Skip to main content

Documentation Index

Fetch the complete documentation index at: https://nvd-54.mintlify.app/llms.txt

Use this file to discover all available pages before exploring further.

Chat models are language models that use a sequence of messages as inputs and return messages as outputs .

​
安装和使用

请参阅此部分了解安装 LangChain 包的通用说明。
Install:
npm i @langchain/openai
添加环境变量：
OPENAI_API_KEY=your-api-key
实例化模型：
import { ChatOpenAI } from "@langchain/openai";

const model = new ChatOpenAI({ model: "gpt-5.4-mini" });

await model.invoke("Hello, world!")
Install:
npm i @langchain/anthropic
添加环境变量：
ANTHROPIC_API_KEY=your-api-key
实例化模型：
import { ChatAnthropic } from "@langchain/anthropic";

const model = new ChatAnthropic({
model: "claude-3-sonnet-20240620",
temperature: 0
});

await model.invoke("Hello, world!")
Install:
npm i @langchain/google
添加环境变量：
GOOGLE_API_KEY=your-api-key
实例化模型：
import { ChatGoogle } from "@langchain/google";

const model = new ChatGoogle("gemini-2.5-flash");

await model.invoke("Hello, world!")
Install:
npm i @langchain/mistralai
添加环境变量：
MISTRAL_API_KEY=your-api-key
实例化模型：
import { ChatMistralAI } from "@langchain/mistralai";

const model = new ChatMistralAI({
model: "mistral-large-latest",
temperature: 0
});

await model.invoke("Hello, world!")
Install:
npm i @langchain/community
添加环境变量：
FIREWORKS_API_KEY=your-api-key
实例化模型：
import { ChatFireworks } from "@langchain/community/chat_models/fireworks";

const model = new ChatFireworks({
model: "accounts/fireworks/models/llama-v3p1-70b-instruct",
temperature: 0
});

await model.invoke("Hello, world!")
Install:
npm i @langchain/groq
添加环境变量：
GROQ_API_KEY=your-api-key
实例化模型：
import { ChatGroq } from "@langchain/groq";

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

await model.invoke("Hello, world!")
While these LangChain classes support the indicated advanced feature, you may need to refer to provider-specific documentation to learn which hosted models or backends support the feature.
ModelStreamTool CallingwithStructuredOutput()Multimodal
ChatOpenAI✅✅✅✅
ChatAnthropic✅✅✅✅
ChatGoogle✅✅✅✅
BedrockChat✅🟡 (Bedrock Anthropic only)🟡 (Bedrock Anthropic only)🟡 (Bedrock Anthropic only)
ChatBedrockConverse✅✅✅✅
ChatCloudflareWorkersAI✅❌❌❌
ChatCohere✅✅✅✅
ChatFireworks✅✅✅✅
ChatGroq✅✅✅✅
ChatMistralAI✅✅✅✅
ChatOllama✅✅✅✅
ChatTogetherAI✅✅✅✅
ChatXAI✅✅✅❌
See the full list of chat model integrations below for more options.

​
Routers & proxies

Routers and proxies give you access to models from multiple providers through a single API and credential. They can simplify billing, let you switch between models without changing integrations, and offer features like automatic fallbacks.
ProviderIntegrationDescription
OpenRouterChatOpenRouterUnified access to models from OpenAI, Anthropic, Google, Meta, and more

​
Chat Completions API

Certain model providers offer endpoints that are compatible with OpenAI’s (legacy) Chat Completions API. In such case, you can use ChatOpenAI with a custom base_url to connect to these endpoints. Note that features built on top of the Chat Completions API may not be fully supported by ChatOpenAI; in such cases, consider using a provider-specific class if available.
To use OpenRouter, you will need to sign up for an account and obtain an API key.
import { ChatOpenAI } from "@langchain/openai";

const model = new ChatOpenAI({
    model: "...", // Specify a model available on OpenRouter
    configuration: {
    apiKey: "OPENROUTER_API_KEY",
    baseURL: "https://openrouter.ai/api/v1",
    }
});
Refer to the OpenRouter documentation for more details.

​
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 Gemini

Groq

IBM watsonx.ai

Llama CPP

Minimax

MistralAI

Moonshot

Novita AI

Ollama

OpenAI

Perplexity

PremAI

Tencent Hunyuan

Together

WebLLM

xAI

YandexGPT

ZhipuAI

If you’d like to contribute an integration, see Contributing integrations.
将这些文档连接到 Claude、VSCode 等工具，通过 MCP 获取实时答案。
在 GitHub 上编辑此页面 或 提交 issue。