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 | No data | — | 99.94% | 791ms | 5.11s | 67 tps | 131K | $0.230 / $2.30 |
DeepInfradeepinfra/fp8fp8 | No data | — | 98.38% | 684ms | 2.55s | 43 tps | 262K | $0.230 / $2.30 |
Novitanovita/fp8fp8 | No data | — | 99.21% | 2.61s | 9.35s | 28 tps | 131K | $0.300 / $3.00 |
Venicevenice/fp8fp8 | No data | — | 97.25% | 1.66s | 1.66s | 40 tps | 128K | $0.450 / $3.50 |
- Alibaba—No data24h 99.94%
- p50
- 791ms
- p99
- 5.11s
- Throughput
- 67 tps
- Context
- 131K
- $/Mtok
- $0.230 / $2.30
alibaba - DeepInfra—No data24h 98.38%
- p50
- 684ms
- p99
- 2.55s
- Throughput
- 43 tps
- Context
- 262K
- $/Mtok
- $0.230 / $2.30
deepinfra/fp8fp8 - Novita—No data24h 99.21%
- p50
- 2.61s
- p99
- 9.35s
- Throughput
- 28 tps
- Context
- 131K
- $/Mtok
- $0.300 / $3.00
novita/fp8fp8 - Venice—No data24h 97.25%
- p50
- 1.66s
- p99
- 1.66s
- Throughput
- 40 tps
- Context
- 128K
- $/Mtok
- $0.450 / $3.50
venice/fp8fp8
Measured 1m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
History
4 endpoints reporting no data are omitted from the charts.
No endpoints with data to chart.