Qwen3.5-9B
qwen/qwen3.5-9b
Compare with Qwen3 235B A22B Instruct 2507, Qwen3.5 397B A17B, Qwen3.6 35B A3B
| Provider | State | Uptime 5m | 24h | p50 latency | p99 | Throughput | Context | $/Mtok |
|---|---|---|---|---|---|---|---|---|
Parasailparasail/bf16bf16 | Healthy | 100% | 99.58% | 669ms | 2.82s | 25 tps | 262K | $0.100 / $0.250 |
Togethertogether | Healthy | 100% | 99.81% | 545ms | 5.57s | 61 tps | 262K | $0.170 / $0.250 |
Venicevenice/fp8fp8 | Healthy | 100% | 99.89% | 1.89s | 15.4s | 67 tps | 256K | $0.100 / $0.150 |
DeepInfradeepinfra/bf16bf16 | Healthy | 99.89% | 96.35% | 591ms | 2.87s | 27 tps | 262K | $0.100 / $0.150 |
SiliconFlowsiliconflow/fp8fp8 | Healthy | 99.81% | 98.96% | 2.11s | 9.59s | 5.0 tps | 262K | $0.100 / $0.150 |
- Parasail100%Healthy24h 99.58%
- p50
- 669ms
- p99
- 2.82s
- Throughput
- 25 tps
- Context
- 262K
- $/Mtok
- $0.100 / $0.250
parasail/bf16bf16 - Together100%Healthy24h 99.81%
- p50
- 545ms
- p99
- 5.57s
- Throughput
- 61 tps
- Context
- 262K
- $/Mtok
- $0.170 / $0.250
together - Venice100%Healthy24h 99.89%
- p50
- 1.89s
- p99
- 15.4s
- Throughput
- 67 tps
- Context
- 256K
- $/Mtok
- $0.100 / $0.150
venice/fp8fp8 - DeepInfra99.89%Healthy24h 96.35%
- p50
- 591ms
- p99
- 2.87s
- Throughput
- 27 tps
- Context
- 262K
- $/Mtok
- $0.100 / $0.150
deepinfra/bf16bf16 - SiliconFlow99.81%Healthy24h 98.96%
- p50
- 2.11s
- p99
- 9.59s
- Throughput
- 5.0 tps
- Context
- 262K
- $/Mtok
- $0.100 / $0.150
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 and p99 are OpenRouter's rolling 30-minute windows.
Throughput
Median tokens per second.