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 | 97.67% | 99.38% | 658ms | 7.23s | 40 tps | 131K | $0.130 / $0.850 |
SiliconFlowsiliconflow/fp8fp8 | No data | — | 97.93% | 1.51s | 2.98s | 20 tps | 131K | $0.140 / $0.860 |
Z.AIz-ai/fp8fp8 | No data | — | 98.99% | 1.48s | 11.2s | 26 tps | 131K | $0.200 / $1.10 |
- Novita97.67%Healthy24h 99.38%
- p50
- 658ms
- p99
- 7.23s
- Throughput
- 40 tps
- Context
- 131K
- $/Mtok
- $0.130 / $0.850
novita/bf16bf16 - SiliconFlow—No data24h 97.93%
- p50
- 1.51s
- p99
- 2.98s
- Throughput
- 20 tps
- Context
- 131K
- $/Mtok
- $0.140 / $0.860
siliconflow/fp8fp8 - Z.AI—No data24h 98.99%
- p50
- 1.48s
- p99
- 11.2s
- Throughput
- 26 tps
- Context
- 131K
- $/Mtok
- $0.200 / $1.10
z-ai/fp8fp8
Measured 5m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
History
2 endpoints reporting no data are 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 and p99 are OpenRouter's rolling 30-minute windows.
Throughput
Median tokens per second.