modelstatus.dev

Kimi K3

moonshotai/kimi-k3InputtextimagevideoOutputtext

Compare its 28 providersIncident RSSCompare with Kimi K2.7 Code, Kimi K2.6, Kimi K2.5

Showing only the wafer provider · show all 28

CompareKimi K3
  • Wafer100%
    Healthy24h 99.56%
    7d
    99.76%
    30d
    99.57%
    p50
    634ms
    p99
    7.69s
    Throughput
    64 tps
    Context
    1.0M
    $/Mtok
    $1.44 / $14.00
    wafer

Measured 2m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.

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, averaged over the hour.

Throughput

Median tokens per second.

Daily availability

One row per endpoint · one dot per day · last 90 days.

Jul
Aug
Sep
Oct
morph/fp4
deepinfra/bf16
together
wafer
modal/mxfp4
phala
makora
morph/fp8
digitalocean
morph/fast
decart/mxfp4
baseten/fp8
fireworks/us
chutes/mxfp4
inference-net
moonshotai/mxfp4
inference-net/fp4
parasail/fp4
fireworks
fireworks/fast
alibaba
relace/fp4
inference-net/fast
morph
sail-research/fp4
amazon-bedrock/us-east-2
wafer/us
akashml/fp4
worst hour ≥ 95%90–95%< 90%no data

Colour by each endpoint's worst hour of each UTC day · 28 endpoints · 46 days with data, 235 endpoint-days below 90%. Tables and charts above are filtered to wafer.

Price changes

  • Kimi K3Waferwafer$1.73 → $1.44 / $14.002026-10-03 17:45 UTC
  • Kimi K3Morphmorph/fp8$1.50 → $0.750 / $11.362026-10-03 17:40 UTC
  • Kimi K3InferenceNetinference-net/fast$3.85 → $3.00 / $19.00 → $15.002026-10-03 17:40 UTC
  • Kimi K3InferenceNetinference-net/fast$3.85 / $19.00cache read $0.800 → $0.9002026-10-03 13:01 UTC
  • Kimi K3Waferwafer$1.44 → $1.73 / $14.002026-10-03 10:16 UTC
  • Kimi K3InferenceNetinference-net/fast$3.50 → $3.85 / $19.002026-10-03 09:25 UTC
  • Kimi K3Relacerelace/fp4$0.980 → $0.990 / $13.002026-10-03 09:10 UTC
  • Kimi K3InferenceNetinference-net/fast$3.50 / $20.50 → $19.002026-10-03 08:55 UTC
  • Kimi K3Waferwafer$0.990 → $1.44 / $14.002026-10-03 08:10 UTC
  • Kimi K3InferenceNetinference-net/fast$3.50 / $19.00 → $20.502026-10-03 07:55 UTC
  • Kimi K3Relacerelace/fp4$0.790 → $0.980 / $13.002026-10-03 07:21 UTC
  • Kimi K3Waferwafer$0.800 → $0.990 / $19.00 → $14.002026-10-03 07:11 UTC
  • Kimi K3Relacerelace/fp4$0.690 → $0.790 / $13.002026-10-03 06:45 UTC
  • Kimi K3Waferwafer$0.700 → $0.800 / $19.002026-10-03 06:31 UTC
  • Kimi K3InferenceNetinference-net/fast$3.50 / $17.50 → $19.002026-10-03 06:21 UTC
  • Kimi K3InferenceNetinference-net/fp4$0.720 → $0.990 / $13.00cache read $0.700 → $0.8002026-10-03 05:50 UTC
  • Kimi K3Waferwafer$0.700 / $16.00 → $19.002026-10-03 05:40 UTC
  • Kimi K3InferenceNetinference-net/fast$3.50 / $17.50cache read $0.360 → $0.8002026-10-03 05:16 UTC
  • Kimi K3Relacerelace/fp4$0.615 → $0.690 / $13.002026-10-03 05:10 UTC
  • Kimi K3Waferwafer$0.700 / $14.00 → $16.002026-10-03 04:55 UTC
  • Kimi K3Morphmorph/fp8$0.625 → $1.50 / $11.362026-10-03 04:55 UTC
  • Kimi K3Waferwafer$0.700 / $13.00 → $14.002026-10-03 04:05 UTC
  • Kimi K3Relacerelace/fp4$0.690 → $0.615 / $13.002026-10-03 04:01 UTC
  • Kimi K3Morphmorph/fp8$0.750 → $0.625 / $11.362026-10-03 03:45 UTC
  • Kimi K3Relacerelace/fp4$0.710 → $0.690 / $13.002026-10-03 03:35 UTC
  • Kimi K3Waferwafer$0.990 → $0.700 / $14.00 → $13.002026-10-03 03:20 UTC
  • Kimi K3Relacerelace/fp4$0.740 → $0.710 / $13.002026-10-03 03:10 UTC
  • Kimi K3InferenceNetinference-net/fp4$0.980 → $0.720 / $13.00cache read $0.800 → $0.7002026-10-03 03:05 UTC
  • Kimi K3InferenceNetinference-net/fast$3.30 → $3.50 / $16.50 → $17.50cache read $0.340 → $0.3602026-10-03 03:05 UTC
  • Kimi K3Relacerelace/fp4$0.970 → $0.740 / $13.002026-10-03 02:35 UTC