Models
14 models
kimi-k2.7-code
$0.670/M input
$3.40/M output
MoonshotAI: Kimi K2.7 Code is a coding-focused model in Moonshot AI's Kimi K2 family, built to complete end-to-end programming tasks reliably over long contexts. It uses a native multimodal mixture-of-experts...
kimi-k2.7-code-highspeed
$0.190/M input
$0.800/M output
kimi-k3
$3.00/M input
$15.00/M output
Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at...
moonshot-v1-128k
$0.200/M input
$0.500/M output
moonshot-v1-128k-vision-preview
$0.200/M input
$0.500/M output
moonshot-v1-32k
$0.100/M input
$0.300/M output
moonshot-v1-32k-vision-preview
$0.100/M input
$0.300/M output
moonshot-v1-8k
$0.020/M input
$0.200/M output
moonshot-v1-8k-vision-preview
$0.020/M input
$0.200/M output
moonshot-v1-auto
— input
— output
MoonshotAI: Kimi K2 0711
$0.570/M input
$2.30/M output
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...
MoonshotAI: Kimi K2 0905
$0.600/M input
$2.50/M output
Kimi K2 0905 is the September update of [Kimi K2 0711](moonshotai/kimi-k2). It is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32...
MoonshotAI: Kimi K2 Thinking
$0.600/M input
$2.50/M output
Kimi K2 Thinking is Moonshot AI’s most advanced open reasoning model to date, extending the K2 series into agentic, long-horizon reasoning. Built on the trillion-parameter Mixture-of-Experts (MoE) architecture introduced in...
MoonshotAI: Kimi K2.7 Code (batch)
$0.475/M input
$2.00/M output
MoonshotAI: Kimi K2.7 Code is a coding-focused model in Moonshot AI's Kimi K2 family, built to complete end-to-end programming tasks reliably over long contexts. It uses a native multimodal mixture-of-experts...