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

# Output Config • AI Agent SDK

> OutputConfig: Configuration for agent output behavior.

# OutputConfig

> Defined in the [**Feature Configs**](../modules/feature_configs) module.

<Badge color="blue">AI Agent</Badge>

Configuration for agent output behavior.

Consolidates: verbose, markdown, stream, metrics, reasoning\_steps, output\_style

DEFAULT: output="silent" (zero overhead, fastest performance)

## Properties

<ResponseField name="verbose" type="bool">
  No description available.
</ResponseField>

<ResponseField name="markdown" type="bool">
  No description available.
</ResponseField>

<ResponseField name="stream" type="bool">
  No description available.
</ResponseField>

<ResponseField name="metrics" type="bool">
  No description available.
</ResponseField>

<ResponseField name="reasoning_steps" type="bool">
  No description available.
</ResponseField>

<ResponseField name="style" type="Optional">
  No description available.
</ResponseField>

<ResponseField name="actions_trace" type="bool">
  No description available.
</ResponseField>

<ResponseField name="json_output" type="bool">
  No description available.
</ResponseField>

<ResponseField name="simple_output" type="bool">
  No description available.
</ResponseField>

<ResponseField name="show_parameters" type="bool">
  No description available.
</ResponseField>

<ResponseField name="status_trace" type="bool">
  No description available.
</ResponseField>

<ResponseField name="output_file" type="Optional">
  No description available.
</ResponseField>

<ResponseField name="template" type="Optional">
  No description available.
</ResponseField>

<Accordion title="Internal & Generic Methods">
  * **to\_dict**: Convert to dictionary.
</Accordion>

## Usage

```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
# Default is silent mode (no output overhead, programmatic use)
    Agent(instructions="...")  # Uses output="silent"
    
    # Actions mode (tool calls + final output trace)
    Agent(output="actions")
    
    # Verbose mode with Rich panels
    Agent(output="verbose")
    
    # JSON mode for piping
    Agent(output="json")
    
    # With config
    Agent(output=OutputConfig(
        verbose=True,
        markdown=True,
        stream=True,
        metrics=True,
        reasoning_steps=True,
    ))
```

## Source

<Card title="View on GitHub" icon="github" href="https://github.com/MervinPraison/PraisonAI/blob/main/src/praisonai-agents/praisonaiagents/config/feature_configs.py#L506">
  `praisonaiagents/config/feature_configs.py` at line 506
</Card>

***

## Related Documentation

<CardGroup cols={2}>
  <Card title="Configuration Overview" icon="gear" href="/docs/configuration/index" />

  <Card title="Agent Config" icon="robot" href="/docs/configuration/agent-config" />

  <Card title="Output Concept" icon="file-export" href="/docs/concepts/output" />

  <Card title="Output Configuration" icon="gear" href="/docs/configuration/output-config" />

  <Card title="Save Output" icon="floppy-disk" href="/docs/features/save-output" />
</CardGroup>