modelstatus.dev

Kimi K3

moonshotai/kimi-k3InputtextimagevideoOutputtext

Compare its 29 providersIncident RSSCompare with Kimi K2.7 Code, Kimi K2.6, Kimi K2.5

Showing only the wafer/us provider · show all 29

CompareKimi K3
  • Wafer100%
    Healthy24h 98.52%
    7d
    99.79%
    30d
    99.79%
    p50
    707ms
    p99
    27.2s
    Throughput
    44 tps
    Context
    1.0M
    $/Mtok
    $2.80 / $14.00
    wafer/us

Measured 3m 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
relace/fp4
morph/fp8
digitalocean
morph/fast
decart/mxfp4
baseten/fp8
fireworks/us
chutes/mxfp4
fireworks
inference-net
moonshotai/mxfp4
inference-net/fp4
parasail/fp4
fireworks/fast
alibaba
morph
sail-research/fp4
inference-net/fast
amazon-bedrock/us-east-2
wafer/us
deepinfra/mxfp4
akashml/fp4
worst hour ≥ 95%90–95%< 90%no data

Colour by each endpoint's worst hour of each UTC day · 29 endpoints · 47 days with data, 240 endpoint-days below 90%. Tables and charts above are filtered to wafer/us.

Price changes

  • Kimi K3InferenceNetinference-net/fast$2.99 → $3.50 / $20.002026-10-04 20:01 UTC
  • Kimi K3Relacerelace/fp4$0.636 → $0.631 / $13.002026-10-04 19:51 UTC
  • Kimi K3Relacerelace/fp4$0.638 → $0.636 / $13.002026-10-04 19:41 UTC
  • Kimi K3Relacerelace/fp4$0.640 → $0.638 / $13.002026-10-04 19:16 UTC
  • Kimi K3Relacerelace/fp4$0.655 → $0.640 / $13.002026-10-04 19:05 UTC
  • Kimi K3Morphmorph/fp8$2.50 → $2.03 / $12.52 → $9.872026-10-04 19:05 UTC
  • Kimi K3Relacerelace/fp4$0.660 → $0.655 / $13.002026-10-04 18:56 UTC
  • Kimi K3Relacerelace/fp4$0.669 → $0.660 / $13.002026-10-04 18:36 UTC
  • Kimi K3Relacerelace/fp4$0.669 → $0.669 / $13.002026-10-04 18:25 UTC
  • Kimi K3Waferwafer$0.730 → $0.950 / $13.002026-10-04 18:02 UTC
  • Kimi K3Relacerelace/fp4$0.676 → $0.669 / $13.002026-10-04 18:02 UTC
  • Kimi K3Relacerelace/fp4$0.677 → $0.676 / $13.002026-10-04 17:51 UTC
  • Kimi K3Relacerelace/fp4$0.680 → $0.677 / $13.002026-10-04 17:41 UTC
  • Kimi K3Decartdecart/mxfp4$2.25 → $2.64 / $11.25 → $13.20cache read $0.225 → $0.2642026-10-04 17:31 UTC
  • Kimi K3InferenceNetinference-net/fast$3.50 → $2.99 / $20.002026-10-04 17:16 UTC
  • Kimi K3Morphmorph/fp8$1.38 → $2.50 / $12.522026-10-04 17:10 UTC
  • Kimi K3InferenceNetinference-net/fast$3.75 → $3.50 / $20.002026-10-04 17:01 UTC
  • Kimi K3Relacerelace/fp4$0.674 → $0.680 / $13.002026-10-04 16:51 UTC
  • Kimi K3Phalaphala$2.25 → $1.95 / $11.25 → $9.75cache read $0.225 → $0.1952026-10-04 16:45 UTC
  • Kimi K3Relacerelace/fp4$0.661 → $0.674 / $13.002026-10-04 16:45 UTC
  • Kimi K3Relacerelace/fp4$0.640 → $0.661 / $13.002026-10-04 16:31 UTC
  • Kimi K3InferenceNetinference-net/fast$3.50 → $3.75 / $20.002026-10-04 16:31 UTC
  • Kimi K3InferenceNetinference-net/fast$2.99 → $3.50 / $20.002026-10-04 16:16 UTC
  • Kimi K3Relacerelace/fp4$0.629 → $0.640 / $13.002026-10-04 15:56 UTC
  • Kimi K3InferenceNetinference-net/fast$3.50 → $2.99 / $20.002026-10-04 15:26 UTC
  • Kimi K3Relacerelace/fp4$0.622 → $0.629 / $13.002026-10-04 15:21 UTC
  • Kimi K3Relacerelace/fp4$0.616 → $0.622 / $13.002026-10-04 15:11 UTC
  • Kimi K3Relacerelace/fp4$0.611 → $0.616 / $13.002026-10-04 15:01 UTC
  • Kimi K3InferenceNetinference-net/fast$3.95 → $3.50 / $20.002026-10-04 15:01 UTC
  • Kimi K3InferenceNetinference-net/fast$3.95 / $22.00 → $20.002026-10-04 14:51 UTC