modelstatus.dev

MiniMax M2.7

minimax/minimax-m2.7

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

CompareMiniMax M2.7
  • Healthy24h 99.15%
    p50
    6.65s
    p99
    66.7s
    Throughput
    3.0 tps
    Context
    197K
    $/Mtok
    $0.300 / $1.20
    atlas-cloud/fp8fp8
  • Healthy24h 99.92%
    p50
    3.83s
    p99
    7.00s
    Throughput
    6.0 tps
    Context
    197K
    $/Mtok
    $0.240 / $0.960
    gmicloud/fp8fp8
  • Groq100%
    Healthy24h 99.73%
    p50
    325ms
    p99
    7.50s
    Throughput
    260 tps
    Context
    197K
    $/Mtok
    $0.600 / $1.80
    groq
  • Mara100%
    Healthy24h 99.47%
    p50
    2.93s
    p99
    18.8s
    Throughput
    67 tps
    Context
    197K
    $/Mtok
    $0.240 / $0.960
    mara
  • Minimax99.43%
    Healthy24h 99.42%
    p50
    2.59s
    p99
    6.57s
    Throughput
    20 tps
    Context
    205K
    $/Mtok
    $0.300 / $1.20
    minimax/fp8fp8
  • Minimax99.39%
    Healthy24h 93.44%
    p50
    1.48s
    p99
    11.4s
    Throughput
    38 tps
    Context
    205K
    $/Mtok
    $0.600 / $2.40
    minimax/highspeedfp8
  • DeepInfra94.83%
    Degraded24h 99.84%
    p50
    466ms
    p99
    4.60s
    Throughput
    32 tps
    Context
    197K
    $/Mtok
    $0.250 / $1.00
    deepinfra/fp8fp8
  • DeepInfra40.48%
    Down24h 59.21%
    p50
    12.1s
    p99
    70.5s
    Throughput
    10 tps
    Context
    197K
    $/Mtok
    $0.380 / $1.70
    deepinfra/turbofp8
  • No data24h 99.76%
    p50
    2.85s
    p99
    8.45s
    Throughput
    179 tps
    Context
    197K
    $/Mtok
    $0.300 / $1.20
    fireworks
  • No data24h 99.21%
    p50
    1.21s
    p99
    6.73s
    Throughput
    33 tps
    Context
    205K
    $/Mtok
    $0.270 / $1.08
    novita/fp8fp8
  • No data24h 97.12%
    p50
    5.26s
    p99
    24.8s
    Throughput
    63 tps
    Context
    197K
    $/Mtok
    $0.600 / $2.40
    sambanova

Measured 1m 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.

Throughput

Median tokens per second.