modelstatus.dev

Kimi K2.6

moonshotai/kimi-k2.6

Compare with Kimi K2.7 Code, Kimi K2.5, Kimi K3

CompareKimi K2.6
  • Baidu100%
    Healthy24h 99.88%
    p50
    1.50s
    p99
    6.46s
    Throughput
    40 tps
    Context
    262K
    $/Mtok
    $0.560 / $2.36
    baidu/fp4fp4
  • Chutes100%
    Healthy24h 98.57%
    p50
    1.70s
    p99
    15.7s
    Throughput
    41 tps
    Context
    262K
    $/Mtok
    $0.580 / $3.40
    chutes/int4int4
  • Crusoe100%
    Healthy24h 98.37%
    p50
    357ms
    p99
    4.74s
    Throughput
    55 tps
    Context
    262K
    $/Mtok
    $0.700 / $3.50
    crusoe/bf16bf16
  • DeepInfra100%
    Healthy24h 97.99%
    p50
    800ms
    p99
    4.43s
    Throughput
    29 tps
    Context
    262K
    $/Mtok
    $0.750 / $3.50
    deepinfra/fp4fp4
  • DigitalOcean100%
    Healthy24h 99.70%
    p50
    799ms
    p99
    3.86s
    Throughput
    43 tps
    Context
    262K
    $/Mtok
    $0.760 / $3.20
    digitalocean
  • Moonshot AI100%
    Healthy24h 99.96%
    p50
    1.80s
    p99
    14.8s
    Throughput
    33 tps
    Context
    262K
    $/Mtok
    $0.950 / $4.00
    moonshotai/int4int4
  • Parasail100%
    Healthy24h 99.31%
    p50
    1.14s
    p99
    25.5s
    Throughput
    19 tps
    Context
    262K
    $/Mtok
    $0.750 / $3.50
    parasail/int4int4
  • SiliconFlow100%
    Healthy24h 99.92%
    p50
    1.26s
    p99
    149s
    Throughput
    35 tps
    Context
    262K
    $/Mtok
    $0.770 / $3.40
    siliconflow/fp8fp8
  • StreamLake100%
    Healthy24h 98.35%
    p50
    1.79s
    p99
    10.7s
    Throughput
    38 tps
    Context
    256K
    $/Mtok
    $0.598 / $2.52
    streamlake/fp8fp8
  • Together100%
    Healthy24h 91.14%
    p50
    334ms
    p99
    1.51s
    Throughput
    131 tps
    Context
    262K
    $/Mtok
    $1.20 / $4.50
    together
  • Decart99.76%
    Healthy24h 97.62%
    p50
    507ms
    p99
    4.98s
    Throughput
    69 tps
    Context
    262K
    $/Mtok
    $0.568 / $3.33
    decart/fp4fp4
  • Novita99.66%
    Healthy24h 99.73%
    p50
    2.48s
    p99
    11.5s
    Throughput
    32 tps
    Context
    262K
    $/Mtok
    $0.800 / $3.40
    novita
  • CoreWeave98.35%
    Healthy24h 99.14%
    p50
    418ms
    p99
    4.24s
    Throughput
    154 tps
    Context
    262K
    $/Mtok
    $0.650 / $3.41
    coreweave/fp4fp4
  • AtlasCloud
    No data24h 97.75%
    p50
    1.44s
    p99
    9.91s
    Throughput
    36 tps
    Context
    262K
    $/Mtok
    $0.950 / $4.00
    atlas-cloud/int4int4
  • BaseTen
    No data24h
    p50
    1.27s
    p99
    1.27s
    Throughput
    80 tps
    Context
    262K
    $/Mtok
    $0.950 / $4.00
    baseten/fp4fp4
  • Cloudflare
    No data24h 99.97%
    p50
    889ms
    p99
    5.71s
    Throughput
    39 tps
    Context
    262K
    $/Mtok
    $0.950 / $4.00
    cloudflare
  • Fireworks
    No data24h 0.00%
    p50
    533ms
    p99
    7.83s
    Throughput
    71 tps
    Context
    262K
    $/Mtok
    $0.950 / $4.00
    fireworks
  • Inceptron
    No data24h 99.61%
    p50
    577ms
    p99
    5.09s
    Throughput
    75 tps
    Context
    262K
    $/Mtok
    $0.600 / $3.41
    inceptron/int4int4
  • Phala
    No data24h 99.54%
    p50
    1.49s
    p99
    5.00s
    Throughput
    20 tps
    Context
    262K
    $/Mtok
    $1.09 / $4.60
    phala
  • Sail Research
    No data24h 99.92%
    p50
    1.19s
    p99
    5.13s
    Throughput
    28 tps
    Context
    262K
    $/Mtok
    $1.00 / $4.00
    sail-research/int4int4
  • Venice
    No data24h 80.40%
    p50
    1.15s
    p99
    4.64s
    Throughput
    33 tps
    Context
    256K
    $/Mtok
    $0.750 / $3.50
    venice/int4int4

Measured 4m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.

8 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.