API host · catalogue checked 27 Oct 2026

Nebius: models, prices and uptime

Nebius serves 10 of the 78 models we benchmark through OpenRouter, 1 of them on no other host. Prices are OpenRouter's list prices per million tokens. We did not measure speed per host.

Models served10of 78 we test

Cheapest host for1of 9 shared models

Median premium+337%over the cheapest host

Uptime100%last 30 min, average

Most accurate models on Nebius

Verification score of each model this host serves

1Muse Spark OpenMeta77.5%
2DeepSeek V4.1 Flash 1017DeepSeek73.8%
3DeepSeek V4 Pro 0813DeepSeek71.2%
4GLM 5.3 FlashZ.ai67.5%
5GLM 5.3Z.ai67.5%
6MiniMax M3.1 FlashMiniMax66.2%
7Kimi K2.7 CodeMoonshotAI65.0%
8gpt-oss-120bOpenAI58.8%
9Nemotron 3.5 Super VLNVIDIA40.0%
10Hermes 4 405BNous26.2%

Models on Nebius

Premium: this host's blended price (3 input : 1 output) against the cheapest host for the same model

Model	Score	Input / 1M	Output / 1M	vs cheapest host	Hosts	Context	Max output	Quantization	Uptime
Muse Spark Open	77.5%	$1.25	$4.25	Cheapest	6	1M	944k	fp4	—
DeepSeek V4.1 Flash 1017	73.8%	$0.3	$1.2	+364%	30	1M	944k	fp8	100%
DeepSeek V4 Pro 0813	71.2%	$1.32	$3.96	+843%	23	979k	881k	fp8	100%
GLM 5.3 Flash	67.5%	$0.15	$0.5	+406%	34	1M	922k	fp4	100%
GLM 5.3	67.5%	$1.4	$4.4	+434%	37	1M	922k	fp4	100%
MiniMax M3.1 Flash	66.2%	$0.15	$0.6	+5%	11	1M	944k	fp4	100%
Kimi K2.7 Code	65.0%	$0.95	$4	+43%	11	262k	236k	fp4	100%
gpt-oss-120b	58.8%	$0.15	$0.6	+337%	23	131k	118k	fp4	100%
Nemotron 3.5 Super VL	40.0%	$0.3	$0.9	+240%	9	1M	944k	bf16	100%
Hermes 4 405B	26.2%	$1	$3	Only host	1	131k	118k	fp8	100%

All API hosts →

Nebius: frequently asked questions

Which AI models does Nebius serve?: Of the models we benchmark, Nebius serves 10 through OpenRouter: Muse Spark Open, DeepSeek V4.1 Flash 1017, DeepSeek V4 Pro 0813, GLM 5.3 Flash, GLM 5.3, MiniMax M3.1 Flash, Kimi K2.7 Code, gpt-oss-120b, Nemotron 3.5 Super VL, Hermes 4 405B.
What is the most accurate model on Nebius?: Muse Spark Open by Meta, with a verification score of 77.5% (62 of 80 questions correct) in our tests.
Is Nebius the cheapest host?: Nebius has the lowest list price for 1 of the 9 models it serves that other hosts also serve (Muse Spark Open). Its median markup over the cheapest host is +337%.
How reliable is Nebius?: Averaged over the models it serves, Nebius reported 100% uptime in the 30 minutes before OpenRouter's catalogue was read for our run.

Model

Score

Input / 1M

Output / 1M

vs cheapest host

Hosts

Context

Max output

Quantization

Uptime

Muse Spark Open

77.5%

$1.25

$4.25

Cheapest

944k

fp4

—

DeepSeek V4.1 Flash 1017

73.8%

$0.3

$1.2

+364%

944k

fp8

100%

DeepSeek V4 Pro 0813

71.2%

$1.32

$3.96

+843%

979k

881k

fp8

100%

GLM 5.3 Flash

67.5%

$0.15

$0.5

+406%

922k

fp4

100%

GLM 5.3

67.5%

$1.4

$4.4

+434%

922k

fp4

100%

MiniMax M3.1 Flash

66.2%

$0.15

$0.6

+5%

944k

fp4

100%

Kimi K2.7 Code

65.0%

$0.95

+43%

262k

236k

fp4

100%

gpt-oss-120b

58.8%

$0.15

$0.6

+337%

131k

118k

fp4

100%

Nemotron 3.5 Super VL

40.0%

$0.3

$0.9

+240%

944k

bf16

100%

Hermes 4 405B

26.2%

Only host

131k

118k

fp8

100%

Nebius: frequently asked questions

Which AI models does Nebius serve?

Of the models we benchmark, Nebius serves 10 through OpenRouter: Muse Spark Open, DeepSeek V4.1 Flash 1017, DeepSeek V4 Pro 0813, GLM 5.3 Flash, GLM 5.3, MiniMax M3.1 Flash, Kimi K2.7 Code, gpt-oss-120b, Nemotron 3.5 Super VL, Hermes 4 405B.

What is the most accurate model on Nebius?

Muse Spark Open by Meta, with a verification score of 77.5% (62 of 80 questions correct) in our tests.

Is Nebius the cheapest host?

Nebius has the lowest list price for 1 of the 9 models it serves that other hosts also serve (Muse Spark Open). Its median markup over the cheapest host is +337%.

How reliable is Nebius?

Averaged over the models it serves, Nebius reported 100% uptime in the 30 minutes before OpenRouter's catalogue was read for our run.