Qwen3 235B A22B Thinking 2507
qwen/qwen3-235b-a22b-thinking-2507
Compare with Qwen3 235B A22B Instruct 2507, Qwen3 30B A3B Instruct 2507, Qwen3 Coder 480B A35B
CompareQwen3 235B A22B Thinking 2507
| Provider | State | Uptime 5m | 24h | p50 latency | p99 | Throughput | Context | $/Mtok |
|---|---|---|---|---|---|---|---|---|
Alibabaalibaba | Healthy | 100% | 99.95% | 844ms | 10.7s | 70 tps | 131K | $0.230 / $2.30 |
DeepInfradeepinfra/fp8fp8 | No data | — | 98.36% | 681ms | 3.65s | 48 tps | 262K | $0.230 / $2.30 |
Novitanovita/fp8fp8 | No data | — | 99.17% | 2.48s | 13.1s | 30 tps | 131K | $0.300 / $3.00 |
Venicevenice/fp8fp8 | No data | — | 97.08% | 829ms | 1.57s | 42 tps | 128K | $0.450 / $3.50 |
- Alibaba100%Healthy24h 99.95%
- p50
- 844ms
- p99
- 10.7s
- Throughput
- 70 tps
- Context
- 131K
- $/Mtok
- $0.230 / $2.30
alibaba - DeepInfra—No data24h 98.36%
- p50
- 681ms
- p99
- 3.65s
- Throughput
- 48 tps
- Context
- 262K
- $/Mtok
- $0.230 / $2.30
deepinfra/fp8fp8 - Novita—No data24h 99.17%
- p50
- 2.48s
- p99
- 13.1s
- Throughput
- 30 tps
- Context
- 131K
- $/Mtok
- $0.300 / $3.00
novita/fp8fp8 - Venice—No data24h 97.08%
- p50
- 829ms
- p99
- 1.57s
- Throughput
- 42 tps
- Context
- 128K
- $/Mtok
- $0.450 / $3.50
venice/fp8fp8
Measured 2m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
History
3 endpoints reporting no data are 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, averaged over the hour.
Throughput
Median tokens per second.