Kimi K2.6
Moonshot's open-weight coding model with state-of-the-art agentic coding capabilities. Ranks #1 on the Artificial Analysis Intelligence Index and outperforms proprietary flagships on coding benchmarks.
Specifications
| Lab | Moonshot |
|---|---|
| Context window | 262.1K tokens |
| Input price | $0.95/1M |
| Output price | $4.00/1M |
| Release | Apr 2026 |
Strengths
- State-of-the-art open-source coding performance
- Strong long-context stability (256K tokens)
- Agentic coding with reliable tool use
- Competitive with proprietary flagships in coding benchmarks
- Modified MIT license enables commercial use
Weaknesses
- Higher output pricing than other open models
- Very verbose output can increase effective cost
- Less optimized for general conversation tasks
Best for
- Agentic coding workflows
- Long-context codebase analysis
- Open-source AI development
- Cost-effective alternative to proprietary coding models
In Depth: Kimi K2.6
Summary
Kimi K2.6 is an AI model from Moonshot.
Released in Apr 2026. It currently appears in the Overall category on LMRank. It takes text input and produces text output, with a context window of 262.1K tokens. Input pricing is $0.95 per 1M tokens and output is $4.00 per 1M tokens on OpenRouter.