Qwen3 32B
qwen/qwen3-32b
Compare with Qwen3 235B A22B Instruct 2507, Qwen3 30B A3B Instruct 2507, Qwen3 Coder 480B A35B
CompareQwen3 32B
| Provider | State | Uptime 5m | 24h | p50 latency | p99 | Throughput | Context | $/Mtok |
|---|---|---|---|---|---|---|---|---|
Groqgroq | Healthy | 100% | 99.98% | 256ms | 4.47s | 216 tps | 131K | $0.290 / $0.590 |
Nebiusnebius/basefp8 | Healthy | 100% | 97.69% | 354ms | 4.71s | 25 tps | 41K | $0.100 / $0.300 |
DeepInfradeepinfra/fp8fp8 | Healthy | 99.94% | 99.03% | 225ms | 2.34s | 39 tps | 41K | $0.080 / $0.280 |
SiliconFlowsiliconflow/fp8fp8 | Healthy | 97.31% | 87.50% | 1.38s | 11.5s | 16 tps | 131K | $0.140 / $0.570 |
- Groq100%Healthy24h 99.98%
- p50
- 256ms
- p99
- 4.47s
- Throughput
- 216 tps
- Context
- 131K
- $/Mtok
- $0.290 / $0.590
groq - Nebius100%Healthy24h 97.69%
- p50
- 354ms
- p99
- 4.71s
- Throughput
- 25 tps
- Context
- 41K
- $/Mtok
- $0.100 / $0.300
nebius/basefp8 - DeepInfra99.94%Healthy24h 99.03%
- p50
- 225ms
- p99
- 2.34s
- Throughput
- 39 tps
- Context
- 41K
- $/Mtok
- $0.080 / $0.280
deepinfra/fp8fp8 - SiliconFlow97.31%Healthy24h 87.50%
- p50
- 1.38s
- p99
- 11.5s
- Throughput
- 16 tps
- Context
- 131K
- $/Mtok
- $0.140 / $0.570
siliconflow/fp8fp8
Measured 4m 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.