Phala
18 endpoints · 5 unhealthy · worst uptime 0.00%
| State | ||||||||
|---|---|---|---|---|---|---|---|---|
Gemma 4 31Bphala | Healthy | 100% | 96.79% | 3.54s | 11.3s | 13 tps | 262K | $0.150 / $0.460 |
gpt-oss-120bphala | Healthy | 100% | 99.83% | 881ms | 5.96s | 67 tps | 131K | $0.150 / $0.600 |
Qwen2.5 7B Instructphala | Healthy | 100% | 100% | 320ms | 1.82s | 38 tps | 33K | $0.100 / $0.200 |
Qwen3.6 27Bphala | Healthy | 100% | 96.85% | 1.67s | 9.60s | 22 tps | 262K | $0.320 / $2.70 |
Qwen3.6 35B A3Bphala | Healthy | 100% | 98.19% | 1.52s | 11.1s | 86 tps | 262K | $0.200 / $1.27 |
| Healthy | 100% | 99.68% | 2.36s | 11.5s | 48 tps | 1.0M | $1.26 / $3.00 | |
Qwen3.5 397B A17Bphala | Healthy | 99.50% | 94.61% | 1.25s | 10.6s | 3.0 tps | 262K | $0.550 / $3.50 |
Gemma 3 27Bphala | Healthy | 97.32% | 97.03% | 2.22s | 10.2s | 14 tps | 262K | $0.150 / $0.460 |
gpt-oss-20bphala | Healthy | 96.97% | 91.76% | 660ms | 5.72s | 48 tps | 131K | $0.040 / $0.150 |
| Healthy | 95.91% | 98.55% | 864ms | 21.9s | 45 tps | 1.0M | $0.200 / $0.400 | |
Muse Glimmer 30Bphala | Down | 76.60% | 98.85% | 2.02s | 53.2s | 43 tps | 131K | $0.300 / $1.10 |
Qwen3.5-27Bphala | Down | 0.00% | 78.23% | 4.12s | 12.4s | 10 tps | 262K | $0.300 / $2.40 |
DeepSeek V3.2phala | No data | — | 99.13% | 3.16s | 186s | 5.0 tps | 164K | $1.00 / $1.00 |
| Down | — | 94.10% | — | — | — | 1.0M | $0.200 / $0.400 | |
Kimi K2.5phala | No data | — | 69.06% | 2.37s | 10.8s | 19 tps | 262K | $0.600 / $3.00 |
Kimi K2.6phala | No data | — | 99.27% | 1.75s | 7.01s | 25 tps | 262K | $1.09 / $4.60 |
Kimi K3phala | Degraded | — | 94.81% | 6.50s | 16.3s | 29 tps | 1.0M | $3.00 / $15.00 |
GLM 5.1phala | Down | — | 91.02% | 4.84s | 25.7s | 28 tps | 203K | $1.21 / $4.20 |
- Gemma 4 31B100%Healthy24h 96.79%
- p50
- 3.54s
- p99
- 11.3s
- Throughput
- 13 tps
- Context
- 262K
- $/Mtok
- $0.150 / $0.460
phala - gpt-oss-120b100%Healthy24h 99.83%
- p50
- 881ms
- p99
- 5.96s
- Throughput
- 67 tps
- Context
- 131K
- $/Mtok
- $0.150 / $0.600
phala - Healthy24h 100%
- p50
- 320ms
- p99
- 1.82s
- Throughput
- 38 tps
- Context
- 33K
- $/Mtok
- $0.100 / $0.200
phala - Qwen3.6 27B100%Healthy24h 96.85%
- p50
- 1.67s
- p99
- 9.60s
- Throughput
- 22 tps
- Context
- 262K
- $/Mtok
- $0.320 / $2.70
phala - Qwen3.6 35B A3B100%Healthy24h 98.19%
- p50
- 1.52s
- p99
- 11.1s
- Throughput
- 86 tps
- Context
- 262K
- $/Mtok
- $0.200 / $1.27
phala - GLM 5.2100%Healthy24h 99.68%
- p50
- 2.36s
- p99
- 11.5s
- Throughput
- 48 tps
- Context
- 1.0M
- $/Mtok
- $1.26 / $3.00
phala/fp8fp8 - Qwen3.5 397B A17B99.50%Healthy24h 94.61%
- p50
- 1.25s
- p99
- 10.6s
- Throughput
- 3.0 tps
- Context
- 262K
- $/Mtok
- $0.550 / $3.50
phala - Gemma 3 27B97.32%Healthy24h 97.03%
- p50
- 2.22s
- p99
- 10.2s
- Throughput
- 14 tps
- Context
- 262K
- $/Mtok
- $0.150 / $0.460
phala - gpt-oss-20b96.97%Healthy24h 91.76%
- p50
- 660ms
- p99
- 5.72s
- Throughput
- 48 tps
- Context
- 131K
- $/Mtok
- $0.040 / $0.150
phala - DeepSeek V4 Flash 073195.91%Healthy24h 98.55%
- p50
- 864ms
- p99
- 21.9s
- Throughput
- 45 tps
- Context
- 1.0M
- $/Mtok
- $0.200 / $0.400
phala - Muse Glimmer 30B76.60%Down24h 98.85%
- p50
- 2.02s
- p99
- 53.2s
- Throughput
- 43 tps
- Context
- 131K
- $/Mtok
- $0.300 / $1.10
phala - Qwen3.5-27B0.00%Down24h 78.23%
- p50
- 4.12s
- p99
- 12.4s
- Throughput
- 10 tps
- Context
- 262K
- $/Mtok
- $0.300 / $2.40
phala - No data24h 99.13%
- p50
- 3.16s
- p99
- 186s
- Throughput
- 5.0 tps
- Context
- 164K
- $/Mtok
- $1.00 / $1.00
phala - Down24h 94.10%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $0.200 / $0.400
phala - No data24h 69.06%
- p50
- 2.37s
- p99
- 10.8s
- Throughput
- 19 tps
- Context
- 262K
- $/Mtok
- $0.600 / $3.00
phala - No data24h 99.27%
- p50
- 1.75s
- p99
- 7.01s
- Throughput
- 25 tps
- Context
- 262K
- $/Mtok
- $1.09 / $4.60
phala - Degraded24h 94.81%
- p50
- 6.50s
- p99
- 16.3s
- Throughput
- 29 tps
- Context
- 1.0M
- $/Mtok
- $3.00 / $15.00
phala - Down24h 91.02%
- p50
- 4.84s
- p99
- 25.7s
- Throughput
- 28 tps
- Context
- 203K
- $/Mtok
- $1.21 / $4.20
phala
Measured 2m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.