Qwen3 30B A3B
qwen/qwen3-30b-a3b
Compare with Qwen3 235B A22B Instruct 2507, Qwen3 30B A3B Instruct 2507, Qwen3 Coder 480B A35B
CompareQwen3 30B A3B
| Provider | State | Uptime 5m | 24h | p50 latency | p99 | Throughput | Context | $/Mtok |
|---|---|---|---|---|---|---|---|---|
Alibabaalibaba | Healthy | 100% | 99.94% | 447ms | 816ms | 64 tps | 131K | $0.130 / $0.520 |
DeepInfradeepinfra/fp8fp8 | Healthy | 100% | 98.37% | 241ms | 1.36s | 82 tps | 41K | $0.120 / $0.500 |
- Alibaba100%Healthy24h 99.94%
- p50
- 447ms
- p99
- 816ms
- Throughput
- 64 tps
- Context
- 131K
- $/Mtok
- $0.130 / $0.520
alibaba - DeepInfra100%Healthy24h 98.37%
- p50
- 241ms
- p99
- 1.36s
- Throughput
- 82 tps
- Context
- 41K
- $/Mtok
- $0.120 / $0.500
deepinfra/fp8fp8
Measured 3m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
History
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.
Throughput
Median tokens per second.