OpenAI
Velaris routes every step to the model that fits it, and OpenAI's models are part of that mesh — GPT for reasoning-heavy drafting, embeddings for search across your own documents. Bring your own API key and the usage stays on your account.
What your agents can do with OpenAI
- Route steps to GPT models
- Generate embeddings for document search
- Bring your own OpenAI key
- Compare output across model providers
How to connect OpenAI to Velaris
- 1
Create your Velaris account
Sign up and open your AI OS desktop.
- 2
Open Connections
Go to Settings → Connections in the OS.
- 3
Connect OpenAI
Authorize OpenAI with scoped access you control.
- 4
Ask an agent to act
Tell Velaris a goal — it uses OpenAI from the mesh automatically.
Popular ways to use it
OpenAI + Velaris — common questions
Does Velaris only run on OpenAI models?
No — it's model-agnostic and routes per step, so one run can use OpenAI for reasoning and a cheaper model for a classification pass.
Can I use my own OpenAI API key?
Yes — bring your key and usage bills to your OpenAI account, which also keeps that traffic under your own organization's data settings.
Is my data used to train OpenAI models?
No. API traffic isn't used for training by default, and with your own key your organization's data controls apply directly.