modelstatus.dev

MiniMax M2.5

minimax/minimax-m2.5

Compare with MiniMax M2.7, MiniMax M2.1, MiniMax M3

CompareMiniMax M2.5
  • AtlasCloud100%
    Healthy24h 99.85%
    p50
    1.33s
    p99
    5.51s
    Throughput
    49 tps
    Context
    197K
    $/Mtok
    $0.295 / $1.20
    atlas-cloud/fp8fp8
  • DigitalOcean100%
    Healthy24h 99.82%
    p50
    568ms
    p99
    3.56s
    Throughput
    49 tps
    Context
    66K
    $/Mtok
    $0.225 / $0.900
    digitalocean
  • Friendli100%
    Healthy24h 99.87%
    p50
    546ms
    p99
    10.7s
    Throughput
    63 tps
    Context
    197K
    $/Mtok
    $0.300 / $1.20
    friendli
  • Minimax100%
    Healthy24h 99.89%
    p50
    1.04s
    p99
    3.39s
    Throughput
    67 tps
    Context
    205K
    $/Mtok
    $0.300 / $1.20
    minimax/fp8fp8
  • StreamLake100%
    Healthy24h 99.92%
    p50
    816ms
    p99
    4.28s
    Throughput
    58 tps
    Context
    200K
    $/Mtok
    $0.270 / $1.08
    streamlake
  • Venice100%
    Healthy24h 99.47%
    p50
    982ms
    p99
    5.49s
    Throughput
    74 tps
    Context
    198K
    $/Mtok
    $0.270 / $0.950
    venice
  • Inceptron
    No data24h
    p50
    p99
    Throughput
    Context
    197K
    $/Mtok
    $0.220 / $0.900
    inceptron/fp8fp8
  • Minimax
    No data24h 98.91%
    p50
    2.21s
    p99
    5.81s
    Throughput
    43 tps
    Context
    205K
    $/Mtok
    $0.600 / $2.40
    minimax/highspeedfp8
  • Novita
    No data24h 99.94%
    p50
    1.36s
    p99
    3.88s
    Throughput
    50 tps
    Context
    205K
    $/Mtok
    $0.300 / $1.20
    novita/fp8fp8
  • SiliconFlow
    No data24h 99.99%
    p50
    1.50s
    p99
    2.64s
    Throughput
    42 tps
    Context
    197K
    $/Mtok
    $0.300 / $1.20
    siliconflow/fp8fp8

Measured 41s ago. Latency and throughput are OpenRouter's rolling 30-minute windows.

4 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 and p99 are OpenRouter's rolling 30-minute windows.

Throughput

Median tokens per second.