# Kimi K2 Thinking: AI model fact sheet

- **Provider:** moonshotai
- **Released:** 2025-11-06
- **Context window:** 262,144 tokens
- **Parameters:** 1T (32B active)
- **API pricing:** $0.60 / 1M input, $2.50 / 1M output
- **OpenRouter ID:** moonshotai/kimi-k2-thinking
- **Capabilities:** conversation, reasoning, code-generation, analysis, tool-use

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 Kimi K2, it activates 32 billion parameters per forward pass and supports 256K-token context windows. The model is optimized for persistent step-by-step thought, dynamic tool invocation, and complex reasoning workflows that span hundreds of turns. It interleaves step-by-step reasoning with tool use, enabling autonomous research, coding, and writing that can persist for hundreds of sequential actions without drift.

## Benchmarks

| Benchmark | Score |
| --- | --- |
| HLE | State-of-the-art |
| BrowseComp | State-of-the-art |
| SWE-Multilingual | State-of-the-art |
| LiveCodeBench | State-of-the-art |

Source: real side-by-side outputs, pricing and specs at https://rival.tips/models/kimi-k2-thinking