Blank cells within this range will be populated with relevant data, guided by existing data in the adjacent cells.

A number of headers in the selected range table. It will help AI better understand the table structure and provide better results.
Options: 1, 2 or 3

A range where a filled table will be posted. If it should be the same as Range to Fill, skip this input.
For Example: =C1:G28 or =C1

It allows the function to access and utilize the spreadsheet's Knowledge Base, enriching the table with pre-configured data and insights. This enhances the function's ability to create more context-aware and informative tables. Recommend to deactivate if a result requires general knowledge and the Knowledge Base information is not enough to make a table.
Options: FALSE or TRUE

It enables the function to fetch data from the internet, adding a layer of real-time information to your table. While this feature can provide valuable insights, be aware that it may increase both the cost and the time required for execution, and the quality of results may vary based on the search.
Options: FALSE or TRUE

Adjust the deviation from deterministic answers from 0 (default, high-confidence) to 100 (greater diversity). In other words, it's the AI's creativity for the result. Creativity above 50 can destroy a result.
For Example: 0, 20, or 100

Specify a role, profession, or perspective for the AI to adopt when generating a response; this parameter guides the AI in providing more context-specific or specialized results.
For example: Products Expert, Geographer, or Google Sheets Table

Provide additional information or instructions to get a better result.
For example: Use metric system, Table should have 20 rows, or ="Remember this: " & B2

Model affects quality, speed, and tokens count of tokens to use. We choose the optimal model by default, and here it's gpt-3.5-turbo-16k. Information about models.
Options: Default, gpt-4, gpt-3.5-turbo, or gpt-3.5-turbo-16k

Limit the number of tokens that can be used for one function run. By default, it's limited only by the model.
1 token ≈ 4 chars in English
1 token ≈ 3/4 words
100 tokens ≈ 75 words
1-2 sentences ≈ 30 tokens
1 paragraph ≈ 100 tokens
1,500 words ≈ 2048 tokens
For Example: 100, 350, or 2048