Chat with a model

Send your first prompt to a hosted model in the AI Studio Text Playground. No setup or training required. Pick a model and start chatting.

See the full Text Playground guide for more details.

Before you begin

You'll need:

1. A Hyperstack account. Sign up on the registration page using your email or an SSO provider (Google, Microsoft, or GitHub).
2. Billing set up. Add credit to your account.
3. Access to AI Studio. Open AI Studio in the Hyperstack console.

Run inference in the Text Playground

1. Open the Text Playground

   Navigate to the Text Playground in AI Studio.

   

2. Select a model

   From the model dropdown, choose any base model, or one of your own fine-tuned models if you have deployed one.

   Compare two models

   Turn on the Compare side-by-side toggle to pick a second model and send the same prompt to both at once. Each model is billed separately. See the Compare Side-by-Side guide.

3. (Optional) Add a system prompt

   To steer the model's behavior, click the + next to System Prompt, enter a prompt name and the instructions (such as You are a concise technical assistant.), then click Save. Select your saved prompt from the Select prompt dropdown to apply it.

4. (Optional) Adjust parameters

   Expand the Settings section to tune the response with the available sliders, such as temperature, max tokens, and top-p. The defaults work well to start. See the parameter reference for what each one does.

5. Send a prompt

   Type your message into the input box and press Enter. The model's response streams back in the chat. Your session, model, and settings are saved after you send the first message.

Next steps

Use the API

Run the same inference programmatically with the OpenAI-compatible API.

Browse models

See every base model available for inference, with pricing and context limits.

Fine-tune a model

Train a model on your own data for better results on your use case.

Overview

Browse the full AI Studio documentation.