Explore
Models
Blueprints
GPUs
Docs
⌘K
Ctrl+K
?
Login
Moonshotai
4 results
Moonshotai
kimi-k2.5
1T multimodal MoE for high‑capacity video and image understanding with efficient inference.
Model
Multimodal
+4
19.83M
1mo
Moonshotai
kimi-k2-thinking
Open reasoning model with 256K context window, native INT4 quantization and enhanced tool use.
Model
Conversational
+4
3.06M
2mo
Moonshotai
kimi-k2-instruct-0905
Follow-on version of Kimi-K2-Instruct with longer context window and enhanced reasoning capabilities.
Model
long-context
+4
10.36M
5mo
Moonshotai
kimi-k2-instruct
State-of-the-art open mixture-of-experts model with strong reasoning, coding, and agentic capabilities
Model
coding
+3
19.43M
7mo