modelstatus.dev

MiniMax M3

minimax/minimax-m3

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

CompareMiniMax M3
  • Healthy24h 99.68%
    7d
    97.24%
    30d
    97.24%
    p50
    574ms
    p99
    19.6s
    Throughput
    89 tps
    Context
    262K
    $/Mtok
    $0.230 / $0.960
    coreweave/fp4fp4
  • Healthy24h 98.42%
    7d
    98.38%
    30d
    98.38%
    p50
    857ms
    p99
    18.2s
    Throughput
    29 tps
    Context
    524K
    $/Mtok
    $0.280 / $1.10
    deepinfra/fp8fp8
  • Healthy24h 99.49%
    7d
    99.33%
    30d
    99.33%
    p50
    3.51s
    p99
    10.4s
    Throughput
    40 tps
    Context
    1.0M
    $/Mtok
    $0.240 / $0.960
    gmicloud/fp8fp8
  • Morph100%
    Healthy24h 96.65%
    7d
    97.49%
    30d
    97.49%
    p50
    1.42s
    p99
    19.0s
    Throughput
    22 tps
    Context
    256K
    $/Mtok
    $0.255 / $1.02
    morph/fp4fp4
  • Healthy24h 99.78%
    7d
    99.78%
    30d
    99.78%
    p50
    852ms
    p99
    10.00s
    Throughput
    77 tps
    Context
    524K
    $/Mtok
    $0.300 / $1.20
    together
  • Minimax99.94%
    Healthy24h 99.53%
    7d
    99.63%
    30d
    99.63%
    p50
    1.43s
    p99
    15.2s
    Throughput
    57 tps
    Context
    524K
    $/Mtok
    $0.300 / $1.20
    minimax/fp8fp8
  • Parasail99.79%
    Healthy24h 98.37%
    7d
    97.91%
    30d
    97.91%
    p50
    934ms
    p99
    13.5s
    Throughput
    51 tps
    Context
    1.0M
    $/Mtok
    $0.300 / $1.20
    parasail/fp8fp8
  • Novita99.45%
    Healthy24h 99.63%
    7d
    99.66%
    30d
    99.66%
    p50
    2.35s
    p99
    16.8s
    Throughput
    40 tps
    Context
    1.0M
    $/Mtok
    $0.300 / $1.20
    novita/fp8fp8
  • ModelRun98.96%
    Healthy24h 99.77%
    7d
    99.76%
    30d
    99.76%
    p50
    1.84s
    p99
    19.3s
    Throughput
    86 tps
    Context
    1.0M
    $/Mtok
    $0.750 / $3.00
    modelrun/fp4fp4
  • Venice98.78%
    Healthy24h 99.81%
    7d
    99.87%
    30d
    99.87%
    p50
    1.28s
    p99
    9.38s
    Throughput
    100 tps
    Context
    524K
    $/Mtok
    $0.300 / $1.20
    venice/fp8fp8
  • Healthy24h 99.70%
    7d
    99.52%
    30d
    99.52%
    p50
    1.25s
    p99
    5.67s
    Throughput
    76 tps
    Context
    524K
    $/Mtok
    $0.300 / $1.20
    atlas-cloud/fp8fp8
  • SambaNova97.44%
    Healthy24h 97.36%
    7d
    98.38%
    30d
    98.38%
    p50
    2.03s
    p99
    28.3s
    Throughput
    131 tps
    Context
    1.0M
    $/Mtok
    $0.600 / $2.40
    sambanova
  • Healthy24h 99.02%
    7d
    98.46%
    30d
    98.46%
    p50
    1.64s
    p99
    8.85s
    Throughput
    59 tps
    Context
    1.0M
    $/Mtok
    $0.300 / $1.20
    streamlake/fp8fp8

Measured 5m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.

Price changes

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.