modelstatus.dev

Qwen3.6 27B

qwen/qwen3.6-27b

Compare with Qwen3.6 35B A3B, Qwen-Plus, Qwen3.6 Flash

CompareQwen3.6 27B
  • Healthy24h 99.93%
    7d
    99.91%
    30d
    99.91%
    p50
    329ms
    p99
    4.17s
    Throughput
    62 tps
    Context
    262K
    $/Mtok
    $0.600 / $3.60
    coreweave/fp8fp8
  • Healthy24h 99.47%
    7d
    97.34%
    30d
    97.34%
    p50
    1.76s
    p99
    46.4s
    Throughput
    39 tps
    Context
    262K
    $/Mtok
    $0.320 / $3.20
    deepinfra/fp8fp8
  • Chutes99.83%
    Healthy24h 93.29%
    7d
    70.25%
    30d
    70.25%
    p50
    1.40s
    p99
    20.4s
    Throughput
    24 tps
    Context
    262K
    $/Mtok
    $0.300 / $2.00
    chutes/fp8fp8
  • Phala98.04%
    Healthy24h 95.11%
    7d
    97.08%
    30d
    97.08%
    p50
    3.19s
    p99
    19.1s
    Throughput
    17 tps
    Context
    262K
    $/Mtok
    $0.320 / $2.70
    phala
  • Healthy24h 93.39%
    7d
    92.49%
    30d
    92.49%
    p50
    2.09s
    p99
    10.0s
    Throughput
    30 tps
    Context
    262K
    $/Mtok
    $0.300 / $3.20
    siliconflow/fp8fp8
  • No data24h 99.74%
    7d
    99.78%
    30d
    99.78%
    p50
    1.67s
    p99
    10.4s
    Throughput
    58 tps
    Context
    262K
    $/Mtok
    $0.450 / $2.70
    alibaba
  • Down24h 96.43%
    7d
    95.54%
    30d
    95.54%
    p50
    1.13s
    p99
    6.35s
    Throughput
    45 tps
    Context
    256K
    $/Mtok
    $0.325 / $3.25
    venice/fp8fp8

Measured 5m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.

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.