modelstatus.dev

Kimi K2.5

moonshotai/kimi-k2.5

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

CompareKimi K2.5
  • AtlasCloud100%
    Healthy24h 98.46%
    p50
    1.45s
    p99
    9.07s
    Throughput
    25 tps
    Context
    262K
    $/Mtok
    $0.490 / $2.50
    atlas-cloud/int4int4
  • DigitalOcean100%
    Healthy24h 99.43%
    p50
    626ms
    p99
    4.03s
    Throughput
    22 tps
    Context
    262K
    $/Mtok
    $0.375 / $2.02
    digitalocean
  • Moonshot AI100%
    Healthy24h 99.98%
    p50
    1.98s
    p99
    11.7s
    Throughput
    31 tps
    Context
    262K
    $/Mtok
    $0.600 / $3.00
    moonshotai/int4int4
  • StreamLake100%
    Healthy24h 99.91%
    p50
    1.26s
    p99
    7.49s
    Throughput
    35 tps
    Context
    256K
    $/Mtok
    $0.540 / $2.70
    streamlake/fp8fp8
  • SiliconFlow99.90%
    Healthy24h 99.91%
    p50
    1.46s
    p99
    32.1s
    Throughput
    41 tps
    Context
    262K
    $/Mtok
    $0.450 / $2.25
    siliconflow/int4int4
  • DeepInfra99.78%
    Healthy24h 99.30%
    p50
    756ms
    p99
    16.6s
    Throughput
    33 tps
    Context
    262K
    $/Mtok
    $0.450 / $2.25
    deepinfra/fp4fp4
  • Novita99.31%
    Healthy24h 98.34%
    p50
    1.10s
    p99
    11.0s
    Throughput
    36 tps
    Context
    262K
    $/Mtok
    $0.570 / $2.85
    novita
  • Venice93.43%
    Degraded24h 96.54%
    p50
    1.72s
    p99
    10.9s
    Throughput
    33 tps
    Context
    256K
    $/Mtok
    $0.532 / $3.32
    venice
  • Amazon Bedrock
    No data24h 97.02%
    p50
    1.31s
    p99
    6.38s
    Throughput
    36 tps
    Context
    262K
    $/Mtok
    $0.600 / $3.00
    amazon-bedrock/us-east-2
  • Phala
    No data24h 84.83%
    p50
    2.64s
    p99
    13.6s
    Throughput
    40 tps
    Context
    262K
    $/Mtok
    $0.600 / $3.00
    phala

Measured 2m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.

2 endpoints reporting no data are 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.