Azure OpenAI Guide

Azure OpenAI uses deployment-specific routes. The most important setup step is matching the base URL and route prefix to the deployment you created in Azure.

Add the connection

1. Open 3sparks Chat and go to Connections.
2. Tap + and choose Azure OpenAI.
3. Leave the name blank to use a generated name, or enter your own.
4. Set Base URL to your Azure resource host, such as YOUR_RESOURCE.openai.azure.com.
5. Set Route Prefix to /openai/deployments/YOUR_DEPLOYMENT_NAME/.
6. Paste your Azure OpenAI key into API Token. Tokens are stored in Keychain.
7. Confirm the API profile is OpenAI and HTTPS is enabled.
8. Tap Create Connection, then fetch or enter the deployment model as needed.

Deployment notes

Azure model names are tied to your deployment names. If fetching models does not return what you expect, check the Azure AI Foundry or Azure Portal deployment name and update the route prefix.

If the chat says the selected model is unavailable, use Switch Model or edit the connection to point at a deployment that exists.

Troubleshooting

• Use the resource host only in Base URL; put the deployment path in Route Prefix.
• Confirm the API key and resource are from the same Azure project/subscription.
• Check quota, region availability, and deployment status in Azure.
• Lower token limits if your deployment has a smaller context window.