> ## Documentation Index
> Fetch the complete documentation index at: https://agno-v2.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Strawberry Letter Counting

> Run three async agents (plain, built-in chain-of-thought, deepseek-reasoner) on the 'r' in 'strawberry' count, with rich console rules.

Demonstrates regular vs reasoning-backed agents for counting tasks.

```python strawberry.py theme={null}
"""
Strawberry Letter Counting
==========================

Demonstrates regular vs reasoning-backed agents for counting tasks.
"""

import asyncio

from agno.agent import Agent
from agno.models.deepseek import DeepSeek
from agno.models.openai import OpenAIResponses
from rich.console import Console

# ---------------------------------------------------------------------------
# Create Agents
# ---------------------------------------------------------------------------
console = Console()

task = "How many 'r' are in the word 'strawberry'?"

regular_agent = Agent(model=OpenAIResponses(id="gpt-5.6"), markdown=True)

reasoning_agent = Agent(
    model=OpenAIResponses(id="gpt-5.6"),
    reasoning_model=DeepSeek(id="deepseek-reasoner"),
    markdown=True,
)


async def run_agents() -> None:
    console.rule("[bold blue]Counting 'r' In 'strawberry'[/bold blue]")

    console.rule("[bold green]Regular Agent[/bold green]")
    await regular_agent.aprint_response(task, stream=True)

    console.rule("[bold cyan]Reasoning Agent (DeepSeek)[/bold cyan]")
    await reasoning_agent.aprint_response(task, stream=True, show_full_reasoning=True)


# ---------------------------------------------------------------------------
# Run Agents
# ---------------------------------------------------------------------------
if __name__ == "__main__":
    asyncio.run(run_agents())
```

## Run the Example

<Snippet file="create-venv-step.mdx" />

**1. Install dependencies**

```bash theme={null}
uv pip install -U agno openai
```

**2. Export your API keys**

```bash Mac/Linux theme={null}
export DEEPSEEK_API_KEY="your_deepseek_api_key_here"
export OPENAI_API_KEY="your_openai_api_key_here"
```

```bash Windows theme={null}
$Env:DEEPSEEK_API_KEY="your_deepseek_api_key_here"
$Env:OPENAI_API_KEY="your_openai_api_key_here"
```

**3. Run the example**

Save the code above as `strawberry.py`, then run:

```bash theme={null}
python strawberry.py
```

Full source: [cookbook/10\_reasoning/agents/strawberry.py](https://github.com/agno-agi/agno/blob/v3.0.4/cookbook/10_reasoning/agents/strawberry.py)


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.