Kimi-K2-Thinking
Kimi-K2-Thinking
About Kimi-K2-Thinking
Kimi K2 Thinking is Moonshot AI's latest open-source agentic model, excelling in multi-step reasoning and tool orchestration. It achieves state-of-the-art performance on HLE and BrowseComp, featuring native INT4 quantization for efficient inference and a 256K context window.
Metadata
Specification
Architecture
Calibrated
Yes
Mixture of Experts
Yes
Total Parameters
Activated Parameters
32B
Reasoning
No
Precision
FP8
Context length
Max Tokens
Compare with Other Models
See how this model stacks up against others.
Moonshot AI
chat
Kimi-K2-Instruct-0905
Release on: Sep 8, 2025
Total Context:
262K
Max output:
262K
Input:
$
0.4
/ M Tokens
Output:
$
2.0
/ M Tokens
Moonshot AI
chat
Kimi-K2-Instruct
Release on: Jul 13, 2025
Total Context:
131K
Max output:
131K
Input:
$
0.58
/ M Tokens
Output:
$
2.29
/ M Tokens
Moonshot AI
chat
Kimi-Dev-72B
Release on: Jun 19, 2025
Total Context:
131K
Max output:
131K
Input:
$
0.29
/ M Tokens
Output:
$
1.15
/ M Tokens
Model FAQs: Usage, Deployment
Learn how to use, fine-tune, and deploy this model with ease.
