modelstatus.dev

Qwen3 32B

qwen/qwen3-32b

Compare with Qwen3 235B A22B Instruct 2507, Qwen3 30B A3B Instruct 2507, Qwen3 Coder 480B A35B

CompareQwen3 32B
  • Healthy24h 99.97%
    7d
    99.72%
    30d
    99.72%
    p50
    354ms
    p99
    2.18s
    Throughput
    29 tps
    Context
    41K
    $/Mtok
    $0.080 / $0.280
    deepinfra/fp8fp8
  • Groq100%
    Healthy24h 99.87%
    7d
    99.96%
    30d
    99.96%
    p50
    414ms
    p99
    5.16s
    Throughput
    223 tps
    Context
    131K
    $/Mtok
    $0.290 / $0.590
    groq
  • Nebius100%
    Healthy24h 98.46%
    7d
    98.48%
    30d
    98.48%
    p50
    525ms
    p99
    5.08s
    Throughput
    24 tps
    Context
    41K
    $/Mtok
    $0.100 / $0.300
    nebius/basefp8
  • Healthy24h 92.58%
    7d
    90.83%
    30d
    90.83%
    p50
    1.98s
    p99
    95.8s
    Throughput
    14 tps
    Context
    131K
    $/Mtok
    $0.140 / $0.570
    siliconflow/fp8fp8

Measured 1m 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 is OpenRouter's rolling 30-minute window.

Throughput

Median tokens per second.