Playground
Chat with models directly in the console and try models from the model square without writing code.
The Playground lets you try models online: https://ai.myaiexp.com/playground, the "Playground" entry in the console's left menu.
How to use it
- Pick a model in the model selector next to the input box (the choices match the model square).
- Type a question in the input box at the bottom, or click one of the sample prompts on the page.
- Click "Send" and wait for the reply; you can keep asking follow-up questions for a multi-turn conversation.
- To start a new conversation, clear the chat history.
Parameters
The "Parameters" button below the input box opens a settings panel where you can adjust temperature, Top P, frequency penalty, presence penalty, max tokens and seed. Only enabled parameters are sent with the request; the model uses its own defaults for the rest.
The Playground is mainly for text chat. To test image understanding, call the API directly; see Multimodal.
When to use it
- To check a model's style, speed and cost before writing integration code.
- To compare a model with its thinking (reasoning) variant on the same question.
- While troubleshooting, to compare how different models answer the same question.
Playground requests are billed too, and show up in Usage Logs. For real integrations, call the API with an API key.
API Keys
Create, view, edit and delete API keys (tokens) in the console, and set quota, expiry, allowed models and an IP allowlist.
Usage Logs
See the key, model, latency, token counts and cost of every API call, and filter them.
This service is provided for learning and research purposes only. Please follow each model provider's usage policies.