Qwen3 VL 30B A3B Thinking
qwen/qwen3-vl-30b-a3b-thinkingInputOutput
Compare its 2 providersIncident RSSCompare with Qwen3 235B A22B Instruct 2507, Qwen3 30B A3B Instruct 2507, Qwen3 VL 235B A22B Instruct
CompareQwen3 VL 30B A3B Thinking
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
Alibabaalibaba | No data | — | 100% | 99.97% | 99.99% | 533ms | 1.44s | 115 tps | 131K | $0.200 / $2.40 |
| No data | — | 99.65% | 100% | 99.87% | 1.01s | 1.26s | 98 tps | 262K | $0.290 / $1.00 |
- No data24h 100%
- 7d
- 99.97%
- 30d
- 99.99%
- p50
- 533ms
- p99
- 1.44s
- Throughput
- 115 tps
- Context
- 131K
- $/Mtok
- $0.200 / $2.40
alibaba - No data24h 99.65%
- 7d
- 100%
- 30d
- 99.87%
- p50
- 1.01s
- p99
- 1.26s
- Throughput
- 98 tps
- Context
- 262K
- $/Mtok
- $0.290 / $1.00
siliconflow/fp8fp8
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, averaged over the hour.
Throughput
Median tokens per second.
Daily availability
One row per endpoint · one dot per day · last 90 days.
worst hour ≥ 95%90–95%< 90%no data
Colour by each endpoint's worst hour of each UTC day · 2 endpoints · 46 days with data, none below the red threshold.