Qwen3 VL 235B A22B Thinking
qwen/qwen3-vl-235b-a22b-thinking
Compare with Qwen3 235B A22B Instruct 2507, Qwen3 30B A3B Instruct 2507, Qwen3 Coder 480B A35B
CompareQwen3 VL 235B A22B Thinking
| Provider | State | Uptime 5m | 24h | p50 latency | p99 | Throughput | Context | $/Mtok |
|---|---|---|---|---|---|---|---|---|
Alibabaalibaba | Degraded | — | 89.96% | 1.00s | 24.3s | 58 tps | 131K | $0.400 / $4.00 |
Novitanovita/bf16bf16 | No data | — | 99.56% | 1.66s | 6.56s | 36 tps | 131K | $0.980 / $3.95 |
- Alibaba—Degraded24h 89.96%
- p50
- 1.00s
- p99
- 24.3s
- Throughput
- 58 tps
- Context
- 131K
- $/Mtok
- $0.400 / $4.00
alibaba - Novita—No data24h 99.56%
- p50
- 1.66s
- p99
- 6.56s
- Throughput
- 36 tps
- Context
- 131K
- $/Mtok
- $0.980 / $3.95
novita/bf16bf16
Measured 1m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
History
1 endpoint reporting no data is omitted from the charts.
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.
Throughput
Median tokens per second.