Decart
Real-time AI lab behind the Lucy video-editing and Oasis world models, with its own inference and training stack.
Overview
Decart models are available through Nautili. Requests to them use the same routing, governance and observability as every other request.
Models
- DeepSeek V4.1 Flashdeepseek/deepseek-v4.1-flashView model: DeepSeek V4.1 Flash
- DeepSeek V4.1 Flash 1017deepseek/deepseek-v4.1-flash-1017View model: DeepSeek V4.1 Flash 1017
- Kimi K2.6moonshotai/kimi-k2.6View model: Kimi K2.6
- Kimi K3moonshotai/kimi-k3View model: Kimi K3
- GLM 5.2z-ai/glm-5.2View model: GLM 5.2
- GLM 5.2 (free)z-ai/glm-5.2:freeView model: GLM 5.2 (free)
- GLM 5.3z-ai/glm-5.3View model: GLM 5.3
- GLM 5.3 Flashz-ai/glm-5.3-flashView model: GLM 5.3 Flash
Integration
Point your existing SDK or tool at your Nautili endpoint and key. Nautili routes requests to Decart models within your policies.
Managed: use Nautili-issued credentials.
Connect your stack to Nautili
Route across supported providers through one control layer.