Connect → LangChain

Use AxForge with LangChain

LangChain builds chains and agents around a chat model. Its ChatOpenAI class takes a base URL, so an AxForge model drops in wherever a model goes: chains, tools, agents, LangGraph.

Set it up

1. Install the OpenAI package for LangChain

   pip install langchain-openai

2. Point ChatOpenAI at AxForge

   import os
   from langchain_openai import ChatOpenAI
   
   llm = ChatOpenAI(
       base_url="https://api.axforge.ai/v1",
       api_key=os.environ["AXFORGE_API_KEY"],
       model="qwen3.8-27b-nvfp4",
   )
   print(llm.invoke("Say hello in five words").content)

3. Run it

   python hello.py

   

From here llm is a LangChain chat model like any other: llm.stream(...), llm.bind_tools([...]), or pass it to an agent.

The settings

Which model for what: qwen3.8-27b-nvfp4 is the everyday default and reads images, glm-5.3-flash thinks before it answers, mimo-v2.6-flash is the fastest. All three can call tools.

Check that it works

The script prints an answer. The call shows in the console under API Keys → Recent calls within a minute.

When it does not work

Test a call says in one click whether a problem is your key, your balance or us.