Quick Start

This guide helps you make your first successful request with VLX FLUX. It is written for customers who purchase distributed API access and want to use VLX FLUX in code, CLI tools, or OpenAI-compatible clients.

What You Need

Before starting, make sure you have:

• A VLX FLUX account
• An active API key
• Available balance or trial credit
• A model that your account can access

The Base URL is:

https://api.vlxflux.io/v1

Step 1: Create an API Key

Sign in to the VLX FLUX dashboard and create an API key.

Keep the key private. Anyone with this key can send requests that may consume your account balance.

If you already have a key, you can continue with the next step.

Step 2: Check the Base URL

Use this Base URL in SDKs, CLI tools, and third-party clients:

https://api.vlxflux.io/v1

Common mistakes:

• Do not write https://api.vlxflux.io if the client expects the /v1 suffix.
• Do not duplicate the version path, such as /v1/v1.
• Do not use the dashboard website URL as the API URL.

Step 3: Query Available Models

Use the model list endpoint to confirm which models your key can access:

curl https://api.vlxflux.io/v1/models \
  -H "Authorization: Bearer YOUR_API_KEY"

Replace YOUR_API_KEY with your own key.

If the request succeeds, you will receive a list of model IDs. Use one of these IDs in later requests.

Step 4: Send Your First Chat Request

Use a model available to your account:

curl https://api.vlxflux.io/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "gpt-4o",
    "messages": [
      { "role": "user", "content": "Say hello in one sentence." }
    ]
  }'

If the request returns a normal assistant message, your API key, Base URL, model name, and account balance are working.

Step 5: Use an SDK

For Python:

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.vlxflux.io/v1"
)

response = client.chat.completions.create(
    model="gpt-4o",
    messages=[
        {"role": "user", "content": "Say hello in one sentence."}
    ]
)

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

For Node.js:

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.VLXFLUX_API_KEY,
  baseURL: "https://api.vlxflux.io/v1",
});

const response = await client.chat.completions.create({
  model: "gpt-4o",
  messages: [
    { role: "user", content: "Say hello in one sentence." },
  ],
});

console.log(response.choices[0].message.content);

Step 6: Configure a Third-Party Client

For OpenAI-compatible clients, fill in:

Field	Value
API Key	Your VLX FLUX API key
Base URL	https://api.vlxflux.io/v1
Model	A model available to your account

Some clients use different labels, such as OpenAI Compatible API, Custom API Endpoint, API Host, or Base URL. These usually refer to the same setting.

Step 7: Check Billing

Each successful request may consume balance based on:

• The selected model
• Input and output token usage
• The model group multiplier
• Current pricing shown in the dashboard

You can review balance, usage history, and model pricing in the dashboard.

Quick Troubleshooting

Symptom	What to check
401 Unauthorized	API key is missing, incorrect, disabled, or has extra spaces
403 Forbidden	The key does not have permission for the selected model or group
404 Not Found	Base URL or request path is incorrect
429 Too Many Requests	Request frequency or concurrency is too high
model not found	Model name is wrong or unavailable to your account
Insufficient balance	Recharge or switch to a lower-cost model

Next Reading

• OpenAI-Compatible API
• API Keys
• Model List
• Pricing
• Error Codes and Troubleshooting