Nebius
9 endpoints · 1 unhealthy · worst uptime 99.39%
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Healthy | 100% | 100% | 100% | 99.99% | 611ms | 3.16s | 31 tps | 131K | $1.00 / $3.00 | |
| Healthy | 100% | 95.70% | 95.92% | 97.80% | 536ms | 9.75s | 130 tps | 131K | $0.150 / $0.600 | |
| Healthy | 100% | 91.22% | 92.23% | 91.19% | 498ms | 6.02s | 52 tps | 262K | $0.200 / $0.600 | |
| Degraded | 100% | 89.42% | 93.85% | 93.80% | 411ms | 5.33s | 34 tps | 262K | $0.100 / $0.300 | |
| Healthy | 100% | 99.81% | 97.39% | 86.13% | 497ms | 3.16s | 23 tps | 203K | $1.40 / $4.40 | |
| Healthy | 99.49% | 99.88% | 99.15% | 98.78% | 539ms | 8.04s | 90 tps | 262K | $0.060 / $0.240 | |
| Healthy | 99.39% | 98.20% | 91.22% | 88.60% | 1.29s | 8.99s | 32 tps | 110K | $0.100 / $0.300 | |
| No data | — | 99.69% | 98.30% | 97.87% | 936ms | 2.44s | 170 tps | 262K | $0.950 / $4.00 | |
| No data | — | 99.86% | 99.67% | 99.67% | 854ms | 15.4s | 182 tps | 1.0M | $1.40 / $4.40 |
- Hermes 4 405B100%Healthy24h 100%
- 7d
- 100%
- 30d
- 99.99%
- p50
- 611ms
- p99
- 3.16s
- Throughput
- 31 tps
- Context
- 131K
- $/Mtok
- $1.00 / $3.00
nebius/fp8fp8 - gpt-oss-120b100%Healthy24h 95.70%
- 7d
- 95.92%
- 30d
- 97.80%
- p50
- 536ms
- p99
- 9.75s
- Throughput
- 130 tps
- Context
- 131K
- $/Mtok
- $0.150 / $0.600
nebius/fp4fp4 - Healthy24h 91.22%
- 7d
- 92.23%
- 30d
- 91.19%
- p50
- 498ms
- p99
- 6.02s
- Throughput
- 52 tps
- Context
- 262K
- $/Mtok
- $0.200 / $0.600
nebius/fp8fp8 - Degraded24h 89.42%
- 7d
- 93.85%
- 30d
- 93.80%
- p50
- 411ms
- p99
- 5.33s
- Throughput
- 34 tps
- Context
- 262K
- $/Mtok
- $0.100 / $0.300
nebius/fp8fp8 - GLM 5.1100%Healthy24h 99.81%
- 7d
- 97.39%
- 30d
- 86.13%
- p50
- 497ms
- p99
- 3.16s
- Throughput
- 23 tps
- Context
- 203K
- $/Mtok
- $1.40 / $4.40
nebius/fp8fp8 - Nemotron 3 Nano 30B A3B99.49%Healthy24h 99.88%
- 7d
- 99.15%
- 30d
- 98.78%
- p50
- 539ms
- p99
- 8.04s
- Throughput
- 90 tps
- Context
- 262K
- $/Mtok
- $0.060 / $0.240
nebius/fp8fp8 - Gemma 3 27B99.39%Healthy24h 98.20%
- 7d
- 91.22%
- 30d
- 88.60%
- p50
- 1.29s
- p99
- 8.99s
- Throughput
- 32 tps
- Context
- 110K
- $/Mtok
- $0.100 / $0.300
nebius/fp8fp8 - No data24h 99.69%
- 7d
- 98.30%
- 30d
- 97.87%
- p50
- 936ms
- p99
- 2.44s
- Throughput
- 170 tps
- Context
- 262K
- $/Mtok
- $0.950 / $4.00
nebius/fp4fp4 - No data24h 99.86%
- 7d
- 99.67%
- 30d
- 99.67%
- p50
- 854ms
- p99
- 15.4s
- Throughput
- 182 tps
- Context
- 1.0M
- $/Mtok
- $1.40 / $4.40
nebius/fp4fp4
Measured 1m 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.