modelstatus.dev

Qwen3.5-35B-A3B

qwen/qwen3.5-35b-a3b

Compare with Qwen3 235B A22B Instruct 2507, Qwen3.5 397B A17B, Qwen3.6 35B A3B

  • CoreWeave100%
    Healthy24h 99.92%
    p50
    305ms
    p99
    6.09s
    Throughput
    216 tps
    Context
    262K
    $/Mtok
    $0.250 / $1.25
    coreweave/fp8fp8
  • DeepInfra100%
    Healthy24h 99.07%
    p50
    1.07s
    p99
    4.32s
    Throughput
    31 tps
    Context
    262K
    $/Mtok
    $0.140 / $1.00
    deepinfra/fp8fp8
  • Parasail100%
    Healthy24h 99.26%
    p50
    1.29s
    p99
    15.2s
    Throughput
    94 tps
    Context
    262K
    $/Mtok
    $0.150 / $1.00
    parasail/fp8fp8
  • Venice100%
    Healthy24h 99.88%
    p50
    1.25s
    p99
    13.0s
    Throughput
    119 tps
    Context
    256K
    $/Mtok
    $0.313 / $1.25
    venice
  • AtlasCloud98.53%
    Healthy24h 99.82%
    p50
    1.00s
    p99
    8.29s
    Throughput
    71 tps
    Context
    262K
    $/Mtok
    $0.225 / $1.80
    atlas-cloud/fp8fp8
  • AkashML
    No data24h
    p50
    p99
    Throughput
    Context
    262K
    $/Mtok
    $0.140 / $1.00
    akashml/fp8fp8
  • Alibaba
    No data24h 99.38%
    p50
    665ms
    p99
    29.8s
    Throughput
    86 tps
    Context
    262K
    $/Mtok
    $0.163 / $1.30
    alibaba
  • SiliconFlow
    No data24h 96.49%
    p50
    1.60s
    p99
    7.28s
    Throughput
    23 tps
    Context
    262K
    $/Mtok
    $0.240 / $1.80
    siliconflow/fp8fp8

Measured 3m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.

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

Throughput

Median tokens per second.