Configuring CLAi
Model Selection
-
OpenAI API Key: First, enter your OpenAI API key in the designated field. This key enables CLAi to make requests on your behalf.
-
Model Options: CLAi supports various models, including
GPT-4-1106-preview
,GPT-4-0163
,GPT-4-0125-preview
, andGPT-4-Turbo preview
. You can select your preferred model from the dropdown list. -
Recommended Model: Through testing, we have determined that the
GPT-4-1106-preview
model provides the best results. We recommend using this model for optimal performance. -
Cost Considerations: Different models may have varying costs associated with their use. For detailed pricing information, visit OpenAI Pricing.
-
Model Updates: A refresh button next to the model selection dropdown allows you to update the list with the latest compatible models from OpenAI.
Token Management
-
Max Conversation Tokens: This setting limits the number of tokens a single conversation can contain, helping to manage costs. The default limit is set to 100,000 tokens. Conversations exceeding this limit will be automatically terminated to prevent further charges.
-
Max Response Tokens: Similarly, you can limit the number of tokens for a single system response (the output from a command or goal). The default limit is 3,500 tokens. Responses exceeding this amount will be truncated, ensuring that costs are kept under control.