Kimi K2.7 Code
Moonshot AI · #6 in our ranking · Best for coding
Kimi K2.7 Code is an open-weight mixture-of-experts model from Moonshot AI, released Jun 2026, with 1T parameters (32B active per token), a 256K-token context window, and the Modified MIT.
Kimi K2.7 Code builds on Kimi K2.6 with large gains on real-world, multi-step coding tasks. Moonshot reports about 30% fewer thinking tokens than K2.6, which lowers cost on long runs.
Kimi K2.7 Code specs
- Provider
- Moonshot AI
- Architecture
- Mixture-of-experts
- Parameters
- 1T total · 32B active
- Context
- 256K tokens | 197K words
- License
- Modified MIT
- Input
- Text, Image
- Released
- Jun 2026
- Weights
- Hugging Face
Sourced from the model card on Hugging Face. Last checked 2026-10-01.
Highlights
- Built for long-horizon coding
- About 30% fewer thinking tokens than K2.6
- 256K context
Where it fits for payment teams
Good for engineering agents that review PRs, write SQL, or patch internal tools your ops teams depend on.
Harnesses in Runtime
Run Kimi K2.7 Code through any of these harnesses on Runtime.
How to run Kimi K2.7 Code
Download the weights
Pull moonshotai/Kimi-K2.7-Code from Hugging Face. Check the Modified MIT before you deploy.
Serve it in your cloud
Run it with vLLM or SGLang on your own GPUs, or use a managed provider that hosts the model.
Put it to work in Runtime
Point an agent or a single skill at the model through OpenCode, then compare it to your current model with evals.
Kimi K2.7 Code FAQ
What is the context window of Kimi K2.7 Code?
+
Kimi K2.7 Code supports a 256K-token context window (262,144 tokens), roughly 197K words of English text.
How many parameters does Kimi K2.7 Code have?
+
Kimi K2.7 Code is a mixture-of-experts model with 1T total parameters, of which 32B are active per token.
Is Kimi K2.7 Code free for commercial use?
+
Kimi K2.7 Code is released under the Modified MIT, a custom license. Commercial use may come with conditions, so read the license on Hugging Face before you deploy or fine-tune it.
What can Kimi K2.7 Code take as input?
+
Kimi K2.7 Code accepts text, image input and generates text.
Can I run Kimi K2.7 Code in my own cloud with Runtime?
+
Yes. Download the weights from Hugging Face (moonshotai/Kimi-K2.7-Code) and serve them with vLLM or SGLang in your cloud, or use a managed provider that hosts the model. Runtime agents can then use Kimi K2.7 Code through a harness like OpenCode, with your data staying in your environment.