Try a model. Start a conversation.

Start chatting#

Open the Playground and sign in to your Tokely account. Choose an available text model, write a message and send it. Generation uses your account balance; you do not need to paste an API key into the Playground.

Use the model picker to search by model or provider. It lists enabled text models and their current input/output prices.

Adjust your request#

Chat settings let you set maximum output tokens, temperature where supported, and system instructions. Settings apply to your next request. Reasoning tokens count toward the output budget.

Stop generation with the square button. Regenerate or retry makes a new API request and uses your balance. The selected model determines whether the request uses Chat Completions or Responses and whether streaming is available.

Keep your conversations#

Use the sidebar to start a new chat, search, rename, reopen or delete a conversation. Chats are stored on this browser/device, separately for each signed-in account. They do not sync across devices.

Conversation history is sent with each request to provide context. Its input tokens contribute to usage. A conversation that reaches the request limits needs a new chat.

Take the prompt to your app#

Use View API request to copy a cURL example with the current model, conversation and settings. Create your own API key in the dashboard and set TOKELY_API_KEY before running it. Copy response and code block controls help you reuse generated text.