Benchmarks

MoonshotAI: Kimi K2 0711

moonshotai/kimi-k2

Kimi K2 Instruct is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32 billion active per forward pass. It is optimized for...

Prompt $/1M
$0.570
Completion $/1M
$2.300
Context
131,072 tok
Best provider
37 tok/s · Artificial Analysis

Specs

Model id
moonshotai/kimi-k2
Display name
MoonshotAI: Kimi K2 0711
Modality
text->text
Tokenizer
Other
Instruct type
Context length
131,072
Max completion
100,352
Prompt $/1M
$0.570
Completion $/1M
$2.300
Free tier
no

Capabilities

  • Function callingno
  • JSON modeno
  • System promptno
  • Visionno
  • 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
Artificial Analysis37
Moonshot AI19
Novitafastest13
moonshotaifastest
MoonshotAI: Kimi K2 0711 - Benchmarks, Pricing and Speed | TryAii