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
  • Healthy24h 99.77%
    7d
    99.14%
    30d
    99.14%
    p50
    1.65s
    p99
    6.44s
    Throughput
    31 tps
    Context
    262K
    $/Mtok
    $0.260 / $2.08
    siliconflow/fp8fp8
  • DeepInfra99.63%
    Healthy24h 99.89%
    7d
    98.34%
    30d
    98.34%
    p50
    573ms
    p99
    2.08s
    Throughput
    88 tps
    Context
    262K
    $/Mtok
    $0.290 / $2.40
    deepinfra/fp4fp4
  • Healthy24h 99.60%
    7d
    99.49%
    30d
    99.49%
    p50
    2.70s
    p99
    7.56s
    Throughput
    62 tps
    Context
    262K
    $/Mtok
    $0.300 / $2.40
    atlas-cloud/fp8fp8
  • Novita98.53%
    Healthy24h 99.73%
    7d
    99.68%
    30d
    99.68%
    p50
    1.42s
    p99
    6.26s
    Throughput
    38 tps
    Context
    262K
    $/Mtok
    $0.400 / $3.20
    novita/bf16bf16
  • Alibaba86.41%
    Down24h 98.15%
    7d
    99.03%
    30d
    99.03%
    p50
    2.26s
    p99
    15.4s
    Throughput
    47 tps
    Context
    262K
    $/Mtok
    $0.260 / $2.08
    alibaba

Measured 2m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.

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.