OpenAI

OpenAI’s GPT models are among the most widely used language models available. Selu supports all GPT models accessible through the OpenAI API, including the latest GPT-4o variants.

Getting an API key

Sign up or log in at platform.openai.com.
Go to API Keys in your account settings.
Click Create new secret key, name it “Selu”, and copy the key immediately.

Connecting to Selu

In the Selu sidebar, click Providers.
Click Add Provider and select OpenAI.
Paste your API key into the API Key field.
Leave Base URL empty to use OpenAI’s default servers.
Click Check & Save. Selu will verify the key works and save it.

The OpenAI provider setup page with fields for API Key and Base URL.

Your API key is encrypted at rest.

Choosing a model

Once connected, you can choose which model your agents use. The model is selected per agent under Agents → (agent name) → Model.

Model	Best for
GPT-4o	OpenAI’s flagship model. Fast, capable, and supports text and images. Recommended for most use cases.
GPT-4o mini	A smaller, faster, and cheaper version of GPT-4o. Great for everyday tasks at lower cost.
o3	Advanced reasoning model for complex problem-solving, math, and multi-step analysis.
o3-mini	A lighter reasoning model that balances capability with speed.
o4-mini	Compact reasoning model optimized for efficiency.

Using an OpenAI-compatible API

If you’re running a model server that exposes an OpenAI-compatible API (like LM Studio or vLLM), you can point Selu to it by entering the server address in the Base URL field during setup:

http://your-server:8080/v1

This works with any server that implements the OpenAI chat completions endpoint.

Troubleshooting

“Insufficient quota” — Check your billing settings at platform.openai.com/billing. You may need to add a payment method or increase your spending limit.
Model not available — Some models require API access approval. Check your account’s model access page.
Timeout errors — Long responses can sometimes time out. If this happens consistently, try using a faster model.