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
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
Alibabaalibaba | Healthy | 100% | 99.95% | 99.91% | 99.91% | 519ms | 1.90s | 17 tps | 131K | $0.130 / $0.520 |
| Healthy | 100% | 98.20% | 97.80% | 97.80% | 2.21s | 6.41s | 2.0 tps | 262K | $0.290 / $1.00 | |
| Healthy | 99.90% | 99.64% | 99.09% | 99.09% | 398ms | 2.42s | 20 tps | 262K | $0.150 / $0.600 | |
| Healthy | 98.27% | 95.52% | 95.89% | 95.89% | 766ms | 5.47s | 8.0 tps | 131K | $0.200 / $0.700 |
- Alibaba100%Healthy24h 99.95%
- 7d
- 99.91%
- 30d
- 99.91%
- p50
- 519ms
- p99
- 1.90s
- Throughput
- 17 tps
- Context
- 131K
- $/Mtok
- $0.130 / $0.520
alibaba - SiliconFlow100%Healthy24h 98.20%
- 7d
- 97.80%
- 30d
- 97.80%
- p50
- 2.21s
- p99
- 6.41s
- Throughput
- 2.0 tps
- Context
- 262K
- $/Mtok
- $0.290 / $1.00
siliconflow/fp8fp8 - DeepInfra99.90%Healthy24h 99.64%
- 7d
- 99.09%
- 30d
- 99.09%
- p50
- 398ms
- p99
- 2.42s
- Throughput
- 20 tps
- Context
- 262K
- $/Mtok
- $0.150 / $0.600
deepinfra/fp8fp8 - Novita98.27%Healthy24h 95.52%
- 7d
- 95.89%
- 30d
- 95.89%
- p50
- 766ms
- p99
- 5.47s
- Throughput
- 8.0 tps
- Context
- 131K
- $/Mtok
- $0.200 / $0.700
novita/bf16bf16
Measured 3m 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.