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 90.16%
    7d
    94.59%
    30d
    94.59%
    p50
    627ms
    p99
    1.95s
    Throughput
    20 tps
    Context
    262K
    $/Mtok
    $0.400 / $2.00
    deepinfra/bf16bf16
  • Novita100%
    Healthy24h 98.24%
    7d
    98.51%
    30d
    98.51%
    p50
    1.68s
    p99
    15.4s
    Throughput
    55 tps
    Context
    1.0M
    $/Mtok
    $0.168 / $0.336
    novita/fp8fp8
  • Healthy24h 99.11%
    7d
    98.03%
    30d
    98.03%
    p50
    443ms
    p99
    4.94s
    Throughput
    45 tps
    Context
    1.0M
    $/Mtok
    $0.140 / $0.280
    parasail/fp8fp8
  • Xiaomi99.82%
    Healthy24h 99.58%
    7d
    98.88%
    30d
    98.88%
    p50
    3.27s
    p99
    31.1s
    Throughput
    31 tps
    Context
    1.0M
    $/Mtok
    $0.140 / $0.280
    xiaomi/fp8fp8
  • GMICloud93.59%
    Degraded24h 89.21%
    7d
    87.94%
    30d
    87.94%
    p50
    3.48s
    p99
    6.76s
    Throughput
    3.0 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.