Menu

logo
Artificial Analysis
HOME
logo

Nebius: Models Intelligence, Performance & Price

Analysis of Nebius's models across key metrics including quality, price, output speed, latency, context window & more. This analysis is intended to support you in choosing the best model provided by Nebius for your use-case. For more details including relating to our methodology, see our FAQs. Models analyzed: Llama 3.3 70B Fast, Llama 3.3 70B Base, Llama 3.1 405B Base, Llama 3.1 70B Base, Llama 3.1 70B Fast, Llama 3.1 8B Fast, Llama 3.1 8B Base, Llama 3.2 3B Base, Llama 3.2 1B Base, Gemma 2 27B Fast, Gemma 2 27B Base, Gemma 2 9B Fast, Gemma 2 9B Base, Mixtral 8x22B Base, Mixtral 8x22B Fast, Mistral NeMo Fast, Mistral NeMo Base, Mixtral 8x7B Fast, Mixtral 8x7B Base, DeepSeek R1 Base, DeepSeek R1 Fast, DeepSeek R1 Distill Llama 70B Base, DeepSeek V3 (Mar' 25) Fast, DeepSeek V3 (Mar' 25), DeepSeek Coder V2 Lite Fast, FP8, DeepSeek Coder V2 Lite Base, FP8, Phi-4, Llama 3.1 Nemotron 70B Base, Llama 3.1 Nemotron 70B Fast, Qwen2.5 72B, Qwen2.5 72B Fast, Qwen2.5 Coder 7B Fast, Qwen2.5 Coder 7B Base, QwQ-32B Base, Qwen2.5 Instruct 32B Fast, Qwen2.5 Instruct 32B Base, DeepSeek V3 (Dec '24), and QwQ 32B-Preview.
Link:

Nebius Model Comparison Summary

Intelligence:DeepSeek R1 Base logo DeepSeek R1 Base and DeepSeek R1 Fast logo DeepSeek R1 Fast are the highest quality models offered by Nebius, followed by QwQ-32B Base logo QwQ-32B Base, DeepSeek V3 (Mar' 25) Fast logo DeepSeek V3 (Mar' 25) Fast & DeepSeek V3 (Mar' 25) logo DeepSeek V3 (Mar' 25).Output Speed (tokens/s):Llama 3.2 1B Base logo Llama 3.2 1B Base (270 t/s) and Qwen2.5 Coder 7B  Fast logo Qwen2.5 Coder 7B Fast (222 t/s) are the fastest models offered by Nebius, followed by Qwen2.5 Coder 7B  Base logo Qwen2.5 Coder 7B Base, Llama 3.1 8B Fast logo Llama 3.1 8B Fast & Gemma 2 9B Fast logo Gemma 2 9B Fast.Latency (seconds):Llama 3.2 1B Base logo Llama 3.2 1B Base (0.46s) and  Gemma 2 9B Fast logo Gemma 2 9B Fast (0.49s) are the lowest latency models offered by Nebius, followed by Qwen2.5 Coder 7B  Fast logo Qwen2.5 Coder 7B Fast, Llama 3.2 3B Base logo Llama 3.2 3B Base & Mistral NeMo Fast logo Mistral NeMo Fast.Blended Price ($/M tokens):Llama 3.2 1B Base logo Llama 3.2 1B Base ($0.01) and Llama 3.2 3B Base logo Llama 3.2 3B Base ($0.01) are the cheapest models offered by Nebius, followed by Qwen2.5 Coder 7B  Base logo Qwen2.5 Coder 7B Base, Llama 3.1 8B Base logo Llama 3.1 8B Base & Gemma 2 9B Base logo Gemma 2 9B Base.Context Window Size:Qwen2.5 72B logo Qwen2.5 72B (131k) and Qwen2.5 72B Fast logo Qwen2.5 72B Fast (131k) are the largest context window models offered by Nebius, followed by Qwen2.5 Coder 7B  Fast logo Qwen2.5 Coder 7B Fast, Qwen2.5 Coder 7B  Base logo Qwen2.5 Coder 7B Base & QwQ-32B Base logo QwQ-32B Base.

Highlights

Intelligence
Artificial Analysis Intelligence Index; Higher is better
Speed
Output Tokens per Second; Higher is better
Price
USD per 1M Tokens; Lower is better
Parallel Queries:
Prompt Length:
Features
Model Intelligence
Price
Output tokens/s
Latency
End-to-End Response Time
Further
Analysis
Nebius Base logo
DeepSeek logo
DeepSeek R1 Base
128k
60
$1.20
27.1
0.65
105.90
86.76
Nebius Fast logo
DeepSeek logo
DeepSeek R1 Fast
128k
60
$3.00
57.4
0.68
50.28
40.89
Nebius Base logo
Alibaba logo
QwQ-32B Base
131k
58
$0.23
25.7
0.62
116.96
96.90
Nebius Fast logo
DeepSeek logo
DeepSeek V3 (Mar' 25) Fast
128k
53
$3.00
88.5
0.65
6.31
N/A
Nebius logo
DeepSeek logo
DeepSeek V3 (Mar' 25)
128k
53
$0.75
30.0
0.69
17.33
N/A
Nebius Base logo
DeepSeek logo
DeepSeek R1 Distill Llama 70B Base
128k
48
$0.38
46.0
0.63
54.93
43.44
Nebius logo
DeepSeek logo
DeepSeek V3 (Dec '24)
128k
46
$0.75
19.6
0.68
26.20
N/A
Nebius logo
Alibaba logo
QwQ 32B-Preview
33k
43
$0.14
62.2
0.64
40.87
32.18
Nebius Fast logo
Meta logo
Llama 3.3 70B Fast
128k
41
$0.38
131.2
0.57
4.38
N/A
Nebius Base logo
Meta logo
Llama 3.3 70B Base
128k
41
$0.20
22.5
0.68
22.88
N/A
Nebius Base logo
Meta logo
Llama 3.1 405B Base
128k
40
$1.50
32.0
0.73
16.35
N/A
Nebius logo
Alibaba logo
Qwen2.5 72B
131k
40
$0.20
21.0
0.73
24.50
N/A
Nebius Fast logo
Alibaba logo
Qwen2.5 72B Fast
131k
40
$0.38
65.7
0.57
8.17
N/A
Nebius logo
Microsoft Azure logo
Phi-4
16k
40
$0.15
120.9
0.53
4.67
N/A
Nebius Fast logo
Alibaba logo
Qwen2.5 Instruct 32B Fast
128k
37
$0.20
83.2
0.54
6.54
N/A
Nebius Base logo
Alibaba logo
Qwen2.5 Instruct 32B Base
128k
37
$0.10
60.1
0.60
8.92
N/A
Nebius Base logo
NVIDIA logo
Llama 3.1 Nemotron 70B Base
128k
37
$0.20
40.1
0.68
13.14
N/A
Nebius Fast logo
NVIDIA logo
Llama 3.1 Nemotron 70B Fast
128k
37
$0.38
72.1
0.57
7.51
N/A
Nebius Base logo
Meta logo
Llama 3.1 70B Base
128k
35
$0.20
26.9
0.68
19.28
N/A
Nebius Fast logo
Meta logo
Llama 3.1 70B Fast
128k
35
$0.38
143.8
0.55
4.03
N/A
Nebius Fast logo
Alibaba logo
Qwen2.5 Coder 7B Fast
131k
27
$0.04
222.1
0.50
2.75
N/A
Nebius Base logo
Alibaba logo
Qwen2.5 Coder 7B Base
131k
27
$0.01
203.4
0.51
2.97
N/A
Nebius Base logo
Mistral logo
Mixtral 8x22B Base
65k
26
$0.60
77.7
0.56
7.00
N/A
Nebius Fast logo
Mistral logo
Mixtral 8x22B Fast
65k
26
$1.05
97.1
0.53
5.69
N/A
Nebius Fast logo
Meta logo
Llama 3.1 8B Fast
128k
24
$0.04
179.3
0.51
3.30
N/A
Nebius Base logo
Meta logo
Llama 3.1 8B Base
128k
24
$0.03
66.3
0.51
8.05
N/A
Nebius Fast logo
Google logo
Gemma 2 9B Fast
8k
22
$0.04
169.2
0.49
3.45
N/A
Nebius Base logo
Google logo
Gemma 2 9B Base
8k
22
$0.03
168.4
0.51
3.48
N/A
Nebius Fast logo
Mistral logo
Mistral NeMo Fast
128k
20
$0.12
161.9
0.50
3.59
N/A
Nebius Base logo
Mistral logo
Mistral NeMo Base
128k
20
$0.06
30.3
0.72
17.23
N/A
Nebius Base logo
Meta logo
Llama 3.2 3B Base
128k
20
$0.01
125.1
0.50
4.50
N/A
Nebius Fast logo
Mistral logo
Mixtral 8x7B Fast
33k
17
$0.23
53.4
0.60
9.97
N/A
Nebius Base logo
Mistral logo
Mixtral 8x7B Base
33k
17
$0.12
52.7
0.57
10.06
N/A
Nebius Base logo
Meta logo
Llama 3.2 1B Base
128k
10
$0.01
270.4
0.46
2.31
N/A
Nebius Fast logo
Google logo
Gemma 2 27B Fast
8k
$0.26
86.5
0.53
6.32
N/A
Nebius Base logo
Google logo
Gemma 2 27B Base
8k
$0.15
54.4
0.57
9.76
N/A
Nebius Fast, FP8 logo
DeepSeek logo
DeepSeek Coder V2 Lite Fast, FP8
128k
$0.12
117.6
0.61
4.86
N/A
Nebius Base, FP8 logo
DeepSeek logo
DeepSeek Coder V2 Lite Base, FP8
128k
$0.06
109.4
0.61
5.18
N/A

Key definitions

Context window: Maximum number of combined input & output tokens. Output tokens commonly have a significantly lower limit (varied by model).
Output Speed: Tokens per second received while the model is generating tokens (ie. after first chunk has been received from the API for models which support streaming).
Latency (Time to First Token): Time to first token received, in seconds, after API request sent. For reasoning models which share reasoning tokens, this will be the first reasoning token. For models which do not support streaming, this represents time to receive the completion.
Price: Price per token, represented as USD per million Tokens. Price is a blend of Input & Output token prices (3:1 ratio).
Output Price: Price per token generated by the model (received from the API), represented as USD per million Tokens.
Input Price: Price per token included in the request/message sent to the API, represented as USD per million Tokens.
Time period: Metrics are 'live' and are based on the past 72 hours of measurements, measurements are taken 8 times a day for single requests and 2 times per day for parallel requests.