Each user has a limit to the number of requests that are sent to the AI server each month and this is managed through the use of credits. The 1-month free evaluation plan includes 500,000 credits. If you have consumed all of your free credits or the evaluation plan expires, the service can only be continued by purchasing a subscription plan.

Each invoked action consumes credits with the AI prompt associated with the action, the input text (editor text, selection from the editor text, chat messages, or user input), and the AI response.

Credits are calculated using a weighted model based on OpenAI tokens:

• 1 token of gpt-3.5-turbo = 1 credit
• 1 token of gpt-3.5-turbo-16k = 2 credits
• 1 token of gpt-4 = 30 credits
• 1 token of gpt-4-turbo = 15 credits
• 1 token of gpt-4-vision-preview = 15 credits

Observations:

• gpt 3.5-turbo-16k is only used if the input exceeds the context window capacity of Oxygen AI Positron's default model. The model switch is preformed automatically upon detecting the need for a bigger context window.
• gpt-4-vision-preview is automatically used by the features that perform image analysis.