modelstatus.dev

MiniMax M2.5

minimax/minimax-m2.5

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

CompareMiniMax M2.5
  • AtlasCloud100%
    Healthy24h 99.86%
    p50
    1.19s
    p99
    3.83s
    Throughput
    54 tps
    Context
    197K
    $/Mtok
    $0.295 / $1.20
    atlas-cloud/fp8fp8
  • DigitalOcean100%
    Healthy24h 99.82%
    p50
    496ms
    p99
    3.51s
    Throughput
    56 tps
    Context
    66K
    $/Mtok
    $0.225 / $0.900
    digitalocean
  • Friendli100%
    Healthy24h 99.85%
    p50
    571ms
    p99
    5.04s
    Throughput
    59 tps
    Context
    197K
    $/Mtok
    $0.300 / $1.20
    friendli
  • StreamLake100%
    Healthy24h 99.92%
    p50
    840ms
    p99
    4.31s
    Throughput
    61 tps
    Context
    200K
    $/Mtok
    $0.270 / $1.08
    streamlake
  • Venice100%
    Healthy24h 99.48%
    p50
    775ms
    p99
    3.42s
    Throughput
    87 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 99.89%
    p50
    975ms
    p99
    4.06s
    Throughput
    66 tps
    Context
    205K
    $/Mtok
    $0.300 / $1.20
    minimax/fp8fp8
  • Minimax
    No data24h 98.94%
    p50
    2.04s
    p99
    4.92s
    Throughput
    41 tps
    Context
    205K
    $/Mtok
    $0.600 / $2.40
    minimax/highspeedfp8
  • Novita
    No data24h 99.94%
    p50
    1.05s
    p99
    3.49s
    Throughput
    77 tps
    Context
    205K
    $/Mtok
    $0.300 / $1.20
    novita/fp8fp8
  • SiliconFlow
    No data24h 99.99%
    p50
    1.12s
    p99
    2.60s
    Throughput
    43 tps
    Context
    197K
    $/Mtok
    $0.300 / $1.20
    siliconflow/fp8fp8

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

5 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.