InferenceNet

Inference infrastructure for AI-native teams: fast serving for open-source and tuned models such as GPT-OSS and Kimi.

Overview

InferenceNet models are available through Nautili. Requests to them use the same routing, governance and observability as every other request.

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
Schematron V2 Smallinference-net/schematron-v2-smallView model: Schematron V2 Small
Schematron V2 Turboinference-net/schematron-v2-turboView model: Schematron V2 Turbo
MiniMax M3.1 Flashminimax/minimax-m3.1-flashView model: MiniMax M3.1 Flash
Kimi K3moonshotai/kimi-k3View model: Kimi K3
Step 5 Previewstepfun/step-5-previewView model: Step 5 Preview
MiMo-V2.6-Flashxiaomi/mimo-v2.6-flashView model: MiMo-V2.6-Flash
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

Point your existing SDK or tool at your Nautili endpoint and key. Nautili routes requests to InferenceNet models within your policies.

Managed: use Nautili-issued credentials.

Route across supported providers through one control layer.