modelstatus.dev

Nebius

9 endpoints · 2 unhealthy · worst uptime 97.87%

	State
Hermes 4 405Bnebius/fp8fp8	Healthy	100%	100%	100%	99.99%	417ms	2.41s	35 tps	131K	$1.00 / $3.00
Nemotron 3 Nano 30B A3Bnebius/fp8fp8	Healthy	100%	99.87%	99.16%	98.78%	1.05s	2.20s	94 tps	262K	$0.060 / $0.240
GLM 5.1nebius/fp8fp8	Healthy	100%	99.79%	97.34%	86.07%	478ms	1.72s	27 tps	203K	$1.40 / $4.40
Qwen3 30B A3B Instruct 2507nebius/fp8fp8	Degraded	99.75%	89.64%	93.90%	93.78%	315ms	4.66s	55 tps	262K	$0.100 / $0.300
Gemma 3 27Bnebius/fp8fp8	Healthy	99.39%	96.45%	91.11%	88.56%	1.03s	6.35s	39 tps	110K	$0.100 / $0.300
gpt-oss-120bnebius/fp4fp4	Healthy	98.69%	95.25%	95.92%	97.80%	1.90s	11.6s	37 tps	131K	$0.150 / $0.600
Qwen3 235B A22B Instruct 2507nebius/fp8fp8	Down	97.87%	91.53%	92.30%	91.16%	1.64s	22.7s	35 tps	262K	$0.200 / $0.600
Kimi K2.7 Codenebius/fp4fp4	No data	—	99.68%	98.30%	97.87%	766ms	9.37s	156 tps	262K	$0.950 / $4.00
GLM 5.3nebius/fp4fp4	No data	—	99.86%	99.67%	99.67%	1.46s	6.87s	58 tps	1.0M	$1.40 / $4.40

Hermes 4 405B100%
Healthy24h 100%
7d
100%
30d
99.99%
p50
417ms
p99
2.41s
Throughput
35 tps
Context
131K
$/Mtok
$1.00 / $3.00
nebius/fp8fp8
Nemotron 3 Nano 30B A3B100%
Healthy24h 99.87%
7d
99.16%
30d
98.78%
p50
1.05s
p99
2.20s
Throughput
94 tps
Context
262K
$/Mtok
$0.060 / $0.240
nebius/fp8fp8
GLM 5.1100%
Healthy24h 99.79%
7d
97.34%
30d
86.07%
p50
478ms
p99
1.72s
Throughput
27 tps
Context
203K
$/Mtok
$1.40 / $4.40
nebius/fp8fp8
Qwen3 30B A3B Instruct 250799.75%
Degraded24h 89.64%
7d
93.90%
30d
93.78%
p50
315ms
p99
4.66s
Throughput
55 tps
Context
262K
$/Mtok
$0.100 / $0.300
nebius/fp8fp8
Gemma 3 27B99.39%
Healthy24h 96.45%
7d
91.11%
30d
88.56%
p50
1.03s
p99
6.35s
Throughput
39 tps
Context
110K
$/Mtok
$0.100 / $0.300
nebius/fp8fp8
gpt-oss-120b98.69%
Healthy24h 95.25%
7d
95.92%
30d
97.80%
p50
1.90s
p99
11.6s
Throughput
37 tps
Context
131K
$/Mtok
$0.150 / $0.600
nebius/fp4fp4
Qwen3 235B A22B Instruct 250797.87%
Down24h 91.53%
7d
92.30%
30d
91.16%
p50
1.64s
p99
22.7s
Throughput
35 tps
Context
262K
$/Mtok
$0.200 / $0.600
nebius/fp8fp8
Kimi K2.7 Code—
No data24h 99.68%
7d
98.30%
30d
97.87%
p50
766ms
p99
9.37s
Throughput
156 tps
Context
262K
$/Mtok
$0.950 / $4.00
nebius/fp4fp4
GLM 5.3—
No data24h 99.86%
7d
99.67%
30d
99.67%
p50
1.46s
p99
6.87s
Throughput
58 tps
Context
1.0M
$/Mtok
$1.40 / $4.40
nebius/fp4fp4

Measured 2m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.

History

Qwen3 30B A3B Instruct 2507 nebius/fp8

Qwen3 235B A22B Instruct 2507 nebius/fp8

gpt-oss-120b nebius/fp4

Gemma 3 27B nebius/fp8

GLM 5.1 nebius/fp8

Nemotron 3 Nano 30B A3B nebius/fp8

GLM 5.3 nebius/fp4

Hermes 4 405B nebius/fp8

Kimi K2.7 Code nebius/fp4

Colour by hourly mean uptime:≥ 95%90–95%< 90%no data

Through the live last bucket (raw rounds, updated every collection round) · 9 endpoints with data, sorted worst-first.