GLM 4.5 vs GLM 4.5 Air
One line per model: the best value available from any of its providers at each point, which is what a caller routing to the healthy endpoint would see.
CompareGLM 4.5GLM 4.5 Air
| Model | Providers | Best uptime | Fastest p50 | Best p99 | Throughput | Context | Cheapest $/Mtok |
|---|---|---|---|---|---|---|---|
| GLM 4.5 | 0/1 | — | — | — | — | 131K | $0.600 / $2.20 Z.AI |
| GLM 4.5 Air | 2/3 | 100% SiliconFlow | 606ms Novita | 3.60s SiliconFlow | 57 tps Novita | 131K | $0.130 / $0.850 Novita |
History
Availability
Best uptime available from any provider. Axis starts at 90%; it expands to 0 when a model falls below.
Time to first token
Fastest p50 available from any provider. Logarithmic axis.
Throughput
Best median tokens per second available.