modelstatus.dev

MiniMax M3

minimax/minimax-m3

Compare with MiniMax M2.7, MiniMax M2.5, MiniMax M3 (batch)

CompareMiniMax M3
  • AtlasCloud100%
    Healthy24h 99.33%
    p50
    882ms
    p99
    4.07s
    Throughput
    87 tps
    Context
    524K
    $/Mtok
    $0.300 / $1.20
    atlas-cloud/fp8fp8
  • Morph100%
    Healthy24h 95.74%
    p50
    2.08s
    p99
    10.9s
    Throughput
    26 tps
    Context
    256K
    $/Mtok
    $0.300 / $1.20
    morph/fp4fp4
  • Venice100%
    Healthy24h 99.83%
    p50
    863ms
    p99
    7.65s
    Throughput
    117 tps
    Context
    524K
    $/Mtok
    $0.300 / $1.20
    venice/fp8fp8
  • ModelRun99.84%
    Healthy24h 99.46%
    p50
    1.83s
    p99
    7.07s
    Throughput
    123 tps
    Context
    1.0M
    $/Mtok
    $0.750 / $3.00
    modelrun/fp4fp4
  • Together99.68%
    Healthy24h 99.73%
    p50
    756ms
    p99
    10.7s
    Throughput
    81 tps
    Context
    524K
    $/Mtok
    $0.300 / $1.20
    together
  • Novita99.68%
    Healthy24h 99.49%
    p50
    1.55s
    p99
    13.4s
    Throughput
    64 tps
    Context
    1.0M
    $/Mtok
    $0.300 / $1.20
    novita/fp8fp8
  • Minimax99.63%
    Healthy24h 99.59%
    p50
    939ms
    p99
    8.39s
    Throughput
    81 tps
    Context
    524K
    $/Mtok
    $0.300 / $1.20
    minimax/fp8fp8
  • StreamLake99.08%
    Healthy24h 98.58%
    p50
    1.71s
    p99
    13.0s
    Throughput
    96 tps
    Context
    1.0M
    $/Mtok
    $0.300 / $1.20
    streamlake/fp8fp8
  • GMICloud99.03%
    Healthy24h 99.12%
    p50
    3.07s
    p99
    8.87s
    Throughput
    42 tps
    Context
    1.0M
    $/Mtok
    $0.240 / $0.960
    gmicloud/fp8fp8
  • CoreWeave98.71%
    Healthy24h 98.51%
    p50
    667ms
    p99
    12.8s
    Throughput
    64 tps
    Context
    262K
    $/Mtok
    $0.230 / $0.960
    coreweave/fp4fp4
  • Parasail98.63%
    Healthy24h 97.95%
    p50
    695ms
    p99
    8.49s
    Throughput
    140 tps
    Context
    1.0M
    $/Mtok
    $0.300 / $1.20
    parasail/fp8fp8
  • DeepInfra97.78%
    Healthy24h 98.10%
    p50
    816ms
    p99
    53.1s
    Throughput
    28 tps
    Context
    524K
    $/Mtok
    $0.280 / $1.10
    deepinfra/fp8fp8

Measured 1m 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 and p99 are OpenRouter's rolling 30-minute windows, averaged over the hour.

Throughput

Median tokens per second.