Qwen3.6 27B
qwen/qwen3.6-27b
Compare with Qwen3.6 35B A3B, Qwen-Plus, Qwen3.6 Flash
CompareQwen3.6 27B
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
Alibabaalibaba | Healthy | 100% | 99.74% | 99.78% | 99.78% | 875ms | 10.8s | 55 tps | 262K | $0.450 / $2.70 |
| Healthy | 100% | 99.93% | 99.91% | 99.91% | 294ms | 3.27s | 64 tps | 262K | $0.600 / $3.60 | |
| Healthy | 100% | 99.45% | 97.34% | 97.34% | 939ms | 9.21s | 43 tps | 262K | $0.320 / $3.20 | |
| Degraded | 98.76% | 93.37% | 70.25% | 70.25% | 9.17s | 52.7s | 9.0 tps | 262K | $0.300 / $2.00 | |
Phalaphala | Degraded | 94.59% | 95.19% | 97.08% | 97.08% | 2.31s | 13.4s | 24 tps | 262K | $0.320 / $2.70 |
| Down | 87.74% | 93.45% | 92.49% | 92.49% | 4.06s | 31.2s | 19 tps | 262K | $0.300 / $3.20 | |
| No data | — | 96.40% | 95.54% | 95.54% | 662ms | 6.80s | 42 tps | 256K | $0.325 / $3.25 |
- Alibaba100%Healthy24h 99.74%
- 7d
- 99.78%
- 30d
- 99.78%
- p50
- 875ms
- p99
- 10.8s
- Throughput
- 55 tps
- Context
- 262K
- $/Mtok
- $0.450 / $2.70
alibaba - CoreWeave100%Healthy24h 99.93%
- 7d
- 99.91%
- 30d
- 99.91%
- p50
- 294ms
- p99
- 3.27s
- Throughput
- 64 tps
- Context
- 262K
- $/Mtok
- $0.600 / $3.60
coreweave/fp8fp8 - DeepInfra100%Healthy24h 99.45%
- 7d
- 97.34%
- 30d
- 97.34%
- p50
- 939ms
- p99
- 9.21s
- Throughput
- 43 tps
- Context
- 262K
- $/Mtok
- $0.320 / $3.20
deepinfra/fp8fp8 - Chutes98.76%Degraded24h 93.37%
- 7d
- 70.25%
- 30d
- 70.25%
- p50
- 9.17s
- p99
- 52.7s
- Throughput
- 9.0 tps
- Context
- 262K
- $/Mtok
- $0.300 / $2.00
chutes/fp8fp8 - Phala94.59%Degraded24h 95.19%
- 7d
- 97.08%
- 30d
- 97.08%
- p50
- 2.31s
- p99
- 13.4s
- Throughput
- 24 tps
- Context
- 262K
- $/Mtok
- $0.320 / $2.70
phala - SiliconFlow87.74%Down24h 93.45%
- 7d
- 92.49%
- 30d
- 92.49%
- p50
- 4.06s
- p99
- 31.2s
- Throughput
- 19 tps
- Context
- 262K
- $/Mtok
- $0.300 / $3.20
siliconflow/fp8fp8 - No data24h 96.40%
- 7d
- 95.54%
- 30d
- 95.54%
- p50
- 662ms
- p99
- 6.80s
- Throughput
- 42 tps
- Context
- 256K
- $/Mtok
- $0.325 / $3.25
venice/fp8fp8
Measured 1m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
History
1 endpoint reporting no data is omitted from the charts.
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 is OpenRouter's rolling 30-minute window.
Throughput
Median tokens per second.