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 99.92%
    7d
    99.62%
    30d
    99.83%
    p50
    761ms
    p99
    14.8s
    Throughput
    53 tps
    Context
    262K
    $/Mtok
    $0.220 / $0.880
    google-vertex/us-south1
  • Parasail99.90%
    Healthy24h 99.94%
    7d
    99.91%
    30d
    99.84%
    p50
    463ms
    p99
    2.75s
    Throughput
    37 tps
    Context
    131K
    $/Mtok
    $0.140 / $0.800
    parasail/fp8fp8
  • GMICloud99.69%
    Healthy24h 99.02%
    7d
    98.21%
    30d
    98.53%
    p50
    1.01s
    p99
    4.99s
    Throughput
    57 tps
    Context
    262K
    $/Mtok
    $0.087 / $0.350
    gmicloud/fp8fp8
  • Novita99.47%
    Healthy24h 97.29%
    7d
    96.78%
    30d
    97.94%
    p50
    752ms
    p99
    73.2s
    Throughput
    51 tps
    Context
    131K
    $/Mtok
    $0.090 / $0.580
    novita/fp8fp8
  • Healthy24h 99.08%
    7d
    98.25%
    30d
    98.80%
    p50
    619ms
    p99
    25.1s
    Throughput
    52 tps
    Context
    128K
    $/Mtok
    $0.210 / $0.840
    streamlake
  • Alibaba99.02%
    Healthy24h 98.89%
    7d
    97.10%
    30d
    99.11%
    p50
    470ms
    p99
    2.11s
    Throughput
    55 tps
    Context
    131K
    $/Mtok
    $0.150 / $0.598
    alibaba
  • DeepInfra94.88%
    Down24h 91.26%
    7d
    85.69%
    30d
    91.17%
    p50
    4.16s
    p99
    21.3s
    Throughput
    8.0 tps
    Context
    262K
    $/Mtok
    $0.090 / $0.550
    deepinfra/fp8fp8
  • Venice89.60%
    Down24h 92.61%
    7d
    91.13%
    30d
    94.31%
    p50
    813ms
    p99
    32.6s
    Throughput
    30 tps
    Context
    128K
    $/Mtok
    $0.150 / $0.750
    venice/fp8fp8
  • Nebius87.30%
    Down24h 90.74%
    7d
    93.18%
    30d
    90.90%
    p50
    561ms
    p99
    15.9s
    Throughput
    52 tps
    Context
    262K
    $/Mtok
    $0.200 / $0.600
    nebius/fp8fp8
  • No data24h —
    7d
    —
    30d
    98.45%
    p50
    —
    p99
    —
    Throughput
    —
    Context
    131K
    $/Mtok
    $0.200 / $0.880
    atlas-cloud/fp8fp8

Measured 1m 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, 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 · 10 endpoints · 47 days with data, 159 endpoint-days below 90%.

Price changes