modelstatus.dev

Qwen3 Coder 480B A35B

qwen/qwen3-coder

Compare with Qwen3 235B A22B Instruct 2507, Qwen3 30B A3B Instruct 2507, Qwen3 Next 80B A3B Instruct

CompareQwen3 Coder 480B A35B
  • Novita100%
    Degraded24h 93.21%
    7d
    91.74%
    30d
    91.74%
    p50
    958ms
    p99
    15.2s
    Throughput
    37 tps
    Context
    262K
    $/Mtok
    $0.380 / $1.55
    novita/fp8fp8
  • Venice99.39%
    Degraded24h 91.32%
    7d
    85.85%
    30d
    85.85%
    p50
    1.06s
    p99
    14.7s
    Throughput
    33 tps
    Context
    256K
    $/Mtok
    $0.350 / $1.50
    venice/fp8fp8
  • Google99.10%
    Healthy24h 99.30%
    7d
    99.31%
    30d
    99.31%
    p50
    439ms
    p99
    2.49s
    Throughput
    82 tps
    Context
    262K
    $/Mtok
    $0.220 / $1.80
    google-vertex/us-south1
  • DeepInfra98.02%
    Healthy24h 96.31%
    7d
    94.79%
    30d
    94.79%
    p50
    345ms
    p99
    10.1s
    Throughput
    78 tps
    Context
    262K
    $/Mtok
    $0.300 / $1.00
    deepinfra/turbofp4
  • No data24h 99.79%
    7d
    99.88%
    30d
    99.88%
    p50
    1.21s
    p99
    16.5s
    Throughput
    22 tps
    Context
    262K
    $/Mtok
    $0.975 / $4.88
    alibaba/opensource

Measured 2m 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.