Qwen3 VL 30B A3B Thinking
qwen/qwen3-vl-30b-a3b-thinking
Compare with Qwen3 235B A22B Instruct 2507, Qwen3 30B A3B Instruct 2507, Qwen3 Coder 480B A35B
CompareQwen3 VL 30B A3B Thinking
| Provider | State | Uptime 5m | 24h | p50 latency | p99 | Throughput | Context | $/Mtok |
|---|---|---|---|---|---|---|---|---|
Alibabaalibaba | No data | — | 100% | 1.17s | 4.70s | 80 tps | 131K | $0.200 / $2.40 |
SiliconFlowsiliconflow/fp8fp8 | No data | — | 99.90% | 1.22s | 19.1s | 40 tps | 262K | $0.290 / $1.00 |
- Alibaba—No data24h 100%
- p50
- 1.17s
- p99
- 4.70s
- Throughput
- 80 tps
- Context
- 131K
- $/Mtok
- $0.200 / $2.40
alibaba - SiliconFlow—No data24h 99.90%
- p50
- 1.22s
- p99
- 19.1s
- Throughput
- 40 tps
- Context
- 262K
- $/Mtok
- $0.290 / $1.00
siliconflow/fp8fp8
Measured 1m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
History
2 endpoints reporting no data are omitted from the charts.
No endpoints with data to chart.