> ## Documentation Index
> Fetch the complete documentation index at: https://docs.gately.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Model Parameters

> Understanding and configuring AI model parameters for optimal results

<Frame>
  <img src="https://mintcdn.com/taamai-c8c27d6c/7tpU7wOp-rlopJuB/images/playground/model-price.jpg?fit=max&auto=format&n=7tpU7wOp-rlopJuB&q=85&s=90549e27d9e575edb3516fef90fd1a4a" alt="Model Parameters Interface" width="1920" height="1200" data-path="images/playground/model-price.jpg" />
</Frame>

## Parameter Controls

<AccordionGroup>
  <Accordion title="Temperature" icon="temperature-half">
    Controls randomness in responses (0.0 - 2.0):

    * 0.0: Focused, deterministic
    * 1.0: Balanced creativity
    * 2.0: Maximum creativity
  </Accordion>

  <Accordion title="Max Tokens" icon="text-size">
    Limits response length:

    * Varies by model
    * Affects credit usage
    * Recommended: Start small
  </Accordion>

  <Accordion title="Top P (Nucleus Sampling)" icon="chart-pie">
    Controls response diversity (0.0 - 1.0):

    * Lower: More focused
    * Higher: More diverse
    * Default: 0.9
  </Accordion>

  <Accordion title="Frequency Penalty" icon="chart-line">
    Reduces word repetition (-2.0 to 2.0):

    * Positive: Less repetition
    * Negative: More repetition
    * Default: 0.0
  </Accordion>
</AccordionGroup>

## Parameter Combinations

<CardGroup cols={2}>
  <Card title="Creative Writing" icon="pen-fancy">
    * Temperature: 0.8
    * Top P: 0.9
    * Frequency Penalty: 0.3
  </Card>

  <Card title="Technical Content" icon="code">
    * Temperature: 0.2
    * Top P: 0.5
    * Frequency Penalty: 0.1
  </Card>
</CardGroup>

<Warning>
  Parameter adjustments affect both response quality and credit consumption.
</Warning>