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 |
|---|---|---|---|---|---|---|---|---|
Z.AIz-ai/fp8fp8 | Healthy | 100% | 98.96% | 1.68s | 8.83s | 51 tps | 131K | $0.200 / $1.10 |
Novitanovita/bf16bf16 | Healthy | 98.02% | 99.36% | 547ms | 5.64s | 54 tps | 131K | $0.130 / $0.850 |
SiliconFlowsiliconflow/fp8fp8 | No data | — | 97.91% | 1.36s | 23.6s | 26 tps | 131K | $0.140 / $0.860 |
- Z.AI100%Healthy24h 98.96%
- p50
- 1.68s
- p99
- 8.83s
- Throughput
- 51 tps
- Context
- 131K
- $/Mtok
- $0.200 / $1.10
z-ai/fp8fp8 - Novita98.02%Healthy24h 99.36%
- p50
- 547ms
- p99
- 5.64s
- Throughput
- 54 tps
- Context
- 131K
- $/Mtok
- $0.130 / $0.850
novita/bf16bf16 - SiliconFlow—No data24h 97.91%
- p50
- 1.36s
- p99
- 23.6s
- Throughput
- 26 tps
- Context
- 131K
- $/Mtok
- $0.140 / $0.860
siliconflow/fp8fp8
Measured 4m 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 and p99 are OpenRouter's rolling 30-minute windows, averaged over the hour.
Throughput
Median tokens per second.