Kimi K2.6
Kimi K2.6 advances the Kimi multimodal agent family with stronger long-horizon coding, coding-driven design, and tool-based execution. It targets complicated end-to-end engineering tasks across languages such as Rust, Go, and Python, including performance optimization and DevOps. Native image and video understanding supports visual interfaces and design workflows. The model is available through Kimi chat, Kimi Code, the official API, and downloadable modified-MIT weights. Agent-swarm demonstrations use orchestration around the model; their concurrency should not be confused with its expert count.
2026-04-20
1T total, 32B activated
Mixture of Experts (MoE) with MoonViT vision encoder
Modified MIT
Specifications
- Parameters
- 1T total, 32B activated
- 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
- Available
Capabilities & Limitations
- Capabilities
- reasoningcode generationtool uselong-horizon codingvisual interface generationagent orchestration
- Known Limitations
- Local deployment requires substantial memory for the full MoE weights.Agent performance depends on tools, harness configuration, and context management.Swarm and persistent-agent demonstrations depend on the surrounding execution system.
- Notable Use Cases
- coding assistantsmulti-step research agentssoftware developmentperformance optimizationcoding-driven design
- Function Calling Support
- Yes
- Tool Use Support
- Yes