Chat models are language models that use a sequence of messages as inputs and return messages as outputs (as opposed to using plain text). These are generally newer models.
If you’d like to write your own chat model, see this how-to. If you’d like to contribute an integration, see Contributing integrations.

​
Install dependencies

See this section for general instructions on installing LangChain packages.
npm i @langchain/groq

​
Add environment variables

GROQ_API_KEY=your-api-key

​
Instantiate the model

import { ChatGroq } from "@langchain/groq";

const model = new ChatGroq({
  model: "llama-3.3-70b-versatile",
  temperature: 0
});

await model.invoke("Hello, world!")
ModelStreamJSON modeTool CallingwithStructuredOutput()Multimodal
BedrockChat✅❌🟡 (Bedrock Anthropic only)🟡 (Bedrock Anthropic only)🟡 (Bedrock Anthropic only)
ChatBedrockConverse✅❌✅✅✅
ChatAnthropic✅❌✅✅✅
ChatCloudflareWorkersAI✅❌❌❌❌
ChatCohere✅❌✅✅✅
ChatFireworks✅✅✅✅✅
ChatGoogleGenerativeAI✅❌✅✅✅
ChatVertexAI✅❌✅✅✅
ChatGroq✅✅✅✅✅
ChatMistralAI✅✅✅✅✅
ChatOllama✅✅✅✅✅
ChatOpenAI✅✅✅✅✅
ChatTogetherAI✅✅✅✅✅
ChatXAI✅✅✅✅❌

​
All chat models

Alibaba Tongyi

Anthropic

Arcjet Redact

Azure OpenAI

Baidu Qianfan

Amazon Bedrock

Amazon Bedrock Converse

Cerebras

Cloudflare Workers AI

Cohere

Deep Infra

DeepSeek

Fake LLM

Fireworks

Friendli

Google GenAI

Google Vertex AI

Groq

IBM watsonx.ai

Llama CPP

Minimax

MistralAI

Moonshot

Novita AI

Ollama

OpenAI

Perplexity

PremAI

Tencent Hunyuan

Together

WebLLM

xAI

YandexGPT

ZhipuAI