Kimi K2.7 Code
Kimi K2.7 Code is a separately positioned coding specialization of the native multimodal K2 family. It improves long-horizon software engineering and reasoning efficiency while retaining image and video input for visual coding tasks. The model supports a 256K context and always runs in thinking mode; Kimi Code requests with thinking disabled fall back to K2.6. Public modified-MIT weights support self-hosting, and the official kimi-k2.7-code API exposes the model to coding agents. Its identity is distinct from a general-purpose K2.7 release, which is not implied by this page.
2026-06-12
1T total, 32B activated; 400M vision encoder
Mixture of Experts (MoE) with MoonViT vision encoder
Modified MIT
Specifications
- Parameters
- 1T total, 32B activated; 400M vision encoder
- Architecture
- Mixture of Experts (MoE) with MoonViT vision encoder
- License
- Modified MIT
- Context Window
- 262,144 tokens
- Type
- multimodal
- Modalities
- textimagevideo
Benchmark Scores
Advanced Specifications
- Model Family
- Kimi
- API Access
- Available
- Chat Interface
- Not Available
- Variants
- Kimi-K2.7-Code-HighSpeed (same coding model, faster serving)
Capabilities & Limitations
- Capabilities
- reasoningcode generationtool uselong-horizon codingvisual debugging
- Known Limitations
- Thinking mode is required; non-thinking requests in Kimi Code can fall back to K2.6.Local deployment requires substantial memory for the full MoE weights.Agent performance depends on tools, harness configuration, and context management.
- Notable Use Cases
- repository maintenancecoding agentsscreenshot-based interface development
- Function Calling Support
- Yes
- Tool Use Support
- Yes