Hy3 preview vs GLM 5.2
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.
CompareHy3 previewGLM 5.2
| Model | Providers | Best uptime | Fastest p50 | Best p99 | Throughput | Context | Cheapest $/Mtok |
|---|---|---|---|---|---|---|---|
| Hy3 preview | 1/1 | 99.85% GMICloud | 3.09s GMICloud | 40.3s GMICloud | 51 tps GMICloud | 262K | $0.180 / $0.600 GMICloud |
| GLM 5.2 | 22/31 | 100% Alibaba | 584ms Inceptron | 6.25s AtlasCloud | 104 tps Inceptron | 1.0M | $0.420 / $1.32 Baidu |
Measured 1m ago. Each figure is the best available across that model's providers.
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.