modelstatus.dev

Qwen3.5-27B

qwen/qwen3.5-27b

Compare with Qwen3.5 397B A17B, Qwen3.5-35B-A3B, Qwen3.5-122B-A10B

CompareQwen3.5-27B
  • Degraded24h 97.03%
    7d
    98.17%
    30d
    98.17%
    p50
    981ms
    p99
    35.2s
    Throughput
    23 tps
    Context
    262K
    $/Mtok
    $0.195 / $1.56
    alibaba
  • Healthy24h 99.11%
    7d
    98.97%
    30d
    98.97%
    p50
    1.07s
    p99
    7.71s
    Throughput
    18 tps
    Context
    262K
    $/Mtok
    $0.270 / $2.16
    atlas-cloud/fp8fp8
  • Healthy24h 98.85%
    7d
    97.87%
    30d
    97.87%
    p50
    386ms
    p99
    5.67s
    Throughput
    46 tps
    Context
    262K
    $/Mtok
    $0.260 / $2.60
    deepinfra/fp8fp8
  • Healthy24h 98.88%
    7d
    98.97%
    30d
    98.97%
    p50
    1.85s
    p99
    24.6s
    Throughput
    10 tps
    Context
    262K
    $/Mtok
    $0.250 / $2.00
    siliconflow/fp8fp8
  • Novita97.92%
    Healthy24h 99.70%
    7d
    99.79%
    30d
    99.79%
    p50
    1.25s
    p99
    8.96s
    Throughput
    12 tps
    Context
    262K
    $/Mtok
    $0.300 / $2.40
    novita/bf16bf16
  • No data24h 65.32%
    7d
    62.74%
    30d
    62.74%
    p50
    8.01s
    p99
    14.1s
    Throughput
    7.0 tps
    Context
    262K
    $/Mtok
    $0.300 / $2.40
    phala

Measured 1m 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.