InferenceNet
5 endpoints · 2 unhealthy · worst uptime 91.23%
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Healthy | 99.53% | 97.80% | 95.36% | 95.36% | 2.30s | 37.3s | 28 tps | 1.0M | $2.10 / $10.95 | |
| Degraded | 97.51% | 96.44% | 96.48% | 96.48% | 3.29s | 37.2s | 12 tps | 1.0M | $0.090 / $0.280 | |
| Degraded | 91.23% | 83.30% | 38.70% | 38.70% | 2.47s | 91.4s | 27 tps | 1.0M | $0.900 / $3.00 | |
Schematron V2 Smallinference-net | No data | — | 100% | 100% | 100% | 945ms | 10.4s | 14 tps | 128K | $0.050 / $0.230 |
Schematron V2 Turboinference-net | No data | — | 100% | 99.99% | 99.99% | 1.31s | 25.6s | 11 tps | 128K | $0.030 / $0.150 |
- Kimi K399.53%Healthy24h 97.80%
- 7d
- 95.36%
- 30d
- 95.36%
- p50
- 2.30s
- p99
- 37.3s
- Throughput
- 28 tps
- Context
- 1.0M
- $/Mtok
- $2.10 / $10.95
inference-net/fp4fp4 - GLM 5.3 Flash97.51%Degraded24h 96.44%
- 7d
- 96.48%
- 30d
- 96.48%
- p50
- 3.29s
- p99
- 37.2s
- Throughput
- 12 tps
- Context
- 1.0M
- $/Mtok
- $0.090 / $0.280
inference-net/fp4fp4 - GLM 5.391.23%Degraded24h 83.30%
- 7d
- 38.70%
- 30d
- 38.70%
- p50
- 2.47s
- p99
- 91.4s
- Throughput
- 27 tps
- Context
- 1.0M
- $/Mtok
- $0.900 / $3.00
inference-net/fp4fp4 - No data24h 100%
- 7d
- 100%
- 30d
- 100%
- p50
- 945ms
- p99
- 10.4s
- Throughput
- 14 tps
- Context
- 128K
- $/Mtok
- $0.050 / $0.230
inference-net - No data24h 100%
- 7d
- 99.99%
- 30d
- 99.99%
- p50
- 1.31s
- p99
- 25.6s
- Throughput
- 11 tps
- Context
- 128K
- $/Mtok
- $0.030 / $0.150
inference-net
Measured 2m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
History
GLM 5.3 inference-net/fp4
Kimi K3 inference-net/fp4
GLM 5.3 Flash inference-net/fp4
Schematron V2 Turbo inference-net
Schematron V2 Small inference-net
Colour by 12-hourly mean uptime:≥ 95%90–95%< 90%no data
Through the live last bucket (raw rounds, updated every collection round) · 5 endpoints with data, sorted worst-first.