Nebius
Nebius-hosted models for chat, embeddings and image generation.
Use models hosted on Nebius through DeepintShield, with your Nebius credentials held on the gateway.
What works
- Chat Completions, and the Responses API through chat
- Text completions and embeddings
- Image generation (no streaming) and list models
- Nebius
ai_project_idsupport
Limits to know: No speech, transcription, files or batch. Cache control is removed from requests.
How to connect
Add your Nebius API key in Model Hub → AI Providers, create a Virtual Key, then call nebius/<model> through https://app.deepintshield.com/v1 with any OpenAI-compatible client.
Read the Nebius provider docs. Requests get the same Virtual Key budgets, guardrails and logs as every other provider on the AI gateway.