modelstatus.dev

Kimi K2.7 Code

moonshotai/kimi-k2.7-code

Compare with Kimi K2.6, Kimi K2.5, Kimi K3

CompareKimi K2.7 Code
  • Healthy24h 99.96%
    7d
    99.91%
    30d
    99.91%
    p50
    1.09s
    p99
    10.1s
    Throughput
    123 tps
    Context
    262K
    $/Mtok
    $0.710 / $3.50
    coreweave/int4int4
  • Healthy24h 99.80%
    7d
    99.83%
    30d
    99.83%
    p50
    969ms
    p99
    112s
    Throughput
    53 tps
    Context
    262K
    $/Mtok
    $0.670 / $3.40
    inceptron/int4int4
  • Healthy24h 99.90%
    7d
    99.90%
    30d
    99.90%
    p50
    2.34s
    p99
    30.0s
    Throughput
    90 tps
    Context
    262K
    $/Mtok
    $1.90 / $8.00
    moonshotai/highspeedint4
  • Novita100%
    Healthy24h 99.76%
    7d
    99.10%
    30d
    99.10%
    p50
    3.13s
    p99
    17.8s
    Throughput
    15 tps
    Context
    262K
    $/Mtok
    $0.912 / $3.84
    novita/int4int4
  • Healthy24h 99.94%
    7d
    99.99%
    30d
    99.99%
    p50
    2.95s
    p99
    18.5s
    Throughput
    30 tps
    Context
    262K
    $/Mtok
    $0.859 / $3.80
    siliconflow/fp8fp8
  • ModelRun73.33%
    Down24h 49.73%
    7d
    84.40%
    30d
    84.40%
    p50
    776ms
    p99
    9.70s
    Throughput
    171 tps
    Context
    262K
    $/Mtok
    $0.850 / $3.75
    modelrun/fp4fp4
  • No data24h 99.85%
    7d
    100%
    30d
    100%
    p50
    3.36s
    p99
    30.6s
    Throughput
    25 tps
    Context
    262K
    $/Mtok
    $0.950 / $4.00
    alibaba/fp8fp8
  • No data24h 99.55%
    7d
    100%
    30d
    100%
    p50
    729ms
    p99
    3.32s
    Throughput
    92 tps
    Context
    262K
    $/Mtok
    $0.690 / $3.49
    ambient
  • No data24h
    7d
    100%
    30d
    100%
    p50
    p99
    Throughput
    Context
    262K
    $/Mtok
    $0.950 / $4.00
    atlas-cloud/int4int4
  • No data24h 100%
    7d
    100%
    30d
    100%
    p50
    761ms
    p99
    12.1s
    Throughput
    45 tps
    Context
    262K
    $/Mtok
    $0.950 / $4.00
    cloudflare
  • No data24h 99.93%
    7d
    99.41%
    30d
    99.41%
    p50
    646ms
    p99
    3.03s
    Throughput
    50 tps
    Context
    262K
    $/Mtok
    $0.680 / $3.40
    deepinfra/fp4fp4
  • No data24h 96.42%
    7d
    30d
    p50
    3.25s
    p99
    16.7s
    Throughput
    26 tps
    Context
    262K
    $/Mtok
    $0.950 / $4.00
    gmicloud/fp8fp8
  • No data24h 99.94%
    7d
    99.69%
    30d
    99.69%
    p50
    3.01s
    p99
    59.4s
    Throughput
    27 tps
    Context
    262K
    $/Mtok
    $0.950 / $4.00
    moonshotai/int4int4
  • No data24h 98.99%
    7d
    99.22%
    30d
    99.22%
    p50
    1.35s
    p99
    5.59s
    Throughput
    54 tps
    Context
    262K
    $/Mtok
    $0.760 / $3.50
    parasail/int4int4
  • Down24h 22.31%
    7d
    78.82%
    30d
    78.82%
    p50
    10.0s
    p99
    11.2s
    Throughput
    353 tps
    Context
    262K
    $/Mtok
    $0.950 / $4.00
    together
  • No data24h 97.98%
    7d
    97.35%
    30d
    97.35%
    p50
    993ms
    p99
    4.02s
    Throughput
    52 tps
    Context
    256K
    $/Mtok
    $0.750 / $3.50
    venice/int4int4

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

9 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 is OpenRouter's rolling 30-minute window.

Throughput

Median tokens per second.