admin管理员组

文章数量:1356329

Why doesn't my Azure OpenAI model show up in Cursor as one of the available models?

I added my Azure OpenAI account show up in Cursor in the Settings window:

The green toggle switch seems to indicate that Cursor has access to the Azure GPT deployment:

But I don't see the Azure OpenAI model as one of the available models:

Why doesn't my Azure OpenAI model show up in Cursor as one of the available models?

Why doesn't my Azure OpenAI model show up in Cursor as one of the available models?

I added my Azure OpenAI account show up in Cursor in the Settings window:

The green toggle switch seems to indicate that Cursor has access to the Azure GPT deployment:

But I don't see the Azure OpenAI model as one of the available models:

Why doesn't my Azure OpenAI model show up in Cursor as one of the available models?

Share Improve this question edited Apr 2 at 5:19 Franck Dernoncourt asked Mar 29 at 23:57 Franck DernoncourtFranck Dernoncourt 83.6k77 gold badges366 silver badges544 bronze badges 2
  • The deployment name must exactly match the name of the deployment you created in the Azure OpenAI portal (not the model name like gpt-35-turbo, but your custom deployment name, e.g., my-gpt35). – Suresh Chikkam Commented Apr 2 at 3:53
  • 1 @SureshChikkam thanks, this is what I've done. The green toggle switch seems to confirm that cursor has access to the GPT deployment. – Franck Dernoncourt Commented Apr 2 at 5:15
Add a comment  | 

1 Answer 1

Reset to default 1

@Franck Dernoncourt, I'm glad that my suggestion was helpful for you. Here, I'm sharing the solution for the benefit of the community, in case any other user encounters a similar issue.

First, check that the Deployment Name you have entered into Cursor exactly matches the name of the deployment you created in the Azure OpenAI portal. It’s not the model name like gpt-4 or gpt-35-turbo it’s the name you gave the deployment when setting it up. This is case-sensitive, so even a small mismatch can prevent it from being recognized.

Next, check you are using a supported model. Cursor currently works with models like gpt-35-turbo, gpt-4, and similar versions. If you deployed something that’s not a chat model, or if it's a newer version that Cursor hasn’t added support for yet, it won’t show up in the model switcher.

The Base URL needs to be correctly formatted. It should look something like https://your-resource-name.openai.azure/. Make sure it includes the trailing slash at the end—Cursor (and some other clients) are picky about that.

Cursor doesn’t always show models right after you save the API info, especially if there’s a minor config issue or network hiccup. Try toggling the Azure API Key switch off and on again in Cursor’s settings, then restart Cursor completely. That usually forces a refresh.

Finally, check that the API key you’re using has the right permissions. It needs to belong to a user or service principal that has access to the Azure OpenAI resource, and the key itself must be active and unrestricted.

If you’re still stuck, Cursor has a help doc on setting up API keys that walks through the process step by step, and it’s worth a look to compare with what you’ve done.

本文标签: Why doesn39t my Azure OpenAI model show up in CursorStack Overflow