# Response Caching (/models/providers/native/openai/completion/usage/cache-response)



<Note>
  For a conceptual overview of response caching, see [Response Caching](/models/cache-response).
</Note>

Response caching stores model responses locally, reducing response times and API costs during development and testing.

## Basic Usage [#basic-usage]

Enable caching by setting `cache_response=True` when initializing the model. This example starts with a temporary, empty cache directory. After a successful first request, the identical second request can reuse its response. Keep the model settings fixed: generation settings such as temperature are not part of the cache key.

```python title="cache_model_response.py"
from tempfile import TemporaryDirectory
from time import perf_counter

from agno.agent import Agent
from agno.models.openai import OpenAIChat

with TemporaryDirectory() as cache_dir:
    agent = Agent(
        model=OpenAIChat(id="gpt-4o", cache_response=True, cache_dir=cache_dir)
    )
    for i in range(1, 3):
        start = perf_counter()
        response = agent.run(
            "Write me a short story about a cat that can talk and solve problems."
        )
        print(f"Run {i}")
        print(response.content)
        print(f"Elapsed time: {perf_counter() - start:.3f}s")
```

## Usage [#usage]

<Steps>
    <Step title="Set up your virtual environment">
      <CodeBlockTabs defaultValue="Mac">
        <CodeBlockTabsList>
          <CodeBlockTabsTrigger value="Mac">
            Mac
          </CodeBlockTabsTrigger>

          <CodeBlockTabsTrigger value="Windows">
            Windows
          </CodeBlockTabsTrigger>
        </CodeBlockTabsList>

        <CodeBlockTab value="Mac">
          ```bash
          uv venv --python 3.12
          source .venv/bin/activate
          ```
        </CodeBlockTab>

        <CodeBlockTab value="Windows">
          ```bash
          uv venv --python 3.12
          .venv\Scripts\activate
          ```
        </CodeBlockTab>
      </CodeBlockTabs>
    </Step>

  <Step title="Set your API key">
    ```bash
    export OPENAI_API_KEY=xxx
    ```
  </Step>

  <Step title="Install dependencies">
    ```bash
    uv pip install -U openai agno
    ```
  </Step>

  <Step title="Run Agent">
    Save the code above as `cache_model_response.py`, then run:

    ```bash
    python cache_model_response.py
    ```
  </Step>
</Steps>