> ## 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.

# Cerebras OpenAI Basic

> Compare synchronous, asynchronous, and streaming calls through Cerebras' OpenAI-compatible endpoint.

> [!WARNING]
>
> This example uses a Cerebras model ID that has been retired. Replace the retired ID with `gpt-oss-120b` before running. Review the [Cerebras migration notes](https://inference-docs.cerebras.ai/support/deprecation) when the example uses reasoning, tools, or structured output.

```python basic.py theme={null}
"""
Cerebras Openai Basic
=====================

Cookbook example for `cerebras_openai/basic.py`.
"""

import asyncio

from agno.agent import Agent
from agno.models.cerebras import CerebrasOpenAI

# ---------------------------------------------------------------------------
# Create Agent
# ---------------------------------------------------------------------------

agent = Agent(
    model=CerebrasOpenAI(id="llama-4-scout-17b-16e-instruct"),
    markdown=True,
)

# Print the response in the terminal

# ---------------------------------------------------------------------------
# Run Agent
# ---------------------------------------------------------------------------
if __name__ == "__main__":
    # --- Sync ---
    agent.print_response("write a two sentence horror story")

    # --- Sync + Streaming ---
    agent.print_response("write a two sentence horror story", stream=True)

    # --- Async ---
    asyncio.run(agent.aprint_response("write a two sentence horror story"))

    # --- Async + Streaming ---
    asyncio.run(agent.aprint_response("write a two sentence horror story", stream=True))
```

## Run the Example

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

**1. Install dependencies**

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

**2. Export your Cerebras OpenAI-compatible API key**

```bash Mac/Linux theme={null}
export CEREBRAS_API_KEY="your_cerebras_api_key_here"
```

```bash Windows theme={null}
$Env:CEREBRAS_API_KEY="your_cerebras_api_key_here"
```

**3. Use a current Cerebras model**

Replace `llama-4-scout-17b-16e-instruct` with `gpt-oss-120b` in the saved Python file before running.

**4. Run the example**

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

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

Full source: [cookbook/90\_models/cerebras\_openai/basic.py](https://github.com/agno-agi/agno/blob/v3.0.4/cookbook/90_models/cerebras_openai/basic.py)


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