modelstatus.dev

MiniMax M3

minimax/minimax-m3

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

CompareMiniMax M3
  • AtlasCloud100%
    Healthy24h 99.29%
    p50
    725ms
    p99
    3.88s
    Throughput
    79 tps
    Context
    524K
    $/Mtok
    $0.300 / $1.20
    atlas-cloud/fp8fp8
  • CoreWeave100%
    Healthy24h 98.64%
    p50
    781ms
    p99
    9.82s
    Throughput
    26 tps
    Context
    262K
    $/Mtok
    $0.230 / $0.960
    coreweave/fp4fp4
  • GMICloud100%
    Healthy24h 99.13%
    p50
    3.41s
    p99
    9.39s
    Throughput
    48 tps
    Context
    1.0M
    $/Mtok
    $0.240 / $0.960
    gmicloud/fp8fp8
  • ModelRun100%
    Healthy24h 99.21%
    p50
    1.84s
    p99
    6.17s
    Throughput
    114 tps
    Context
    1.0M
    $/Mtok
    $0.750 / $3.00
    modelrun/fp4fp4
  • Parasail100%
    Healthy24h 98.18%
    p50
    721ms
    p99
    9.37s
    Throughput
    110 tps
    Context
    1.0M
    $/Mtok
    $0.300 / $1.20
    parasail/fp8fp8
  • Together100%
    Healthy24h 99.18%
    p50
    981ms
    p99
    16.3s
    Throughput
    48 tps
    Context
    524K
    $/Mtok
    $0.300 / $1.20
    together
  • Venice100%
    Healthy24h 99.82%
    p50
    1.13s
    p99
    10.5s
    Throughput
    103 tps
    Context
    524K
    $/Mtok
    $0.300 / $1.20
    venice/fp8fp8
  • Minimax99.75%
    Healthy24h 99.54%
    p50
    1.30s
    p99
    16.4s
    Throughput
    65 tps
    Context
    524K
    $/Mtok
    $0.300 / $1.20
    minimax/fp8fp8
  • Novita99.42%
    Healthy24h 99.39%
    p50
    2.13s
    p99
    22.8s
    Throughput
    51 tps
    Context
    1.0M
    $/Mtok
    $0.300 / $1.20
    novita/fp8fp8
  • DeepInfra98.52%
    Healthy24h 97.93%
    p50
    811ms
    p99
    54.4s
    Throughput
    26 tps
    Context
    524K
    $/Mtok
    $0.280 / $1.10
    deepinfra/fp8fp8
  • StreamLake97.30%
    Healthy24h 98.58%
    p50
    1.97s
    p99
    12.1s
    Throughput
    64 tps
    Context
    1.0M
    $/Mtok
    $0.300 / $1.20
    streamlake/fp8fp8
  • Morph95.97%
    Healthy24h 94.44%
    p50
    1.27s
    p99
    19.8s
    Throughput
    26 tps
    Context
    256K
    $/Mtok
    $0.300 / $1.20
    morph/fp4fp4

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.

Throughput

Median tokens per second.