Yes, SourceAI is a commercial software.
For regular English text, 1 token is approximately 4 characters. To further understand the tokens required for your API calls, you can use the Token Estimator.
Yes, both prompt and completion tokens are included in the total number of tokens used by a request.
The pricing is based on the total number of tokens needed to instruct the model on how to perform the operation (about 1000), plus the tokens in the query and the tokens generated by the API.
We are using Davinci engine. Davinci is the most capable engine and can perform any task the other models can perform and often with less instruction. For applications requiring a lot of understanding of the content, Davinci is going to produce the best results.
We are currently testing the new Codex model.