Model Selection & Playground

Before you write integration code, the console helps you find a model, review its details, and validate it interactively.

1. Discover and compare models on the Models page.
2. Test the selected model interactively in the Playground.

​

1. Review and choose a model

Browse the Models page to explore the catalog. You can narrow the catalog by organization, model type, context window, and input price, search by name, or sort by release time or price. If you are not sure where to start, describe your task in Find Model. The recommendation assistant suggests suitable models and asks follow-up questions when needed. Open View Details on any model card to confirm the information you need for integration, including model name, context window, pricing, and copy-ready curl and Python examples.

​

2. Test in Playground

Click Try Now to open Playground with the selected model. You can run prompts, compare responses, and confirm that the model fits your task before writing any code. In Playground, you can:

• Pick a preset, such as Balanced, Creative, or Precise.
• Tune individual parameters, such as temperature, top-p, top-k, max tokens, and frequency penalty.
• Use a system prompt to set the assistant’s role, tone, or constraints.
• Stream responses in real time for faster prompt iteration.

Parameters a model does not support are disabled automatically, so only valid settings are sent. Each user’s configuration is saved per model.

​

3. Monitor usage

On the Home page, you can review total tokens, API requests, and throughput, with charts filtered by metric and model. Use the time presets (24 hours, 7 days, 30 days) for a quick look on Home. For custom date ranges and deeper analysis, open Metrics. See the view usage for details on filtering and reading the Metrics charts.

​

4. Move to API calls

Once the model and parameters are confirmed, create an API key and call the model from your application.