Cerebras

LLM service implementation using Cerebras’s API with OpenAI-compatible interface

Overview

CerebrasLLMService provides access to Cerebras’s language models through an OpenAI-compatible interface. It inherits from OpenAILLMService and supports streaming responses, function calling, and context management with ultra-fast inference speeds.

Cerebras LLM API Reference

Pipecat’s API methods for Cerebras integration

Example Implementation

Complete example with function calling

Cerebras Documentation

Official Cerebras inference API documentation

Cerebras Platform

Access models and manage API keys

Installation

To use Cerebras services, install the required dependency:

pip install "pipecat-ai[cerebras]"

Prerequisites

Cerebras Account Setup

Before using Cerebras LLM services, you need:

1. Cerebras Account: Sign up at Cerebras Cloud
2. API Key: Generate an API key from your account dashboard
3. Model Selection: Choose from available Cerebras models with ultra-fast inference

Required Environment Variables

• CEREBRAS_API_KEY: Your Cerebras API key for authentication

Configuration

api_key · str · required

Cerebras API key for authentication.

base_url · str · default: "https://api.cerebras.ai/v1"

Base URL for Cerebras API endpoint.

model · str · default: "gpt-oss-120b"

Model identifier to use.

InputParams

This service uses the same input parameters as OpenAILLMService. See OpenAI LLM for details.

Usage

Basic Setup

import os
from pipecat.services.cerebras import CerebrasLLMService

llm = CerebrasLLMService(
    api_key=os.getenv("CEREBRAS_API_KEY"),
    model="gpt-oss-120b",
)

With Custom Parameters

from pipecat.services.cerebras import CerebrasLLMService

llm = CerebrasLLMService(
    api_key=os.getenv("CEREBRAS_API_KEY"),
    model="gpt-oss-120b",
    params=CerebrasLLMService.InputParams(
        temperature=0.7,
        top_p=0.9,
        max_completion_tokens=1024,
    ),
)

Notes

• Cerebras supports a subset of OpenAI parameters. Advanced parameters like frequency_penalty and presence_penalty are not passed to the API.
• Cerebras is known for ultra-fast inference speeds on supported models.