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% | 317ms | 7.59s | 72 tps | 131K | $0.130 / $0.520 |
StreamLakestreamlake | Healthy | 99.97% | 99.73% | 1.39s | 8.30s | 21 tps | 128K | $0.048 / $0.193 |
Nebiusnebius/fp8fp8 | Healthy | 96.04% | 86.11% | 384ms | 7.28s | 36 tps | 262K | $0.100 / $0.300 |
SiliconFlowsiliconflow/fp8fp8 | Degraded | 94.00% | 89.97% | 2.38s | 8.47s | 12 tps | 262K | $0.090 / $0.300 |
CoreWeavecoreweave/bf16bf16 | Degraded | 92.91% | 97.91% | 431ms | 5.95s | 37 tps | 262K | $0.100 / $0.300 |
- Alibaba100%Healthy24h 99.96%
- p50
- 317ms
- p99
- 7.59s
- Throughput
- 72 tps
- Context
- 131K
- $/Mtok
- $0.130 / $0.520
alibaba - StreamLake99.97%Healthy24h 99.73%
- p50
- 1.39s
- p99
- 8.30s
- Throughput
- 21 tps
- Context
- 128K
- $/Mtok
- $0.048 / $0.193
streamlake - Nebius96.04%Healthy24h 86.11%
- p50
- 384ms
- p99
- 7.28s
- Throughput
- 36 tps
- Context
- 262K
- $/Mtok
- $0.100 / $0.300
nebius/fp8fp8 - SiliconFlow94.00%Degraded24h 89.97%
- p50
- 2.38s
- p99
- 8.47s
- Throughput
- 12 tps
- Context
- 262K
- $/Mtok
- $0.090 / $0.300
siliconflow/fp8fp8 - CoreWeave92.91%Degraded24h 97.91%
- p50
- 431ms
- p99
- 5.95s
- Throughput
- 37 tps
- Context
- 262K
- $/Mtok
- $0.100 / $0.300
coreweave/bf16bf16
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, averaged over the hour.
Throughput
Median tokens per second.