Qwen3 30B A3B vs Qwen3 235B A22B Instruct 2507
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.
CompareQwen3 30B A3BQwen3 235B A22B Instruct 2507
| Model | Providers | Best uptime | Fastest p50 | Best p99 | Throughput | Context | Cheapest $/Mtok |
|---|---|---|---|---|---|---|---|
| Qwen3 30B A3B | 2/2 | 100% Alibaba | 228ms DeepInfra | 1.20s Alibaba | 58 tps DeepInfra | 131K | $0.120 / $0.500 DeepInfra |
| Qwen3 235B A22B Instruct 2507 | 9/10 | 100% Alibaba | 336ms DeepInfra | 1.46s Alibaba | 43 tps Alibaba | 262K | $0.090 / $0.550 DeepInfra |
Measured 2m 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.