modelstatus.dev

Qwen3 235B A22B Instruct 2507

qwen/qwen3-235b-a22b-2507InputtextOutputtext

Compare its 10 providersIncident RSSCompare with Qwen3 30B A3B Instruct 2507, Qwen3 Coder 480B A35B, Qwen3 Next 80B A3B Instruct

CompareQwen3 235B A22B Instruct 2507
  • Google100%
    Healthy24h 99.93%
    7d
    99.62%
    30d
    99.83%
    p50
    600ms
    p99
    10.2s
    Throughput
    43 tps
    Context
    262K
    $/Mtok
    $0.220 / $0.880
    google-vertex/us-south1
  • Nebius100%
    Down24h 92.03%
    7d
    93.36%
    30d
    90.95%
    p50
    451ms
    p99
    26.0s
    Throughput
    61 tps
    Context
    262K
    $/Mtok
    $0.200 / $0.600
    nebius/fp8fp8
  • Healthy24h 99.95%
    7d
    99.91%
    30d
    99.84%
    p50
    433ms
    p99
    2.54s
    Throughput
    42 tps
    Context
    131K
    $/Mtok
    $0.140 / $0.800
    parasail/fp8fp8
  • Healthy24h 98.98%
    7d
    98.25%
    30d
    98.80%
    p50
    590ms
    p99
    24.1s
    Throughput
    51 tps
    Context
    128K
    $/Mtok
    $0.210 / $0.840
    streamlake
  • Alibaba99.94%
    Healthy24h 98.96%
    7d
    97.07%
    30d
    99.12%
    p50
    535ms
    p99
    1.96s
    Throughput
    58 tps
    Context
    131K
    $/Mtok
    $0.150 / $0.598
    alibaba
  • GMICloud99.49%
    Healthy24h 98.91%
    7d
    98.21%
    30d
    98.48%
    p50
    1.18s
    p99
    19.6s
    Throughput
    38 tps
    Context
    262K
    $/Mtok
    $0.087 / $0.350
    gmicloud/fp8fp8
  • Novita97.93%
    Healthy24h 97.59%
    7d
    96.66%
    30d
    97.87%
    p50
    702ms
    p99
    12.4s
    Throughput
    48 tps
    Context
    131K
    $/Mtok
    $0.090 / $0.580
    novita/fp8fp8
  • DeepInfra73.04%
    Down24h 94.19%
    7d
    85.29%
    30d
    91.19%
    p50
    777ms
    p99
    11.4s
    Throughput
    10 tps
    Context
    262K
    $/Mtok
    $0.090 / $0.550
    deepinfra/fp8fp8
  • No data24h —
    7d
    —
    30d
    98.47%
    p50
    —
    p99
    —
    Throughput
    —
    Context
    131K
    $/Mtok
    $0.200 / $0.880
    atlas-cloud/fp8fp8
  • No data24h 94.29%
    7d
    90.96%
    30d
    94.26%
    p50
    4.72s
    p99
    8.66s
    Throughput
    7.5 tps
    Context
    128K
    $/Mtok
    $0.150 / $0.750
    venice/fp8fp8

Measured 4m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.

1 endpoint has no chartable data in this range.

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.

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 · 10 endpoints · 46 days with data, 158 endpoint-days below 90%.

Price changes