SDKs & Developer Tools

Libraries

Official SDKs

Type-safe, async-ready, and optimized for low-latency inference.

🐍 Python Stable

Full-featured async client with streaming, batch processing, and pandas/numpy integration.

pip install nexusai-sdk 📋

Documentation Examples PyPI

🟨 Node.js Stable

TypeScript-first client with native streaming, retries, and OpenAPI compatibility.

npm install @nexusai/js-sdk 📋

Documentation Examples npm

🐹 Go Stable

High-performance gRPC/HTTP client with context propagation and zero-allocation pooling.

go get github.com/nexusai/go-sdk 📋

Documentation Examples GoDoc

🦀 Rust Beta

Async-first Rust bindings with serde support, tokio integration, and minimal overhead.

cargo add nexusai-sdk 📋

Documentation Examples crates.io

Get Started

Quick Start

Copy-paste ready examples to spin up your first AI inference pipeline.

from nexusai import Client

# Initialize with your API key
ai = Client(api_key="nx_live_...")

# Run inference
response = ai.models.run(
    model="nexus-v3-ultra",
    input="Analyze sentiment of this text...",
    stream=True
)

for chunk in response.stream():
    print(chunk.content, end="", flush=True)

import { NexusAI } from '@nexusai/js-sdk';

// Initialize client
const ai = new NexusAI({ apiKey: 'nx_live_...' });

// Run inference with streaming
const stream = await ai.models.run({
  model: 'nexus-v3-ultra',
  input: 'Analyze sentiment...',
  stream: true
});

for await (chunk of stream) {
  process.stdout.write(chunk.content);
}

package main

import (
  "context"
  "fmt"
  "github.com/nexusai/go-sdk"
)

func main() {
  client := nexusai.New(nexusai.WithAPIKey("nx_live_..."))
  
  resp := client.Models.Run(context.Background(),
    nexusai.RunOptions{
      Model: "nexus-v3-ultra",
      Input: "Analyze sentiment...",
    })
  
  for resp.Stream() {
    fmt.Print(resp.Content)
  }
}

curl https://api.nexusai.com/v1/inference \
  -H "Authorization: Bearer nx_live_..." \
  -H "Content-Type: application/json" \
  -d '{
    "model": "nexus-v3-ultra",
    "input": "Analyze sentiment...",
    "stream": true
  }'

Ecosystem

Integration Tools

Infrastructure, CLI, and platform tools for enterprise deployment.

⌨️

Nexus CLI

Manage deployments, monitor jobs, and run local evaluations directly from your terminal.

Documentation →

🏗️

Terraform Provider

Provision models, configure endpoints, and manage permissions using Infrastructure as Code.

Registry →

☸️

K8s Operator

Deploy autoscaling inference clusters with GPU management and zero-downtime rolling updates.

Operator Hub →

🔔

Webhooks & Events

Real-time event streaming for model runs, billing alerts, and pipeline lifecycle triggers.

Event Schema →

📦

Postman Collection

Pre-built workflows, environment variables, and test scripts for rapid API exploration.

Import Collection →

🐳

Docker Images

Official containerized runtimes with ONNX, TensorRT, and CUDA optimizations pre-configured.

GitHub Container →

System Status

Real-time health monitoring for all NexusAI endpoints.

All Systems Operational

Service	Region	Latency	Status
Inference API	US-East-1	42ms	Operational
Model Training	EU-West-1	128ms	Operational
Vector Database	AP-South-1	67ms	Degraded
Auth & Billing	Global	24ms	Operational

Developer SDKs & Tools