Ionstream
GPU cloud offering dedicated single-tenant NVIDIA B200 and B300 bare-metal servers for training and inference.
Overview
Ionstream models are available through Nautili. Requests to them use the same routing, governance and observability as every other request.
Models
- DeepSeek V4 Pro 0813deepseek/deepseek-v4-pro-0813View model: DeepSeek V4 Pro 0813
- 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
- Qwen3.8 27Bqwen/qwen3.8-27bView model: Qwen3.8 27B
Integration
Point your existing SDK or tool at your Nautili endpoint and key. Nautili routes requests to Ionstream models within your policies.
Managed: use Nautili-issued credentials.
Connect your stack to Nautili
Route across supported providers through one control layer.