> ## 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.

# CachingConfig

> Configure caching behavior for agent responses and prompts

Enable response and prompt caching to improve performance and reduce API costs.

```mermaid theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
graph LR
    subgraph "Caching Flow"
        A[📝 Request] --> B{Cache?}
        B -->|Hit| C[⚡ Return]
        B -->|Miss| D[🤖 Process]
        D --> E[💾 Store]
        E --> C
    end
    
    classDef request fill:#6366F1,stroke:#7C90A0,color:#fff
    classDef check fill:#F59E0B,stroke:#7C90A0,color:#fff
    classDef process fill:#189AB4,stroke:#7C90A0,color:#fff
    classDef output fill:#10B981,stroke:#7C90A0,color:#fff
    
    class A request
    class B check
    class D process
    class E process
    class C output
```

## Quick Start

<Steps>
  <Step title="Simple Enable">
    Enable caching with defaults:

    ```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
    from praisonaiagents import Agent

    agent = Agent(
        name="Cached Agent",
        instructions="Use caching",
        caching=True
    )
    ```
  </Step>

  <Step title="With Configuration">
    Configure caching behavior:

    ```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
    from praisonaiagents import Agent
    from praisonaiagents.config import CachingConfig

    agent = Agent(
        name="Cached Agent",
        instructions="Use caching",
        caching=CachingConfig(
            enabled=True,
            prompt_caching=True
        )
    )
    ```
  </Step>
</Steps>

***

## Configuration Options

```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
from praisonaiagents.config import CachingConfig

config = CachingConfig(
    # Response caching
    enabled=True,
    
    # Prompt caching (provider-specific)
    prompt_caching=None
)
```

| Parameter        | Type           | Default | Description                                                                     |
| ---------------- | -------------- | ------- | ------------------------------------------------------------------------------- |
| `enabled`        | `bool`         | `True`  | Enable response caching                                                         |
| `prompt_caching` | `bool \| None` | `None`  | Enable prompt caching (auto-detect via `litellm.utils.supports_prompt_caching`) |

***

## Common Patterns

### Pattern 1: Full Caching

```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
from praisonaiagents import Agent
from praisonaiagents.config import CachingConfig

agent = Agent(
    name="Full Cache Agent",
    instructions="Maximum caching",
    caching=CachingConfig(
        enabled=True,
        prompt_caching=True
    )
)
```

### Pattern 2: Auto-Detection with Memory

Even without explicit `prompt_caching=True`, the SDK auto-detects model support and arranges the prefix accordingly:

```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
from praisonaiagents import Agent

agent = Agent(
    name="Auto Cache Agent",
    instructions="Cache optimization happens automatically",
    llm="openai/gpt-4o",      # SDK detects prompt cache support
    memory=True,              # Enables cache-optimized memory context
    caching=CachingConfig()   # prompt_caching=None means auto-detect
)
```

### Pattern 3: Disable Caching

```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
from praisonaiagents import Agent
from praisonaiagents.config import CachingConfig

agent = Agent(
    name="No Cache Agent",
    instructions="Always fresh responses",
    caching=CachingConfig(enabled=False)
)
```

***

## Best Practices

<AccordionGroup>
  <Accordion title="Enable Prompt Caching for Anthropic">
    Anthropic Claude supports prompt caching for significant cost savings on repeated prompts.
  </Accordion>

  <Accordion title="Disable for Real-Time Data">
    Turn off caching when agents need fresh, real-time information.
  </Accordion>
</AccordionGroup>

***

## Related

<CardGroup cols={2}>
  <Card title="Performance" icon="gauge-high" href="/docs/best-practices/performance-tuning">
    Performance optimization tips
  </Card>

  <Card title="ExecutionConfig" icon="bolt" href="/docs/configuration/execution-config">
    Execution limits configuration
  </Card>
</CardGroup>