Qwen3 30B A3B Instruct 2507
qwen/qwen3-30b-a3b-instruct-2507
Compare with Qwen3 235B A22B Instruct 2507, Qwen3 Coder 480B A35B, Qwen3 Next 80B A3B Instruct
CompareQwen3 30B A3B Instruct 2507
| Provider | State | Uptime 5m | 24h | p50 latency | p99 | Throughput | Context | $/Mtok |
|---|---|---|---|---|---|---|---|---|
Alibabaalibaba | Healthy | 100% | 99.96% | 329ms | 2.64s | 60 tps | 131K | $0.130 / $0.520 |
StreamLakestreamlake | Healthy | 99.94% | 99.74% | 1.30s | 7.73s | 22 tps | 128K | $0.048 / $0.193 |
Nebiusnebius/fp8fp8 | Degraded | 97.95% | 86.06% | 351ms | 7.47s | 39 tps | 262K | $0.100 / $0.300 |
CoreWeavecoreweave/bf16bf16 | Degraded | 94.57% | 97.83% | 383ms | 5.56s | 46 tps | 262K | $0.100 / $0.300 |
SiliconFlowsiliconflow/fp8fp8 | Down | 81.01% | 89.96% | 2.59s | 11.1s | 10 tps | 262K | $0.090 / $0.300 |
- Alibaba100%Healthy24h 99.96%
- p50
- 329ms
- p99
- 2.64s
- Throughput
- 60 tps
- Context
- 131K
- $/Mtok
- $0.130 / $0.520
alibaba - StreamLake99.94%Healthy24h 99.74%
- p50
- 1.30s
- p99
- 7.73s
- Throughput
- 22 tps
- Context
- 128K
- $/Mtok
- $0.048 / $0.193
streamlake - Nebius97.95%Degraded24h 86.06%
- p50
- 351ms
- p99
- 7.47s
- Throughput
- 39 tps
- Context
- 262K
- $/Mtok
- $0.100 / $0.300
nebius/fp8fp8 - CoreWeave94.57%Degraded24h 97.83%
- p50
- 383ms
- p99
- 5.56s
- Throughput
- 46 tps
- Context
- 262K
- $/Mtok
- $0.100 / $0.300
coreweave/bf16bf16 - SiliconFlow81.01%Down24h 89.96%
- p50
- 2.59s
- p99
- 11.1s
- Throughput
- 10 tps
- Context
- 262K
- $/Mtok
- $0.090 / $0.300
siliconflow/fp8fp8
Measured 1m 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.