| Name | Description |
|---|---|
| Continue if max output tokens reached | If set to yes, the generation will continue beyond the maximum token limit by sending the prompt and generated output back to the model. |
| Output language | Output language of the prompt |
| Model | Select the Perplexity model to use for generating responses. Available models: llama-3.1-sonar-small-128k-online llama-3.1-sonar-small-128k-chat llama-3.1-sonar-large-128k-online llama-3.1-sonar-large-128k-chat llama-3.1-sonar-huge-128k-online llama-3.1-8b-instruct llama-3.1-70b-instruct llama-3-sonar-small-32k-chat llama-3-sonar-small-32k-online llama-3-sonar-large-32k-chat llama-3-sonar-large-32k-online mixtral-8x7b-instruct |
| Prompt | |
| Temperature | Controls randomness: Lowering results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. |
| Top P | Controls diversity via nucleus sampling: 0.5 means half of all likelihood-weighted options are considered. |
