Skip to main content
In just a few minutes, you’ll be chatting with the latest open source models and sending inference requests with the Modular Cloud API.

Try the playground

Here’s how to play with some models without writing any code.
1

Log in

Sign up with your work email at console.modular.com.
2

Chat with a model

Click Playground in the sidebar and select a shared model from the dropdown.Now start chatting!

Run inference with the API

Here’s a quick guide to running inference with the chat completions API.
1

Set your API key

Create an API key with Model access, then export it:
2

Install the OpenAI client

You can skip this if you’re going to use cURL.
3

Copy this code

4

Run it

You should quickly see the response.
That’s it! You’re up and running. To try a different model, just change the code’s model parameter: Browse the available shared endpoints and click a model, then copy the Model ID shown on the right.

Next steps

Check out these guides to learn more about using the Modular Cloud APIs: