NexusAI Docs

Welcome to the NexusAI documentation. This guide will help you integrate the NexusAI API into your application in under 5 minutes. You'll learn how to authenticate, make your first API call, and handle responses.

🚀 Prerequisites A NexusAI account, an API key, and a basic understanding of REST APIs or HTTP requests.

1. Installation

Install the official NexusAI SDK using your preferred package manager:

# Install via pip
pip install nexusai

# Or via conda
conda install -c conda-forge nexusai

# Install via npm
npm install @nexusai/sdk

# Or via yarn
yarn add @nexusai/sdk

# No installation required. Use any HTTP client.

2. Authentication

NexusAI uses API keys for authentication. You can generate and manage your keys in the Developer Dashboard. Always keep your API keys secure and never expose them in client-side code.

Header / Param	Description	Example
`Authorization`	Bearer token authentication	`Bearer nx_live_8x9...`
`X-Nexus-Version`	API version targeting (optional)	`2025-03-01`

⚠️ Security Notice Live API keys have full access to your account. Use restricted/test keys for development environments whenever possible.

3. Your First API Call

Let's send a request to the /v1/chat/completions endpoint. This example uses the nexus-v3-ultra model.

import os
from nexusai import Client

client = Client(api_key=os.environ["NEXUS_API_KEY"])

response = client.chat.completions.create(
    model="nexus-v3-ultra",
    messages=[
        {"role": "system", "content": "You are a helpful AI assistant."},
        {"role": "user", "content": "Explain quantum computing in simple terms."}
    ],
    temperature=0.7
)

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

import { NexusAI } from "@nexusai/sdk";

const client = new NexusAI({ apiKey: process.env.NEXUS_API_KEY });

const response = await client.chat.completions.create({
    model: "nexus-v3-ultra",
    messages: [
        { role: "system", content: "You are a helpful AI assistant." },
        { role: "user", content: "Explain quantum computing in simple terms." }
    ],
    temperature: 0.7
});

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

curl -X POST https://api.nexusai.com/v1/chat/completions \n  -H "Authorization: Bearer $NEXUS_API_KEY" \n  -H "Content-Type: application/json" \n  -d '{
    "model": "nexus-v3-ultra",
    "messages": [
      {"role": "system", "content": "You are a helpful AI assistant."},
      {"role": "user", "content": "Explain quantum computing in simple terms."}
    ],
    "temperature": 0.7
  }'

Response:

{
  "id": "chatcmpl-9x7K2pLm4nQ8",n  "object": "chat.completion",
  "created": 1710456789,
  "model": "nexus-v3-ultra",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Quantum computing leverages quantum mechanics..."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 24,
    "completion_tokens": 182,
    "total_tokens": 206
  }
}

4. Error Handling

NexusAI uses standard HTTP status codes. Here's how to handle common errors:

Status	Code	Meaning
`400`	`invalid_request_error`	Malformed request or missing parameters
`401`	`authentication_error`	Invalid or expired API key
`429`	`rate_limit_error`	Too many requests. Retry after backoff.
`500`	`internal_error`	Server-side issue. Contact support if persistent.

✅ Best Practice Always implement exponential backoff with jitter for 429 and 5xx errors. The SDK handles retries automatically when max_retries=3 is enabled.

Next Steps

Explore the Models Guide - Compare model capabilities, context windows, and pricing.
Structured Outputs - Learn how to enforce JSON schemas in model responses.
Function Calling - Connect AI to external tools and APIs seamlessly.
Rate Limits & Quotas - Understand usage tiers and optimization strategies.

💡 Need Help? Join our Developer Community, check the Troubleshooting Guide, or contact support@nexusai.dev.

Quickstart Guide

1. Installation

2. Authentication

3. Your First API Call

4. Error Handling

Next Steps