Qwen3.5-9B
qwen/qwen3.5-9b
Compare with Qwen3.5 397B A17B, Qwen3.5-35B-A3B, Qwen3.5-27B
CompareQwen3.5-9B
| Provider | State | Uptime 5m | 24h | p50 latency | p99 | Throughput | Context | $/Mtok |
|---|---|---|---|---|---|---|---|---|
Parasailparasail/bf16bf16 | Healthy | 100% | 99.56% | 644ms | 3.39s | 31 tps | 262K | $0.100 / $0.250 |
SiliconFlowsiliconflow/fp8fp8 | Healthy | 100% | 99.22% | 1.70s | 6.12s | 13 tps | 262K | $0.100 / $0.150 |
Togethertogether | Healthy | 100% | 99.85% | 527ms | 5.57s | 80 tps | 262K | $0.170 / $0.250 |
Venicevenice/fp8fp8 | Healthy | 100% | 99.88% | 754ms | 7.24s | 105 tps | 256K | $0.100 / $0.150 |
DeepInfradeepinfra/bf16bf16 | Healthy | 99.01% | 97.24% | 374ms | 2.21s | 36 tps | 262K | $0.100 / $0.150 |
- Parasail100%Healthy24h 99.56%
- p50
- 644ms
- p99
- 3.39s
- Throughput
- 31 tps
- Context
- 262K
- $/Mtok
- $0.100 / $0.250
parasail/bf16bf16 - SiliconFlow100%Healthy24h 99.22%
- p50
- 1.70s
- p99
- 6.12s
- Throughput
- 13 tps
- Context
- 262K
- $/Mtok
- $0.100 / $0.150
siliconflow/fp8fp8 - Together100%Healthy24h 99.85%
- p50
- 527ms
- p99
- 5.57s
- Throughput
- 80 tps
- Context
- 262K
- $/Mtok
- $0.170 / $0.250
together - Venice100%Healthy24h 99.88%
- p50
- 754ms
- p99
- 7.24s
- Throughput
- 105 tps
- Context
- 256K
- $/Mtok
- $0.100 / $0.150
venice/fp8fp8 - DeepInfra99.01%Healthy24h 97.24%
- p50
- 374ms
- p99
- 2.21s
- Throughput
- 36 tps
- Context
- 262K
- $/Mtok
- $0.100 / $0.150
deepinfra/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.
Throughput
Median tokens per second.