modelstatus.dev

Qwen3 VL 235B A22B Instruct

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

Compare its 5 providersIncident RSSCompare with Qwen3 235B A22B Instruct 2507, Qwen3 30B A3B Instruct 2507, Qwen3 Coder 480B A35B

CompareQwen3 VL 235B A22B Instruct
  • Healthy24h 99.18%
    7d
    98.94%
    30d
    99.47%
    p50
    845ms
    p99
    2.30s
    Throughput
    48 tps
    Context
    131K
    $/Mtok
    $0.260 / $1.04
    alibaba
  • Parasail98.84%
    Healthy24h 99.57%
    7d
    99.16%
    30d
    99.10%
    p50
    1.15s
    p99
    8.43s
    Throughput
    27 tps
    Context
    131K
    $/Mtok
    $0.210 / $1.90
    parasail/fp8fp8
  • DeepInfra97.39%
    Healthy24h 96.59%
    7d
    97.03%
    30d
    95.86%
    p50
    4.27s
    p99
    19.1s
    Throughput
    10 tps
    Context
    262K
    $/Mtok
    $0.200 / $0.880
    deepinfra/fp8fp8
  • Novita92.54%
    Degraded24h 96.13%
    7d
    96.20%
    30d
    95.80%
    p50
    2.10s
    p99
    66.1s
    Throughput
    39 tps
    Context
    131K
    $/Mtok
    $0.300 / $1.50
    novita/bf16bf16
  • Venice92.31%
    Degraded24h 97.48%
    7d
    96.65%
    30d
    96.21%
    p50
    2.15s
    p99
    9.42s
    Throughput
    30 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, averaged over the hour.

Throughput

Median tokens per second.

Daily availability

One row per endpoint · one dot per day · last 90 days.

worst hour ≥ 95%90–95%< 90%no data

Colour by each endpoint's worst hour of each UTC day · 5 endpoints · 46 days with data, 78 endpoint-days below 90%.