Cerebras OpenAI Structured Output

Return a typed MovieScript from a CerebrasOpenAI agent with output_schema.

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 when the example uses reasoning, tools, or structured output.

structured_output.py

"""
Cerebras Openai Structured Output
=================================

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

from typing import List

from agno.agent import Agent, RunOutput  # noqa
from agno.models.cerebras import CerebrasOpenAI
from pydantic import BaseModel, Field
from rich.pretty import pprint  # noqa

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


class MovieScript(BaseModel):
    setting: str = Field(
        ..., description="Provide a nice setting for a blockbuster movie."
    )
    ending: str = Field(
        ...,
        description="Ending of the movie. If not available, provide a happy ending.",
    )
    genre: str = Field(
        ...,
        description="Genre of the movie. If not available, select action, thriller or romantic comedy.",
    )
    name: str = Field(..., description="Give a name to this movie")
    characters: List[str] = Field(..., description="Name of characters for this movie.")
    storyline: str = Field(
        ..., description="3 sentence storyline for the movie. Make it exciting!"
    )


# Agent that uses a structured output
structured_output_agent = Agent(
    model=CerebrasOpenAI(id="llama-4-scout-17b-16e-instruct"),
    description="You are a helpful assistant. Summarize the movie script based on the location in a JSON object.",
    output_schema=MovieScript,
)

structured_output_agent.print_response("New York")

# ---------------------------------------------------------------------------
# Run Agent
# ---------------------------------------------------------------------------

if __name__ == "__main__":
    pass

Run the Example

1. Set up your virtual environment

   Mac

   uv venv --python 3.12
   source .venv/bin/activate
   

   uv venv --python 3.12
   .venv\Scripts\activate
   
2. Install dependencies

   uv pip install -U agno cerebras-cloud-sdk openai
   
3. Export your Cerebras OpenAI-compatible API key

   Mac/Linux

   export CEREBRAS_API_KEY="your_cerebras_api_key_here"
   

   $Env:CEREBRAS_API_KEY="your_cerebras_api_key_here"
   
4. Use a current Cerebras model

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

5. Run the example

   Save the code above as structured_output.py, then run:

   python structured_output.py
   

Full source: cookbook/90_models/cerebras_openai/structured_output.py