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% | 733ms | 4.01s | 29 tps | 131K | $0.260 / $1.04 |
DeepInfradeepinfra/fp8fp8 | Degraded | 100% | 96.14% | 1.33s | 7.06s | 7.0 tps | 262K | $0.200 / $0.880 |
Parasailparasail/fp8fp8 | Healthy | 99.27% | 99.45% | 750ms | 6.03s | 16 tps | 131K | $0.210 / $1.90 |
Venicevenice/fp8fp8 | Healthy | 99.21% | 97.57% | 1.31s | 6.62s | 23 tps | 128K | $0.210 / $1.90 |
Novitanovita/bf16bf16 | Healthy | 95.74% | 94.35% | 1.50s | 15.3s | 20 tps | 131K | $0.300 / $1.50 |
- Alibaba100%Healthy24h 99.90%
- p50
- 733ms
- p99
- 4.01s
- Throughput
- 29 tps
- Context
- 131K
- $/Mtok
- $0.260 / $1.04
alibaba - DeepInfra100%Degraded24h 96.14%
- p50
- 1.33s
- p99
- 7.06s
- Throughput
- 7.0 tps
- Context
- 262K
- $/Mtok
- $0.200 / $0.880
deepinfra/fp8fp8 - Parasail99.27%Healthy24h 99.45%
- p50
- 750ms
- p99
- 6.03s
- Throughput
- 16 tps
- Context
- 131K
- $/Mtok
- $0.210 / $1.90
parasail/fp8fp8 - Venice99.21%Healthy24h 97.57%
- p50
- 1.31s
- p99
- 6.62s
- Throughput
- 23 tps
- Context
- 128K
- $/Mtok
- $0.210 / $1.90
venice/fp8fp8 - Novita95.74%Healthy24h 94.35%
- p50
- 1.50s
- p99
- 15.3s
- 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, averaged over the hour.
Throughput
Median tokens per second.