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 |
|---|---|---|---|---|---|---|---|---|
Alibabaalibaba | Healthy | 100% | 99.84% | 1.13s | 14.5s | 27 tps | 262K | $0.450 / $2.70 |
CoreWeavecoreweave/fp8fp8 | Healthy | 100% | 99.66% | 381ms | 3.91s | 62 tps | 262K | $0.600 / $3.60 |
Venicevenice/fp8fp8 | Healthy | 100% | 97.25% | 819ms | 5.23s | 48 tps | 256K | $0.325 / $3.25 |
SiliconFlowsiliconflow/fp8fp8 | Healthy | 99.92% | 95.67% | 1.08s | 24.9s | 2.0 tps | 262K | $0.300 / $3.20 |
DeepInfradeepinfra/fp8fp8 | Healthy | 99.76% | 98.88% | 957ms | 7.92s | 28 tps | 262K | $0.320 / $3.20 |
Phalaphala | Healthy | 96.00% | 98.36% | 1.09s | 9.25s | 34 tps | 262K | $0.320 / $2.70 |
Chuteschutes/fp8fp8 | Down | 82.22% | 92.44% | 12.2s | 53.7s | 6.0 tps | 262K | $0.300 / $2.00 |
- Alibaba100%Healthy24h 99.84%
- p50
- 1.13s
- p99
- 14.5s
- Throughput
- 27 tps
- Context
- 262K
- $/Mtok
- $0.450 / $2.70
alibaba - CoreWeave100%Healthy24h 99.66%
- p50
- 381ms
- p99
- 3.91s
- Throughput
- 62 tps
- Context
- 262K
- $/Mtok
- $0.600 / $3.60
coreweave/fp8fp8 - Venice100%Healthy24h 97.25%
- p50
- 819ms
- p99
- 5.23s
- Throughput
- 48 tps
- Context
- 256K
- $/Mtok
- $0.325 / $3.25
venice/fp8fp8 - SiliconFlow99.92%Healthy24h 95.67%
- p50
- 1.08s
- p99
- 24.9s
- Throughput
- 2.0 tps
- Context
- 262K
- $/Mtok
- $0.300 / $3.20
siliconflow/fp8fp8 - DeepInfra99.76%Healthy24h 98.88%
- p50
- 957ms
- p99
- 7.92s
- Throughput
- 28 tps
- Context
- 262K
- $/Mtok
- $0.320 / $3.20
deepinfra/fp8fp8 - Phala96.00%Healthy24h 98.36%
- p50
- 1.09s
- p99
- 9.25s
- Throughput
- 34 tps
- Context
- 262K
- $/Mtok
- $0.320 / $2.70
phala - Chutes82.22%Down24h 92.44%
- p50
- 12.2s
- p99
- 53.7s
- Throughput
- 6.0 tps
- Context
- 262K
- $/Mtok
- $0.300 / $2.00
chutes/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, averaged over the hour.
Throughput
Median tokens per second.