modelstatus.dev

← Qwen3 Coder Next

Qwen3 Coder Next: providers compared

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

  • Alibaba100%◆ (best)
    Healthy24h 98.77%
    7d
    99.72%
    30d
    99.19%
    p50
    827ms
    p99
    1.50s◆ (best)
    Throughput
    156 tps◆ (best)
    Context
    262K
    $/Mtok
    $0.300 / $1.50
    alibaba
  • Parasail100%◆ (best)
    Healthy24h 99.94%
    7d
    99.96%◆ (best)
    30d
    99.96%◆ (best)
    p50
    468ms◆ (best)
    p99
    2.92s
    Throughput
    70 tps
    Context
    262K
    $/Mtok
    $0.120 / $0.800◆ (best)
    parasail/bf16bf16
  • StreamLake100%◆ (best)
    Healthy24h 99.46%
    7d
    99.34%
    30d
    99.36%
    p50
    1.30s
    p99
    20.2s
    Throughput
    74 tps
    Context
    256K
    $/Mtok
    $0.180 / $0.900
    streamlake
  • Novita97.35%
    Healthy24h 99.58%
    7d
    99.66%
    30d
    99.63%
    p50
    1.31s
    p99
    3.45s
    Throughput
    156 tps◆ (best)
    Context
    262K
    $/Mtok
    $0.200 / $1.50
    novita/fp8fp8

Measured 4m 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.