modelstatus.dev

Qwen3 30B A3B Instruct 2507

Qwen3 30B A3B Instruct 2507: providers compared

Every endpoint serving this model, side by side. ◆ marks the best value in each column — per model, never fleet-wide.

  • CoreWeave100% (best)
    Healthy24h 98.50%
    7d
    97.12%
    30d
    97.12%
    p50
    338ms
    p99
    1.44s (best)
    Throughput
    52 tps (best)
    Context
    262K
    $/Mtok
    $0.100 / $0.300
    coreweave/bf16bf16
  • Healthy24h 99.89%
    7d
    99.86%
    30d
    99.86%
    p50
    1.36s
    p99
    6.07s
    Throughput
    24 tps
    Context
    128K
    $/Mtok
    $0.048 / $0.193 (best)
    streamlake
  • Nebius99.61%
    Healthy24h 98.33%
    7d
    96.91%
    30d
    96.91%
    p50
    349ms
    p99
    5.21s
    Throughput
    27 tps
    Context
    262K
    $/Mtok
    $0.100 / $0.300
    nebius/fp8fp8
  • Alibaba99.56%
    Healthy24h 99.95%
    7d
    99.96% (best)
    30d
    99.96% (best)
    p50
    337ms (best)
    p99
    1.62s
    Throughput
    44 tps
    Context
    131K
    $/Mtok
    $0.130 / $0.520
    alibaba
  • Degraded24h 90.28%
    7d
    90.45%
    30d
    90.45%
    p50
    2.21s
    p99
    10.1s
    Throughput
    9.0 tps
    Context
    262K
    $/Mtok
    $0.090 / $0.300
    siliconflow/fp8fp8

Measured 2m ago. Latency and throughput are OpenRouter's rolling 30-minute windows. ◆ marks the best value in each column among these endpoints.

Price vs latency

One dot per endpoint at the latest round · further left = faster, lower = cheaper · hover a dot for its tag

History

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.