modelstatus.dev

MiniMax M2.7

minimax/minimax-m2.7

Compare with MiniMax M2.5, MiniMax M3, MiniMax M2.1

CompareMiniMax M2.7
  • Degraded24h 99.72%
    p50
    656ms
    p99
    38.5s
    Throughput
    27 tps
    Context
    197K
    $/Mtok
    $0.250 / $1.00
    deepinfra/fp8fp8
  • Healthy24h 99.92%
    p50
    3.68s
    p99
    5.80s
    Throughput
    6.0 tps
    Context
    197K
    $/Mtok
    $0.240 / $0.960
    gmicloud/fp8fp8
  • Groq100%
    Healthy24h 99.73%
    p50
    300ms
    p99
    6.81s
    Throughput
    244 tps
    Context
    197K
    $/Mtok
    $0.600 / $1.80
    groq
  • Mara100%
    Healthy24h 99.49%
    p50
    2.04s
    p99
    12.7s
    Throughput
    75 tps
    Context
    197K
    $/Mtok
    $0.240 / $0.960
    mara
  • Degraded24h 93.43%
    p50
    4.01s
    p99
    10.5s
    Throughput
    6.0 tps
    Context
    205K
    $/Mtok
    $0.600 / $2.40
    minimax/highspeedfp8
  • Minimax99.87%
    Healthy24h 99.42%
    p50
    859ms
    p99
    6.70s
    Throughput
    50 tps
    Context
    205K
    $/Mtok
    $0.300 / $1.20
    minimax/fp8fp8
  • Healthy24h 99.12%
    p50
    10.3s
    p99
    68.2s
    Throughput
    3.0 tps
    Context
    197K
    $/Mtok
    $0.300 / $1.20
    atlas-cloud/fp8fp8
  • Novita87.99%
    Down24h 98.94%
    p50
    3.34s
    p99
    6.20s
    Throughput
    7.0 tps
    Context
    205K
    $/Mtok
    $0.270 / $1.08
    novita/fp8fp8
  • No data24h 57.57%
    p50
    36.0s
    p99
    64.8s
    Throughput
    1.0 tps
    Context
    197K
    $/Mtok
    $0.380 / $1.70
    deepinfra/turbofp8
  • No data24h 99.76%
    p50
    3.00s
    p99
    8.72s
    Throughput
    172 tps
    Context
    197K
    $/Mtok
    $0.300 / $1.20
    fireworks
  • No data24h 96.82%
    p50
    17.0s
    p99
    55.9s
    Throughput
    1.0 tps
    Context
    197K
    $/Mtok
    $0.600 / $2.40
    sambanova

Measured 2m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.

3 endpoints reporting no data are omitted from the charts.

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.