Nvidia
NVIDIA's hosted API catalog for its own and partner models.
Overview
Nvidia models are available through Nautili. Requests to them use the same routing, governance and observability as every other request.
Models
- Nemotron 3 Nano Omni (free)nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:freeView model: Nemotron 3 Nano Omni (free)
- Nemotron 3 Ultra (free)nvidia/nemotron-3-ultra-550b-a55b:freeView model: Nemotron 3 Ultra (free)
- Nemotron 3.5 Lightning (free)nvidia/nemotron-3.5-lightning:freeView model: Nemotron 3.5 Lightning (free)
- Nemotron 3.5 Super VL (free)nvidia/nemotron-3.5-super-vl:freeView model: Nemotron 3.5 Super VL (free)
Integration
Point your existing SDK or tool at your Nautili endpoint and key. Nautili routes requests to Nvidia models within your policies.
Managed: use Nautili-issued credentials.
Connect your stack to Nautili
Route across supported providers through one control layer.