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
  • CoreWeave100%
    Healthy24h 99.92%
    p50
    306ms
    p99
    5.89s
    Throughput
    218 tps
    Context
    262K
    $/Mtok
    $0.250 / $1.25
    coreweave/fp8fp8
  • DeepInfra100%
    Healthy24h 99.07%
    p50
    855ms
    p99
    2.28s
    Throughput
    81 tps
    Context
    262K
    $/Mtok
    $0.140 / $1.00
    deepinfra/fp8fp8
  • Parasail100%
    Healthy24h 99.25%
    p50
    673ms
    p99
    14.2s
    Throughput
    92 tps
    Context
    262K
    $/Mtok
    $0.150 / $1.00
    parasail/fp8fp8
  • Venice100%
    Healthy24h 99.88%
    p50
    1.16s
    p99
    21.0s
    Throughput
    94 tps
    Context
    256K
    $/Mtok
    $0.313 / $1.25
    venice
  • AkashML
    No data24h
    p50
    p99
    Throughput
    Context
    262K
    $/Mtok
    $0.140 / $1.00
    akashml/fp8fp8
  • Alibaba
    No data24h 99.39%
    p50
    656ms
    p99
    18.9s
    Throughput
    82 tps
    Context
    262K
    $/Mtok
    $0.163 / $1.30
    alibaba
  • AtlasCloud
    No data24h 99.78%
    p50
    1.11s
    p99
    3.20s
    Throughput
    47 tps
    Context
    262K
    $/Mtok
    $0.225 / $1.80
    atlas-cloud/fp8fp8
  • SiliconFlow
    No data24h 95.73%
    p50
    1.73s
    p99
    8.08s
    Throughput
    26 tps
    Context
    262K
    $/Mtok
    $0.240 / $1.80
    siliconflow/fp8fp8

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

Throughput

Median tokens per second.