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
    764ms
    p99
    5.28s
    Throughput
    28 tps
    Context
    262K
    $/Mtok
    $0.560 / $2.36
    baidu/fp4fp4
  • Cloudflare100%
    Healthy24h 99.97%
    p50
    877ms
    p99
    7.36s
    Throughput
    46 tps
    Context
    262K
    $/Mtok
    $0.950 / $4.00
    cloudflare
  • Crusoe100%
    Healthy24h 98.37%
    p50
    427ms
    p99
    2.68s
    Throughput
    51 tps
    Context
    262K
    $/Mtok
    $0.700 / $3.50
    crusoe/bf16bf16
  • DeepInfra100%
    Healthy24h 97.97%
    p50
    829ms
    p99
    3.72s
    Throughput
    25 tps
    Context
    262K
    $/Mtok
    $0.750 / $3.50
    deepinfra/fp4fp4
  • DigitalOcean100%
    Healthy24h 99.68%
    p50
    1.08s
    p99
    3.19s
    Throughput
    38 tps
    Context
    262K
    $/Mtok
    $0.760 / $3.20
    digitalocean
  • Inceptron100%
    Healthy24h 99.63%
    p50
    627ms
    p99
    4.71s
    Throughput
    52 tps
    Context
    262K
    $/Mtok
    $0.600 / $3.41
    inceptron/int4int4
  • Moonshot AI100%
    Healthy24h 99.96%
    p50
    1.31s
    p99
    11.0s
    Throughput
    32 tps
    Context
    262K
    $/Mtok
    $0.950 / $4.00
    moonshotai/int4int4
  • StreamLake100%
    Healthy24h 98.36%
    p50
    2.37s
    p99
    26.8s
    Throughput
    34 tps
    Context
    256K
    $/Mtok
    $0.598 / $2.52
    streamlake/fp8fp8
  • Venice100%
    Healthy24h 80.17%
    p50
    1.15s
    p99
    4.13s
    Throughput
    29 tps
    Context
    256K
    $/Mtok
    $0.750 / $3.50
    venice/int4int4
  • Decart99.72%
    Healthy24h 97.43%
    p50
    705ms
    p99
    7.92s
    Throughput
    57 tps
    Context
    262K
    $/Mtok
    $0.568 / $3.33
    decart/fp4fp4
  • Together99.19%
    Healthy24h 91.04%
    p50
    365ms
    p99
    2.32s
    Throughput
    108 tps
    Context
    262K
    $/Mtok
    $1.20 / $4.50
    together
  • CoreWeave98.87%
    Healthy24h 99.14%
    p50
    418ms
    p99
    8.12s
    Throughput
    145 tps
    Context
    262K
    $/Mtok
    $0.650 / $3.41
    coreweave/fp4fp4
  • Chutes98.82%
    Healthy24h 98.56%
    p50
    3.28s
    p99
    21.3s
    Throughput
    25 tps
    Context
    262K
    $/Mtok
    $0.580 / $3.40
    chutes/int4int4
  • Novita98.33%
    Healthy24h 99.73%
    p50
    1.75s
    p99
    16.6s
    Throughput
    22 tps
    Context
    262K
    $/Mtok
    $0.800 / $3.40
    novita
  • AtlasCloud
    No data24h 97.67%
    p50
    1.47s
    p99
    12.3s
    Throughput
    40 tps
    Context
    262K
    $/Mtok
    $0.950 / $4.00
    atlas-cloud/int4int4
  • BaseTen
    No data24h
    p50
    653ms
    p99
    2.82s
    Throughput
    103 tps
    Context
    262K
    $/Mtok
    $0.950 / $4.00
    baseten/fp4fp4
  • Fireworks
    Down24h 0.00%
    p50
    611ms
    p99
    8.66s
    Throughput
    63 tps
    Context
    262K
    $/Mtok
    $0.950 / $4.00
    fireworks
  • Parasail
    No data24h 99.32%
    p50
    p99
    Throughput
    Context
    262K
    $/Mtok
    $0.750 / $3.50
    parasail/int4int4
  • Phala
    No data24h 99.54%
    p50
    1.47s
    p99
    6.27s
    Throughput
    21 tps
    Context
    262K
    $/Mtok
    $1.09 / $4.60
    phala
  • Sail Research
    No data24h 99.87%
    p50
    778ms
    p99
    2.02s
    Throughput
    24 tps
    Context
    262K
    $/Mtok
    $1.00 / $4.00
    sail-research/int4int4
  • SiliconFlow
    No data24h 99.92%
    p50
    1.37s
    p99
    25.0s
    Throughput
    33 tps
    Context
    262K
    $/Mtok
    $0.770 / $3.40
    siliconflow/fp8fp8

Measured 3m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.

6 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, averaged over the hour.

Throughput

Median tokens per second.