LangChain
Point LangChain's ChatOpenAI at AI Nexus, with Python and JavaScript examples.
LangChain's ChatOpenAI accepts a custom base URL, so you can point it straight at the AI Nexus OpenAI-compatible API. You can use any model on the model square that supports /v1/chat/completions.
Verification status
The examples follow LangChain's official documentation and have not all been tested against AI Nexus. Only two values matter: Base URL and API Key.
Put your key in an environment variable first:
export MYAIEXP_API_KEY="sk-xxxxxxxx"Python
pip install langchain-openaiimport os
from langchain_openai import ChatOpenAI
llm = ChatOpenAI(
model="your-model-id", # replace with a model ID from the model square
api_key=os.environ["MYAIEXP_API_KEY"],
base_url="https://ai.myaiexp.com/v1",
)
print(llm.invoke("Introduce yourself in one sentence.").content)JavaScript / TypeScript
npm install @langchain/openaiimport { ChatOpenAI } from "@langchain/openai";
const llm = new ChatOpenAI({
model: "your-model-id", // replace with a model ID from the model square
apiKey: process.env.MYAIEXP_API_KEY,
configuration: { baseURL: "https://ai.myaiexp.com/v1" },
});
const res = await llm.invoke("Introduce yourself in one sentence.");
console.log(res.content);Notes
- Streaming,
bind_toolsand similar features use the OpenAI format underneath; see Streaming and Function calling for gateway support. - Model names must exactly match
GET /v1/models; see the model square for the full list. - For Claude-native features (such as Prompt caching), you can use
ChatAnthropicfromlangchain-anthropicwith base URLhttps://ai.myaiexp.com(no/v1). Pick a model that supports/v1/messages; see Anthropic format.
Cherry Studio
Add AI Nexus as a model provider in Cherry Studio and chat with models from the desktop client.
Dify
Connect AI Nexus in Dify through the OpenAI-API-compatible model provider.
This service is provided for learning and research purposes only. Please follow each model provider's usage policies.