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
  • Healthy24h 90.26%
    7d
    94.68%
    30d
    94.68%
    p50
    552ms
    p99
    1.48s
    Throughput
    24 tps
    Context
    262K
    $/Mtok
    $0.400 / $2.00
    deepinfra/bf16bf16
  • Novita99.89%
    Healthy24h 98.24%
    7d
    98.46%
    30d
    98.46%
    p50
    2.44s
    p99
    16.2s
    Throughput
    43 tps
    Context
    1.0M
    $/Mtok
    $0.168 / $0.336
    novita/fp8fp8
  • Xiaomi99.80%
    Healthy24h 99.59%
    7d
    98.89%
    30d
    98.89%
    p50
    3.17s
    p99
    30.3s
    Throughput
    33 tps
    Context
    1.0M
    $/Mtok
    $0.140 / $0.280
    xiaomi/fp8fp8
  • Parasail99.74%
    Healthy24h 99.12%
    7d
    98.06%
    30d
    98.06%
    p50
    450ms
    p99
    7.90s
    Throughput
    42 tps
    Context
    1.0M
    $/Mtok
    $0.140 / $0.280
    parasail/fp8fp8
  • GMICloud94.16%
    Degraded24h 89.67%
    7d
    87.92%
    30d
    87.92%
    p50
    3.19s
    p99
    7.66s
    Throughput
    37 tps
    Context
    1.1M
    $/Mtok
    $0.119 / $0.238
    gmicloud/fp8fp8

Measured 2m 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 is OpenRouter's rolling 30-minute window.

Throughput

Median tokens per second.