Turbo
651
OpenAI131K ctx90 t/s$10/M/M output
7.7
Command A
652
Cohere131K ctx60 t/s$10/M/M output
7.5
Nova Pro
653
Amazon131K ctx60 t/s$3.2/M/M output
7.5
Gemma 3 27b
654
Google131K ctx120 t/s$5/M/M output
7.4
Terbuka
Llama 3 1 Instruct 8b
655
Meta131K ctx80 t/s$0/M/M output
7.4
Terbuka
Llama 3 1 Nemotron Instruct 70b
656
Meta131K ctx80 t/s$0/M/M output
7.4
Terbuka
Nvidia Nemotron 3 Nano 30b A3b
657
NVIDIA131K ctx150 t/s$1/M/M output
7.2
Nvidia Nemotron Nano 9b V2
658
NVIDIA131K ctx150 t/s$1/M/M output
7.2
Ministral 3 3b
659
Mistral131K ctx100 t/s$6/M/M output
7.1
Mistral Large 2407
660
Mistral131K ctx100 t/s$6/M/M output
7.0
Terbuka
Gpt 4
661
OpenAI131K ctx90 t/s$10/M/M output
6.8
Qwen3 14b Instruct
662
Alibaba131K ctx85 t/s$2/M/M output
6.8
Terbuka
Gemini 2 5 Flash Lite
663
Google131K ctx120 t/s$5/M/M output
6.7
Hermes 4 Llama 3 1 70b
664
Meta131K ctx80 t/s$0/M/M output
6.7
Terbuka
Mistral Small 3
665
Mistral131K ctx100 t/s$6/M/M output
6.7
Terbuka
Nova Lite
666
Amazon131K ctx60 t/s$3.2/M/M output
6.7
Qwen3 30b A3b Instruct
667
Alibaba131K ctx85 t/s$2/M/M output
6.6
Terbuka
Llama 3 1 Instruct 70b
668
Meta131K ctx80 t/s$0/M/M output
6.5
Terbuka
Qwen Turbo
669
Alibaba131K ctx85 t/s$2/M/M output
6.0
Terbuka
Reka Flash
670
Reka131K ctx60 t/s$3/M/M output
6.0
Solar Mini
671
Upstage131K ctx60 t/s$3/M/M output
6.0
Phi 4 Mini
672
Microsoft131K ctx60 t/s$0.6/M/M output
5.7
Terbuka
Gemma 3 12b
673
Google131K ctx120 t/s$5/M/M output
5.5
Terbuka
DeepSeek R1
674
DeepSeek163.8K ctx60 t/s$1.1/M/M output
5.4
Terbukalawas
Granite 4 0 H Small
675
IBM131K ctx60 t/s$3/M/M output
4.9
Terbuka
Hermes 3 Llama 3 1 70b
676
Meta131K ctx80 t/s$0/M/M output
4.8
Terbuka
Jamba 1 5 Large
677
AI21 Labs131K ctx60 t/s$3/M/M output
4.8
Qwen3 8b Instruct
678
Alibaba131K ctx85 t/s$2/M/M output
4.8
Terbuka
Qwen3 Omni 30b A3b Instruct
679
Alibaba131K ctx85 t/s$2/M/M output
4.8
Terbuka
Phi-4
680
Microsoft128K ctx70 t/s$0.6/M/M output
4.6
Nova Micro
681
Amazon131K ctx60 t/s$3.2/M/M output
4.4
Mistral Small
682
Mistral131K ctx100 t/s$6/M/M output
4.3
Terbuka
Nvidia Nemotron Nano 12b V2 Vl
683
NVIDIA131K ctx150 t/s$1/M/M output
4.2
Mistral Large
684
Mistral131K ctx100 t/s$6/M/M output
4.1
Terbuka
Llama 2 Chat 7b
685
Meta131K ctx80 t/s$0/M/M output
3.9
Terbuka
Reka Flash 3
686
Reka131K ctx60 t/s$3/M/M output
3.7
Claude 3 Haiku
687
Anthropic131K ctx80 t/s$15/M/M output
3.5
Gpt 35 Turbo
688
OpenAI131K ctx90 t/s$10/M/M output
3.2
Mistral Medium
689
Mistral131K ctx100 t/s$6/M/M output
3.2
Terbuka
Mistral Small 2402
690
Mistral131K ctx100 t/s$6/M/M output
3.2
Terbuka
Llama 3 Instruct 70b
691
Meta131K ctx80 t/s$0/M/M output
3.1
Terbuka
Llama 3 2 Instruct 11b Vision
692
Meta131K ctx80 t/s$0/M/M output
3.0
Terbuka
Command R Plus 04 2024
693
Cohere131K ctx60 t/s$10/M/M output
2.6
Olmo 3 7b Instruct
694
AI2131K ctx60 t/s$3/M/M output
2.4
Terbuka
Jamba 1 5 Mini
695
AI21 Labs131K ctx60 t/s$3/M/M output
2.3
Apertus 70b Instruct
696
Swiss AI131K ctx60 t/s$3/M/M output
2.0
Mixtral 8x7b Instruct
697
Mistral131K ctx100 t/s$6/M/M output
2.0
Command R 03 2024
698
Cohere131K ctx60 t/s$10/M/M output
1.7
Mistral 7b Instruct
699
Mistral131K ctx100 t/s$6/M/M output
1.7
Terbuka
Granite 3 3 8b Instruct
700
IBM131K ctx60 t/s$3/M/M output
1.3
Terbuka
Apertus 8b Instruct
701
Swiss AI131K ctx60 t/s$3/M/M output
1.0
Gemma 3 1b
702
Google131K ctx120 t/s$5/M/M output
1.0
Terbuka
Gemma 3 4b
703
Google131K ctx120 t/s$5/M/M output
1.0
Terbuka
Gemma 3n E2b
704
Google131K ctx120 t/s$5/M/M output
1.0
Terbuka
Gemma 3n E4b
705
Google131K ctx120 t/s$5/M/M output
1.0
Terbuka
Llama 3 Instruct 8b
706
Meta131K ctx80 t/s$0/M/M output
1.0
Terbuka
Tiny Aya Global
707
Cohere131K ctx60 t/s$10/M/M output
1.0
Claude Mythos 5
708
Anthropic1.0M ctx50 t/s$50/M/M output
0.0
pratinjau
GPT-5.5 Pro
709
OpenAI1.1M ctx60 t/s$10/M/M output
0.0
Claude Sonnet 4.6 (max)
710
Anthropic1.0M ctx50 t/s$15/M/M output
0.0
Amazon Nova
711
Amazon131K ctx60 t/s$3.2/M/M output
0.0
Async Flash V1 5
712
Async131K ctx60 t/s$3/M/M output
0.0
Async Pro V1 0
713
Async131K ctx60 t/s$3/M/M output
0.0
Asyncflow V2
714
Async131K ctx60 t/s$3/M/M output
0.0
Claude Sonnet 5 High
715
Anthropic131K ctx80 t/s$15/M/M output
0.0
Claude Sonnet 5 Low
716
Anthropic131K ctx80 t/s$15/M/M output
0.0
Claude Sonnet 5 Medium
717
Anthropic131K ctx80 t/s$15/M/M output
0.0
Claude Sonnet 5 Xhigh
718
Anthropic131K ctx80 t/s$15/M/M output
0.0
Cogito V2 1 Reasoning
719
Cogito131K ctx40 t/s$3/M/M output
0.0
Falcon 2
720
TII131K ctx60 t/s$3/M/M output
0.0
Terbuka
Gemini
721
Google131K ctx120 t/s$5/M/M output
0.0
Gemini 2 5 Flash Dec 2025
722
Google131K ctx120 t/s$5/M/M output
0.0
Gemini_nano Banana Pro
723
Google131K ctx120 t/s$5/M/M output
0.0
Gladia Solaria
724
Upstage131K ctx60 t/s$3/M/M output
0.0
Gpt 5 4 Pro
725
OpenAI131K ctx90 t/s$10/M/M output
0.0
Gpt Realtime 2
726
OpenAI131K ctx90 t/s$10/M/M output
0.0
Grok Stt
727
xAI131K ctx80 t/s$15/M/M output
0.0
Hidream O1 Image
728
OpenAI131K ctx60 t/s$10/M/M output
0.0
Minimax H3
729
MiniMax131K ctx60 t/s$2/M/M output
0.0
Terbuka
Mistral
730
Mistral131K ctx100 t/s$6/M/M output
0.0
Terbuka
Nvidia
731
NVIDIA131K ctx150 t/s$1/M/M output
0.0
Nvidia Nemotron Asr Streaming
732
NVIDIA131K ctx150 t/s$1/M/M output
0.0
Ocateve 2
733
Ocat131K ctx60 t/s$3/M/M output
0.0
Qwen Image
734
Alibaba131K ctx85 t/s$2/M/M output
0.0
Terbuka
Qwen3 Asr
735
Alibaba131K ctx85 t/s$2/M/M output
0.0
Terbuka
Apodex 1.1
736
Independent128K ctx145 t/s$0.8/M/M output
0.0
Terbuka
Muse Spark 1.3 (xhigh)
737
Muse256K ctx65 t/s$10/M/M output
0.0
Quasar 438B
738
Open Source128K ctx95 t/s$1.6/M/M output
0.0
Terbuka
0 / 4
Bandingkan sekarang →