Qwen3.6 27B
qwen/qwen3.6-27b
Compare with Qwen3.6 35B A3B, Qwen-Plus, Qwen3.6 Flash
CompareQwen3.6 27B
| Provider | State | Uptime 5m | 24h | p50 latency | p99 | Throughput | Context | $/Mtok |
|---|---|---|---|---|---|---|---|---|
CoreWeavecoreweave/fp8fp8 | Healthy | 100% | 99.67% | 896ms | 2.75s | 52 tps | 262K | $0.600 / $3.60 |
Alibabaalibaba | Healthy | 98.95% | 99.85% | 1.29s | 18.8s | 44 tps | 262K | $0.450 / $2.70 |
Venicevenice/fp8fp8 | Degraded | 96.09% | 97.49% | 933ms | 5.87s | 49 tps | 256K | $0.325 / $3.25 |
Phalaphala | Healthy | 95.12% | 98.32% | 1.35s | 10.7s | 31 tps | 262K | $0.320 / $2.70 |
DeepInfradeepinfra/fp8fp8 | Degraded | 94.49% | 98.95% | 1.02s | 11.7s | 25 tps | 262K | $0.320 / $3.20 |
SiliconFlowsiliconflow/fp8fp8 | Down | 58.90% | 95.44% | 1.26s | 8.39s | 38 tps | 262K | $0.300 / $3.20 |
Chuteschutes/fp8fp8 | Down | — | 92.79% | 3.30s | 34.8s | 19 tps | 262K | $0.300 / $2.00 |
- CoreWeave100%Healthy24h 99.67%
- p50
- 896ms
- p99
- 2.75s
- Throughput
- 52 tps
- Context
- 262K
- $/Mtok
- $0.600 / $3.60
coreweave/fp8fp8 - Alibaba98.95%Healthy24h 99.85%
- p50
- 1.29s
- p99
- 18.8s
- Throughput
- 44 tps
- Context
- 262K
- $/Mtok
- $0.450 / $2.70
alibaba - Venice96.09%Degraded24h 97.49%
- p50
- 933ms
- p99
- 5.87s
- Throughput
- 49 tps
- Context
- 256K
- $/Mtok
- $0.325 / $3.25
venice/fp8fp8 - Phala95.12%Healthy24h 98.32%
- p50
- 1.35s
- p99
- 10.7s
- Throughput
- 31 tps
- Context
- 262K
- $/Mtok
- $0.320 / $2.70
phala - DeepInfra94.49%Degraded24h 98.95%
- p50
- 1.02s
- p99
- 11.7s
- Throughput
- 25 tps
- Context
- 262K
- $/Mtok
- $0.320 / $3.20
deepinfra/fp8fp8 - SiliconFlow58.90%Down24h 95.44%
- p50
- 1.26s
- p99
- 8.39s
- Throughput
- 38 tps
- Context
- 262K
- $/Mtok
- $0.300 / $3.20
siliconflow/fp8fp8 - Chutes—Down24h 92.79%
- p50
- 3.30s
- p99
- 34.8s
- Throughput
- 19 tps
- Context
- 262K
- $/Mtok
- $0.300 / $2.00
chutes/fp8fp8
Measured 3m 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.