Using ElkAPI with Gemini CLI

Introduction

Gemini CLI is Google’s official command-line tool that allows developers to interact with Gemini AI models through the terminal. By configuring ElkAPI API, you can use various advanced AI models provided by ElkAPI in Gemini CLI, including GPT, Claude, and Gemini series.

Prerequisites

Before getting started, ensure you have:

Node.js and npm installed
Download and install from Node.js official website (v16 or higher recommended)
ElkAPI API Key
Log in to ElkAPI Console to obtain your API key (starts with sk-)

Tip: If you don’t have an ElkAPI account yet, register at ElkAPI first and obtain an API key.

Step 1: Install Gemini CLI

1.1 Global Installation

Install Gemini CLI globally using npm:

npm install -g @google/gemini-cli

1.2 Verify Installation

Check if the installation was successful:

gemini --version

If it displays a version number, the installation was successful.

Step 2: Configure ElkAPI API

2.1 Temporary Environment Variables

For testing or one-time use, expires when terminal is closed: Windows (PowerShell):

$env:GEMINI_API_KEY = "sk-xxxxxxxxxxxx"
$env:GEMINI_BASE_URL = "https://api.elkapi.com/v1"

macOS/Linux (Bash):

export GEMINI_API_KEY="sk-xxxxxxxxxxxx"
export GEMINI_BASE_URL="https://api.elkapi.com/v1"

2.2 Permanent Environment Variables (Recommended)

Write configuration to system, automatically applies on every terminal session: Windows (PowerShell):

Run PowerShell as Administrator
Execute the following commands to set user-level environment variables:

[System.Environment]::SetEnvironmentVariable('GEMINI_API_KEY', 'sk-xxxxxxxxxxxx', 'User')
[System.Environment]::SetEnvironmentVariable('GEMINI_BASE_URL', 'https://api.elkapi.com/v1', 'User')

Restart PowerShell or execute the following commands to refresh environment variables:

$env:GEMINI_API_KEY = [System.Environment]::GetEnvironmentVariable('GEMINI_API_KEY', 'User')
$env:GEMINI_BASE_URL = [System.Environment]::GetEnvironmentVariable('GEMINI_BASE_URL', 'User')

macOS/Linux (Bash):

Edit the configuration file (choose based on your shell):

# For Bash
nano ~/.bashrc

# For Zsh (macOS default)
nano ~/.zshrc

Add the following at the end of the file:

# ElkAPI Gemini CLI Configuration
export GEMINI_API_KEY="sk-xxxxxxxxxxxx"
export GEMINI_BASE_URL="https://api.elkapi.com/v1"

Save the file and reload configuration:

# For Bash
source ~/.bashrc

# For Zsh
source ~/.zshrc

2.3 Using .env File

Create a .env file in your project directory:

# .env
GEMINI_API_KEY=sk-xxxxxxxxxxxx
GEMINI_BASE_URL=https://api.elkapi.com/v1

Then load environment variables before running commands: macOS/Linux:

export $(cat .env | xargs) && gemini chat

Windows (PowerShell):

Get-Content .env | ForEach-Object {
    $name, $value = $_.split('=')
    Set-Content env:\$name $value
}
gemini chat

Important:

Replace sk-xxxxxxxxxxxx with your actual API key from ElkAPI Console
Set GEMINI_BASE_URL to https://api.elkapi.com/v1 to ensure Gemini CLI connects to ElkAPI
If using .env file, add it to .gitignore to avoid exposing your API key

2.4 Verify Configuration

Check if environment variables are set correctly: macOS/Linux:

echo $GEMINI_API_KEY
echo $GEMINI_BASE_URL

Windows (PowerShell):

echo $env:GEMINI_API_KEY
echo $env:GEMINI_BASE_URL

If the correct values are displayed, the configuration is successful.

Step 3: Start Using Gemini CLI

3.1 Basic Conversation

Start interactive conversation:

gemini chat

Or send a one-time request:

gemini "Please explain the history of artificial intelligence"

3.2 Specify Model

Chat with a specific model:

gemini chat --model gpt-5.5

Or:

gemini "Write a Python quicksort algorithm" --model claude-sonnet-4-6

Step 4: Using ElkAPI API with Code

2.1 Using Python SDK

import openai

# Configure ElkAPI API
openai.api_key = "sk-xxxxxxxxxxxx"  # Your ElkAPI API key
openai.api_base = "https://api.elkapi.com/v1"

# Use Gemini model
response = openai.ChatCompletion.create(
    model="gemini-3.1-flash-lite-preview",
    messages=[
        {"role": "user", "content": "Hello, please introduce yourself"}
    ]
)

print(response.choices[0].message.content)

2.2 Using JavaScript/TypeScript

import OpenAI from 'openai';

const client = new OpenAI({
  apiKey: 'sk-xxxxxxxxxxxx', // Your ElkAPI API key
  baseURL: 'https://api.elkapi.com/v1'
});

async function main() {
  const completion = await client.chat.completions.create({
    model: 'gemini-3.1-flash-lite-preview',
    messages: [
      { role: 'user', content: 'Hello, please introduce yourself' }
    ]
  });
  
  console.log(completion.choices[0].message.content);
}

main();

2.3 Using cURL

curl https://api.elkapi.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-xxxxxxxxxxxx" \
  -d '{
    "model": "gemini-3.1-flash-lite-preview",
    "messages": [
      {"role": "user", "content": "Hello, please introduce yourself"}
    ]
  }'

Step 3: Choose the Right Model

Recommended Models

Gemini Series:

Model Name	Model ID	Features	Use Cases
Gemini 3.1 Flash Lite	`gemini-3.1-flash-lite-preview`	Lightweight, economical	Fast simple tasks
Gemini 3.1 Pro	`gemini-3.1-pro-preview`	Powerful performance	Complex tasks, professional analysis
Gemini 3.1 Flash Lite	`gemini-3.1-flash-lite-preview`	High-speed response	Real-time interaction, batch processing

GPT Series:

Model Name	Model ID	Features	Use Cases
GPT-5	`gpt-5.5`	Latest and strongest	Complex reasoning, creative writing
GPT-5.5	`gpt-5.5`	High quality	Daily conversation, content generation
GPT-5.4 Mini	`gpt-5.4-mini`	Cost-effective	Simple tasks, high-frequency use

Claude Series:

Model Name	Model ID	Features	Use Cases
Claude Sonnet 4.6	`claude-sonnet-4-6`	Strong reasoning	Code generation, logical analysis
Claude Opus 4.7	`claude-sonnet-4-6`	Extremely fast	Quick Q&A, real-time chat

Model Selection Tips:

🚀 Google Ecosystem: gemini-3.1-flash-lite-preview, gemini-3.1-pro-preview
💡 Code Development: claude-sonnet-4-6, gpt-5.5
💰 Cost Optimization: gpt-5.4-mini, claude-sonnet-4-6
⚡ Fast Response: gemini-3.1-flash-lite-preview, gpt-5.4-mini

Advanced Features

Multimodal Support

response = openai.ChatCompletion.create(
    model="gemini-3.1-flash-lite-preview",
    messages=[
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "What's in this image?"},
                {
                    "type": "image_url",
                    "image_url": {
                        "url": "https://example.com/image.jpg"
                    }
                }
            ]
        }
    ]
)

Streaming Output

stream = openai.ChatCompletion.create(
    model="gemini-3.1-flash-lite-preview",
    messages=[{"role": "user", "content": "Write a poem about spring"}],
    stream=True
)

for chunk in stream:
    if chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end='')

FAQ

Q1: How to verify API configuration?

import openai

openai.api_key = "sk-xxxxxxxxxxxx"
openai.api_base = "https://api.elkapi.com/v1"

try:
    response = openai.ChatCompletion.create(
        model="gemini-3.1-flash-lite-preview",
        messages=[{"role": "user", "content": "test"}],
        max_tokens=10
    )
    print("✅ API configuration successful!")
    print(f"Response: {response.choices[0].message.content}")
except Exception as e:
    print(f"❌ API configuration failed: {e}")

Q2: Supported Programming Languages?

ElkAPI API supports all programming languages that can send HTTP requests:

✅ Python - Recommended with OpenAI SDK
✅ JavaScript/TypeScript - Node.js and browser
✅ Java - HTTP client
✅ Go - Standard library or third-party packages
✅ PHP - cURL or Guzzle
✅ Ruby - HTTP library
✅ C#/.NET - HttpClient
✅ Swift - URLSession
✅ Other languages - Any language supporting HTTP

Features

Using Google AI Studio + ElkAPI, you can:

🤖 Multi-model Support - Access GPT, Claude, Gemini, and more
🌍 OpenAI Compatible - Standard OpenAI API format
⚡ High Performance - Low latency, high concurrency
💰 Transparent Pricing - Clear pay-as-you-go pricing
📊 Usage Monitoring - Real-time API call tracking
🔒 Secure & Reliable - Enterprise-grade security
🚀 Quick Integration - Simple API calls
📚 Complete Documentation - Detailed development docs and examples

Support & Help

If you encounter any issues:

Chat Applications

Development Tools

Application Platforms

Using ElkAPI with Gemini CLI

Introduction

Prerequisites

Step 1: Install Gemini CLI

1.1 Global Installation

1.2 Verify Installation

Step 2: Configure ElkAPI API

2.1 Temporary Environment Variables

2.2 Permanent Environment Variables (Recommended)

2.3 Using .env File

2.4 Verify Configuration

Step 3: Start Using Gemini CLI

3.1 Basic Conversation

3.2 Specify Model

Step 4: Using ElkAPI API with Code

2.1 Using Python SDK

2.2 Using JavaScript/TypeScript

2.3 Using cURL

Step 3: Choose the Right Model

Recommended Models

Advanced Features

Multimodal Support

Streaming Output

FAQ

Q1: How to verify API configuration?

Q2: Supported Programming Languages?

Features

Support & Help

Get Started with ElkAPI

​Introduction

​Prerequisites

​Step 1: Install Gemini CLI

​1.1 Global Installation

​1.2 Verify Installation

​Step 2: Configure ElkAPI API

​2.1 Temporary Environment Variables

​2.2 Permanent Environment Variables (Recommended)

​2.3 Using .env File

​2.4 Verify Configuration

​Step 3: Start Using Gemini CLI

​3.1 Basic Conversation

​3.2 Specify Model

​Step 4: Using ElkAPI API with Code

​2.1 Using Python SDK

​2.2 Using JavaScript/TypeScript

​2.3 Using cURL

​Step 3: Choose the Right Model

​Recommended Models

​Advanced Features

​Multimodal Support

​Streaming Output

​FAQ

​Q1: How to verify API configuration?

​Q2: Supported Programming Languages?

​Features

​Support & Help

Get Started with ElkAPI

Introduction

Prerequisites

Step 1: Install Gemini CLI

1.1 Global Installation

1.2 Verify Installation

Step 2: Configure ElkAPI API

2.1 Temporary Environment Variables

2.2 Permanent Environment Variables (Recommended)

2.3 Using .env File

2.4 Verify Configuration

Step 3: Start Using Gemini CLI

3.1 Basic Conversation

3.2 Specify Model

Step 4: Using ElkAPI API with Code

2.1 Using Python SDK

2.2 Using JavaScript/TypeScript

2.3 Using cURL

Step 3: Choose the Right Model

Recommended Models

Advanced Features

Multimodal Support

Streaming Output

FAQ

Q1: How to verify API configuration?

Q2: Supported Programming Languages?

Features

Support & Help