Skip to main content

​
Overview

GrokLLMService provides access to Grok’s language models through an OpenAI-compatible interface. It inherits from OpenAILLMService and supports streaming responses, function calling, and context management with Grok’s unique reasoning capabilities.

Grok LLM API Reference

Pipecat’s API methods for Grok integration

Example Implementation

Complete example with function calling

Grok Documentation

Official Grok API documentation and features

X.AI Platform

Access Grok models and manage API keys

​
Installation

To use Grok services, install the required dependencies:

​
Prerequisites

​
Grok Account Setup

Before using Grok LLM services, you need:
  1. X.AI Account: Sign up at X.AI Console
  2. API Key: Generate an API key from your console dashboard
  3. Model Selection: Choose from available Grok models

​
Required Environment Variables

  • XAI_API_KEY: Your X.AI API key for authentication

​
Configuration

​
str
required
X.AI API key for authentication. Raises ValueError when empty.
​
str
default:"https://api.x.ai/v1"
Base URL for Grok API endpoint.
​
str
default:"None"
deprecated
Deprecated since 0.0.105, removed in 2.0.0. Use settings=GrokLLMService.Settings(model=...) instead.
​
GrokLLMService.Settings
default:"None"
Runtime-configurable settings. See Settings below.

​
Settings

Runtime-configurable settings passed via the settings constructor argument using GrokLLMService.Settings(...). These can be updated mid-conversation with LLMUpdateSettingsFrame. See Service Settings for details.
​
Literal['none', 'low', 'medium', 'high', 'xhigh'] | None
default:"None"
How much the model thinks before answering. Accepted values vary by model: "low", "medium", and "high" on the Grok 4 reasoning models, "xhigh" on grok-4.6 and later, and "none" on models that can turn reasoning off. The non-reasoning models, including the default model, reject the parameter. When unset, xAI’s per-model default applies.
This service also inherits settings from OpenAILLMService. See OpenAI LLM Settings for additional parameters. The service defaults to model="grok-4.20-non-reasoning" when no model is specified.

​
Usage

​
Basic Setup

​
With Custom Settings

​
Notes

  • Token usage is reported once per completion at the end of each request.
  • Grok supports prompt caching and reasoning tokens, which are tracked in usage metrics when available.