Qwen3 VL 30B A3B Instruct
qwen/qwen3-vl-30b-a3b-instruct
Compare with Qwen3 235B A22B Instruct 2507, Qwen3 30B A3B Instruct 2507, Qwen3 Coder 480B A35B
CompareQwen3 VL 30B A3B Instruct
| Provider | State | Uptime 5m | 24h | p50 latency | p99 | Throughput | Context | $/Mtok |
|---|---|---|---|---|---|---|---|---|
Alibabaalibaba | Healthy | 100% | 99.90% | 540ms | 2.55s | 30 tps | 131K | $0.130 / $0.520 |
DeepInfradeepinfra/fp8fp8 | Healthy | 100% | 99.04% | 746ms | 5.12s | 14 tps | 262K | $0.150 / $0.600 |
SiliconFlowsiliconflow/fp8fp8 | Healthy | 97.92% | 97.24% | 2.58s | 14.4s | 7.0 tps | 262K | $0.290 / $1.00 |
Novitanovita/bf16bf16 | Down | 80.39% | 96.65% | 925ms | 6.66s | 15 tps | 131K | $0.200 / $0.700 |
- Alibaba100%Healthy24h 99.90%
- p50
- 540ms
- p99
- 2.55s
- Throughput
- 30 tps
- Context
- 131K
- $/Mtok
- $0.130 / $0.520
alibaba - DeepInfra100%Healthy24h 99.04%
- p50
- 746ms
- p99
- 5.12s
- Throughput
- 14 tps
- Context
- 262K
- $/Mtok
- $0.150 / $0.600
deepinfra/fp8fp8 - SiliconFlow97.92%Healthy24h 97.24%
- p50
- 2.58s
- p99
- 14.4s
- Throughput
- 7.0 tps
- Context
- 262K
- $/Mtok
- $0.290 / $1.00
siliconflow/fp8fp8 - Novita80.39%Down24h 96.65%
- p50
- 925ms
- p99
- 6.66s
- Throughput
- 15 tps
- Context
- 131K
- $/Mtok
- $0.200 / $0.700
novita/bf16bf16
Measured 4m 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.