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
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
Alibabaalibaba | Healthy | 100% | 99.96% | 99.96% | 99.96% | 322ms | 2.95s | 38 tps | 131K | $0.130 / $0.520 |
| Healthy | 100% | 97.15% | 96.76% | 96.76% | 292ms | 3.77s | 39 tps | 262K | $0.100 / $0.300 | |
| Healthy | 99.92% | 98.29% | 96.83% | 96.83% | 315ms | 4.49s | 26 tps | 262K | $0.100 / $0.300 | |
StreamLakestreamlake | Healthy | 99.63% | 99.87% | 99.86% | 99.86% | 2.16s | 7.72s | 9.0 tps | 128K | $0.048 / $0.193 |
| Down | 81.79% | 89.08% | 90.42% | 90.42% | 2.31s | 29.6s | 8.0 tps | 262K | $0.090 / $0.300 |
- Alibaba100%Healthy24h 99.96%
- 7d
- 99.96%
- 30d
- 99.96%
- p50
- 322ms
- p99
- 2.95s
- Throughput
- 38 tps
- Context
- 131K
- $/Mtok
- $0.130 / $0.520
alibaba - CoreWeave100%Healthy24h 97.15%
- 7d
- 96.76%
- 30d
- 96.76%
- p50
- 292ms
- p99
- 3.77s
- Throughput
- 39 tps
- Context
- 262K
- $/Mtok
- $0.100 / $0.300
coreweave/bf16bf16 - Nebius99.92%Healthy24h 98.29%
- 7d
- 96.83%
- 30d
- 96.83%
- p50
- 315ms
- p99
- 4.49s
- Throughput
- 26 tps
- Context
- 262K
- $/Mtok
- $0.100 / $0.300
nebius/fp8fp8 - StreamLake99.63%Healthy24h 99.87%
- 7d
- 99.86%
- 30d
- 99.86%
- p50
- 2.16s
- p99
- 7.72s
- Throughput
- 9.0 tps
- Context
- 128K
- $/Mtok
- $0.048 / $0.193
streamlake - SiliconFlow81.79%Down24h 89.08%
- 7d
- 90.42%
- 30d
- 90.42%
- p50
- 2.31s
- p99
- 29.6s
- Throughput
- 8.0 tps
- Context
- 262K
- $/Mtok
- $0.090 / $0.300
siliconflow/fp8fp8
Measured 2m 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 is OpenRouter's rolling 30-minute window.
Throughput
Median tokens per second.