API Quickstart

Name: Thox OS
Author: Thox.ai LLC

Get your first API call running in 5 minutes.

Prerequisites

Thox.ai device powered on and connected to your network
Device showing green LED (ready state)
Computer on the same network as the device

Verify Connection

First, verify that your device is accessible on the network:

# Check if device is reachable

curl http://thox.local:8080/health

# Expected response:

{"status": "healthy", "version": "1.2.0"}

If thox.local doesn't resolve, use your device's IP address instead (check your router's DHCP client list).

List Available Models

See what models are available on your device:

curl http://thox.local:8080/v1/models

# Response:

{
  "data": [
    {
      "id": "thox-coder",
      "object": "model",
      "owned_by": "thoxai"
    },
    {
      "id": "thox-chat",
      "object": "model",
      "owned_by": "thoxai"
    }
  ]
}

Make Your First Request

Using cURL

curl http://thox.local:8080/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "thox-coder",
    "messages": [
      {"role": "user", "content": "Write a hello world in Python"}
    ]
  }'

Using Python

import requests

response = requests.post(
    "http://thox.local:8080/v1/chat/completions",
    json={
        "model": "thox-coder",
        "messages": [
            {"role": "user", "content": "Write a hello world in Python"}
        ]
    }
)

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

Using JavaScript/Node.js

const response = await fetch('http://thox.local:8080/v1/chat/completions', {
  method: 'POST',
  headers: { 'Content-Type': 'application/json' },
  body: JSON.stringify({
    model: 'thox-coder',
    messages: [
      { role: 'user', content: 'Write a hello world in Python' }
    ]
  })
});

const data = await response.json();
console.log(data.choices[0].message.content);

Enable Streaming

For real-time token-by-token output, enable streaming:

import requests

response = requests.post(
    "http://thox.local:8080/v1/chat/completions",
    json={
        "model": "thox-coder",
        "messages": [
            {"role": "user", "content": "Explain async/await"}
        ],
        "stream": True
    },
    stream=True
)

for line in response.iter_lines():
    if line:
        print(line.decode())

Next Steps

API Reference

Explore all available endpoints

Model Catalog

Browse available AI models

IDE Integration

Connect your code editor

CLI Tools

Install command-line tools

CONFIDENTIAL AND PROPRIETARY INFORMATION

This documentation is provided for informational and operational purposes only. The specifications and technical details herein are subject to change without notice. Thox.ai LLC reserves all rights in the technologies, methods, and implementations described.

Nothing in this documentation shall be construed as granting any license or right to use any patent, trademark, trade secret, or other intellectual property right of Thox.ai LLC, except as expressly provided in a written agreement.

Patent Protection

The MagStack™ magnetic stacking interface technology, including the magnetic alignment system, automatic cluster formation, NFC-based device discovery, and distributed inference me...

Reverse Engineering Prohibited

You may not reverse engineer, disassemble, decompile, decode, or otherwise attempt to derive the source code, algorithms, data structures, or underlying ideas of any Thox.ai hardwa...

Thox.ai™, Thox OS™, MagStack™, and the Thox.ai logo are trademarks or registered trademarks of Thox.ai LLC in the United States and other countries.

NVIDIA, Jetson, TensorRT, and related marks are trademarks of NVIDIA Corporation. Ollama is a trademark of Ollama, Inc. All other trademarks are the property of their respective owners.