GLM 4.5 Air
z-ai/glm-4.5-air
CompareGLM 4.5 Air
| Provider | State | Uptime 5m | 24h | p50 latency | p99 | Throughput | Context | $/Mtok |
|---|---|---|---|---|---|---|---|---|
Novitanovita/bf16bf16 | Healthy | 100% | 99.40% | 588ms | 8.64s | 50 tps | 131K | $0.130 / $0.850 |
SiliconFlowsiliconflow/fp8fp8 | Healthy | 100% | 97.90% | 1.37s | 5.44s | 23 tps | 131K | $0.140 / $0.860 |
Z.AIz-ai/fp8fp8 | Healthy | 100% | 99.06% | 1.82s | 9.86s | 29 tps | 131K | $0.200 / $1.10 |
- Novita100%Healthy24h 99.40%
- p50
- 588ms
- p99
- 8.64s
- Throughput
- 50 tps
- Context
- 131K
- $/Mtok
- $0.130 / $0.850
novita/bf16bf16 - SiliconFlow100%Healthy24h 97.90%
- p50
- 1.37s
- p99
- 5.44s
- Throughput
- 23 tps
- Context
- 131K
- $/Mtok
- $0.140 / $0.860
siliconflow/fp8fp8 - Z.AI100%Healthy24h 99.06%
- p50
- 1.82s
- p99
- 9.86s
- Throughput
- 29 tps
- Context
- 131K
- $/Mtok
- $0.200 / $1.10
z-ai/fp8fp8
Measured 3m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
History
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 and p99 are OpenRouter's rolling 30-minute windows.
Throughput
Median tokens per second.