Makora
Startup whose AI agent writes and tunes GPU kernels, serving open-weight models like Kimi, GLM and Gemma with them.
Overview
Makora models are available through Nautili. Requests to them use the same routing, governance and observability as every other request.
Models
- DeepSeek V4 Flash 0731deepseek/deepseek-v4-flash-0731View model: DeepSeek V4 Flash 0731
- 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
- Gemma 4 26B A4B google/gemma-4-26b-a4b-itView model: Gemma 4 26B A4B
- Muse Spark Openmeta/muse-spark-openView model: Muse Spark Open
- Kimi K3moonshotai/kimi-k3View model: Kimi K3
- Hy4 previewtencent/hy4-previewView model: Hy4 preview
- MiMo-V2.6-Flashxiaomi/mimo-v2.6-flashView model: MiMo-V2.6-Flash
- 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 Makora models within your policies.
Managed: use Nautili-issued credentials.
Connect your stack to Nautili
Route across supported providers through one control layer.