modelstatus.dev

Qwen3 30B A3B Instruct 2507

qwen/qwen3-30b-a3b-instruct-2507

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

  • Alibaba100%
    Healthy24h 99.96%
    p50
    314ms
    p99
    4.06s
    Throughput
    65 tps
    Context
    131K
    $/Mtok
    $0.130 / $0.520
    alibaba
  • StreamLake100%
    Healthy24h 99.72%
    p50
    1.74s
    p99
    5.26s
    Throughput
    18 tps
    Context
    128K
    $/Mtok
    $0.048 / $0.193
    streamlake
  • Nebius99.52%
    Degraded24h 86.20%
    p50
    345ms
    p99
    8.56s
    Throughput
    36 tps
    Context
    262K
    $/Mtok
    $0.100 / $0.300
    nebius/fp8fp8
  • CoreWeave98.88%
    Healthy24h 97.99%
    p50
    405ms
    p99
    6.61s
    Throughput
    23 tps
    Context
    262K
    $/Mtok
    $0.100 / $0.300
    coreweave/bf16bf16
  • SiliconFlow79.28%
    Down24h 89.93%
    p50
    2.77s
    p99
    7.46s
    Throughput
    11 tps
    Context
    262K
    $/Mtok
    $0.090 / $0.300
    siliconflow/fp8fp8

Measured 3m 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.

Throughput

Median tokens per second.