modelstatus.dev

Qwen3.5-35B-A3B

qwen/qwen3.5-35b-a3b

Compare with Qwen3.5 397B A17B, Qwen3.5-27B, Qwen3.5-122B-A10B

CompareQwen3.5-35B-A3B
  • Alibaba100%
    Healthy24h 99.33%
    p50
    707ms
    p99
    6.61s
    Throughput
    77 tps
    Context
    262K
    $/Mtok
    $0.163 / $1.30
    alibaba
  • AtlasCloud100%
    Healthy24h 99.71%
    p50
    980ms
    p99
    4.16s
    Throughput
    80 tps
    Context
    262K
    $/Mtok
    $0.225 / $1.80
    atlas-cloud/fp8fp8
  • CoreWeave100%
    Healthy24h 99.93%
    p50
    341ms
    p99
    7.34s
    Throughput
    183 tps
    Context
    262K
    $/Mtok
    $0.250 / $1.25
    coreweave/fp8fp8
  • Parasail100%
    Healthy24h 99.34%
    p50
    1.36s
    p99
    12.9s
    Throughput
    95 tps
    Context
    262K
    $/Mtok
    $0.150 / $1.00
    parasail/fp8fp8
  • Venice100%
    Healthy24h 99.86%
    p50
    758ms
    p99
    9.49s
    Throughput
    140 tps
    Context
    256K
    $/Mtok
    $0.313 / $1.25
    venice
  • DeepInfra76.09%
    Down24h 98.59%
    p50
    589ms
    p99
    24.3s
    Throughput
    30 tps
    Context
    262K
    $/Mtok
    $0.140 / $1.00
    deepinfra/fp8fp8
  • AkashML
    No data24h
    p50
    p99
    Throughput
    Context
    262K
    $/Mtok
    $0.140 / $1.00
    akashml/fp8fp8
  • SiliconFlow
    Down24h 94.03%
    p50
    1.98s
    p99
    48.1s
    Throughput
    21 tps
    Context
    262K
    $/Mtok
    $0.240 / $1.80
    siliconflow/fp8fp8

Measured 4m 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.