modelstatus.dev

Qwen3.6 35B A3B

qwen/qwen3.6-35b-a3b

Compare with Qwen3.6 27B, Qwen-Plus, Qwen3.6 Flash

CompareQwen3.6 35B A3B
  • AkashML100%
    Healthy24h 99.71%
    p50
    667ms
    p99
    5.60s
    Throughput
    76 tps
    Context
    262K
    $/Mtok
    $0.140 / $1.00
    akashml/fp8fp8
  • AtlasCloud100%
    Healthy24h 99.81%
    p50
    838ms
    p99
    5.95s
    Throughput
    105 tps
    Context
    262K
    $/Mtok
    $0.186 / $1.11
    atlas-cloud/fp8fp8
  • CoreWeave100%
    Healthy24h 99.65%
    p50
    411ms
    p99
    6.17s
    Throughput
    156 tps
    Context
    262K
    $/Mtok
    $0.250 / $1.25
    coreweave/fp8fp8
  • Parasail100%
    Healthy24h 99.49%
    p50
    713ms
    p99
    7.51s
    Throughput
    41 tps
    Context
    262K
    $/Mtok
    $0.150 / $1.00
    parasail/fp8fp8
  • Phala100%
    Healthy24h 99.13%
    p50
    1.61s
    p99
    8.44s
    Throughput
    94 tps
    Context
    262K
    $/Mtok
    $0.200 / $1.27
    phala
  • SiliconFlow100%
    Healthy24h 98.53%
    p50
    1.97s
    p99
    21.4s
    Throughput
    47 tps
    Context
    262K
    $/Mtok
    $0.200 / $1.60
    siliconflow/fp8fp8
  • Venice100%
    Healthy24h 99.84%
    p50
    754ms
    p99
    4.05s
    Throughput
    147 tps
    Context
    256K
    $/Mtok
    $0.098 / $0.950
    venice/fp8fp8
  • DeepInfra98.17%
    Healthy24h 96.00%
    p50
    800ms
    p99
    27.9s
    Throughput
    23 tps
    Context
    262K
    $/Mtok
    $0.100 / $0.950
    deepinfra/fp8fp8
  • Io Net95.77%
    Healthy24h 99.01%
    p50
    1.55s
    p99
    11.0s
    Throughput
    26 tps
    Context
    262K
    $/Mtok
    $0.190 / $1.19
    io-net/fp8fp8

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 and p99 are OpenRouter's rolling 30-minute windows, averaged over the hour.

Throughput

Median tokens per second.