modelstatus.dev

Qwen3.5-27B

qwen/qwen3.5-27b

Compare with Qwen3.5 397B A17B, Qwen3.5-35B-A3B, Qwen3.5-122B-A10B

CompareQwen3.5-27B
  • DeepInfra100%
    Healthy24h 96.24%
    p50
    385ms
    p99
    57.8s
    Throughput
    48 tps
    Context
    262K
    $/Mtok
    $0.260 / $2.60
    deepinfra/fp8fp8
  • Novita100%
    Healthy24h 99.84%
    p50
    932ms
    p99
    4.86s
    Throughput
    15 tps
    Context
    262K
    $/Mtok
    $0.300 / $2.40
    novita/bf16bf16
  • SiliconFlow100%
    Healthy24h 98.59%
    p50
    1.65s
    p99
    9.55s
    Throughput
    11 tps
    Context
    262K
    $/Mtok
    $0.250 / $2.00
    siliconflow/fp8fp8
  • Alibaba99.75%
    Healthy24h 97.49%
    p50
    1.39s
    p99
    8.76s
    Throughput
    25 tps
    Context
    262K
    $/Mtok
    $0.195 / $1.56
    alibaba
  • AtlasCloud99.37%
    Healthy24h 97.72%
    p50
    1.39s
    p99
    5.96s
    Throughput
    28 tps
    Context
    262K
    $/Mtok
    $0.270 / $2.16
    atlas-cloud/fp8fp8
  • Phala50.00%
    Down24h 91.41%
    p50
    4.33s
    p99
    12.7s
    Throughput
    11 tps
    Context
    262K
    $/Mtok
    $0.300 / $2.40
    phala

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.