Benchmarks

MoonshotAI: Kimi K3

moonshotai/kimi-k3

Kimi K3 is MoonshotAI's open-weight flagship and the strongest model in its open-weight class, ranking #9 of 235 on the TryAii Score. It's strongest on head-to-head chat (#6 on Chatbot Arena Elo (Code)). API pricing starts at $3/$15 per million input/output tokens, though similar scores now sell for about $8 per million output tokens, with 15 independent hosts serving it. It's reasonably quick at roughly 28-45 tokens/sec.

Prompt $/1M
$3.000
Completion $/1M
$15.000
Context
1,048,576 tok
Best provider
92 tok/s · Modal

Specs

Model id
moonshotai/kimi-k3
Display name
MoonshotAI: Kimi K3
Modality
text+image+video->text
Tokenizer
Other
Instruct type
Context length
1,048,576
Max completion
943,718
Prompt $/1M
$3.000
Completion $/1M
$15.000
Free tier
no

Capabilities

  • Function callingno
  • JSON modeno
  • System promptno
  • Visionyes
  • Moderatedno

Benchmark scores

Each axis is one benchmark, normalized to the best model in the field.

No benchmark data for this model.

Speed by provider

Providertok/s
Modalfastest92
Fireworks79
Parasail62
Together61
Phala45
Wafer42
BaseTen42
Sail Research41
Artificial Analysis38
DigitalOcean31
DeepInfra29
Moonshot AI28
Alibaba28
Makora21
Chutes16
Morph10
Nebius7
moonshotaifastest