Friendli
Inference platform focused on fast, efficient serving.
Overview
Friendli models are available through Nautili. Requests to them use the same routing, governance and observability as every other request.
Models
- DeepSeek V3.2deepseek/deepseek-v3.2View model: DeepSeek V3.2
- Gemma 4 31Bgoogle/gemma-4-31b-itView model: Gemma 4 31B
- MiniMax M2.5minimax/minimax-m2.5View model: MiniMax M2.5
- GLM 5.1z-ai/glm-5.1View model: GLM 5.1
- GLM 5.2z-ai/glm-5.2View model: GLM 5.2
- 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 Friendli models within your policies.
Managed: use Nautili-issued credentials.
Connect your stack to Nautili
Route across supported providers through one control layer.