modelstatus.dev

Kimi K2.5

moonshotai/kimi-k2.5

Compare with Kimi K2.6, Kimi K2.7 Code, Kimi K3

  • DeepInfra100%
    Healthy24h 99.26%
    p50
    861ms
    p99
    36.1s
    Throughput
    15 tps
    Context
    262K
    $/Mtok
    $0.450 / $2.25
    deepinfra/fp4fp4
  • DigitalOcean100%
    Healthy24h 99.40%
    p50
    1.20s
    p99
    5.25s
    Throughput
    7.0 tps
    Context
    262K
    $/Mtok
    $0.375 / $2.02
    digitalocean
  • Moonshot AI100%
    Healthy24h 99.99%
    p50
    2.05s
    p99
    13.5s
    Throughput
    27 tps
    Context
    262K
    $/Mtok
    $0.600 / $3.00
    moonshotai/int4int4
  • StreamLake100%
    Healthy24h 99.91%
    p50
    1.28s
    p99
    11.4s
    Throughput
    35 tps
    Context
    256K
    $/Mtok
    $0.540 / $2.70
    streamlake/fp8fp8
  • Venice100%
    Healthy24h 95.13%
    p50
    1.93s
    p99
    7.90s
    Throughput
    36 tps
    Context
    256K
    $/Mtok
    $0.532 / $3.32
    venice
  • SiliconFlow99.85%
    Healthy24h 99.91%
    p50
    1.46s
    p99
    22.8s
    Throughput
    40 tps
    Context
    262K
    $/Mtok
    $0.450 / $2.25
    siliconflow/int4int4
  • AtlasCloud99.68%
    Healthy24h 98.83%
    p50
    1.35s
    p99
    10.8s
    Throughput
    27 tps
    Context
    262K
    $/Mtok
    $0.490 / $2.50
    atlas-cloud/int4int4
  • Novita98.98%
    Healthy24h 98.44%
    p50
    1.13s
    p99
    12.1s
    Throughput
    35 tps
    Context
    262K
    $/Mtok
    $0.570 / $2.85
    novita
  • Amazon Bedrock98.57%
    Healthy24h 97.23%
    p50
    955ms
    p99
    4.98s
    Throughput
    45 tps
    Context
    262K
    $/Mtok
    $0.600 / $3.00
    amazon-bedrock/us-east-2
  • Phala
    No data24h 83.02%
    p50
    1.93s
    p99
    9.88s
    Throughput
    27 tps
    Context
    262K
    $/Mtok
    $0.600 / $3.00
    phala

Measured 2m 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.

Throughput

Median tokens per second.