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

# Model Settings

> Configure temperature, max tokens, and other LLM parameters

Each prompt includes settings that control how the LLM generates responses. Understanding these settings helps you get better, more consistent outputs.

## Core Settings

### Temperature

Controls randomness in the model's output.

| Value         | Behavior                        | Use Cases                                |
| ------------- | ------------------------------- | ---------------------------------------- |
| **0.0**       | Most deterministic              | Extraction, classification, factual Q\&A |
| **0.1 - 0.3** | Consistent with minor variation | Summarization, analysis                  |
| **0.4 - 0.6** | Balanced                        | General tasks                            |
| **0.7 - 0.9** | Creative variation              | Writing, brainstorming                   |
| **1.0**       | Maximum randomness              | Creative exploration                     |

<Tip>
  For production APIs, use lower temperatures (0.1-0.3) to ensure consistent responses.
</Tip>

### Max Tokens

Maximum number of tokens in the model's response.

| Setting   | Typical Use                    |
| --------- | ------------------------------ |
| 100-300   | Short answers, classifications |
| 500-1000  | Summaries, explanations        |
| 1000-2000 | Detailed analyses              |
| 2000+     | Long-form content, reports     |

<Warning>
  Setting max tokens too low may truncate responses mid-sentence. Too high wastes capacity and cost.
</Warning>

### System Prompt

An optional instruction that sets the AI's behavior and persona:

```
You are a professional legal analyst with expertise in contract law.
Always cite specific clauses when making recommendations.
Never provide advice that constitutes legal representation.
```

System prompts are useful for:

* Setting a consistent persona
* Establishing behavioral guidelines
* Defining constraints and limitations

<Note>
  System prompts are separate from your main template. They're sent to the model as a "system" message when supported.
</Note>

## Advanced Settings

### Top P (Nucleus Sampling)

Alternative to temperature for controlling randomness:

* **Top P = 1.0**: Consider all tokens (default)
* **Top P = 0.9**: Consider tokens in top 90% probability mass
* **Top P = 0.5**: More focused, less diverse outputs

<Tip>
  Use either temperature OR top\_p, not both. Temperature is more intuitive for most users.
</Tip>

### Frequency Penalty

Reduces repetition by penalizing tokens based on how often they've appeared:

| Value | Effect                               |
| ----- | ------------------------------------ |
| 0.0   | No penalty (default)                 |
| 0.5   | Moderate reduction in repetition     |
| 1.0+  | Strong avoidance of repeated phrases |

### Presence Penalty

Encourages the model to talk about new topics:

| Value | Effect                               |
| ----- | ------------------------------------ |
| 0.0   | No penalty (default)                 |
| 0.5   | Moderate encouragement of new topics |
| 1.0+  | Strong push for novelty              |

## Settings by Use Case

### Classification / Extraction

```
Temperature: 0.0 - 0.2
Max Tokens: 100 - 500
```

You want consistent, predictable outputs.

### Summarization

```
Temperature: 0.2 - 0.4
Max Tokens: 500 - 1500
```

Some flexibility in wording, but consistent structure.

### Content Generation

```
Temperature: 0.5 - 0.8
Max Tokens: 1000 - 3000
```

Allow creativity while maintaining coherence.

### Brainstorming / Ideation

```
Temperature: 0.8 - 1.0
Max Tokens: 1000+
```

Maximum creativity and diversity.

## Model-Specific Defaults

Different models may have different optimal settings:

| Model           | Recommended Temp | Notes                               |
| --------------- | ---------------- | ----------------------------------- |
| GPT-4o          | 0.3              | Very capable at low temps           |
| GPT-4           | 0.3              | Excellent reasoning                 |
| GPT-3.5-turbo   | 0.5              | May need higher temp for quality    |
| Claude 3 Opus   | 0.3              | Excellent at following instructions |
| Claude 3 Sonnet | 0.4              | Good balance                        |
| Claude 3 Haiku  | 0.5              | May need higher temp                |

## Setting Configuration

In the prompt editor:

1. Open the **Settings** panel (usually on the right side)
2. Adjust the sliders or enter values
3. Settings are saved with the prompt

<Note>
  Different prompts on the same endpoint can have different settings—useful for A/B testing configurations.
</Note>

## Testing Settings

When experimenting with settings:

<Steps>
  <Step title="Start Conservative">
    Begin with temperature 0.3, reasonable max tokens.
  </Step>

  <Step title="Test Multiple Times">
    Run the same input 3-5 times to see variation.
  </Step>

  <Step title="Adjust Incrementally">
    Change one setting at a time to understand its effect.
  </Step>

  <Step title="Document What Works">
    Note optimal settings for each type of task.
  </Step>
</Steps>

## Common Issues

### Truncated Responses

**Symptom**: Response ends mid-sentence.
**Solution**: Increase max tokens.

### Too Much Variation

**Symptom**: Same input gives wildly different outputs.
**Solution**: Lower temperature to 0.1-0.3.

### Repetitive Output

**Symptom**: Model repeats phrases or ideas.
**Solution**: Increase frequency penalty to 0.3-0.5.

### Boring/Generic Output

**Symptom**: Responses feel template-like.
**Solution**: Increase temperature to 0.6-0.8.

## Best Practices

<AccordionGroup>
  <Accordion title="Match settings to task" icon="bullseye">
    Classification needs low temp. Creative writing needs higher temp.
  </Accordion>

  <Accordion title="Test before production" icon="flask">
    Always test settings with real-world inputs before going live.
  </Accordion>

  <Accordion title="Be conservative with max tokens" icon="minimize">
    Set max tokens to what you actually need, not the maximum possible.
  </Accordion>

  <Accordion title="Document your choices" icon="file-lines">
    Note why you chose specific settings in the prompt description.
  </Accordion>
</AccordionGroup>

## Next Steps

<CardGroup cols={2}>
  <Card title="API Authentication" icon="key" href="/api/authentication">
    Set up keys to call your endpoints
  </Card>

  <Card title="Making Requests" icon="arrow-right" href="/api/making-requests">
    Learn how to call your endpoints
  </Card>
</CardGroup>