Amazon Bedrock
Claude Opus 5 (max)
1M
Proprietary
63
$2.34
55
65.08
74.25
--
Anthropic
Claude Opus 5 (max)
1M
Proprietary
63
$2.34
58
47.83
56.50
--
Google
Claude Opus 5 (max)
1M
Proprietary
63
$3.31
54
45.70
54.95
--
Anthropic
Claude Opus 5 (xhigh)
1M
Proprietary
63
$1.80
53
35.30
44.65
--
Google
Claude Opus 5 (xhigh)
1M
Proprietary
63
$2.51
54
29.15
38.37
--
Amazon Bedrock
Claude Opus 5 (xhigh)
1M
Proprietary
63
$1.80
56
37.85
46.71
--
Anthropic
Claude Fable 5 (with fallback)
1M
Proprietary
62
$3.14
70
111.36
118.51
--
Google
Claude Fable 5 (with fallback)
1M
Proprietary
62
$3.32
70
88.70
95.82
--
Microsoft Azure
Claude Fable 5 (with fallback)
1M
Proprietary
62
$10.16
68
100.69
108.10
--
Anthropic
Claude Opus 5 (high)
1M
Proprietary
61
$1.23
54
19.95
29.22
--
Google
Claude Opus 5 (high)
1M
Proprietary
61
$1.67
53
16.89
26.39
--
Amazon Bedrock
Claude Opus 5 (high)
1M
Proprietary
61
$1.23
54
24.08
33.38
--
Amazon Bedrock
GPT-5.6 Sol (max)
1M
Proprietary
61
$1.66
118
79.64
83.88
--
OpenAI
GPT-5.6 Sol (max)
1M
Proprietary
61
$1.23
74
146.36
153.16
--
SpaceXAI
Grok 4.6 (high)
500k
Proprietary
61
$0.84
66
41.87
49.47
--
SpaceXAI
Grok 4.6 (xhigh)
500k
Proprietary
60
$1.04
62
46.08
54.10
--
Kimi
![]()
Kimi K3 (max)
1.05M
Open
60
$0.84
35
3.26
75.19
57.55
Fireworks
![]()
Kimi K3 (max)
1.05M
Open
60
$0.89
58
1.45
44.32
34.29
Fireworks
![]()
Kimi K3 (max) (FAST)
1.05M
Open
60
$1.34
124
1.02
21.15
16.11
Modal
![]()
Kimi K3 (max)
1.05M
Open
60
$1.24
143
2.02
19.55
14.03
Together AI
![]()
Kimi K3 (max)
1.05M
Open
60
$1.43
44
1.07
57.67
45.28
DigitalOcean
![]()
Kimi K3 (max)
1.05M
Open
60
$0.96
33
1.20
77.49
61.04
Baseten
![]()
Kimi K3 (max)
1.05M
Open
60
$1.26
114
0.93
22.77
17.47
Parasail
![]()
Kimi K3 (max)
1.05M
Open
60
$0.78
180
1.77
15.68
11.13
Makora
![]()
Kimi K3 (max)
1.05M
Open
60
$0.56
158
1.63
17.47
12.67
Nebius
![]()
Kimi K3 (max)
1.05M
Open
60
$3.11
147
1.56
18.59
13.63
Databricks
![]()
Kimi K3 (max)
205k
Open
60
$0.79
103
0.91
25.29
19.50
Bitdeer AI
![]()
Kimi K3 (max)
262k
Open
60
$1.19
17
3.11
150.50
117.91
Zai
GLM-5.3 (max)
1M
Proprietary
60
$0.68
--
--
--
--
OpenAI
GPT-5.6 Sol (xhigh)
1M
Proprietary
59
$0.81
68
35.87
43.27
--
SpaceXAI
Grok 4.6 (medium)
500k
Proprietary
59
$0.67
61
26.99
35.16
--
Anthropic
Claude Opus 5 (medium)
1M
Proprietary
59
$0.72
53
5.27
14.66
--
Amazon Bedrock
Claude Opus 5 (medium)
1M
Proprietary
59
$0.72
53
10.31
19.69
--
Google
Claude Opus 5 (medium)
1M
Proprietary
59
$0.95
53
4.29
13.73
--
Alibaba Cloud
Qwen3.8 Max
1M
Proprietary
58
$1.13
54
2.56
48.52
36.77
Fireworks
Qwen3.8 2.4T A95B
262k
Open
58
$0.72
125
1.01
20.93
15.94
Together AI
Qwen3.8 2.4T A95B
262k
Open
58
$1.74
185
1.09
14.63
10.83
DeepInfra
Qwen3.8 2.4T A95B
262k
Open
58
$1.03
84
1.33
31.26
23.94
DigitalOcean
Qwen3.8 2.4T A95B
262k
Open
58
$0.70
--
--
--
--
Bitdeer AI
Qwen3.8 2.4T A95B (FP8)
262k
Open
58
$0.61
88
3.35
31.61
22.60
Alibaba Cloud
Qwen3.8 2.4T A95B
984k
Open
58
$1.09
53
2.62
50.20
38.06
OpenAI
GPT-5.6 Sol (high)
1M
Proprietary
57
$0.55
67
11.15
18.59
--
Meta
Muse Spark 1.2 (xhigh)
1.05M
Proprietary
57
$0.40
--
--
--
--
OpenAI
GPT-5.6 Terra (max)
1M
Proprietary
57
$0.51
123
185.76
189.84
--
Amazon Bedrock
GPT-5.6 Terra (max)
1M
Proprietary
57
$0.97
155
124.81
128.03
--
Google
Gemini 3.7 Flash (high) AI Studio
1M
Proprietary
56
$0.40
340
11.81
13.28
--
SpaceXAI
Grok 4.5 (high)
500k
Proprietary
56
$0.36
66
7.54
15.09
--
OpenAI
GPT-5.6 Sol (medium)
1M
Proprietary
56
$0.37
69
4.61
11.89
--
Google
Claude Sonnet 5 (max)
1M
Proprietary
55
$2.22
79
162.12
168.41
--
Microsoft Azure
Claude Sonnet 5 (max)
1M
Proprietary
55
$1.64
78
178.63
185.06
--
Anthropic
Claude Sonnet 5 (max)
1M
Proprietary
55
$1.72
79
183.18
189.48
--
Amazon Bedrock
Claude Sonnet 5 (max)
1M
Proprietary
55
$1.96
93
189.40
194.81
--
Google
Gemini 3.7 Flash (medium) AI Studio
1M
Proprietary
53
$0.26
348
4.74
6.18
--
DeepSeek
DeepSeek V4 Pro 0813 (max)
1.05M
Open
53
$0.25
72
1.81
36.66
27.88
GMI
DeepSeek V4 Pro 0813 (max)
1.05M
Open
53
$0.56
69
3.58
40.07
29.20
SiliconFlow
DeepSeek V4 Pro 0813 (max)
1.05M
Open
53
$0.51
63
3.68
43.20
31.62
Fireworks
DeepSeek V4 Pro 0813 (max)
1M
Open
53
$0.65
89
1.55
29.76
22.57
Baseten
DeepSeek V4 Pro 0813 (max)
1M
Open
53
$1.09
180
0.92
14.80
11.11
DeepInfra
DeepSeek V4 Pro 0813 (max)
1M
Open
53
$0.46
81
1.49
32.42
24.74
Novita
DeepSeek V4 Pro 0813 (max)
1.05M
Open
53
$0.55
68
2.06
38.66
29.28
DigitalOcean
DeepSeek V4 Pro 0813 (max)
1.05M
Open
53
$0.39
66
2.80
40.95
30.52
OpenAI
GPT-5.6 Terra (xhigh)
1M
Proprietary
53
$0.31
111
26.38
30.89
--
Wafer
GLM-5.2 (max)
205k
Open
53
$0.36
63
5.02
44.43
31.53
FriendliAI
GLM-5.2 (max)
1M
Open
53
$0.42
189
1.26
14.49
10.59
Makora
GLM-5.2 (max) (NVFP4)
1M
Open
53
$0.34
317
0.86
8.76
6.32
Baseten
GLM-5.2 (max) (FAST)
524k
Open
53
$0.54
248
1.24
11.31
8.06
Novita
GLM-5.2 (max) (FP8)
1.05M
Open
53
$0.42
87
1.48
30.35
23.09
Parasail
GLM-5.2 (max) (NVFP4)
1M
Open
53
--
184
0.97
14.53
10.85
CoreWeave
GLM-5.2 (max)
262k
Open
53
$0.38
174
1.19
15.53
11.47
DeepInfra
GLM-5.2 (max) (FP4)
1.05M
Open
53
$0.25
69
1.08
37.10
28.81
Nebius
GLM-5.2 (max) (FP4)
432k
Open
53
$1.06
172
1.16
15.69
11.62
Together AI
GLM-5.2 (max)
262k
Open
53
$0.67
133
0.78
19.65
15.09
Scaleway
GLM-5.2 (max)
262k
Open
53
$1.57
86
1.63
30.59
23.17
Databricks
GLM-5.2 (max)
1M
Open
53
--
339
0.94
8.32
5.90
Crusoe
GLM-5.2 (max) (NVFP4)
1M
Open
53
$0.42
145
0.94
18.20
13.81
Bitdeer AI
GLM-5.2 (max)
1M
Open
53
$0.17
152
3.07
19.56
13.20
Fireworks
GLM-5.2 (max)
1M
Open
53
$0.48
74
1.60
35.45
27.08
GMI
GLM-5.2 (max) (FP8)
1.05M
Open
53
--
--
--
--
--
Baseten
GLM-5.2 (max)
261k
Open
53
$0.46
105
1.93
25.67
18.99
Modular
GLM-5.2 (max)
164k
Open
53
$0.51
233
1.09
11.80
8.57
Zai
GLM-5.2 (max)
1M
Open
53
$0.44
--
--
--
--
Mistral
GLM-5.2 (max)
1.05M
Open
53
$0.38
204
1.06
13.34
9.83
SiliconFlow
GLM-5.2 (max) (FP8)
1.05M
Open
53
$0.62
99
2.03
27.19
20.13
Anthropic
Claude Opus 5 (low)
1M
Proprietary
52
$0.43
55
3.55
12.68
--
Amazon Bedrock
Claude Opus 5 (low)
1M
Proprietary
52
$0.43
54
2.60
11.91
--
Google
Claude Opus 5 (low)
1M
Proprietary
52
$0.55
53
3.13
12.54
--
OpenAI
GPT-5.6 Luna (max)
1M
Proprietary
52
$0.05
144
146.22
149.69
--
Amazon Bedrock
GPT-5.6 Luna (max)
1M
Proprietary
52
$0.34
235
106.72
108.85
--
DeepInfra
Qwen3.8 27B (xhigh)
262k
Open
52
$0.31
48
0.97
53.17
41.76
Alibaba Cloud
Qwen3.8 27B (xhigh)
1M
Open
52
$0.25
53
2.98
50.22
37.79
CoreWeave
DeepSeek V4 Flash 0731 (max)
262k
Open
52
$0.12
175
1.64
15.94
11.44
Wafer
DeepSeek V4 Flash 0731 (max) (FAST)
1M
Open
52
$0.17
294
1.80
10.31
6.81
Nebius
DeepSeek V4 Flash 0731 (max)
1.05M
Open
52
$0.20
113
1.97
24.09
17.70
DeepSeek
DeepSeek V4 Flash 0731 (max)
1M
Open
52
$0.11
123
1.13
21.38
16.20
Bitdeer AI
DeepSeek V4 Flash 0731 (max)
1M
Open
52
$0.02
111
2.88
25.43
18.04
Parasail
DeepSeek V4 Flash 0731 (max)
1.05M
Open
52
$0.13
55
1.63
46.85
36.18
Fireworks
DeepSeek V4 Flash 0731 (max)
1.05M
Open
52
$0.08
113
0.77
22.83
17.65
SiliconFlow
DeepSeek V4 Flash 0731 (max)
1.05M
Open
52
$0.09
67
1.48
38.71
29.78
Baseten
DeepSeek V4 Flash 0731 (max)
1.05M
Open
52
$0.14
211
0.86
12.72
9.49
GMI
DeepSeek V4 Flash 0731 (max)
1.05M
Open
52
$0.09
129
2.39
21.81
15.54
Novita
DeepSeek V4 Flash 0731 (max)
1.05M
Open
52
$0.08
115
1.48
23.18
17.36
DeepInfra
DeepSeek V4 Flash 0731 (max)
1M
Open
52
$0.05
76
0.75
33.59
26.27
DigitalOcean
DeepSeek V4 Flash 0731 (max)
1.05M
Open
52
$0.06
82
0.59
31.16
24.46
Makora
DeepSeek V4 Flash 0731 (max)
1M
Open
52
$0.13
281
0.73
9.61
7.11
SpaceXAI
Grok 4.6 (low)
500k
Proprietary
52
$0.22
62
6.64
14.67
--
Google
Gemini 3.6 Flash AI Studio
1M
Proprietary
52
$0.34
209
15.80
18.19
--
Google
Gemini 3.7 Flash (low) AI Studio
1M
Proprietary
51
$0.16
314
1.00
2.59
--
OpenAI
GPT-5.6 Sol (low)
1M
Proprietary
51
$0.23
68
2.83
10.22
--
OpenAI
GPT-5.6 Terra (high)
1M
Proprietary
50
$0.22
113
2.34
6.75
--
OpenAI
GPT-5.6 Luna (xhigh)
1M
Proprietary
50
$0.03
135
58.90
62.60
--
Kimi
![]()
Kimi K3 (low)
1.05M
Open
48
$0.24
35
3.83
75.53
57.37
Google
Gemini 3.1 Pro Preview (AI Studio)
1M
Proprietary
48
$0.33
124
28.63
32.66
--
Google
Gemini 3.1 Pro Preview (Vertex)
1M
Proprietary
48
$0.43
130
26.25
30.09
--
OpenAI
GPT-5.6 Luna (high)
1M
Proprietary
47
$0.02
141
12.84
16.38
--
OpenAI
GPT-5.6 Terra (medium)
1M
Proprietary
47
$0.12
107
1.78
6.46
--
Google
Gemini 3.5 Flash (medium)
1M
Proprietary
--
217
15.31
17.61
--
OpenAI
GPT-5.3 Codex (xhigh)
400k
Proprietary
--
143
59.29
62.79
--
Parasail
MiniMax-M3 (MXFP8)
1M
Open
45
$0.18
88
2.02
30.35
22.66
CoreWeave
MiniMax-M3
262k
Open
45
$0.11
196
1.24
13.99
10.21
Together AI
MiniMax-M3
1M
Open
45
$0.21
127
0.71
20.45
15.79
Novita
MiniMax-M3
1M
Open
45
$0.13
133
1.30
20.03
14.98
Modular
MiniMax-M3
1M
Open
45
$0.18
220
0.52
11.91
9.11
Nebius
MiniMax-M3 (FP8)
1.05M
Open
45
$0.45
261
1.93
11.52
7.67
SiliconFlow
MiniMax-M3 (FP8)
1M
Open
45
$0.12
112
1.30
23.60
17.83
Bitdeer AI
MiniMax-M3
524k
Open
45
$0.12
37
2.84
69.61
53.42
MiniMax
MiniMax-M3
512k
Open
45
$0.14
103
1.31
25.58
19.42
DeepInfra
MiniMax-M3
524k
Open
45
$0.12
44
0.90
57.94
45.63
GMI
MiniMax-M3
1.05M
Open
45
--
--
--
--
--
DeepInfra
DeepSeek V4 Pro (max) (FP4)
1.05M
Open
45
$0.27
51
1.33
96.55
85.45
Microsoft Azure
DeepSeek V4 Pro (max)
1M
Open
45
$0.89
83
1.74
60.45
52.69
Novita
DeepSeek V4 Pro (max)
1.05M
Open
45
$0.23
72
1.90
69.73
60.87
Bitdeer AI
DeepSeek V4 Pro (max)
1M
Open
45
$0.21
33
2.15
148.98
131.78
SiliconFlow
DeepSeek V4 Pro (max) (FP8)
1.05M
Open
45
$0.31
50
1.77
100.19
88.33
GMI
DeepSeek V4 Pro (max)
1.05M
Open
45
--
--
--
--
--
Nebius
DeepSeek V4 Pro (max)
1M
Open
45
$0.90
144
1.30
35.04
30.28
Fireworks
DeepSeek V4 Pro (max)
1.05M
Open
45
$0.38
78
1.86
64.48
56.20
Baseten
DeepSeek V4 Pro (max)
131k
Open
45
--
--
--
--
--
DeepSeek
DeepSeek V4 Pro (max)
1M
Open
45
$0.05
75
1.65
66.79
58.46
Alibaba Cloud
Qwen3.8 27B (medium)
1M
Open
44
$0.19
64
3.01
42.06
31.24
DeepInfra
DeepSeek V4 Pro (high) (FP4)
65.5k
Open
44
$0.26
56
1.21
45.94
35.75
Fireworks
DeepSeek V4 Pro (high)
1.05M
Open
44
$0.36
77
1.92
34.35
25.92
Microsoft Azure
DeepSeek V4 Pro (high)
1M
Open
44
$0.94
83
1.67
31.68
23.99
DeepSeek
DeepSeek V4 Pro (high)
1M
Open
44
$0.04
73
1.66
35.64
27.16
Bitdeer AI
DeepSeek V4 Pro (high)
1M
Open
44
$0.18
48
1.83
53.54
41.33
SiliconFlow
DeepSeek V4 Pro (high) (FP8)
1.05M
Open
44
$0.29
50
2.30
52.42
40.07
Nebius
DeepSeek V4 Pro (high)
1M
Open
44
$0.94
140
1.34
19.14
14.22
Novita
DeepSeek V4 Pro (high)
1.05M
Open
44
$0.20
73
1.95
36.18
27.37
Baseten
DeepSeek V4 Pro (high)
131k
Open
44
$0.68
162
0.55
15.89
12.27
Nebius
![]()
Kimi K2.7 Code (FP4)
256k
Open
43
$0.64
132
1.88
22.53
16.87
GMI
![]()
Kimi K2.7 Code (FP8)
65.5k
Open
43
$0.46
57
4.25
52.53
39.43
CoreWeave
![]()
Kimi K2.7 Code
262k
Open
43
$0.28
299
1.09
10.22
7.46
Parasail
![]()
Kimi K2.7 Code
262k
Open
43
$0.18
82
1.29
34.69
27.28
Together AI
![]()
Kimi K2.7 Code
262k
Open
43
$0.30
167
0.46
16.82
13.36
Baseten
![]()
Kimi K2.7 Code
262k
Open
43
$0.29
--
--
--
--
Modular
![]()
Kimi K2.7 Code
262k
Open
43
$0.57
148
0.60
18.98
15.01
Novita
![]()
Kimi K2.7 Code
262k
Open
43
$0.23
51
3.71
56.84
43.39
DeepInfra
![]()
Kimi K2.7 Code
262k
Open
43
$0.16
50
0.58
55.54
44.89
Kimi
![]()
Kimi K2.7 Code
256k
Open
43
$0.22
49
2.90
58.26
45.22
Novita
MiMo-V2.5-Pro
1.05M
Open
43
$0.04
52
2.61
50.96
38.68
GMI
MiMo-V2.5-Pro
1.05M
Open
43
--
--
--
--
--
DeepInfra
MiMo-V2.5-Pro
65.5k
Open
43
$0.18
125
0.72
20.70
15.98
Xiaomi
MiMo-V2.5-Pro
1M
Open
43
$0.03
51
3.12
51.76
38.91
Alibaba Cloud
Qwen3.8 27B (low)
1M
Open
43
$0.17
64
2.99
41.77
31.03
Anthropic
Claude Sonnet 5 (Non-reasoning)
1M
Proprietary
43
$0.42
69
1.83
9.07
--
Amazon Bedrock
Claude Sonnet 5 (Non-reasoning)
1M
Proprietary
43
$0.61
67
1.70
9.17
--
DeepInfra
Inkling (FP8)
131k
Open
42
$0.43
195
0.55
13.38
10.27
Baseten
Inkling
262k
Open
42
$0.34
261
0.62
10.22
7.68
Together AI
Inkling
524k
Open
42
$0.62
146
0.82
17.96
13.71
Thinking Machines
Inkling
262k
Open
42
$0.34
56
2.64
47.10
35.57
SiliconFlow
Hy3 (FP8)
256k
Open
42
$0.03
85
2.80
32.09
23.43
Novita
Hy3
262k
Open
42
$0.04
69
2.95
39.30
29.08
DeepInfra
Hy3 (FP8)
262k
Open
42
$0.04
68
1.17
37.83
29.33
GMI
Hy3
262k
Open
42
$0.03
76
3.30
36.22
26.33
OpenAI
GPT-5.6 Sol (Non-reasoning)
1M
Proprietary
42
$0.24
62
1.32
9.37
--
Amazon Bedrock
GPT-5.6 Sol (Non-reasoning)
1M
Proprietary
42
$0.30
94
0.79
6.09
--
SiliconFlow
Nex-N2-Pro (FP8)
262k
Open
42
--
134
1.59
20.22
14.91
Upstage
Solar Pro 4
512k
Proprietary
42
$0.22
59
2.30
44.72
33.93
OpenAI
GPT-5.6 Terra (low)
1M
Proprietary
41
$0.09
106
1.29
6.02
--
Thinking Machines
Inkling Small
256k
Open
41
$0.07
130
2.00
21.30
15.44
DeepInfra
Inkling Small
524k
Open
41
$0.13
192
0.72
13.73
10.41
Baseten
Inkling Small
262k
Open
41
$0.13
342
0.49
7.81
5.86
Agnes (NG)
Agnes 2.5 Pro Alpha
1M
Proprietary
40
--
130
2.05
21.32
15.42
Alibaba Cloud
Qwen3.7 Plus
1M
Proprietary
39
$0.24
56
2.12
46.73
35.68
OpenAI
GPT-5.6 Luna (medium)
1M
Proprietary
39
$0.01
137
2.11
5.74
--
CoreWeave
Nemotron 3 Ultra
262k
Open
38
$0.16
274
1.05
11.17
8.30
GMI
Nemotron 3 Ultra
262k
Open
38
--
--
--
--
--
Together AI
Nemotron 3 Ultra
512k
Open
38
$0.40
165
0.70
17.52
13.79
DeepInfra
Nemotron 3 Ultra
262k
Open
38
$0.23
94
3.96
33.45
24.18
DeepInfra
Nemotron 3 Ultra BF16
262k
Open
38
--
83
4.89
38.24
27.34
Nebius
Nemotron 3 Ultra
256k
Open
38
$0.60
302
2.30
11.48
7.52
Lightning AI
Nemotron 3 Ultra
262k
Open
38
$0.25
--
--
--
--
Blackbox AI
Nemotron 3 Ultra
262k
Open
38
$0.22
--
--
--
--
Novita
MiMo-V2.5
1.05M
Open
38
$0.01
70
2.57
38.10
28.42
Parasail
MiMo-V2.5
1M
Open
38
$0.04
67
1.46
38.74
29.83
DeepInfra
MiMo-V2.5
262k
Open
38
$0.08
58
0.75
43.66
34.32
GMI
MiMo-V2.5
1.05M
Open
38
$0.02
--
--
--
--
Xiaomi
MiMo-V2.5
1M
Open
38
$0.01
66
4.44
42.13
30.15
DeepInfra
![]()
Ling 3.0 Flash
131k
Open
38
$0.03
114
0.67
22.54
17.50
InclusionAI
![]()
Ling 3.0 Flash
262k
Open
38
$0.04
399
2.54
8.81
5.01
DeepInfra
Qwen3.6 27B FP8
262k
Open
38
$0.19
51
0.99
123.22
112.34
Groq
Qwen3.6 27B
131k
Open
38
$0.27
438
1.43
15.51
12.95
Novita
Qwen3.6 27B
262k
Open
38
$0.29
56
2.94
112.53
100.72
Alibaba Cloud
Qwen3.6 27B
262k
Open
38
$0.29
58
3.68
110.55
98.22
CompactifAI
Qwen3.6 27B
262k
Open
38
$0.07
173
1.27
36.90
32.75
SiliconFlow
Qwen3.6 27B (FP8)
262k
Open
38
$0.19
36
3.58
173.92
156.55
Google
Gemini 3.5 Flash-Lite AI Studio
1M
Proprietary
37
$0.10
370
8.70
10.05
--
Amazon Bedrock
Grok 4.3 (medium)
524k
Proprietary
--
265
6.14
8.03
--
Microsoft Azure
Grok 4.3 (medium)
200k
Proprietary
--
156
9.02
12.22
--
SpaceXAI
Grok 4.3 (medium)
1M
Proprietary
--
132
11.88
15.66
--
Amazon Bedrock
Grok 4.3 (low)
524k
Proprietary
--
265
2.76
4.64
--
Microsoft Azure
Grok 4.3 (low)
200k
Proprietary
--
151
5.17
8.48
--
SpaceXAI
Grok 4.3 (low)
1M
Proprietary
--
120
5.52
9.69
--
Google
Gemini 3.5 Flash (minimal) AI Studio
1M
Proprietary
--
185
0.81
3.52
--
Anthropic
Claude Sonnet 4.6 (Non-reasoning, Low Effort)
1M
Proprietary
--
46
1.54
12.52
--
Together AI
Muse Glimmer (high)
131k
Open
35
$0.08
61
0.85
41.56
32.56
DeepInfra
Muse Glimmer (high)
131k
Open
35
$0.07
151
0.79
17.35
13.24
Baseten
GLM-5.2 (FAST)
524k
Open
35
--
196
1.71
4.26
--
Nebius
GLM-5.2 (FP4)
432k
Open
35
--
140
1.33
4.89
--
Scaleway
GLM-5.2
262k
Open
35
--
85
1.58
7.43
--
Wafer
GLM-5.2
205k
Open
35
--
63
5.17
13.11
--
Bitdeer AI
GLM-5.2
1M
Open
35
--
141
2.68
6.22
--
SiliconFlow
GLM-5.2 (FP8)
1.05M
Open
35
--
90
1.94
7.49
--
Modular
GLM-5.2
164k
Open
35
--
189
1.07
3.72
--
OpenAI
GPT-5.6 Terra (Non-reasoning)
1M
Proprietary
35
$0.10
102
0.79
5.69
--
Amazon Bedrock
GPT-5.6 Terra (Non-reasoning)
1M
Proprietary
35
$0.20
139
0.72
4.31
--
Clarifai
Qwen3.5 397B A17B
256k
Open
34
$0.36
--
--
--
--
Alibaba Cloud
Qwen3.5 397B A17B
262k
Open
34
$0.36
79
2.19
48.89
40.37
Wafer
Qwen3.5 397B A17B
262k
Open
34
$0.12
80
2.39
48.18
39.58
Parasail
Qwen3.5 397B A17B
262k
Open
34
$0.23
72
1.17
52.25
44.15
SiliconFlow
Qwen3.5 397B A17B (FP8)
262k
Open
34
$0.23
91
2.18
42.51
34.86
DeepInfra
Qwen3.5 397B A17B (FP8)
262k
Open
34
$0.19
46
1.18
82.19
70.02
DigitalOcean
Qwen3.5 397B A17B
262k
Open
34
$0.10
13
1.39
289.43
248.97
GMI
Qwen3.5 397B A17B (FP8)
262k
Open
34
$0.36
--
--
--
--
Nebius
Qwen3.5 397B A17B (Base, FP4)
262k
Open
34
$0.36
137
2.08
28.93
23.21
Novita
Qwen3.5 397B A17B
262k
Open
34
$0.36
79
1.62
48.28
40.33
AI9Stars
G9v3-39A5B
131k
Open
34
$0.00
--
--
--
--
SiliconFlow
LongCat 2.0 (FP8)
1M
Open
34
$0.12
45
2.65
57.70
44.04
OpenAI
GPT-5.6 Luna (low)
1M
Proprietary
34
$0.01
137
1.61
5.27
--
Novita
KAT-Coder-Pro V2
256k
Proprietary
34
--
105
1.42
6.19
--
StreamLake
KAT-Coder-Pro V2
256k
Proprietary
34
--
--
--
--
--
SiliconFlow
Qwen3.5 122B A10B (FP8)
262k
Open
33
$0.16
35
2.08
73.49
57.13
DeepInfra
Qwen3.5 122B A10B (FP4)
262k
Open
33
$0.12
159
0.79
16.52
12.59
Alibaba Cloud
Qwen3.5 122B A10B
262k
Open
33
$0.25
129
2.31
21.72
15.53
GMI
Qwen3.5 122B A10B (FP8)
262k
Open
33
$0.25
--
--
--
--
Novita
Qwen3.5 122B A10B
262k
Open
33
$0.25
121
1.92
22.55
16.50
Wafer
Qwen3.5 397B A17B
262k
Open
--
81
2.18
8.38
--
DeepInfra
Qwen3.5 397B A17B (FP8)
262k
Open
--
47
1.17
11.78
--
Alibaba Cloud
Qwen3.5 397B A17B
262k
Open
--
79
2.08
8.43
--
Nebius
Qwen3.5 397B A17B (Base, FP4)
262k
Open
--
140
2.08
5.66
--
DigitalOcean
Qwen3.5 397B A17B
262k
Open
--
18
1.19
28.93
--
Novita
Qwen3.5 397B A17B
262k
Open
--
76
1.44
8.00
--
Alibaba Cloud
Qwen3.6 35B A3B
229k
Open
32
$0.29
119
2.06
51.74
45.46
SiliconFlow
Qwen3.6 35B A3B (FP8)
262k
Open
32
$0.17
95
2.09
64.34
56.97
Scaleway
Qwen3.6 35B A3B
262k
Open
32
$0.23
194
0.89
31.33
27.86
DeepInfra
Qwen3.6 35B A3B (FP8)
262k
Open
32
$0.09
76
0.68
78.63
71.34
Clarifai
Qwen3.6 35B A3B (FP8)
262k
Open
32
$0.47
--
--
--
--
GMI
Qwen3.6 35B A3B FP8
262k
Open
32
$0.19
--
--
--
--
Parasail
Qwen3.6 35B A3B
262k
Open
32
$0.08
120
0.85
49.91
44.90
Novita
Qwen3.6 35B A3B
205k
Open
32
$0.19
132
1.47
46.24
40.97
Microsoft Azure
DeepSeek V4 Pro
1M
Open
--
93
1.76
7.15
--
Bitdeer AI
DeepSeek V4 Pro
1M
Open
--
49
1.99
12.16
--
Nebius
DeepSeek V4 Pro
1.05M
Open
--
130
1.45
5.29
--
DeepSeek
DeepSeek V4 Pro
1M
Open
--
73
1.83
8.68
--
InclusionAI
![]()
Ring-2.6-1T
262k
Open
32
$0.36
127
4.24
23.88
15.71
Alibaba Cloud
Qwen3.5 Omni Plus
256k
Proprietary
--
47
2.38
13.01
--
Groq
Qwen3.6 27B
131k
Open
31
$0.39
465
1.09
2.17
--
CompactifAI
Qwen3.6 27B
262k
Open
31
$0.10
220
1.08
3.35
--
DeepInfra
Qwen3.6 27B FP8
262k
Open
31
$0.23
47
1.00
11.57
--
Alibaba Cloud
Qwen3.6 27B
262k
Open
31
$0.40
57
3.78
12.55
--
Novita
Qwen3.6 27B
262k
Open
31
$0.40
61
2.99
11.21
--
Microsoft Azure
o3
200k
Proprietary
--
112
26.09
30.55
--
OpenAI
o3
200k
Proprietary
--
--
--
--
--
OpenAI
o3
200k
Proprietary
--
150
6.43
9.76
--
StepFun
Step 3.7 Flash
256k
Open
31
$0.09
137
2.73
21.03
14.64
DeepInfra
Step 3.7 Flash
256k
Open
31
--
162
0.62
16.03
12.33
Mistral
![]()
Mistral Medium 3.5
262k
Open
30
$0.46
148
2.23
19.09
13.48
Amazon Bedrock
Claude 4.5 Haiku
200k
Proprietary
30
$0.24
123
12.67
16.73
--
Google
Claude 4.5 Haiku Vertex
200k
Proprietary
30
$0.25
128
25.38
29.29
--
Anthropic
Claude 4.5 Haiku
200k
Proprietary
30
$0.22
110
23.78
28.31
--
Microsoft Azure
Claude 4.5 Haiku
200k
Proprietary
30
$0.54
100
21.30
26.31
--
CoreWeave
Gemma 4 31B
262k
Open
30
--
35
1.93
65.56
49.40
Modular
Gemma 4 31B (NVFP4)
262k
Open
30
--
243
0.48
9.69
7.15
GMI
Gemma 4 31B (FP8)
262k
Open
30
$0.04
--
--
--
--
Novita
Gemma 4 31B
262k
Open
30
$0.04
18
7.92
135.58
99.11
Cerebras
Gemma 4 31B
131k
Open
30
$0.24
1,414
0.51
2.09
1.23
Google
Gemma 4 31B (AI Studio)
262k
Open
30
$0.00
35
1.06
64.58
49.31
Parasail
Gemma 4 31B
262k
Open
30
$0.02
57
1.50
40.97
30.64
DeepInfra
Gemma 4 31B
262k
Open
30
$0.01
62
1.03
37.33
28.19
SiliconFlow
Gemma 4 31B (FP8)
262k
Open
30
$0.03
58
3.34
41.92
29.95
SambaNova
Gemma 4 31B
131k
Open
30
$0.10
199
2.38
13.60
8.71
FriendliAI
Gemma 4 31B
256k
Open
30
$0.04
148
1.27
16.37
11.73
Lightning AI
Gemma 4 31B
131k
Open
30
$0.04
150
0.84
15.76
11.59
Together AI
Gemma 4 31B (FP8)
262k
Open
30
$0.10
63
1.15
36.48
27.43
GMI
DeepSeek V4 Flash
1.05M
Open
--
--
--
--
--
Makora
DeepSeek V4 Flash
1M
Open
--
301
0.73
2.39
--
CoreWeave
DeepSeek V4 Flash
1M
Open
--
68
1.54
8.88
--
OpenAI
GPT-5.5 Instant (June 2026)
400k
Proprietary
29
$0.54
141
1.01
18.71
14.16
GMI
MiMo-V2.5-Pro
1.05M
Open
--
--
--
--
--
DeepInfra
MiMo-V2.5-Pro
65.5k
Open
--
106
0.72
5.42
--
Xiaomi
MiMo-V2.5-Pro
131k
Open
--
47
3.54
14.25
--
Novita
MiMo-V2.5-Pro
1.05M
Open
--
49
3.67
13.97
--
DeepInfra
Qwen3.5 122B A10B (FP4)
262k
Open
28
$0.10
155
0.81
4.03
--
Alibaba Cloud
Qwen3.5 122B A10B
262k
Open
28
$0.20
149
2.38
5.74
--
OpenAI
GPT-5.6 Luna (Non-reasoning)
1M
Proprietary
27
$0.01
136
0.72
4.39
--
Amazon Bedrock
GPT-5.6 Luna (Non-reasoning)
1M
Proprietary
27
$0.09
190
0.66
3.30
--
Makora
Gemma 4 26B A4B
1M
Open
26
$0.02
174
0.94
15.33
11.52
Novita
Gemma 4 26B A4B
262k
Open
26
$0.04
31
1.47
82.90
65.15
Google
Gemma 4 26B A4B AI Studio
262k
Open
26
$0.00
47
1.02
54.39
42.69
Cloudflare
Gemma 4 26B A4B
256k
Open
26
$0.03
--
--
--
--
DeepInfra
Gemma 4 26B A4B (FP8)
262k
Open
26
$0.03
29
0.81
87.13
69.05
Parasail
Gemma 4 26B A4B
256k
Open
26
$0.03
40
1.50
64.21
50.17
Clarifai
Gemma 4 26B A4B
256k
Open
26
$0.20
--
--
--
--
GMI
Gemma 4 26B A4B (FP8)
1.05M
Open
26
$0.04
--
--
--
--
CoreWeave
Nemotron 3 Super
262k
Open
26
$0.23
142
0.93
18.58
14.12
Nebius
Nemotron 3 Super
256k
Open
26
$0.33
380
1.78
8.36
5.27
DeepInfra
Nemotron 3 Super
262k
Open
26
$0.10
56
44.13
88.93
35.84
Amazon Bedrock
Grok 4.3 (Non-reasoning)
524k
Proprietary
25
$0.91
252
0.73
2.72
--
SpaceXAI
Grok 4.3 (Non-reasoning)
1M
Proprietary
25
$0.29
128
0.73
4.64
--
Clarifai
Qwen3.6 35B A3B (FP8)
262k
Open
25
$1.19
--
--
--
--
Scaleway
Qwen3.6 35B A3B
262k
Open
25
$0.49
199
0.89
3.40
--
DeepInfra
Qwen3.6 35B A3B (FP8)
262k
Open
25
$0.29
87
0.71
6.45
--
Novita
Qwen3.6 35B A3B
205k
Open
25
$0.42
146
1.34
4.76
--
GMI
Qwen3.6 35B A3B FP8
262k
Open
25
$0.42
--
--
--
--
Parasail
Qwen3.6 35B A3B (FP8)
262k
Open
25
$0.15
111
0.90
5.42
--
Alibaba Cloud
Qwen3.6 35B A3B
262k
Open
25
$0.63
139
2.00
5.60
--
Novita
![]()
Ling 3.0 Tiny
262k
Open
25
$0.00
--
--
--
--
InclusionAI
![]()
Ling 3.0 Tiny
262k
Open
25
$0.00
169
2.57
17.33
11.81
DeepInfra
Qwen3.5 35B A3B FP8
262k
Open
24
$0.07
146
0.49
3.90
--
Alibaba Cloud
Qwen3.5 35B A3B
262k
Open
24
$0.24
169
2.03
4.99
--
Microsoft Azure
Claude 4.5 Haiku
200k
Proprietary
--
92
1.09
6.52
--
Amazon Bedrock
Claude 4.5 Haiku
200k
Proprietary
--
109
1.01
5.59
--
Anthropic
Claude 4.5 Haiku
200k
Proprietary
--
93
0.80
6.17
--
Google
Claude 4.5 Haiku Vertex
200k
Proprietary
--
98
0.62
5.71
--
Groq
gpt-oss-120b (high)
131k
Open
24
$0.06
477
0.73
5.97
4.19
Cloudflare
gpt-oss-120b (high)
116k
Open
24
$0.15
--
--
--
--
Scaleway
gpt-oss-120b (high)
128k
Open
24
$0.08
149
1.23
18.01
13.42
DeepInfra
gpt-oss-120b (high)
131k
Open
24
$0.02
51
0.56
49.24
38.94
CoreWeave
gpt-oss-120b (high)
131k
Open
24
$0.02
48
1.37
53.39
41.62
Microsoft Azure
gpt-oss-120b (high)
131k
Open
24
$0.07
320
0.69
8.51
6.25
Novita
gpt-oss-120b (high)
131k
Open
24
$0.03
109
0.94
23.79
18.28
DeepInfra
gpt-oss-120b (high) (Turbo)
131k
Open
24
$0.07
205
0.78
12.98
9.76
Cerebras
gpt-oss-120b (high)
131k
Open
24
$0.15
1,669
0.48
1.98
1.20
Google
gpt-oss-120b (high) Vertex
131k
Open
24
$0.04
123
1.16
21.53
16.30
Clarifai
gpt-oss-120b (high)
131k
Open
24
$0.04
--
--
--
--
Baseten
gpt-oss-120b (high)
128k
Open
24
$0.05
369
0.23
7.02
5.43
SambaNova
gpt-oss-120b (high)
131k
Open
24
$0.10
697
0.96
4.54
2.87
Parasail
gpt-oss-120b (high)
131k
Open
24
--
131
0.73
19.80
15.25
Nebius
gpt-oss-120b (high) (Base)
128k
Open
24
$0.07
324
1.00
8.73
6.18
Hyperbolic
gpt-oss-120b (high)
131k
Open
24
$0.11
--
--
--
--
Amazon Bedrock
gpt-oss-120b (high)
131k
Open
24
$0.07
101
1.04
25.92
19.90
Together AI
gpt-oss-120b (high)
131k
Open
24
$0.07
147
0.57
17.57
13.60
DeepInfra
Nemotron 3.5 Lightning (NVFP4)
28.7k
Open
24
$0.10
385
0.43
6.92
5.19
Nebius
Nemotron 3.5 Lightning (BF16)
1.05M
Open
24
$0.07
277
1.79
10.83
7.23
CoreWeave
Nemotron 3.5 Lightning (BF16)
262k
Open
24
$0.08
358
0.83
7.82
5.59
Bitdeer AI
Nemotron 3.5 Lightning (BF16)
262k
Open
24
$0.10
356
1.63
8.65
5.62
GMI
Nemotron 3.5 Lightning (BF16)
65.5k
Open
24
$0.00
302
1.84
10.11
6.61
Fireworks
Nemotron 3.5 Lightning (BF16)
262k
Open
24
$0.03
519
0.64
5.46
3.85
Cohere
Command A+
200k
Open
23
$0.00
237
0.41
10.97
8.44
Modular
Gemma 4 31B (NVFP4)
262k
Open
22
--
237
0.47
2.57
--
Parasail
Gemma 4 31B
262k
Open
22
$0.03
49
1.48
11.77
--
Cerebras
Gemma 4 31B
131k
Open
22
$0.28
1,325
0.54
0.92
--
FriendliAI
Gemma 4 31B
262k
Open
22
$0.04
154
1.66
4.91
--
Together AI
Gemma 4 31B (FP8)
262k
Open
22
$0.11
67
1.18
8.69
--
SiliconFlow
Gemma 4 31B (FP8)
262k
Open
22
$0.04
60
3.49
11.87
--
DeepInfra
Gemma 4 31B (FP8)
262k
Open
22
$0.04
62
0.99
9.11
--
SambaNova
Gemma 4 31B
131k
Open
22
$0.11
200
2.34
4.84
--
Novita
Gemma 4 31B
262k
Open
22
$0.04
61
1.32
9.58
--
SiliconFlow
Gemma 4 12B
262k
Open
--
112
2.26
24.53
17.82
Amazon Bedrock
Nova 2.0 Pro Preview (medium)
256k
Proprietary
--
123
15.37
35.68
16.24
Inception
Mercury 2
128k
Proprietary
22
$0.08
932
3.85
4.39
--
SiliconFlow
Qwen3.5 9B (FP8)
262k
Open
22
$0.18
60
2.61
44.50
33.51
Together AI
Qwen3.5 9B (FP8)
262k
Open
22
$0.30
84
0.77
30.61
23.87
Amazon Bedrock
Qwen3 Coder Next
128k
Open
21
$0.47
149
0.99
4.35
--
Parasail
Qwen3 Coder Next (FP8)
262k
Open
21
$0.08
96
0.85
6.07
--
Together AI
Qwen3 Coder Next (FP8)
262k
Open
21
$0.47
--
--
--
--
Novita
Qwen3 Coder Next (FP8)
262k
Open
21
$0.21
174
2.57
5.45
--
Amazon Bedrock
Nova 2.0 Omni (medium)
1M
Proprietary
--
--
--
--
--
Amazon Bedrock
Nova 2.0 Omni (medium)
1M
Proprietary
--
--
--
--
--
Together AI
Apriel-v1.6-15B-Thinker
131k
Open
--
--
--
--
--
Amazon Bedrock
Nova 2.0 Lite (high)
1M
Proprietary
--
--
--
--
--
Amazon Bedrock
Nova 2.0 Lite (high)
1M
Proprietary
--
178
15.76
29.80
11.23
Together AI
Qwen3.5 9B (FP8)
262k
Open
--
85
0.78
6.66
--
Makora
Gemma 4 26B A4B
1M
Open
--
170
0.96
3.90
--
Parasail
Gemma 4 26B A4B
262k
Open
--
52
1.52
11.16
--
GMI
Gemma 4 26B A4B (FP8)
1.05M
Open
--
--
--
--
--
SiliconFlow
Gemma 4 26B A4B (FP8)
262k
Open
--
104
2.19
7.02
--
Clarifai
Gemma 4 26B A4B
256k
Open
--
--
--
--
--
Scaleway
Gemma 4 26B A4B
262k
Open
--
140
1.06
4.62
--
DeepInfra
Gemma 4 26B A4B (FP8)
262k
Open
--
32
0.74
16.17
--
Novita
Gemma 4 26B A4B
262k
Open
--
28
1.03
19.20
--
DeepInfra
Qwen3.5 4B (FP8)
262k
Open
--
24
0.84
103.90
82.44
Cohere
North Mini Code
256k
Open
20
$0.00
27
0.49
93.47
74.38
Amazon Bedrock
Nova 2.0 Pro Preview (low)
256k
Proprietary
--
129
11.16
30.50
15.48
Mistral
![]()
Mistral Small 4
256k
Open
20
$0.10
179
0.75
14.73
11.19
Mistral
![]()
Devstral 2
262k
Open
19
$0.00
47
1.47
12.20
--
Amazon Bedrock
Nova 2.0 Lite (medium)
1M
Proprietary
--
188
17.68
30.96
10.62
Alibaba Cloud
Qwen3.5 Omni Flash
256k
Proprietary
--
246
1.81
3.84
--
Arcee AI
Trinity Large Thinking
262k
Open
19
$0.20
205
1.20
13.41
9.77
Parasail
Trinity Large Thinking (FP8)
262k
Open
19
$0.08
183
0.61
14.25
10.91
Amazon Bedrock
Nova 2.0 Lite (low)
1M
Proprietary
--
170
8.91
23.62
11.77
Mistral
![]()
Devstral Small 2
256k
Open
18
$0.00
141
2.22
5.78
--
GMI
Qwen3 Next 80B A3B
262k
Open
17
$0.05
--
--
--
--
Google
Qwen3 Next 80B A3B Vertex
262k
Open
17
$0.04
165
0.70
15.89
12.15
Alibaba Cloud
Qwen3 Next 80B A3B
262k
Open
17
$0.04
203
2.23
14.56
9.86
Nebius
Qwen3 Next 80B A3B (FP8)
262k
Open
17
$0.04
96
1.17
27.29
20.90
Hyperbolic
Qwen3 Next 80B A3B
262k
Open
17
$0.03
--
--
--
--
Amazon Bedrock
Nova 2.0 Omni (low)
1M
Proprietary
--
--
--
--
--
AI9Stars
G9v3-3B
131k
Open
--
--
--
--
--
DeepInfra
Qwen3.5 4B FP8
262k
Open
--
17
0.94
30.94
--
Amazon Bedrock
![]()
Mistral Large 3
256k
Open
16
$0.08
166
1.20
4.21
--
Microsoft Azure
![]()
Mistral Large 3
256k
Open
16
$0.08
75
1.69
8.36
--
Mistral
![]()
Mistral Large 3
262k
Open
16
$0.08
45
1.18
12.21
--
CoreWeave
gpt-oss-20b (high)
131k
Open
15
$0.01
91
0.90
28.25
21.87
Amazon Bedrock
gpt-oss-20b (high)
131k
Open
15
$0.03
188
39.08
52.36
10.62
DeepInfra
gpt-oss-20b (high)
131k
Open
15
$0.01
95
0.44
26.63
20.95
Hyperbolic
gpt-oss-20b (high)
131k
Open
15
$0.04
--
--
--
--
Lightning AI
gpt-oss-20b (high)
128k
Open
15
$0.02
--
--
--
--
Cloudflare
gpt-oss-20b (high)
128k
Open
15
$0.08
--
--
--
--
Novita
gpt-oss-20b (high)
131k
Open
15
$0.02
118
1.18
22.30
16.89
Google
gpt-oss-20b (high) Vertex
131k
Open
15
$0.03
145
15.64
32.93
13.83
Groq
gpt-oss-20b (high)
131k
Open
15
$0.03
958
0.83
3.44
2.09
Clarifai
gpt-oss-20b (high)
131k
Open
15
$0.02
--
--
--
--
Clarifai
Nemotron 3 Nano Omni 30B A3B
262k
Open
--
--
--
--
--
Nebius
Nemotron 3 Nano Omni 30B A3B (FP8)
65.5k
Open
--
323
1.02
8.76
6.19
Snowflake
gpt-oss-120b (low)
131k
Open
15
$0.03
--
--
--
--
Hyperbolic
gpt-oss-120b (low)
131k
Open
15
$0.04
--
--
--
--
Nebius
gpt-oss-120b (low) Base
128k
Open
15
$0.02
324
1.00
8.72
6.18
SambaNova
gpt-oss-120b (low)
131k
Open
15
$0.03
727
0.89
4.33
2.75
Google
gpt-oss-120b (low) Vertex
131k
Open
15
$0.01
124
0.82
20.99
16.13
CoreWeave
gpt-oss-120b (low)
131k
Open
15
$0.0042
43
1.41
60.23
47.05
Cerebras
gpt-oss-120b (low)
131k
Open
15
$0.05
1,604
0.50
2.06
1.25
Microsoft Azure
gpt-oss-120b (low)
131k
Open
15
$0.02
337
0.72
8.13
5.93
Cloudflare
gpt-oss-120b (low)
128k
Open
15
$0.05
--
--
--
--
Baseten
gpt-oss-120b (low)
128k
Open
15
$0.01
360
0.23
7.17
5.55
Amazon Bedrock
gpt-oss-120b (low)
131k
Open
15
$0.02
89
1.10
29.11
22.41
Parasail
gpt-oss-120b (low)
131k
Open
15
--
147
0.75
17.71
13.57
Together AI
gpt-oss-120b (low)
131k
Open
15
$0.02
134
0.62
19.30
14.94
Groq
gpt-oss-120b (low)
131k
Open
15
$0.02
476
0.70
5.95
4.20
Clarifai
gpt-oss-120b (low)
131k
Open
15
$0.01
--
--
--
--
Novita
gpt-oss-120b (low)
131k
Open
15
$0.01
105
0.98
24.77
19.03
Nebius
Nemotron 3 Nano
262k
Open
15
$0.03
312
1.11
9.12
6.41
Novita
Nemotron 3 Nano (FP4)
262k
Open
15
$0.02
283
0.97
9.81
7.07
DeepInfra
Nemotron 3 Nano
262k
Open
15
$0.02
224
3.17
14.34
8.94
Upstage
Solar Pro 3
131k
Proprietary
14
$0.15
144
2.30
19.69
13.91
Novita
Llama 4 Maverick (FP8)
1.05M
Open
14
$0.04
78
0.78
7.22
--
Microsoft Azure
Llama 4 Maverick (FP8)
128k
Open
14
$0.03
530
1.10
2.04
--
Amazon Bedrock
Llama 4 Maverick
128k
Open
14
$0.03
222
0.81
3.06
--
Together AI
Llama 4 Maverick
1.05M
Open
14
$0.04
--
--
--
--
DeepInfra
Llama 4 Maverick (FP8)
1.05M
Open
14
$0.03
74
0.50
7.30
--
Parasail
Llama 4 Maverick (FP8)
1.05M
Open
14
$0.03
99
1.10
6.18
--
Amazon Bedrock
Nova 2.0 Pro Preview
256k
Proprietary
--
115
1.07
5.41
--
Clarifai
gpt-oss-20b (low)
131k
Open
--
--
--
--
--
Groq
gpt-oss-20b (low)
131k
Open
--
942
0.79
3.44
2.12
Lightning AI
gpt-oss-20b (low)
128k
Open
--
--
--
--
--
Hyperbolic
gpt-oss-20b (low)
131k
Open
--
--
--
--
--
CoreWeave
gpt-oss-20b (low)
131k
Open
--
98
0.92
26.32
20.32
Cloudflare
gpt-oss-20b (low)
128k
Open
--
--
--
--
--
Amazon Bedrock
gpt-oss-20b (low)
131k
Open
--
69
19.69
56.17
29.18
Novita
gpt-oss-20b (low)
131k
Open
--
132
1.11
20.00
15.11
Google
gpt-oss-20b (low) Vertex
131k
Open
--
96
13.16
39.14
20.78
Hyperbolic
Qwen3 Next 80B A3B
262k
Open
--
--
--
--
--
Google
Qwen3 Next 80B A3B Vertex
262k
Open
--
131
0.66
4.47
--
GMI
Qwen3 Next 80B A3B
262k
Open
--
181
2.19
4.94
--
DeepInfra
Qwen3 Next 80B A3B
262k
Open
--
145
0.62
4.07
--
Parasail
Qwen3 Next 80B A3B
262k
Open
--
123
1.31
5.37
--
Novita
Qwen3 Next 80B A3B
131k
Open
--
188
1.55
4.20
--
Alibaba Cloud
Qwen3 Next 80B A3B
131k
Open
--
189
2.13
4.77
--
SiliconFlow
Gemma 4 12B (Non-reasoning)
262k
Open
--
114
2.30
6.67
--
Amazon Bedrock
Nova Premier
1M
Proprietary
--
33
2.90
17.95
--
DeepInfra
Llama Nemotron Super 49B v1.5
131k
Open
--
102
8.51
33.06
19.65
Celeris
Celeris-1
131k
Proprietary
12
$0.26
1,541
0.58
0.91
--
Mistral
![]()
Mistral Small 4
262k
Open
--
169
0.79
3.74
--
DeepInfra
Gemma 4 E4B
262k
Open
--
46
0.77
54.59
43.05
Sarvam
Sarvam 105B (high)
128k
Open
--
--
--
--
--
Amazon Bedrock
Nova 2.0 Lite
1M
Proprietary
--
181
1.01
3.77
--
Amazon Bedrock
![]()
Magistral Small 1.2
128k
Open
11
$0.30
90
1.55
29.29
22.19
Mistral
![]()
Ministral 3 14B
262k
Open
11
$0.16
99
0.93
5.99
--
Amazon Bedrock
![]()
Ministral 3 14B
256k
Open
11
$0.16
237
0.99
3.09
--
Liquid AI
LFM2.5-2.6B
32.8k
Open
11
$0.00
--
--
--
--
Amazon Bedrock
Nova 2.0 Omni
1M
Proprietary
--
--
--
--
--
DeepInfra
Llama 4 Scout
328k
Open
10
$0.01
58
0.66
9.22
--
Microsoft Azure
Llama 4 Scout
128k
Open
10
$0.01
133
0.81
4.56
--
Google
Llama 4 Scout Vertex
1.31M
Open
10
$0.01
155
0.68
3.90
--
Cloudflare
Llama 4 Scout
131k
Open
10
$0.02
--
--
--
--
Amazon Bedrock
Llama 4 Scout
128k
Open
10
$0.01
183
0.80
3.54
--
Novita
Llama 4 Scout
131k
Open
10
$0.01
62
0.82
8.91
--
Groq
Llama 4 Scout
131k
Open
10
$0.01
451
0.72
1.83
--
Nebius
![]()
Hermes 4 70B (FP8)
128k
Open
--
87
1.42
30.23
23.05
Alibaba Cloud
Qwen3 Omni 30B A3B
65.5k
Open
--
101
1.90
26.77
19.90
Fireworks
Llama 3.3 70B
131k
Open
--
--
--
--
--
Google
Llama 3.3 70B Vertex
128k
Open
--
150
0.67
3.99
--
Groq
Llama 3.3 70B
131k
Open
--
315
0.84
2.43
--
Novita
Llama 3.3 70B
131k
Open
--
43
1.75
13.49
--
Parasail
Llama 3.3 70B (FP8)
131k
Open
--
80
2.53
8.80
--
SambaNova
Llama 3.3 70B
128k
Open
--
295
1.81
3.51
--
Nebius
Llama 3.3 70B Base
128k
Open
--
8
2.50
67.57
--
CoreWeave
Llama 3.3 70B
128k
Open
--
80
0.88
7.10
--
Together AI
Llama 3.3 70B Turbo
131k
Open
--
72
1.41
8.33
--
Microsoft Azure
Llama 3.3 70B
128k
Open
--
115
2.12
6.45
--
DeepInfra
Llama 3.3 70B (Turbo, FP8)
131k
Open
--
18
2.31
29.47
--
Cloudflare
Llama 3.3 70B
24k
Open
--
--
--
--
--
Amazon Bedrock
Llama 3.3 70B
128k
Open
--
152
1.13
4.41
--
Scaleway
Llama 3.3 70B
100k
Open
--
88
1.29
6.99
--
Amazon Bedrock
![]()
Ministral 3 8B
256k
Open
9
$0.18
251
1.01
3.01
--
Mistral
![]()
Ministral 3 8B
262k
Open
9
$0.18
123
0.83
4.89
--
Nebius
Llama Nemotron Ultra Base
131k
Open
--
52
2.40
50.05
38.12
SiliconFlow
ERNIE 4.5 300B A47B
131k
Open
--
--
--
--
--
Nebius
![]()
Hermes 4 405B (FP8)
128k
Open
--
35
2.76
74.82
57.65
DeepInfra
NVIDIA Nemotron Nano 12B v2 VL (FP8)
131k
Open
--
133
4.31
23.10
15.04
DeepInfra
Gemma 4 E4B
262k
Open
--
47
0.73
11.36
--
DeepInfra
NVIDIA Nemotron Nano 9B V2
131k
Open
--
214
2.93
14.60
9.33
Nebius
![]()
Hermes 4 405B (FP8)
128k
Open
--
34
2.45
16.95
--
DeepInfra
Llama Nemotron Super 49B v1.5
131k
Open
--
77
6.36
12.84
--
Liquid AI
LFM2.5-8B-A1B
32.8k
Open
--
338
1.82
9.21
5.91
SiliconFlow
![]()
Ring-flash-2.0
131k
Open
--
--
--
--
--
Parasail
Olmo 3.1 32B Think
65.5k
Open
--
--
--
--
--
Cohere
Command A
288k
Open
--
74
1.58
8.32
--
Microsoft Azure
Command A
256k
Open
--
43
2.98
14.54
--
DeepInfra
Llama 3.1 Nemotron 70B
131k
Open
--
100
3.86
8.88
--
Novita
Nemotron 3 Nano (FP4)
262k
Open
--
307
0.97
2.60
--
DeepInfra
Nemotron 3 Nano
262k
Open
--
229
0.58
2.76
--
DeepInfra
NVIDIA Nemotron Nano 9B V2
131k
Open
--
218
3.67
5.96
--
Amazon Bedrock
NVIDIA Nemotron Nano 9B V2
131k
Open
--
168
1.12
4.09
--
Amazon Bedrock
![]()
Ministral 3 3B
256k
Open
7
$0.13
409
0.93
2.15
--
Mistral
![]()
Ministral 3 3B
131k
Open
7
$0.13
208
0.60
3.01
--
Nebius
![]()
Hermes 4 70B (FP8)
128k
Open
--
85
1.40
7.27
--
CoreWeave
Granite 4.1 8B
131k
Open
--
124
0.75
4.78
--
Sarvam
Sarvam 30B (high)
64k
Open
--
--
--
--
--
Microsoft Azure
Phi-4 Mini
128k
Open
--
43
0.82
12.43
--
Replicate
Granite 4.0 H Small
128k
Open
--
14
37.45
74.38
--
Alibaba Cloud
Qwen3 Omni 30B A3B
65.5k
Open
--
95
1.85
7.13
--
Microsoft Azure
Phi-4
16.4k
Open
--
42
2.45
14.35
--
DeepInfra
Phi-4
16.4k
Open
--
74
0.87
7.67
--
Amazon Bedrock
Nova Micro
130k
Proprietary
--
281
0.86
2.64
--
Amazon Bedrock
NVIDIA Nemotron Nano 12B v2 VL
128k
Open
--
179
1.16
3.95
--
DeepInfra
NVIDIA Nemotron Nano 12B v2 VL (FP8)
131k
Open
--
129
6.26
10.12
--
Microsoft Azure
Phi-4 Multimodal
128k
Open
--
18
0.82
29.23
--
Reka AI
Reka Flash 3
54k
Open
--
--
--
--
--
DeepInfra
Llama 3.2 11B (Vision)
131k
Open
--
65
1.03
8.78
--
Parasail
Olmo 3 7B
65.5k
Open
--
--
--
--
--
Public AI
![]()
Apertus 70B Instruct
64k
Open
--
--
--
--
--
Liquid AI
LFM2.5-VL-1.6B
32.8k
Open
--
352
1.20
2.62
--
Cohere
Tiny Aya Global
8.19k
Open
--
--
--
--
--
Public AI
![]()
Apertus 8B Instruct
64k
Open
--
--
--
--
--
Anthropic
Claude Sonnet 5 (low)
1M
Proprietary
--
--
64
2.31
10.18
--
Anthropic
Claude Sonnet 5 (xhigh)
1M
Proprietary
--
--
72
28.11
35.10
--
Anthropic
Claude Sonnet 5 (high)
1M
Proprietary
--
--
71
14.63
21.69
--
Together AI
![]()
Cogito v2.1
164k
Open
--
--
--
--
--
--
Anthropic
Claude Sonnet 5 (medium)
1M
Proprietary
--
--
68
2.84
10.20
--