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% | 99.48% | 566ms | 3.15s | 41 tps | 262K | $0.100 / $0.250 |
Togethertogether | Healthy | 100% | 99.80% | 596ms | 6.43s | 47 tps | 262K | $0.170 / $0.250 |
Venicevenice/fp8fp8 | Healthy | 100% | 99.89% | 1.97s | 14.5s | 56 tps | 256K | $0.100 / $0.150 |
SiliconFlowsiliconflow/fp8fp8 | Healthy | 99.03% | 99.25% | 1.65s | 9.06s | 24 tps | 262K | $0.100 / $0.150 |
DeepInfradeepinfra/bf16bf16 | Down | 89.33% | 96.59% | 817ms | 4.78s | 20 tps | 262K | $0.100 / $0.150 |
- Parasail100%Healthy24h 99.48%
- p50
- 566ms
- p99
- 3.15s
- Throughput
- 41 tps
- Context
- 262K
- $/Mtok
- $0.100 / $0.250
parasail/bf16bf16 - Together100%Healthy24h 99.80%
- p50
- 596ms
- p99
- 6.43s
- Throughput
- 47 tps
- Context
- 262K
- $/Mtok
- $0.170 / $0.250
together - Venice100%Healthy24h 99.89%
- p50
- 1.97s
- p99
- 14.5s
- Throughput
- 56 tps
- Context
- 256K
- $/Mtok
- $0.100 / $0.150
venice/fp8fp8 - SiliconFlow99.03%Healthy24h 99.25%
- p50
- 1.65s
- p99
- 9.06s
- Throughput
- 24 tps
- Context
- 262K
- $/Mtok
- $0.100 / $0.150
siliconflow/fp8fp8 - DeepInfra89.33%Down24h 96.59%
- p50
- 817ms
- p99
- 4.78s
- Throughput
- 20 tps
- Context
- 262K
- $/Mtok
- $0.100 / $0.150
deepinfra/bf16bf16
Measured 5m 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.