Overview

Getting Started

EvolveX is a universal API gateway that gives you access to 150+ state-of-the-art Large Language Models through a single, unified endpoint. It natively supports standard OpenAI formatting.

Base URL & Authentication

All API requests should be prefixed with the base URL and include your API key in the Authorization header.

Base URL

https://api.evolvex.gg/v1

Get API Key

Making your first request (cURL)

You can immediately test the API using your terminal. Just replace YOUR_API_KEY with your actual EvolveX secret key.

curl https://api.evolvex.gg/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer evx-sk-YOUR_API_KEY" \
  -d '{
    "model": "gpt-4o",
    "messages": [
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "Hello! What can you do?"}
    ]
  }'

Fetching Available Models

To see the full, live list of supported models programmatically, use the models endpoint:

curl https://api.evolvex.gg/v1/models \
  -H "Authorization: Bearer evx-sk-YOUR_API_KEY"

SDK Integration

OpenAI Compatible

Because EvolveX perfectly mimics the OpenAI API specification, you do not need to learn a new library. You can use the official OpenAI SDKs in your language of choice—just change the Base URL and the API Key.

Python (OpenAI SDK)

Install the package: pip install openai

import openai

# 1. Initialize client pointing to EvolveX
client = openai.OpenAI(
    base_url="https://api.evolvex.gg/v1",
    api_key="evx-sk-YOUR_API_KEY"
)

# 2. Make your request (You can use Anthropic models here too!)
response = client.chat.completions.create(
    model="claude-sonnet-4-6", 
    messages=[{"role": "user", "content": "Write a python script to fetch a URL."}]
)

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

Node.js / TypeScript (OpenAI SDK)

Install the package: npm install openai

import OpenAI from 'openai';

// 1. Initialize client pointing to EvolveX
const openai = new OpenAI({
  baseURL: 'https://api.evolvex.gg/v1',
  apiKey: 'evx-sk-YOUR_API_KEY',
});

async function main() {
  // 2. Make your request
  const chatCompletion = await openai.chat.completions.create({
    messages: [{ role: 'user', content: 'Explain quantum computing simply.' }],
    model: 'gpt-4.1-mini', // Access any EvolveX model
  });
  
  console.log(chatCompletion.choices[0].message.content);
}

main();

Terminal AI

Claude Code Tutorial

Claude Code is Anthropic's official CLI tool that provides a powerful AI programming assistant right in your terminal. This tutorial will guide you through installing it and configuring it to run entirely through your EvolveX API key.

1. Installation

Claude Code requires Node.js. If you don't have it, download it here. Once Node.js is installed, open your terminal and run:

npm install -g @anthropic-ai/claude-code

Troubleshooting: If you encounter permission errors on macOS/Linux, run the command with sudo: sudo npm install -g @anthropic-ai/claude-code

2. Route Traffic to EvolveX

To make Claude Code use EvolveX instead of Anthropic's default servers, you must override its environment variables. Find your Operating System below:

macOS & Linux (Bash / Zsh)

For a temporary session, run:

export ANTHROPIC_BASE_URL="https://api.evolvex.gg"
export ANTHROPIC_AUTH_TOKEN="evx-sk-YOUR_API_KEY"

Permanent Configuration:

echo 'export ANTHROPIC_BASE_URL="https://api.evolvex.gg"' >> ~/.zshrc
echo 'export ANTHROPIC_AUTH_TOKEN="evx-sk-YOUR_KEY"' >> ~/.zshrc
source ~/.zshrc

Windows (PowerShell)

For a temporary session, run:

$env:ANTHROPIC_BASE_URL = "https://api.evolvex.gg"
$env:ANTHROPIC_AUTH_TOKEN = "evx-sk-YOUR_API_KEY"

Permanent Configuration:

[System.Environment]::SetEnvironmentVariable("ANTHROPIC_BASE_URL", "https://api.evolvex.gg", "User")
[System.Environment]::SetEnvironmentVariable("ANTHROPIC_AUTH_TOKEN", "evx-sk-YOUR_KEY", "User")

3. Start Coding

Navigate to any project folder in your terminal and type:

claude

Claude will launch. Because of the variables you set, all intelligence requests will automatically route through your EvolveX account!

Reference

Available Models

EvolveX routes traffic to over 150+ models globally. Below are the string identifiers for some of our most popular and capable models. Use these in the model: "..." parameter of your API calls.

OpenAI

gpt-4o
gpt-4.1-mini
gpt-5.3-codex

Anthropic

claude-sonnet-4-6
claude-opus-4-6
claude-haiku-4-5

Google

gemini-2.5-pro
gemini-3-pro
gemini-3-flash

Open Source & Others

qwen3-coder-max
glm-5
grok-code-fast-1

Documentation