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
  • Alibaba100%
    Healthy24h 99.43%
    p50
    1.30s
    p99
    23.3s
    Throughput
    18 tps
    Context
    262K
    $/Mtok
    $0.975 / $4.88
    alibaba/opensource
  • DeepInfra100%
    Healthy24h 96.88%
    p50
    308ms
    p99
    22.2s
    Throughput
    90 tps
    Context
    262K
    $/Mtok
    $0.300 / $1.00
    deepinfra/turbofp4
  • Novita99.19%
    Degraded24h 89.56%
    p50
    992ms
    p99
    23.5s
    Throughput
    23 tps
    Context
    262K
    $/Mtok
    $0.380 / $1.55
    novita/fp8fp8
  • Google
    No data24h 99.76%
    p50
    422ms
    p99
    2.12s
    Throughput
    64 tps
    Context
    262K
    $/Mtok
    $0.220 / $1.80
    google-vertex/us-south1
  • Venice
    No data24h 85.53%
    p50
    37.8s
    p99
    124s
    Throughput
    4.0 tps
    Context
    256K
    $/Mtok
    $0.350 / $1.50
    venice/fp8fp8

Measured 3m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.

2 endpoints reporting no data are 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 and p99 are OpenRouter's rolling 30-minute windows, averaged over the hour.

Throughput

Median tokens per second.