Qwen3 VL 235B A22B Instruct
qwen/qwen3-vl-235b-a22b-instruct
Compare with Qwen3 235B A22B Instruct 2507, Qwen3 30B A3B Instruct 2507, Qwen3 Coder 480B A35B
CompareQwen3 VL 235B A22B Instruct
| Provider | State | Uptime 5m | 24h | p50 latency | p99 | Throughput | Context | $/Mtok |
|---|---|---|---|---|---|---|---|---|
Alibabaalibaba | Healthy | 100% | 99.90% | 770ms | 7.04s | 26 tps | 131K | $0.260 / $1.04 |
DeepInfradeepinfra/fp8fp8 | Healthy | 100% | 96.85% | 743ms | 6.92s | 12 tps | 262K | $0.200 / $0.880 |
Venicevenice/fp8fp8 | Healthy | 99.15% | 97.49% | 1.43s | 7.67s | 24 tps | 128K | $0.210 / $1.90 |
Parasailparasail/fp8fp8 | Healthy | 99.05% | 99.43% | 843ms | 5.64s | 13 tps | 131K | $0.210 / $1.90 |
Novitanovita/bf16bf16 | Degraded | 93.71% | 94.57% | 1.25s | 14.9s | 20 tps | 131K | $0.300 / $1.50 |
- Alibaba100%Healthy24h 99.90%
- p50
- 770ms
- p99
- 7.04s
- Throughput
- 26 tps
- Context
- 131K
- $/Mtok
- $0.260 / $1.04
alibaba - DeepInfra100%Healthy24h 96.85%
- p50
- 743ms
- p99
- 6.92s
- Throughput
- 12 tps
- Context
- 262K
- $/Mtok
- $0.200 / $0.880
deepinfra/fp8fp8 - Venice99.15%Healthy24h 97.49%
- p50
- 1.43s
- p99
- 7.67s
- Throughput
- 24 tps
- Context
- 128K
- $/Mtok
- $0.210 / $1.90
venice/fp8fp8 - Parasail99.05%Healthy24h 99.43%
- p50
- 843ms
- p99
- 5.64s
- Throughput
- 13 tps
- Context
- 131K
- $/Mtok
- $0.210 / $1.90
parasail/fp8fp8 - Novita93.71%Degraded24h 94.57%
- p50
- 1.25s
- p99
- 14.9s
- Throughput
- 20 tps
- Context
- 131K
- $/Mtok
- $0.300 / $1.50
novita/bf16bf16
Measured 1m 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.
Throughput
Median tokens per second.