| Connected Account | The connected account to use for the request | Connected Account | Yes | |
| Model | The model which will generate the completion | Text (Short) | No | |
| Message Role 1 | | Predefined Choice List | No | |
| Message Content 1 | | Text (Long) | No | |
| Message Role 2 | | Predefined Choice List | No | |
| Message Content 2 | | Text (Short) | No | |
| Message Role 3 | | Predefined Choice List | No | |
| Message Content 3 | | Text (Long) | No | |
| Simplify? | Whether to return a simplified version of the response instead of the raw data | True/False | No | |
| Frequency penalty | Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim | Number with decimals | No | |
| Maximum number of tokens | The maximum number of tokens to generate in the completion. Most models have a context length of 2048 tokens (except for the newest models, which support 32,768) | Number | No | |
| Number of completions | How many completions to generate for each prompt. Note: Because this parameter generates many completions, it can quickly consume your token quota. Use carefully and ensure that you have reasonable settings for max_tokens and stop | Number | No | |
| Presence penalty | Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics | Number with decimals | No | |
| Sampling temperature | Controls randomness: Lowering results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive | Number with decimals | No | |
| Top p | Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered. We generally recommend altering this or temperature but not both | Number with decimals | No | |