Azure OpenAI
Last updated
Was this helpful?
Azure OpenAI is Microsoft's OpenAI model service hosted on Azure, suitable for teams that need enterprise compliance, data residency commitments, or the Microsoft ecosystem.
Azure subscription activated
Applied for and approved for Azure OpenAI Service access in Azure Portal
Created at least one resource (Resource) and deployment (Deployment)
Azure Portal → Your Azure OpenAI resource → Keys and Endpoint
Copy KEY 1 or KEY 2, note down Endpoint(in the form of https://<your-name>.openai.azure.com/)
After enabling it Settings → Model Services, find Azure OpenAI Provider to enter the details page
API key: enter the copied KEY
API address: enter the resource Endpoint (no trailing path required)
API Version: in the dedicated field, enter your deployment's API version (for example 2024-08-01-preview)
Click Get model list, or manually add the model name you have deployed on Azure (i.e., Deployment Name, not the original OpenAI model ID)
Deployment Name vs Model ID: Azure uses the name you gave the deployment (e.g. gpt-4o-prod), not gpt-4o original ID like this. Entering the wrong one will cause a 404.
gpt-4o / gpt-4o-mini: general chat, Agent
gpt-4 turbo: long context
text-embedding-3-*: embedding models, can be used for knowledge bases
401 Unauthorized: check whether the Key is correct and whether there is an extra slash at the end of the Endpoint
404 Not Found: check whether Deployment Name matches Azure, and whether API Version has been filled in
429 Throttled: check Azure quota (Quota & Limits page)
If you encounter any questions or bugs during configuration or use, or have suggestions for feature improvements, please refer to the official channels provided in Feedback and Suggestions .
Last updated
Was this helpful?
Was this helpful?