Qwen3 32B
qwen/qwen3-32b
Compare with Qwen3 235B A22B Instruct 2507, Qwen3 30B A3B Instruct 2507, Qwen3 Coder 480B A35B
CompareQwen3 32B
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Healthy | 100% | 99.97% | 99.72% | 99.72% | 353ms | 2.22s | 28 tps | 41K | $0.080 / $0.280 | |
Groqgroq | Healthy | 100% | 99.87% | 99.96% | 99.96% | 411ms | 5.01s | 229 tps | 131K | $0.290 / $0.590 |
| Healthy | 100% | 98.46% | 98.48% | 98.48% | 541ms | 5.08s | 24 tps | 41K | $0.100 / $0.300 | |
| Healthy | 100% | 92.57% | 90.83% | 90.83% | 1.75s | 98.5s | 14 tps | 131K | $0.140 / $0.570 |
- DeepInfra100%Healthy24h 99.97%
- 7d
- 99.72%
- 30d
- 99.72%
- p50
- 353ms
- p99
- 2.22s
- Throughput
- 28 tps
- Context
- 41K
- $/Mtok
- $0.080 / $0.280
deepinfra/fp8fp8 - Groq100%Healthy24h 99.87%
- 7d
- 99.96%
- 30d
- 99.96%
- p50
- 411ms
- p99
- 5.01s
- Throughput
- 229 tps
- Context
- 131K
- $/Mtok
- $0.290 / $0.590
groq - Nebius100%Healthy24h 98.46%
- 7d
- 98.48%
- 30d
- 98.48%
- p50
- 541ms
- p99
- 5.08s
- Throughput
- 24 tps
- Context
- 41K
- $/Mtok
- $0.100 / $0.300
nebius/basefp8 - SiliconFlow100%Healthy24h 92.57%
- 7d
- 90.83%
- 30d
- 90.83%
- p50
- 1.75s
- p99
- 98.5s
- Throughput
- 14 tps
- Context
- 131K
- $/Mtok
- $0.140 / $0.570
siliconflow/fp8fp8
Measured 2m 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 is OpenRouter's rolling 30-minute window.
Throughput
Median tokens per second.