Your Azure deployments. Your tenant. One workspace.
Azure OpenAI serves the models you deploy in your own Azure resource. Big-AGI is the workspace. Add your endpoint and key, keep prompts inside your tenant, and run your deployments next to Claude, Gemini, and Grok.
Bring your Azure key · Your tenant · Enterprise-ready
Why Azure in Big-AGI
Azure OpenAI, with a real workspace on top.
Stays in your tenant
Requests go to your Azure OpenAI endpoint, under your resource and region. The compliance boundary is the one you already run.
Your Azure billing
Usage bills through your Azure subscription at your own rates. No markup, no intermediary, nothing proxied through us.
Your deployments, your names
Big-AGI talks to the deployments you created, by the deployment name you chose. Point it at the endpoint and it uses what you provisioned.
Beam across clouds
Run your Azure deployment against Claude, Gemini, or Grok in parallel, then merge the answers. Consensus is signal, disagreement is where you dig deeper.
Set it up
Three steps to your first Azure chat.
01
Create an Azure OpenAI resource
In the Azure portal, create an Azure OpenAI resource, then note its endpoint, for example https://your-resource.openai.azure.com, and a key.
02
Deploy a model
Deploy the models you want in Azure AI Foundry, for example a GPT deployment. The deployment name is what Big-AGI will call.
03
Connect it in Big-AGI
In Models, add Azure OpenAI, then paste your endpoint, key, and deployment name. No account needed on our side, your key stays in the browser.
Run Azure OpenAI in Big-AGI.
Your endpoint, your key, your tenant. Frontier models one click away, all in one workspace.
BIG-AGI
Resources
© 2026 Token Fabrics·Built with passion in San Diego