📋 Migration Guide

Switch to Celuxe in
under 5 minutes

Drop-in replacement for OpenAI, Anthropic, Google, and 30+ AI providers. Just change your base URL and API key — nothing else needed.

⏱️ Average migration time: 3 minutes
Feature Celuxe Your Current Provider
Models available 30+ models · 1 API key 1 provider at a time
Pricing Cost-effective · No markup Varies by provider
API compatibility ✓ OpenAI-compatible —
Model fallback ✓ Automatic failover ✗ Not available
Multi-provider access ✓ GPT-4o + Claude + Gemini + DeepSeek ✗ Single provider
Global latency <200ms average Varies
1
Get your Celuxe API key
Sign up and create an API key in 30 seconds. No credit card required.
🌐 Dashboard
https://celuxe.shop/dashboard.html
💡

New here? Sign up at celuxe.shop/signup.html and get 200,000 free tokens to start. No credit card required.

2
Update your base URL
Change your OpenAI-compatible base URL to Celuxe. That's it.
Python
from openai import OpenAI client = OpenAI( api_key="sk-celu-xxxxxxxxxxxx", # ← Your Celuxe API key base_url="https://api.celuxe.shop/v1" # ← Change this URL ) # Everything else stays exactly the same! response = client.chat.completions.create( model="gpt-4o", messages=[{"role": "user", "content": "Hello!"}] ) print(response.choices[0].message.content)
TypeScript / Node.js
import OpenAI from "openai"; const client = new OpenAI({ apiKey: "sk-celu-xxxxxxxxxxxx", // ← Your Celuxe API key baseURL: "https://api.celuxe.shop/v1" // ← Change this URL }); // Everything else stays exactly the same! const response = await client.chat.completions.create({ model: "gpt-4o", messages: [{ role: "user", content: "Hello!" }] });
curl
curl https://api.celuxe.shop/v1/chat/completions \\ -H "Authorization: Bearer sk-celu-xxxxxxxxxxxx" \\ -H "Content-Type: application/json" \\ -d '{ "model": "gpt-4o", "messages": [{"role": "user", "content": "Hello!"}] }'
3
Switch models instantly
Use any model with the same API call. Just change the model name.
Model Mapping
# Same code, different model — Celuxe handles the routing model = "gpt-4o" # → OpenAI GPT-4o model = "claude-3-5-sonnet" # → Anthropic Claude 3.5 Sonnet model = "gemini-2.0-flash" # → Google Gemini 2.0 Flash model = "deepseek-v3" # → DeepSeek V3 model = "deepseek-r1" # → DeepSeek R1 (reasoning) model = "minimax" # → MiniMax M2.7 model = "llama-3-70b" # → Meta Llama-3 70B model = "gpt-4o-mini" # → OpenAI GPT-4o Mini (fast & cheap)
🔄

Automatic Fallback: If the primary model fails, Celuxe automatically routes to an equivalent model. Your app never breaks.

One key, 30+ models

From OpenAI to Anthropic to open-source models — all accessible via a single Celuxe API key.

OpenAI
GPT-4o / o3-mini / DALL-E 3
6 models
Anthropic
Claude 3.5 Sonnet / Claude 4
4 models
Google
Gemini 2.0 Flash / 1.5 Pro
3 models
DeepSeek
V3 / R1 / Chat / Coder
7 models ✓
MiniMax
M2.7 (Reasoning)
1 model ✓
Meta
Llama-3 70B / 8B
2 models

⚠️ Important notes

📊

Pricing: Celuxe prices are shown in USD and may differ slightly from the upstream provider's official pricing due to routing and infrastructure costs. Always check the current rate on our Models page before running large workloads.

🔑

API Key format: Celuxe API keys start with sk-celu-. If you have existing sk- keys from other providers, you can still use them via our BYOK (Bring Your Own Key) feature on the VIP page.

🔒

Authentication: Celuxe uses the same Bearer token authentication as OpenAI. Your existing SDKs work without modification — only the base URL and API key change.

Ready to switch?

Join thousands of developers who switched to Celuxe for better pricing and unified API access.

🚀 Get Started Free → 📊 View All Models 📖 Read the Docs