ChatXAI

xAI is an artificial intelligence company that develops large language models (LLMs). Their flagship model, Grok, is trained on real-time X (formerly Twitter) data and aims to provide witty, personality-rich responses while maintaining high capability on technical tasks.

This guide will help you getting started with ChatXAI chat models. For detailed documentation of all ChatXAI features and configurations head to the API reference.

Overview

Integration details

Class	Package	Local	Serializable	PY support	Downloads	Version
ChatXAI	@langchain/xai	❌	✅	❌

Model features

See the links in the table headers below for guides on how to use specific features.

Tool calling	Structured output	JSON mode	Image input	Audio input	Video input	Token-level streaming	Token usage	Logprobs
✅	✅	✅	❌	❌	❌	✅	✅	✅

Setup

To access ChatXAI models you’ll need to create an xAI account, get an API key, and install the @langchain/xai integration package.

Credentials

Head to the xAI website to sign up to xAI and generate an API key. Once you’ve done this set the XAI_API_KEY environment variable:

export XAI_API_KEY="your-api-key"

If you want to get automated tracing of your model calls you can also set your LangSmith API key by uncommenting below:

# export LANGSMITH_TRACING="true"
# export LANGSMITH_API_KEY="your-api-key"

Installation

The LangChain ChatXAI integration lives in the @langchain/xai package:

npm

npm install @langchain/xai @langchain/core

Instantiation

Now we can instantiate our model object and generate chat completions:

import { ChatXAI } from "@langchain/xai"

const llm = new ChatXAI({
    model: "grok-beta", // default
    temperature: 0,
    maxTokens: undefined,
    maxRetries: 2,
    // other params...
})

Invocation

const aiMsg = await llm.invoke([
    [
      "system",
      "You are a helpful assistant that translates English to French. Translate the user sentence.",
    ],
    ["human", "I love programming."],
])
console.log(aiMsg)

AIMessage {
  "id": "71d7e3d8-30dd-472c-8038-b6b283dcee63",
  "content": "J'adore programmer.",
  "additional_kwargs": {},
  "response_metadata": {
    "tokenUsage": {
      "promptTokens": 30,
      "completionTokens": 6,
      "totalTokens": 36
    },
    "finish_reason": "stop",
    "usage": {
      "prompt_tokens": 30,
      "completion_tokens": 6,
      "total_tokens": 36
    },
    "system_fingerprint": "fp_3e3898d4ce"
  },
  "tool_calls": [],
  "invalid_tool_calls": [],
  "usage_metadata": {
    "output_tokens": 6,
    "input_tokens": 30,
    "total_tokens": 36,
    "input_token_details": {},
    "output_token_details": {}
  }
}

console.log(aiMsg.content)

J'adore programmer.

API reference

For detailed documentation of all ChatXAI features and configurations head to the API reference.

---

Edit the source of this page on GitHub.

Connect these docs programmatically to Claude, VSCode, and more via MCP for real-time answers.