Qwen3 30B A3B Instruct 2507 vs Qwen3.5 397B A17B
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 A3B Instruct 2507Qwen3.5 397B A17B
| Model | Providers | Best uptime | Fastest p50 | Best p99 | Throughput | Context | Cheapest $/Mtok |
|---|---|---|---|---|---|---|---|
| Qwen3 30B A3B Instruct 2507 | 3/5 | 100% Alibaba | 317ms Alibaba | 5.95s CoreWeave | 72 tps Alibaba | 262K | $0.048 / $0.193 StreamLake |
| Qwen3.5 397B A17B | 8/10 | 100% Alibaba | 540ms DeepInfra | 4.58s StreamLake | 61 tps Venice | 262K | $0.302 / $1.93 DigitalOcean |
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.