modelstatus.dev

Nebius

11 endpoints · 2 unhealthy · worst uptime 98.99%

	State
Hermes 4 405Bnebius/fp8fp8	Healthy	100%	100%	607ms	4.28s	32 tps	131K	$1.00 / $3.00
Hermes 4 70Bnebius/fp8fp8	Healthy	100%	100%	223ms	5.24s	71 tps	131K	$0.130 / $0.400
gpt-oss-120bnebius/fp4fp4	Healthy	100%	99.46%	218ms	1.11s	298 tps	131K	$0.150 / $0.600
Qwen2.5 VL 72B Instructnebius/fp8fp8	Healthy	100%	97.30%	1.30s	5.01s	11 tps	32K	$0.250 / $0.750
Qwen3 30B A3B Instruct 2507nebius/fp8fp8	Healthy	100%	98.04%	298ms	2.92s	46 tps	262K	$0.100 / $0.300
Qwen3 32Bnebius/basefp8	Healthy	100%	97.04%	441ms	3.92s	25 tps	41K	$0.100 / $0.300
Gemma 3 27Bnebius/fp8fp8	Degraded	99.88%	81.35%	590ms	7.26s	23 tps	110K	$0.100 / $0.300
Qwen3 235B A22B Instruct 2507nebius/fp8fp8	Healthy	98.99%	97.21%	663ms	16.3s	40 tps	262K	$0.200 / $0.600
Llama 3.3 70B Instructnebius/fp8fp8	Down	—	32.76%	2.83s	21.7s	3.5 tps	131K	$0.130 / $0.400
Qwen3 Next 80B A3B Thinkingnebius/fp8fp8	No data	—	97.38%	577ms	585ms	15 tps	128K	$0.150 / $1.20
GLM 5.1nebius/fp8fp8	No data	—	97.27%	694ms	6.64s	31 tps	203K	$1.40 / $4.40

Hermes 4 405B100%
Healthy24h 100%
p50
607ms
p99
4.28s
Throughput
32 tps
Context
131K
$/Mtok
$1.00 / $3.00
nebius/fp8fp8
Hermes 4 70B100%
Healthy24h 100%
p50
223ms
p99
5.24s
Throughput
71 tps
Context
131K
$/Mtok
$0.130 / $0.400
nebius/fp8fp8
gpt-oss-120b100%
Healthy24h 99.46%
p50
218ms
p99
1.11s
Throughput
298 tps
Context
131K
$/Mtok
$0.150 / $0.600
nebius/fp4fp4
Qwen2.5 VL 72B Instruct100%
Healthy24h 97.30%
p50
1.30s
p99
5.01s
Throughput
11 tps
Context
32K
$/Mtok
$0.250 / $0.750
nebius/fp8fp8
Qwen3 30B A3B Instruct 2507100%
Healthy24h 98.04%
p50
298ms
p99
2.92s
Throughput
46 tps
Context
262K
$/Mtok
$0.100 / $0.300
nebius/fp8fp8
Qwen3 32B100%
Healthy24h 97.04%
p50
441ms
p99
3.92s
Throughput
25 tps
Context
41K
$/Mtok
$0.100 / $0.300
nebius/basefp8
Gemma 3 27B99.88%
Degraded24h 81.35%
p50
590ms
p99
7.26s
Throughput
23 tps
Context
110K
$/Mtok
$0.100 / $0.300
nebius/fp8fp8
Qwen3 235B A22B Instruct 250798.99%
Healthy24h 97.21%
p50
663ms
p99
16.3s
Throughput
40 tps
Context
262K
$/Mtok
$0.200 / $0.600
nebius/fp8fp8
Llama 3.3 70B Instruct—
Down24h 32.76%
p50
2.83s
p99
21.7s
Throughput
3.5 tps
Context
131K
$/Mtok
$0.130 / $0.400
nebius/fp8fp8
Qwen3 Next 80B A3B Thinking—
No data24h 97.38%
p50
577ms
p99
585ms
Throughput
15 tps
Context
128K
$/Mtok
$0.150 / $1.20
nebius/fp8fp8
GLM 5.1—
No data24h 97.27%
p50
694ms
p99
6.64s
Throughput
31 tps
Context
203K
$/Mtok
$1.40 / $4.40
nebius/fp8fp8

Measured 3m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.