Fast · framework

Use Gemini 2.5 Flash with LangChain

Updated 2026-05-21 · By XALEN

How to use Gemini 2.5 Flash (Fast, ~200B) with LangChain. Install, authenticate, and make your first API call in minutes. Working code example included.

Model

Gemini 2.5 Flash

~200B · 1M context · $0.015 input

Framework

LangChain

framework · pip install langchain-openai

1. Install

pip install langchain-openai

2. Code

from langchain_openai import ChatOpenAI

llm = ChatOpenAI(
    model="gemini-2-5-flash",
    openai_api_key="xln_test_YOUR_KEY",
    openai_api_base="https://api.xalen.io/v1"
)

response = llm.invoke("What is Gemini 2.5 Flash?")
print(response.content)

Gemini 2.5 Flash with Other Frameworks

Python JavaScript React Next.js Flask FastAPI Django Express.js

Other Models with LangChain

Vedika Standard Vedika Fast Vedika Pro Ultra Vedika Vision Vedika Code Vedika Astro Agent

200+ models. One API. Works with any framework.

Get API Key

Last updated: 2026-05-21