Get Started with NexusAI
Deploy your first AI model and make your first inference in under 5 minutes. No prior ML experience required.
⏱️ Estimated time: 5 minutes
⚡ Prerequisites
- A NexusAI account and active API key (get one at app.nexusai.com)
- Node.js 18+ or Python 3.9+ installed locally
- Basic familiarity with REST APIs or terminal usage
📦 Installation & Setup
1
Install the SDK
Add the official NexusAI client to your project using your preferred package manager.
2
Authenticate
Set your API key as an environment variable or pass it directly during initialization.
3
Initialize & Run
Create a client instance and send your first inference request to the NexusAI v3 engine.
🚀 Your First Inference
Copy the code below, replace YOUR_API_KEY, and run it. You'll receive a structured JSON response in ~150ms.
import os
from nexusai import NexusClient
# Initialize client
client = NexusClient(api_key=os.getenv("NEXUS_API_KEY"))
# Run inference
response = client.inference(
model="nexus-v3-ultra",
prompt="Analyze sentiment and extract key entities from: 'The new AI deployment exceeded all expectations.'",
temperature=0.2,
max_tokens=512
)
print(response.json())
# Output: { "sentiment": "positive", "confidence": 0.98, "entities": ["AI deployment"], ... }🔍 Troubleshooting
API Key Authentication Failed
Ensure your key starts with
nxs_live_ for production or nxs_test_ for sandbox. Check for trailing spaces and verify the key is active in your dashboard.Rate Limit Exceeded (429)
Free tier allows 1,000 requests/day. Upgrade to Professional for 5M/month, or implement exponential backoff in your retry logic.
Model Timeout or Slow Response
NexusAI v3 averages <150ms latency. If experiencing delays, check network connectivity or switch to the
async endpoint for heavy workloads.What's Next?
You're ready to build. Explore advanced features, deployment guides, and production best practices.