Here’s a guide to set up Cursor, a leading AI-powered IDE, with lightning-fast Cerebras inference. Whether you’re building agents, refactoring legacy code, or exploring new codebases, you can now work at the speed of thought using the latest open models like Qwen3-32B and Qwen3-235B — powered by Cerebras’s wafer-scale inference.

How to Use Cerebras in Cursor

1

Obtain Cerebras API Key

Get a free Cerebras API key here.
2

Install Cursor

Head to Cursor.com to install the AI dev environment.Install PnFollow the steps to download the software on your machine.
3

Open up Cursor settings

Settings Pn
4

Select the "Models" tab

Models Pn
5

Deactivate Models

Models PnDeactivate all other models in the list. You must deactivate all other models in order to use custom ones.
6

Add a Cerebras model

You can find a list of available models here.Add Cerebras Model Pn
7

Setting custom API key

Click “API Keys“ and set the default OpenAI key to your Cerebras key.Api Key Pn
8

Override the OpenAI base URL

9

Confirm Settings

You can now click the “Verify“ button to confirm your API key and URL overrides!Confirm Settings Pn
10

Try it out!

Now, go select your custom model just like any other!Try Model Pn