AI inference playground

The inference playground lets you send test prompts to an available text generation endpoint.

Start a chat

Open AI inference

In your project, open AI Inference.

Create an API key

Create an inference API key if the project does not already have one.

Open Playground

Choose the Playground tab.

Pick a model and key

Choose an inference endpoint and an API key.

Send a message

Enter a prompt and submit the request.

Advanced settings can include:

Use lower temperature for deterministic answers and higher temperature for more varied responses.

If file upload is available for the selected endpoint, attach files only when the model supports that input type.

Embedding endpoints are not chat models. Use text generation endpoints in the playground.

Error	What to check
`400` response	Confirm the selected model supports the request shape.
Missing API key	Create an inference API key first.
Empty response	Try a shorter prompt or a different model.
Unauthorized	Make sure the key belongs to the current project.