# PydanticAI Instantiation Performance Evaluation (/examples/evals/performance/comparison/pydantic-ai-instantiation)



Demonstrates agent instantiation benchmarking with PydanticAI.

This evaluation performs 2,010 callable invocations: 10 warm-ups, 1,000 runtime measurements, and 1,000 memory measurements. It measures construction, not model inference.

`PerformanceEval` runs the callable separately for each enabled metric: warm-ups first, then runtime measurements, then memory measurements. `num_iterations` applies to each metric, and the default is 10 additional warm-up calls. Model retries, tools, delegation, and memory extraction can add provider requests beyond the callable count.

Memory measurements use Python’s `tracemalloc`; they do not measure process RSS, GPU memory, database-server memory, or remote model memory. Record dependency versions, database state, and model settings when comparing results.

```python title="pydantic_ai_instantiation.py"
"""
PydanticAI Instantiation Performance Evaluation
===============================================

Demonstrates agent instantiation benchmarking with PydanticAI.
"""

from typing import Literal

from agno.eval.performance import PerformanceEval
from pydantic_ai import Agent


# ---------------------------------------------------------------------------
# Create Benchmark Function
# ---------------------------------------------------------------------------
def instantiate_agent():
    agent = Agent(
        "openai:gpt-5.6-luna", system_prompt="Be concise, reply with one sentence."
    )

    # Tool definition remains scoped to agent construction by design.
    @agent.tool_plain
    def get_weather(city: Literal["nyc", "sf"]):
        """Use this to get weather information."""
        if city == "nyc":
            return "It might be cloudy in nyc"
        elif city == "sf":
            return "It's always sunny in sf"
        else:
            raise AssertionError("Unknown city")

    return agent


# ---------------------------------------------------------------------------
# Create Evaluation
# ---------------------------------------------------------------------------
pydantic_instantiation = PerformanceEval(func=instantiate_agent, num_iterations=1000)

# ---------------------------------------------------------------------------
# Run Evaluation
# ---------------------------------------------------------------------------
if __name__ == "__main__":
    pydantic_instantiation.run(print_results=True, print_summary=True)
```

## Run the Example [#run-the-example]

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

  <Step title="Export your API keys">
    <CodeBlockTabs defaultValue="Mac/Linux">
      <CodeBlockTabsList>
        <CodeBlockTabsTrigger value="Mac/Linux">
          Mac/Linux
        </CodeBlockTabsTrigger>

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

      <CodeBlockTab value="Mac/Linux">
        ```bash
        export OPENAI_API_KEY="your_openai_api_key_here"
        ```
      </CodeBlockTab>

      <CodeBlockTab value="Windows">
        ```bash
        $Env:OPENAI_API_KEY="your_openai_api_key_here"
        ```
      </CodeBlockTab>
    </CodeBlockTabs>
  </Step>

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

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

Full source: [cookbook/09\_evals/performance/comparison/pydantic\_ai\_instantiation.py](https://github.com/agno-agi/agno/blob/8f36eaf2d18e91afa7b327eec66a3cd3685dcb87/cookbook/09_evals/performance/comparison/pydantic_ai_instantiation.py)