modelstatus.dev

Qwen3.5-122B-A10B

qwen/qwen3.5-122b-a10b

Compare with Qwen3.5 397B A17B, Qwen3.5-35B-A3B, Qwen3.5-27B

CompareQwen3.5-122B-A10B
  • Novita100%
    Healthy24h 99.59%
    p50
    1.61s
    p99
    12.5s
    Throughput
    34 tps
    Context
    262K
    $/Mtok
    $0.400 / $3.20
    novita/bf16bf16
  • SiliconFlow100%
    Healthy24h 98.07%
    p50
    1.41s
    p99
    6.27s
    Throughput
    43 tps
    Context
    262K
    $/Mtok
    $0.260 / $2.08
    siliconflow/fp8fp8
  • Alibaba96.92%
    Healthy24h 99.78%
    p50
    1.39s
    p99
    6.04s
    Throughput
    20 tps
    Context
    262K
    $/Mtok
    $0.260 / $2.08
    alibaba
  • AtlasCloud
    Degraded24h 99.52%
    p50
    3.28s
    p99
    11.6s
    Throughput
    10 tps
    Context
    262K
    $/Mtok
    $0.300 / $2.40
    atlas-cloud/fp8fp8
  • DeepInfra
    No data24h 99.48%
    p50
    1.04s
    p99
    2.21s
    Throughput
    19 tps
    Context
    262K
    $/Mtok
    $0.290 / $2.40
    deepinfra/fp4fp4

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 and p99 are OpenRouter's rolling 30-minute windows.

Throughput

Median tokens per second.