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 |
|---|---|---|---|---|---|---|---|---|
Togethertogether | Healthy | 100% | 99.81% | 1.35s | 10.8s | 60 tps | 262K | $0.170 / $0.250 |
Venicevenice/fp8fp8 | Healthy | 100% | 99.89% | 791ms | 7.71s | 85 tps | 256K | $0.100 / $0.150 |
Parasailparasail/bf16bf16 | Healthy | 98.56% | 99.54% | 678ms | 5.01s | 11 tps | 262K | $0.100 / $0.250 |
SiliconFlowsiliconflow/fp8fp8 | Healthy | 97.69% | 99.02% | 2.12s | 13.3s | 7.0 tps | 262K | $0.100 / $0.150 |
DeepInfradeepinfra/bf16bf16 | Healthy | 96.95% | 96.47% | 586ms | 31.9s | 26 tps | 262K | $0.100 / $0.150 |
- Together100%Healthy24h 99.81%
- p50
- 1.35s
- p99
- 10.8s
- Throughput
- 60 tps
- Context
- 262K
- $/Mtok
- $0.170 / $0.250
together - Venice100%Healthy24h 99.89%
- p50
- 791ms
- p99
- 7.71s
- Throughput
- 85 tps
- Context
- 256K
- $/Mtok
- $0.100 / $0.150
venice/fp8fp8 - Parasail98.56%Healthy24h 99.54%
- p50
- 678ms
- p99
- 5.01s
- Throughput
- 11 tps
- Context
- 262K
- $/Mtok
- $0.100 / $0.250
parasail/bf16bf16 - SiliconFlow97.69%Healthy24h 99.02%
- p50
- 2.12s
- p99
- 13.3s
- Throughput
- 7.0 tps
- Context
- 262K
- $/Mtok
- $0.100 / $0.150
siliconflow/fp8fp8 - DeepInfra96.95%Healthy24h 96.47%
- p50
- 586ms
- p99
- 31.9s
- Throughput
- 26 tps
- Context
- 262K
- $/Mtok
- $0.100 / $0.150
deepinfra/bf16bf16
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.