Integration & Keys

Integrate our advanced multi-layer models seamlessly. Nexify.ai acts as a drop-in replacement for standard chat completions.

verified_user

terminal API Authentication

Nexify uses Bearer Token authentication. Include an Authorization header with your secure nx_dev_ key.

link Endpoint V1 Active
security HTTPS Encryption

layers Core Models

Nexify

Nexify.ai

General Purpose

Powered by a customized Llama 3.1 70B Instruct core. Best for incredibly fast, general-purpose chat completions and creative reasoning.

Alias ID "model": "nexify.ai"
Nexify

Nexify Omni

Advanced

Powered by Mistral 4 Large (Mixtral 8x22B). Designed for highly complex logic, extensive contextual understanding, and precise data formatting.

Alias ID "model": "nexify-omni"

speed Rate Limits & Usage

During the Developer Preview, all nx_dev_ keys are placed in the Free Tier. This strictly limits your application to 25 successful completions per day, with a burst limit of 3 Requests Per Minute (RPM) to ensure network stability. Errors (400/500) do not consume quota.

memory Context Windows

Nexify.ai provides 128k tokens (~300 pages). Nexify Omni provides 64k tokens. Messages exceeding limits are automatically truncated. Target <200ms time-to-first-token (TTFT).

lightbulb Prompting Rules

  • ✦ System inputs must use {"role":"system"} at index 0.
  • ✦ Set temp: 0.1 for determinism or core data formats.

api API Reference

Create chat completion

Creates a model response for the given chat conversation.

POST https://study-with-assistant.netlify.app/v1/chat/completions

Headers

Authorization Bearer nx_dev_...
Content-Type application/json

Request Body

Parameter Description
model
Required
 ID of the model to use. You must provide either nexify.ai, nexify-omni, or ultron.cyber (Cyber Intelligence AI by Nexify Labs).
messages
Required
 A list of messages comprising the conversation so far. Each message must be an object with strict role (system, user, assistant) and content properties.
temperature
Optional
 What sampling temperature to use, between 0 and 2. Higher values like 0.8 make the output more random, while lower values like 0.2 make it more focused and deterministic.
max_tokens
Optional
 The maximum number of tokens to generate in the chat completion. The total length of input tokens and generated tokens is limited by the model's context length.
upload REQUEST PAYLOAD 
{
  "model": "nexify.ai",
  "messages": [
    {"role": "system", "content": "You are helpful"},
    {"role": "user", "content": "Hello"}
  ],
  "temperature": 0.7,
  "max_tokens": 1000
}
download RESPONSE PAYLOAD 
{
  "id": "chatcmpl-xyz",
  "object": "chat.completion",
  "choices": [
    {
      "message": {
        "role": "assistant",
        "content": "Hello! How can I help you?"
      }
    }
  ],
  "usage": {
    "prompt_tokens": 10,
    "completion_tokens": 12
  }
}
warning ERROR RESPONSE 
{
  "error": {
    "message": "Invalid API key",
    "type": "authentication_error",
    "code": 401
  }
}
401 → Invalid API key
429 → Limit: 25 requests/day
500 → Internal Server Error
code Python terminal Node.js sync_alt cURL
Free Demo: 20 requests (3h)
-- / --
info Free Demo — No login required to test.

terminal Command Line Access

v2.1
lock_person

Sign in to unlock CLI Terminal access

PRO DEVELOPER TOOLS

NEXIFY TEXT CLI CHAT
expand_more

Interactive AI chat in your terminal. Ask questions, get coding help, brainstorm — all without leaving the command line.

INSTALL & RUN
$ ./nexify
EXAMPLE SESSION nexify (text) > What is quantum computing? Nexify AI: Quantum computing uses qubits... nexify (text) > /agent ✓ Switched to Agent Mode
NEXIFY AGENT CLI EDIT FILES
expand_more

Autonomous code agent that reads your files, applies AI-powered changes, and saves them instantly. Like having a senior engineer in your terminal.

USAGE
$ ./nexify
> /agent
EXAMPLE SESSION nexify (agent) > edit my page File: index.html What to change: Add a dark mode toggle ✓ index.html updated successfully. 🚀
ULTRON CYBER AI BY NEXIFY LABS
expand_more

Elite Cyber Intelligence AI — specialized in penetration testing, malware analysis, network forensics, OSINT, and full-stack security engineering. Built and trained by Nexify Labs with 1,020 expert training examples.

API USAGE
"model": "ultron.cyber"
EXAMPLE SESSION ultron (cyber) > How to detect ARP spoofing? ULTRON: Use arpwatch to monitor ARP tables... ultron (cyber) > Write a Python port scanner ULTRON: import socket; def scan(host, port)...
✦ 1,020 cybersecurity training examples
✦ Pentest, OSINT, Forensics, Full-Stack Dev
✦ Cloud-powered (70B) + Local Ollama fallback
terminal Quick Install
v6.0 PRODUCTION

Install Nexify AI globally with one command. Works on every major operating system.

Terminal / iTerm2 RECOMMENDED
$ curl -fsSL https://study-with-assistant.netlify.app/install.sh | bash
✓ Requires Python 3.7+ (pre-installed on macOS)
✓ Auto-adds to PATH via ~/.zshrc
✓ After install, just type: nexify
✓ Zero dependencies ✓ Smart Mode AI ✓ Free & Open Source
Python 3.7+
Nexify

Nexify Code for VS Code

EXT

Full context-aware coding assistant inside your editor. Highlight code, press Option+K, and fix bugs instantly.

open_in_new OPEN VSX REGISTRY download DOWNLOAD .VSIX
shield_lock Keep your API key secure. Never expose it in client-side code.

joystick Interactive Playground

Chat Session Started

contact_mail Request Token

Need more than 25 requests/day or higher rate limits for production? Request a tier upgrade.