modelstatus.dev

Qwen3.8 2.4T A95B

qwen/qwen3.8-2.4t-a95b

Compare with Qwen3.8 27B, Qwen-Plus, Qwen3.8 Max

CompareQwen3.8 2.4T A95B
  • Healthy24h 93.56%
    7d
    98.60%
    30d
    98.60%
    p50
    3.30s
    p99
    18.0s
    Throughput
    13 tps
    Context
    262K
    $/Mtok
    $2.00 / $6.00
    digitalocean
  • Healthy24h 99.90%
    7d
    99.76%
    30d
    99.76%
    p50
    620ms
    p99
    5.97s
    Throughput
    74 tps
    Context
    1.0M
    $/Mtok
    $2.50 / $6.25
    together
  • DeepInfra95.00%
    Healthy24h 95.18%
    7d
    96.46%
    30d
    96.46%
    p50
    1.34s
    p99
    8.08s
    Throughput
    8.0 tps
    Context
    262K
    $/Mtok
    $2.00 / $6.00
    deepinfra/fp4fp4
  • No data24h 99.95%
    7d
    100%
    30d
    100%
    p50
    1.41s
    p99
    9.32s
    Throughput
    41 tps
    Context
    1.0M
    $/Mtok
    $2.00 / $6.00
    alibaba
  • No data24h 98.99%
    7d
    99.03%
    30d
    99.03%
    p50
    1.76s
    p99
    24.8s
    Throughput
    108 tps
    Context
    1.0M
    $/Mtok
    $2.00 / $6.00
    modal/nvfp4nvfp4
  • No data24h 99.92%
    7d
    99.77%
    30d
    99.77%
    p50
    1.36s
    p99
    34.9s
    Throughput
    42 tps
    Context
    1.0M
    $/Mtok
    $2.00 / $6.00
    siliconflow/fp8fp8
  • No data24h 99.25%
    7d
    98.46%
    30d
    98.46%
    p50
    1.54s
    p99
    10.1s
    Throughput
    89 tps
    Context
    262K
    $/Mtok
    $2.50 / $7.50
    venice

Measured 1m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.

4 endpoints reporting no data are 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.