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
  • Parasail99.95%
    Healthy24h 99.04%
    7d
    97.99%
    30d
    97.99%
    p50
    482ms
    p99
    4.80s
    Throughput
    34 tps
    Context
    1.0M
    $/Mtok
    $0.140 / $0.280
    parasail/fp8fp8
  • Xiaomi99.59%
    Healthy24h 99.41%
    7d
    98.87%
    30d
    98.87%
    p50
    3.82s
    p99
    38.0s
    Throughput
    28 tps
    Context
    1.0M
    $/Mtok
    $0.140 / $0.280
    xiaomi/fp8fp8
  • Novita98.88%
    Healthy24h 99.00%
    7d
    98.52%
    30d
    98.52%
    p50
    3.36s
    p99
    28.2s
    Throughput
    35 tps
    Context
    1.0M
    $/Mtok
    $0.168 / $0.336
    novita/fp8fp8
  • GMICloud82.03%
    Down24h 89.64%
    7d
    88.03%
    30d
    88.03%
    p50
    3.93s
    p99
    8.93s
    Throughput
    18 tps
    Context
    1.1M
    $/Mtok
    $0.119 / $0.238
    gmicloud/fp8fp8
  • No data24h 90.28%
    7d
    94.48%
    30d
    94.48%
    p50
    1.00s
    p99
    3.89s
    Throughput
    12 tps
    Context
    262K
    $/Mtok
    $0.400 / $2.00
    deepinfra/bf16bf16

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

1 endpoint reporting no data is 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.