modelstatus.dev

Qwen3 VL 235B A22B Instruct

qwen/qwen3-vl-235b-a22b-instruct

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

CompareQwen3 VL 235B A22B Instruct
  • Healthy24h 99.90%
    7d
    99.91%
    30d
    99.91%
    p50
    653ms
    p99
    3.70s
    Throughput
    22 tps
    Context
    131K
    $/Mtok
    $0.260 / $1.04
    alibaba
  • Parasail99.77%
    Healthy24h 99.36%
    7d
    99.38%
    30d
    99.38%
    p50
    1.08s
    p99
    5.64s
    Throughput
    25 tps
    Context
    131K
    $/Mtok
    $0.210 / $1.90
    parasail/fp8fp8
  • Venice92.02%
    Degraded24h 97.29%
    7d
    94.46%
    30d
    94.46%
    p50
    1.73s
    p99
    7.05s
    Throughput
    30 tps
    Context
    128K
    $/Mtok
    $0.210 / $1.90
    venice/fp8fp8
  • DeepInfra89.74%
    Down24h 98.21%
    7d
    96.71%
    30d
    96.71%
    p50
    986ms
    p99
    17.5s
    Throughput
    12 tps
    Context
    262K
    $/Mtok
    $0.200 / $0.880
    deepinfra/fp8fp8
  • Novita71.43%
    Down24h 92.46%
    7d
    94.69%
    30d
    94.69%
    p50
    1.32s
    p99
    10.1s
    Throughput
    13 tps
    Context
    131K
    $/Mtok
    $0.300 / $1.50
    novita/bf16bf16

Measured 2m 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.