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 99.89%
    7d
    99.91%
    30d
    99.91%
    p50
    691ms
    p99
    4.14s
    Throughput
    37 tps
    Context
    131K
    $/Mtok
    $0.260 / $1.04
    alibaba
  • Parasail99.88%
    Healthy24h 99.34%
    7d
    99.37%
    30d
    99.37%
    p50
    1.48s
    p99
    5.80s
    Throughput
    26 tps
    Context
    131K
    $/Mtok
    $0.210 / $1.90
    parasail/fp8fp8
  • DeepInfra99.11%
    Healthy24h 98.17%
    7d
    96.62%
    30d
    96.62%
    p50
    749ms
    p99
    5.91s
    Throughput
    16 tps
    Context
    262K
    $/Mtok
    $0.200 / $0.880
    deepinfra/fp8fp8
  • Novita98.73%
    Healthy24h 93.27%
    7d
    94.80%
    30d
    94.80%
    p50
    1.55s
    p99
    11.3s
    Throughput
    14 tps
    Context
    131K
    $/Mtok
    $0.300 / $1.50
    novita/bf16bf16
  • Venice81.05%
    Down24h 96.99%
    7d
    94.42%
    30d
    94.42%
    p50
    1.68s
    p99
    8.79s
    Throughput
    32 tps
    Context
    128K
    $/Mtok
    $0.210 / $1.90
    venice/fp8fp8

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.