Cerebras OpenAI

OpenAI-Compatible Integration

Cerebras also exposes an OpenAI-compatible interface, so you can use it with tools and libraries built for the OpenAI API.

Agno v2.7.2 defaults CerebrasOpenAI.id to the retired llama-4-scout-17b-16e-instruct model. Set id="gpt-oss-120b" or another current Cerebras model explicitly.

Basic Usage

The CerebrasOpenAI class provides an OpenAI-style interface for Cerebras models. First, install the required packages:

uv pip install openai cerebras-cloud-sdk

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

agent = Agent(
    model=CerebrasOpenAI(
        id="gpt-oss-120b",  # Model ID to use
        # base_url="https://api.cerebras.ai/v1", # Optional: default endpoint for Cerebras
    ),
    markdown=True,
)

# Print the response in the terminal
agent.print_response("write a two sentence horror story")

Configuration Options

The CerebrasOpenAI class accepts the following parameters:

Parameter	Type	Description	Default
`id`	str	Model identifier (for example, “gpt-oss-120b”)	“llama-4-scout-17b-16e-instruct”
`name`	str	Display name for the model	”CerebrasOpenAI”
`provider`	str	Provider name	”CerebrasOpenAI”
`api_key`	str	API key (falls back to CEREBRAS_API_KEY environment variable)	None
`base_url`	str	URL of the Cerebras OpenAI-compatible endpoint	”https://api.cerebras.ai/v1”
`parallel_tool_calls`	Optional[bool]	Whether to run tool calls in parallel (set to False automatically for llama-4-scout-17b-16e-instruct)	None

CerebrasOpenAI also supports the parameters of OpenAI.

Examples

More examples

Agent with Knowledge Basic Agent

⌘I

Get Started

Basics

Advanced

Production

Providers

Other

Additional Resources

Cerebras OpenAI

OpenAI-Compatible Integration

Basic Usage

Configuration Options

Examples

​OpenAI-Compatible Integration

​Basic Usage

​Configuration Options

​Examples

OpenAI-Compatible Integration

Basic Usage

Configuration Options

Examples