Speed & Latency

Output speed (tokens per second) and latency (time to first token) benchmarks across models and providers.

Quick filters
EU Providers
Creators

Speed vs Intelligence

EUGlobal
Axes stay fixed while filtering · Drag to zoom · Click to pin
45 selected of 45 chartable models. Axes stay fixed for comparison.
111 models
#
1
Gemini 3.5 Flash-LiteGlobal
Google-334.8 t/s6.44s
22.2
$0.85
2
Ministral 3 3BOpenGlobal
Mistral-238.9 t/s0.52s
4.8
$0.10
3
Gemini 3.8 FlashRGlobal
Google-238.1 t/s11.91s
40.9
$1.50
4
DeepSeek V4 Flash VisionRGlobal
DeepSeek-227.5 t/s0.79s
34.8
$0.66
5
DeepSeek V4.1 FlashROpenGlobal
DeepSeek-217.6 t/s0.79s
39.5
$0.53
6
GPT-OSS 120BOpenEU
OpenAINebius214.9 t/s0.56s
11.6
$0.26
7
Nova 2 LiteREU
AmazonBedrock208.5 t/s13.83s
13.4
$0.85
8
Muse Spark 1.3RGlobal
Meta-189.5 t/s19.26s
48.1
$2.00
9
Mistral Small 4ROpenGlobal
Mistral-174.1 t/s0.54s
11.3
$0.15
10
o3REU
OpenAIAzure170.5 t/s4.62s
20.2
$3.50
11
Mistral Medium 3.5Global
Mistral-168 t/s0.61s
14.2
$3.00
12
Ling 3.0 Flash FinROpenGlobal
InclusionAI-166.7 t/s1.41s
22.6
$0.11
13
Nemotron 3 SuperROpenGlobal
NVIDIA-165.3 t/s0.81s
12.8
$0.45
14
Ling 3.0 Flash VLROpenGlobal
InclusionAI-149.2 t/s1.24s
24.6
$0.11
15
Claude Sonnet 5.5RGlobal
Anthropic-145.1 t/s347.54s
56
$4.00
16
GPT-6 LunaRGlobal
OpenAI-143.3 t/s68.01s
37.3
$0.20
17
MiniMax M3REU
MiniMaxTensorix137.6 t/s0.91s
29.2
$0.80
18
Gemini 3.1 ProRGlobal
Google-131.4 t/s20.31s
29.7
$4.50
19
GPT-5.3 CodexRGlobal
OpenAI-113.8 t/s37.74s
32.5
$4.81
20
GPT-5.6 TerraRGlobal
OpenAI-109 t/s82.01s
42.1
$4.50
21
Llama 4 MaverickOpenGlobal
Meta-105.5 t/s0.58s
10
$0.42
22
Ministral 3 8BOpenGlobal
Mistral-104.6 t/s0.46s
5.5
$0.15
23
Claude Haiku 4.5REU
AnthropicBedrock104.4 t/s13.41s
16.9
$2.00
24
Claude Opus 5.5RGlobal
Anthropic-95.8 t/s486.44s
57.6
$8.00
25
Llama 3.3 70BOpenGlobal
Meta-95.2 t/s0.63s
7.7
$0.71
26
Ministral 3 14BOpenGlobal
Mistral-91.3 t/s0.52s
6
$0.20
27
DeepSeek V4 ProREU
DeepSeekTensorix89.4 t/s1.15s
36
$2.19
28
Qwen3.5 397BROpenGlobal
Alibaba-89.3 t/s1.68s
18.4
$1.35
29
GPT-6 SolRGlobal
OpenAI-84.3 t/s108.52s
47.5
$4.00
30
Claude Sonnet 5RGlobal
Anthropic-84.2 t/s127.30s
38.2
$4.00
31
Step 5 PreviewRGlobal
StepFun-84.1 t/s1.94s
43.7
$1.43
32
Mistral Large 3OpenGlobal
Mistral-77.6 t/s0.78s
9.3
$0.75
33
Grok 4.6RGlobal
xAI-74.9 t/s24.04s
44.3
$3.00
34
GLM-5.3RGlobal
Z AI-74.8 t/s2.75s
44.8
$2.15
35
Grok 4.7RGlobal
xAI-72.3 t/s19.84s
46.4
$3.00
36
Claude Fable 5.1RGlobal
Anthropic-68.9 t/s119.53s
53.4
$20.00
37
GPT-6 AstraRGlobal
OpenAI-61.7 t/s190.62s
52.7
$20.00
38
Qwen3.8 Flash NextROpenGlobal
Alibaba-52.9 t/s1.53s
39.8
$0.23
39
GLM-5.3 FlashROpenGlobal
Z AI-48.2 t/s2.91s
41.8
$0.24
40
MiMo V2.6 FlashROpenGlobal
Xiaomi-46.3 t/s3.99s
37.9
$0.17
41
Qwen3.8 27BROpenEU
AlibabaHetzner46.1 t/s1.25s
33.7
$1.13
42
MiMo V2.6 ProROpenGlobal
Xiaomi-44.3 t/s2.94s
46.3
$0.54
43
Hermes 4 405BROpenEU
NousResearchNebius44.1 t/s0.72s
7.5
$1.50
44
Qwen3.8 2.4T A95BROpenGlobal
Alibaba-38.4 t/s1.99s
39.9
$3.00
45
Qwen3.8 MaxRGlobal
Alibaba-38.3 t/s1.96s
45.4
$3.00
46
GPT-5.1REU
OpenAIAzure--
24.7
$3.44
47
GPT-5REU
OpenAIAzure--
23
$3.44
48
GPT-5 MiniREU
OpenAIAzure--
16.8
$0.69
49
GPT-5 NanoREU
OpenAIAzure--
13
$0.14
50
o4-miniREU
OpenAIAzure--
16.7
$1.93
51
o3-miniREU
OpenAIAzure--
11
$1.93
52
o1REU
OpenAIAzure--
15.2
$26.25
53
GPT-4.1EU
OpenAIAzure--
12.7
$3.50
54
GPT-4.1 MiniEU
OpenAIAzure--
10.2
$0.70
55
GPT-4.1 NanoEU
OpenAIAzure--
7.8
$0.17
56
GPT-4oEU
OpenAIAzure--
8.4
$4.38
57
GPT-4o MiniEU
OpenAIAzure--
6.7
$0.26
58
Gemini 2.5 ProREU
GoogleGoogle Cloud--
16.1
$3.44
59
Gemini 2.5 FlashREU
GoogleGoogle Cloud--
13.1
$0.85
60
Gemini 2.5 Flash-LiteEU
GoogleGoogle Cloud--
8.5
$0.17
61
Claude Opus 4.6REU
AnthropicBedrock--
31.9
$10.00
62
Claude Sonnet 4.6REU
AnthropicBedrock--
30.1
$6.00
63
Claude Opus 4.5REU
AnthropicBedrock--
29.1
$10.00
64
Claude Sonnet 4.5REU
AnthropicBedrock--
20.7
$6.00
65
Claude Sonnet 4REU
AnthropicBedrock--
18.9
$0.00
66
Claude 3.7 SonnetREU
AnthropicBedrock--
17.7
$6.00
67
Claude Opus 4.7REU
AnthropicBedrock--
40.7
$10.00
68
Claude Opus 4.8REU
AnthropicBedrock--
41.8
$10.00
69
MiniMax M2.1REU
MiniMaxNebius--
20.9
$0.53
70
Hermes 4 70BROpenEU
NousResearchNebius--
7.9
$0.00
71
Qwen3 235BROpenEU
AlibabaNebius--
9.5
$2.63
72
DeepSeek V4 FlashREU
DeepSeekTensorix--
34.3
$0.19
73
GLM-5.2REU
Z AITensorix--
33.7
$2.25
74
Kimi K2.7 CodeREU
KimiTensorix--
25.8
$2.06
75
Claude Opus 5RGlobal
Anthropic---
50.8
$10.00
76
Kimi K3RGlobal
Kimi---
43.6
$6.00
77
GPT-5.6 SolRGlobal
OpenAI---
47
$8.00
78
GPT-5.6 LunaRGlobal
OpenAI---
37.3
$0.45
79
Claude Fable 5RGlobal
Anthropic---
49.6
$20.00
80
Grok 4.5RGlobal
xAI---
38.8
$3.00
81
Gemini 3 ProRGlobal
Google---
28
$4.50
82
Gemini 3 FlashRGlobal
Google---
26.3
$1.13
83
GPT-5.4RGlobal
OpenAI---
39
$5.63
84
GPT-5.4 MiniRGlobal
OpenAI---
24.1
$1.69
85
GPT-5.4 NanoRGlobal
OpenAI---
20.7
$0.46
86
GPT-5.2RGlobal
OpenAI---
30.4
$4.81
87
Muse SparkRGlobal
Meta---
31.3
$0.00
88
Grok 4.20RGlobal
xAI---
25.7
$1.56
89
Grok 4RGlobal
xAI---
22.5
$6.00
90
DeepSeek V3.2ROpenGlobal
DeepSeek---
21.5
$0.32
91
DeepSeek V3.2 (Non-reasoning)OpenGlobal
DeepSeek---
16
$0.32
92
Qwen3.6 PlusRGlobal
Alibaba---
27
$1.13
93
GLM-5.1RGlobal
Z AI---
26.1
$1.98
94
GLM-5RGlobal
Z AI---
27.9
$1.55
95
MiniMax M2.7RGlobal
MiniMax---
22.8
$0.53
96
MiniMax M2.5RGlobal
MiniMax---
22.8
$0.53
97
MiMo V2 ProROpenGlobal
Xiaomi---
28.6
$0.00
98
Kimi K2.5RGlobal
Kimi---
23.5
$1.20
99
SonarGlobal
Perplexity---
7.7
$1.00
100
Sonar ProGlobal
Perplexity---
7.6
$6.00
101
Sonar Reasoning ProRGlobal
Perplexity---
11.8
$3.50
102
Gemini 3.1 Flash-LiteGlobal
Google---
15.6
$0.56
103
Gemini 3.5 FlashRGlobal
Google---
32.6
$3.38
104
Magistral MediumRGlobal
Mistral---
9.1
$2.75
105
Magistral SmallRGlobal
Mistral---
8.2
$0.75
106
GPT-5.4 ProRGlobal
OpenAI----$67.50
107
GPT-5.5RGlobal
OpenAI---
38.4
$11.25
108
GPT-5.5 ProRGlobal
OpenAI----$67.50
109
Grok 3Global
xAI---
12.1
$8.00
110
Grok 3 MiniRGlobal
xAI---
14.6
$0.35
111
Grok 4.3RGlobal
xAI---
24.9
$1.56