modelstatus.dev

MiMo-V2.5-Pro

xiaomi/mimo-v2.5-pro

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

CompareMiMo-V2.5-Pro
  • DeepInfra100%
    Healthy24h 97.32%
    p50
    417ms
    p99
    9.76s
    Throughput
    67 tps
    Context
    1.0M
    $/Mtok
    $1.00 / $3.00
    deepinfra/fp8fp8
  • DigitalOcean100%
    Healthy24h 98.94%
    p50
    947ms
    p99
    4.86s
    Throughput
    33 tps
    Context
    262K
    $/Mtok
    $0.400 / $1.50
    digitalocean
  • GMICloud100%
    Healthy24h 93.68%
    p50
    3.35s
    p99
    6.98s
    Throughput
    22 tps
    Context
    1.1M
    $/Mtok
    $0.304 / $0.609
    gmicloud/bf16bf16
  • Novita100%
    Healthy24h 99.40%
    p50
    3.13s
    p99
    25.2s
    Throughput
    29 tps
    Context
    1.0M
    $/Mtok
    $0.480 / $0.960
    novita
  • Xiaomi99.92%
    Healthy24h 99.60%
    p50
    2.71s
    p99
    23.9s
    Throughput
    37 tps
    Context
    1.0M
    $/Mtok
    $0.435 / $0.870
    xiaomi/fp8fp8
  • AtlasCloud98.15%
    Healthy24h 98.37%
    p50
    2.56s
    p99
    30.2s
    Throughput
    31 tps
    Context
    1.0M
    $/Mtok
    $0.435 / $0.870
    atlas-cloud/fp8fp8
  • StreamLake
    No data24h 93.78%
    p50
    2.18s
    p99
    5.09s
    Throughput
    38 tps
    Context
    1.0M
    $/Mtok
    $0.522 / $1.04
    streamlake

Measured 4m 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 and p99 are OpenRouter's rolling 30-minute windows, averaged over the hour.

Throughput

Median tokens per second.