modelstatus.dev

Qwen3.5-9B

qwen/qwen3.5-9b

Compare with Qwen3.5 397B A17B, Qwen3.5-35B-A3B, Qwen3.5-27B

CompareQwen3.5-9B
  • Healthy24h 99.70%
    7d
    99.80%
    30d
    99.80%
    p50
    300ms
    p99
    3.96s
    Throughput
    52 tps
    Context
    262K
    $/Mtok
    $0.170 / $0.250
    together
  • Venice100%
    Healthy24h 99.95%
    7d
    99.94%
    30d
    99.94%
    p50
    1.15s
    p99
    3.88s
    Throughput
    19 tps
    Context
    256K
    $/Mtok
    $0.100 / $0.150
    venice/fp8fp8
  • Healthy24h 97.80%
    7d
    98.45%
    30d
    98.45%
    p50
    1.93s
    p99
    16.4s
    Throughput
    10 tps
    Context
    262K
    $/Mtok
    $0.100 / $0.150
    siliconflow/fp8fp8
  • DeepInfra94.66%
    Degraded24h 96.55%
    7d
    96.32%
    30d
    96.32%
    p50
    613ms
    p99
    1.90s
    Throughput
    35 tps
    Context
    262K
    $/Mtok
    $0.100 / $0.150
    deepinfra/bf16bf16
  • No data24h 99.54%
    7d
    99.65%
    30d
    99.65%
    p50
    679ms
    p99
    2.93s
    Throughput
    12 tps
    Context
    262K
    $/Mtok
    $0.100 / $0.250
    parasail/bf16bf16

Measured 1m 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 is OpenRouter's rolling 30-minute window.

Throughput

Median tokens per second.