MoonshotAI: Kimi K2 Thinking
7.6 / 10
262.1K context
Proprietary
About this model
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...
Benchmark Scores
HLE
51.0
IFEval
68.0
AIME-2025
100.0
LiveCodeBench
83.1
Technical Specs
- Architecture: text->text
- Context Window: 262,144 tokens
- Input Modalities: text
Hardware Requirements
- API-only (no local hardware needed)
Pricing
| Input | Output | Currency |
|---|---|---|
| 0.6 / 1M tokens | 2.5 / 1M tokens | USD |