modelstatus.dev

Kimi K3

Kimi K3: providers compared

Every endpoint serving this model, side by side. ◆ marks the best value in each column — per model, never fleet-wide.

  • BaseTen100% (best)
    Healthy24h 97.94%
    7d
    98.27%
    30d
    98.27%
    p50
    1.28s (best)
    p99
    24.5s
    Throughput
    60 tps (best)
    Context
    1.0M
    $/Mtok
    $3.00 / $15.00
    baseten/fp8fp8
  • Modal100% (best)
    Healthy24h 99.60%
    7d
    99.66% (best)
    30d
    99.66% (best)
    p50
    2.26s
    p99
    26.7s
    Throughput
    56 tps
    Context
    1.0M
    $/Mtok
    $3.00 / $15.00
    modal/mxfp4mxfp4
  • Healthy24h 99.33%
    7d
    99.30%
    30d
    99.30%
    p50
    2.65s
    p99
    41.4s
    Throughput
    16 tps
    Context
    1.0M
    $/Mtok
    $2.85 / $14.25
    digitalocean
  • Fireworks99.83%
    Healthy24h 98.95%
    7d
    98.99%
    30d
    98.99%
    p50
    2.17s
    p99
    35.1s
    Throughput
    43 tps
    Context
    1.0M
    $/Mtok
    $3.00 / $15.00
    fireworks
  • Healthy24h 98.33%
    7d
    99.08%
    30d
    99.08%
    p50
    5.52s
    p99
    45.6s
    Throughput
    22 tps
    Context
    1.0M
    $/Mtok
    $3.00 / $15.00
    moonshotai/mxfp4mxfp4
  • Together98.41%
    Healthy24h 98.79%
    7d
    98.74%
    30d
    98.74%
    p50
    4.82s
    p99
    27.5s
    Throughput
    26 tps
    Context
    1.0M
    $/Mtok
    $3.00 / $15.00
    together
  • Fireworks98.07%
    Degraded24h 92.22%
    7d
    94.16%
    30d
    94.16%
    p50
    5.16s
    p99
    88.1s
    Throughput
    29 tps
    Context
    1.0M
    $/Mtok
    $3.30 / $16.50
    fireworks/us
  • Healthy24h 97.17%
    7d
    98.39%
    30d
    98.39%
    p50
    5.74s
    p99
    101s
    Throughput
    16 tps
    Context
    975K
    $/Mtok
    $2.60 / $13.00 (best)
    sail-research/fp4fp4
  • Chutes96.21%
    Healthy24h 98.77%
    7d
    97.32%
    30d
    97.32%
    p50
    1.77s
    p99
    13.7s (best)
    Throughput
    17 tps
    Context
    1.0M
    $/Mtok
    $3.00 / $15.00
    chutes/mxfp4mxfp4
  • Morph63.23%
    Down24h 82.62%
    7d
    84.42%
    30d
    84.42%
    p50
    8.77s
    p99
    76.4s
    Throughput
    15 tps
    Context
    1.0M
    $/Mtok
    $6.00 / $22.50
    morph/fastfp4
  • DeepInfra57.81%
    Down24h 84.12%
    7d
    86.85%
    30d
    86.85%
    p50
    1.52s
    p99
    133s
    Throughput
    11 tps
    Context
    1.0M
    $/Mtok
    $2.85 / $14.25
    deepinfra/bf16bf16
  • Morph44.13%
    Down24h 95.27%
    7d
    88.81%
    30d
    88.81%
    p50
    7.69s
    p99
    71.4s
    Throughput
    18 tps
    Context
    1.0M
    $/Mtok
    $2.80 / $14.00
    morph/fp4fp4
  • Down24h 90.19%
    7d
    93.90%
    30d
    93.90%
    p50
    9.38s
    p99
    110s
    Throughput
    20 tps
    Context
    1.0M
    $/Mtok
    $3.00 / $15.00
    phala
  • Down24h 89.45%
    7d
    95.20%
    30d
    95.20%
    p50
    187s
    p99
    287s
    Throughput
    1.0 tps
    Context
    1.0M
    $/Mtok
    $3.00 / $15.00
    wafer

Measured 4m ago. Latency and throughput are OpenRouter's rolling 30-minute windows. ◆ marks the best value in each column among these endpoints.

Price vs latency

One dot per endpoint at the latest round · further left = faster, lower = cheaper · hover a dot for its tag

History

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.