modelstatus.dev

MiMo-V2.5

xiaomi/mimo-v2.5

Compare with MiMo-V2.5-Pro, GLM 5.2, DeepSeek V4 Flash 0731

CompareMiMo-V2.5
  • Xiaomi99.84%
    Healthy24h 97.51%
    p50
    3.70s
    p99
    21.0s
    Throughput
    29 tps
    Context
    1.0M
    $/Mtok
    $0.140 / $0.280
    xiaomi/fp8fp8
  • DeepInfra99.31%
    Healthy24h 98.53%
    p50
    643ms
    p99
    3.65s
    Throughput
    23 tps
    Context
    262K
    $/Mtok
    $0.400 / $2.00
    deepinfra/bf16bf16
  • Parasail97.91%
    Degraded24h 98.09%
    p50
    2.81s
    p99
    35.0s
    Throughput
    20 tps
    Context
    1.0M
    $/Mtok
    $0.140 / $0.280
    parasail/fp8fp8
  • Novita96.50%
    Healthy24h 98.00%
    p50
    2.03s
    p99
    15.6s
    Throughput
    23 tps
    Context
    1.0M
    $/Mtok
    $0.168 / $0.336
    novita/fp8fp8
  • GMICloud95.57%
    Degraded24h 91.10%
    p50
    3.40s
    p99
    7.35s
    Throughput
    10 tps
    Context
    1.1M
    $/Mtok
    $0.119 / $0.238
    gmicloud/fp8fp8

Measured 3m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.

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, averaged over the hour.

Throughput

Median tokens per second.