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 97.95%
    7d
    98.25%
    30d
    98.25%
    p50
    952ms (best)
    p99
    20.2s
    Throughput
    63 tps
    Context
    1.0M
    $/Mtok
    $3.00 / $15.00
    baseten/fp8fp8
  • Chutes100% (best)
    Healthy24h 98.88%
    7d
    97.30%
    30d
    97.30%
    p50
    1.72s
    p99
    10.3s (best)
    Throughput
    19 tps
    Context
    1.0M
    $/Mtok
    $3.00 / $15.00
    chutes/mxfp4mxfp4
  • Modal99.59%
    Healthy24h 99.60%
    7d
    99.66% (best)
    30d
    99.66% (best)
    p50
    1.90s
    p99
    17.1s
    Throughput
    69 tps (best)
    Context
    1.0M
    $/Mtok
    $3.00 / $15.00
    modal/mxfp4mxfp4
  • Fireworks99.32%
    Healthy24h 98.84%
    7d
    98.98%
    30d
    98.98%
    p50
    2.38s
    p99
    21.5s
    Throughput
    43 tps
    Context
    1.0M
    $/Mtok
    $3.00 / $15.00
    fireworks
  • Healthy24h 99.35%
    7d
    99.30%
    30d
    99.30%
    p50
    2.19s
    p99
    29.0s
    Throughput
    26 tps
    Context
    1.0M
    $/Mtok
    $2.85 / $14.25
    digitalocean
  • Healthy24h 98.34%
    7d
    99.09%
    30d
    99.09%
    p50
    5.12s
    p99
    43.9s
    Throughput
    23 tps
    Context
    1.0M
    $/Mtok
    $3.00 / $15.00
    moonshotai/mxfp4mxfp4
  • Together98.15%
    Healthy24h 98.84%
    7d
    98.73%
    30d
    98.73%
    p50
    3.44s
    p99
    25.7s
    Throughput
    32 tps
    Context
    1.0M
    $/Mtok
    $3.00 / $15.00
    together
  • Healthy24h 97.14%
    7d
    98.41%
    30d
    98.41%
    p50
    5.00s
    p99
    102s
    Throughput
    22 tps
    Context
    975K
    $/Mtok
    $2.60 / $13.00 (best)
    sail-research/fp4fp4
  • Morph93.44%
    Degraded24h 95.53%
    7d
    88.67%
    30d
    88.67%
    p50
    5.56s
    p99
    30.8s
    Throughput
    22 tps
    Context
    1.0M
    $/Mtok
    $2.80 / $14.00
    morph/fp4fp4
  • Phala89.36%
    Down24h 91.40%
    7d
    93.89%
    30d
    93.89%
    p50
    4.97s
    p99
    52.0s
    Throughput
    23 tps
    Context
    1.0M
    $/Mtok
    $3.00 / $15.00
    phala
  • Down24h 92.48%
    7d
    95.46%
    30d
    95.46%
    p50
    4.08s
    p99
    71.6s
    Throughput
    27 tps
    Context
    1.0M
    $/Mtok
    $3.30 / $16.50
    fireworks/us
  • No data24h 85.54%
    7d
    87.68%
    30d
    87.68%
    p50
    969ms
    p99
    30.3s
    Throughput
    20 tps
    Context
    1.0M
    $/Mtok
    $2.85 / $14.25
    deepinfra/bf16bf16
  • No data24h 82.58%
    7d
    84.04%
    30d
    84.04%
    p50
    4.76s
    p99
    37.2s
    Throughput
    20 tps
    Context
    1.0M
    $/Mtok
    $6.00 / $22.50
    morph/fastfp4
  • No data24h 90.15%
    7d
    95.20%
    30d
    95.20%
    p50
    34.4s
    p99
    54.2s
    Throughput
    3.0 tps
    Context
    1.0M
    $/Mtok
    $3.00 / $15.00
    wafer

Measured 2m 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.