> ## 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.

# Anthropic Async Reasoning Stream

> Stream Claude extended-thinking reasoning events asynchronously with stream_events.

```python async_reasoning_stream.py theme={null}
"""
Async Reasoning Stream
======================

Demonstrates this reasoning cookbook example.
"""

import asyncio

from agno.agent import Agent
from agno.models.anthropic import Claude
from agno.run.agent import RunEvent  # noqa


# ---------------------------------------------------------------------------
# Create Example
# ---------------------------------------------------------------------------
def run_example() -> None:
    async def streaming_reasoning():
        """Test streaming reasoning with an OpenAI model."""
        # Create an agent with reasoning enabled
        agent = Agent(
            reasoning_model=Claude(
                id="claude-sonnet-4-5",
                thinking={"type": "enabled", "budget_tokens": 1024},
            ),
            instructions="Think step by step about the problem.",
        )

        prompt = "What is 25 * 37? Show your reasoning."

        await agent.aprint_response(prompt, stream=True, stream_events=True)

        # # or you can capture the event using
        # async for run_output_event in agent.arun(
        #     prompt,
        #     stream=True,
        #     stream_events=True,
        # ):
        #     if run_output_event.event == RunEvent.run_started:
        #         print(f"\nEVENT: {run_output_event.event}")

        #     elif run_output_event.event == RunEvent.reasoning_started:
        #         print(f"\nEVENT: {run_output_event.event}")
        #         print("Reasoning started...\n")

        #     elif run_output_event.event == RunEvent.reasoning_content_delta:
        #         # This is the NEW streaming event for reasoning content
        #         # It streams the raw content as it's being generated
        #         print(run_output_event.reasoning_content, end="", flush=True)

        #     elif run_output_event.event == RunEvent.run_content:
        #         if run_output_event.content:
        #             print(run_output_event.content, end="", flush=True)

        #     elif run_output_event.event == RunEvent.run_completed:
        #         print(f"\n\nEVENT: {run_output_event.event}")

    if __name__ == "__main__":
        asyncio.run(streaming_reasoning())


# ---------------------------------------------------------------------------
# Run Example
# ---------------------------------------------------------------------------
if __name__ == "__main__":
    run_example()
```

## Run the Example

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

**1. Install dependencies**

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

**2. Export your API keys**

```bash Mac/Linux theme={null}
export ANTHROPIC_API_KEY="your_anthropic_api_key_here"
export OPENAI_API_KEY="your_openai_api_key_here"
```

```bash Windows theme={null}
$Env:ANTHROPIC_API_KEY="your_anthropic_api_key_here"
$Env:OPENAI_API_KEY="your_openai_api_key_here"
```

**3. Run the example**

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

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

Full source: [cookbook/10\_reasoning/models/anthropic/async\_reasoning\_stream.py](https://github.com/agno-agi/agno/blob/v3.0.4/cookbook/10_reasoning/models/anthropic/async_reasoning_stream.py)


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