Kimi K2 Thinking
Moonshot AI
🧠 Language Model
Most powerful open-source thinking model. 1T MoE with 32B active, 256K context, native INT4 quantization.
Specifications
Context Window262,144 tokens
Max Output131,072 tokens
Speed●●●●● Average
ModalitiesInput: text · Output: text
FeaturesTools: Yes Streaming: Yes
Pricing
Included with plan
Capabilities
More from Moonshot AI
Kimi K2 Thinking Turbo
Fast variant of Kimi K2 Thinking optimized for speed while maintaining reasoning capabilities.
Moonshot v1 128K
General-purpose model with 128K context window for long document processing.
Moonshot v1 32K
Balanced model with 32K context for everyday tasks.
Moonshot v1 8K
Fast model with 8K context for quick responses.