GLM 4.5 Air
z-ai/glm-4.5-air
CompareGLM 4.5 Air
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Healthy | 100% | 99.10% | 99.73% | 99.73% | 1.89s | 24.4s | 16 tps | 131K | $0.140 / $0.860 | |
| Healthy | 97.83% | 98.92% | 99.08% | 99.08% | 920ms | 16.8s | 25 tps | 131K | $0.130 / $0.850 | |
| No data | — | 98.53% | 98.84% | 98.84% | 661ms | 22.4s | 28 tps | 131K | $0.200 / $1.10 |
- SiliconFlow100%Healthy24h 99.10%
- 7d
- 99.73%
- 30d
- 99.73%
- p50
- 1.89s
- p99
- 24.4s
- Throughput
- 16 tps
- Context
- 131K
- $/Mtok
- $0.140 / $0.860
siliconflow/fp8fp8 - Novita97.83%Healthy24h 98.92%
- 7d
- 99.08%
- 30d
- 99.08%
- p50
- 920ms
- p99
- 16.8s
- Throughput
- 25 tps
- Context
- 131K
- $/Mtok
- $0.130 / $0.850
novita/bf16bf16 - Z.AI—No data24h 98.53%
- 7d
- 98.84%
- 30d
- 98.84%
- p50
- 661ms
- p99
- 22.4s
- Throughput
- 28 tps
- Context
- 131K
- $/Mtok
- $0.200 / $1.10
z-ai/fp8fp8
Measured 1m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
History
1 endpoint reporting no data is omitted from the charts.
Availability
Axis starts at 90% so small differences stay visible; it expands to 0 when an endpoint falls below.
Time to first token
Logarithmic axis — the fleet spans two orders of magnitude. P50 is OpenRouter's rolling 30-minute window.
Throughput
Median tokens per second.