How I Set Up GLM-5-Turbo on My Debian Linux Machine (June 2026)

Final Result

A beautiful, fast, and persistent terminal-based chat application powered by GLM-5-Turbo.

Key Features of My Setup

• Real-time Streaming — Words appear as they are generated (much more natural than waiting for full responses)
• Persistent Chat History — Conversations are saved automatically to a JSON file and restored when you reopen the app
• Beautiful Terminal UI — Colored text using the rich library
• Secure API Key Handling — Never hardcoded, loaded from environment variable
• Error Handling — Graceful handling of API issues
• Easy to Extend — Ready for future additions like tool calling or LangChain integration

---

Step-by-Step Setup Guide

1. Install Required Packages

Bash

pip install openai rich

2. Get Your API Key

1. Go to OpenRouter
2. Sign up / Log in
3. Go to Settings → API Keys
4. Create a new key and copy it

3. Set API Key Permanently

Bash

# Add to bashrc so it persists
echo 'export OPENROUTER_API_KEY="sk-or-v1-..."' >> ~/.bashrc
source ~/.bashrc

Verify it:

Bash

echo $OPENROUTER_API_KEY

4. Create the Chat Application

Bash

nano chat_glm.py

Paste the full code (same as before, but now included for completeness):

Python

import os
import json
from openai import OpenAI
from rich.console import Console

api_key = os.getenv("OPENROUTER_API_KEY")
if not api_key:
    print("❌ Error: OPENROUTER_API_KEY is not set!")
    exit(1)

client = OpenAI(api_key=api_key, base_url="https://openrouter.ai/api/v1")
console = Console()
HISTORY_FILE = "glm_chat_history.json"

def load_history():
    if os.path.exists(HISTORY_FILE):
        try:
            with open(HISTORY_FILE, "r", encoding="utf-8") as f:
                return json.load(f)
        except:
            return []
    return []

def save_history(messages):
    try:
        with open(HISTORY_FILE, "w", encoding="utf-8") as f:
            json.dump(messages, f, ensure_ascii=False, indent=2)
    except:
        pass

console.print("[bold cyan]🤖 GLM-5-Turbo Chat with History[/bold cyan] (type 'exit' to quit)\n")

messages = load_history()
if messages:
    console.print(f"

[dim]Loaded {len(messages)//2} previous messages from history[/dim]

\n”) while True: console.print(“[bold green]You:[/bold green] “, end=””) user_input = input() if user_input.lower() in [‘exit’, ‘quit’, ‘bye’]: console.print(“[yellow]Goodbye! Chat history saved.[/yellow]”) save_history(messages) break messages.append({“role”: “user”, “content”: user_input}) console.print(“[bold blue]GLM:[/bold blue] “, end=””) try: response = client.chat.completions.create( model=”z-ai/glm-5-turbo”, messages=messages, temperature=0.7, max_tokens=2048, stream=True ) reply = “” for chunk in response: if chunk.choices[0].delta.content: content = chunk.choices[0].delta.content console.print(content, end=””) reply += content console.print(“\n”) messages.append({“role”: “assistant”, “content”: reply}) save_history(messages) except Exception as e: console.print(f”

[red]Error: {e}[/red]

“)

5. Run the Chat

Bash

python3 chat_glm.py

---