Speed & Latency

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

Filters:
Provider:
Creators:

Speed vs Intelligence

EUGlobal
Drag to zoom ยท Click to pin
69 models
#
Model
Creator
Output Speed (t/s)โ†“
Latency TTFT (s)
Total Response (s)
Intelligence
Price $/1M
1
GPT-OSS 120BOpenEU
OpenAI362.9 t/s0.52s-
33.3
$0.26
2
Gemini 2.5 Flash-LiteEU
Google311.4 t/s22.36s-
17.6
$0.17
3
Gemini 3.1 Flash-LiteGlobal
Google296.3 t/s5.38s-
33.5
$0.56
4
o3-miniREU
OpenAI212.4 t/s20.09s-
25.2
$1.93
5
Gemini 2.5 FlashREU
Google212.3 t/s10.21s-
27
$0.85
6
Gemini 3.5 FlashRGlobal
Google212.1 t/s12.39s-
55.3
$3.38
7
MiniMax M2.1REU
MiniMax210.5 t/s2.36s-
39.4
$0.53
8
MiniMax M2.5RGlobal
MiniMax202.4 t/s2.38s-
41.9
$0.53
9
Gemini 3 FlashRGlobal
Google184.5 t/s5.29s-
46.4
$1.13
10
Grok 4.3RGlobal
xAI176.4 t/s21.45s-
53.2
$1.56
11
Mistral Small 4ROpenGlobal
Mistral176.2 t/s0.50s-
27.8
$0.26
12
Grok 4.20RGlobal
xAI170.6 t/s15.73s-
49.3
$3.00
13
GPT-5 NanoREU
OpenAI168.8 t/s88.92s-
26.8
$0.14
14
GPT-5.4 NanoRGlobal
OpenAI161.3 t/s3.48s-
44
$0.46
15
GPT-5.4 MiniRGlobal
OpenAI158.7 t/s4.17s-
48.9
$1.69
16
o4-miniREU
OpenAI153.9 t/s17.65s-
33.1
$1.93
17
Nemotron 3 SuperROpenGlobal
NVIDIA150.2 t/s1.08s-
36
$0.41
18
GPT-4oEU
OpenAI142.1 t/s0.50s-
17.3
$4.38
19
Nova 2 LiteREU
Amazon139.7 t/s17.29s-
34.5
$0.85
20
Claude Haiku 4.5REU
Anthropic135.4 t/s11.09s-
37.1
$2.19
21
GPT-4.1EU
OpenAI128.7 t/s0.55s-
26.3
$3.50
22
Gemini 2.5 ProREU
Google123.6 t/s19.28s-
34.6
$3.44
23
Gemini 3.1 ProRGlobal
Google123.3 t/s20.05s-
57.2
$4.50
24
Mistral Medium 3.5Global
Mistral120.6 t/s0.75s-
39.2
$3.00
25
GPT-5.1REU
OpenAI118.6 t/s29.12s-
47.7
$3.44
26
DeepSeek V4 FlashREU
DeepSeek118.6 t/s0.88s-
46.5
$0.17
27
o1REU
OpenAI116.3 t/s15.39s-
30.7
$26.25
28
GPT-4.1 NanoEU
OpenAI114.4 t/s0.42s-
13
$0.17
29
Llama 4 MaverickOpenGlobal
Meta113.7 t/s0.61s-
18.4
$0.47
30
o3REU
OpenAI106.5 t/s6.69s-
38.4
$3.50
31
GPT-5REU
OpenAI105.4 t/s84.61s-
44.6
$3.44
32
Llama 3.3 70BOpenGlobal
Meta92.3 t/s0.64s-
14.5
$0.61
33
GPT-5 MiniREU
OpenAI89.9 t/s78.72s-
41.2
$0.69
34
GPT-4.1 MiniEU
OpenAI89.2 t/s0.50s-
22.9
$0.70
35
Hermes 4 70BROpenEU
NousResearch87.4 t/s0.64s-
16
$0.20
36
GLM-5RGlobal
Z AI81.4 t/s0.82s-
49.8
$1.55
37
GPT-5.4RGlobal
OpenAI80.3 t/s195.49s-
56.8
$5.63
38
GPT-5.2RGlobal
OpenAI71 t/s89.53s-
51.3
$4.81
39
GPT-5.3 CodexRGlobal
OpenAI70.6 t/s64.99s-
53.6
$4.81
40
GPT-4o MiniEU
OpenAI69.8 t/s0.57s-
12.6
$0.26
41
MiniMax M2.7RGlobal
MiniMax66.6 t/s2.94s-
49.6
$0.53
42
Claude Sonnet 4.6REU
Anthropic64.3 t/s67.87s-
51.7
$6.56
43
Grok 3 MiniRGlobal
xAI63.9 t/s0.61s-
32.1
$0.35
44
Qwen3 235BROpenEU
Alibaba61.7 t/s1.24s-
19.8
$2.63
45
GPT-5.5RGlobal
OpenAI61.7 t/s70.44s-
60.2
$11.25
46
Mistral Large 3OpenGlobal
Mistral60.6 t/s0.57s-
22.8
$0.75
47
Claude Opus 4.8REU
Anthropic57.5 t/s25.68s-
61.4
$10.94
48
Claude Opus 4.5REU
Anthropic54.3 t/s12.51s-
49.7
$10.94
49
Qwen3.6 PlusRGlobal
Alibaba52.7 t/s1.84s-
50
$1.13
50
Claude Opus 4.7REU
Anthropic52.1 t/s15.94s-
57.3
$10.94
51
Qwen3.5 397BROpenGlobal
Alibaba51.5 t/s1.81s-
45
$1.35
52
GLM-5.1RGlobal
Z AI50.8 t/s1.01s-
51.4
$2.15
53
Claude Opus 4.6REU
Anthropic49.1 t/s13.49s-
52.9
$10.94
54
Claude Sonnet 4.5REU
Anthropic48.9 t/s9.16s-
43
$6.56
55
DeepSeek V4 ProREU
DeepSeek48.2 t/s1.18s-
51.5
$0.54
56
Claude Sonnet 4REU
Anthropic46.7 t/s9.60s-
38.7
$6.56
57
MiMo V2 ProROpenGlobal
Xiaomi42.5 t/s2.65s-
49.2
$1.50
58
Hermes 4 405BROpenEU
NousResearch41.1 t/s0.77s-
18.6
$1.50
59
Kimi K2.5RGlobal
Kimi33.3 t/s1.32s-
46.8
$1.19
60
Gemini 3 ProRGlobal
Google---
48.4
$4.50
61
Muse SparkRGlobal
Meta---
52.2
$0.00
62
Grok 4RGlobal
xAI---
41.5
$11.00
63
DeepSeek V3.2ROpenGlobal
DeepSeek---
41.7
$0.34
64
DeepSeek V3.2 (Non-reasoning)OpenGlobal
DeepSeek---
32.1
$0.78
65
Magistral MediumRGlobal
Mistral---
18.8
$1.00
66
Magistral SmallRGlobal
Mistral---
16.8
$0.50
67
GPT-5.4 ProRGlobal
OpenAI----$67.50
68
GPT-5.5 ProRGlobal
OpenAI----$0.00
69
Grok 3Global
xAI---
25.2
$8.00