ChatGPT Plus ($20/mo) vs API Pay-As-You-Go

# docker-compose.yml for LibreChat (The #1 Open-Source ChatGPT Alternative)
# Features: Multi-model (OpenAI, Anthropic, Gemini, DeepSeek), File Uploads, Web Search, Artifacts
version: '3.8'

services:
  librechat:
    image: ghcr.io/danny-avila/librechat:latest
    container_name: LibreChat
    ports:
      - "3080:3080"
    environment:
      - HOST=0.0.0.0
      - MONGO_URI=mongodb://mongodb:27017/LibreChat
      - OPENAI_API_KEY=sk-proj-YOUR_PERSONAL_OPENAI_KEY
      - ANTHROPIC_API_KEY=sk-ant-YOUR_ANTHROPIC_KEY
      - TITLE=My Private AI Studio
      - CUSTOM_MODELS=gpt-4o,gpt-4o-mini,o3-mini,claude-3-7-sonnet
    depends_on:
      - mongodb
    restart: always

  mongodb:
    image: mongo:latest
    container_name: chat-mongodb
    volumes:
      - ./data/mongo:/data/db
    restart: always

// TypingMind Zero-Server Setup Instructions (typingmind.com)
// 1. Visit https://www.typingmind.com
// 2. Open Settings -> API Keys
// 3. Paste your personal OpenAI API Key (stored client-side in browser LocalStorage)
// 4. (Optional) Configure Prompt Caching:
{
  "provider": "openai",
  "enable_prompt_caching": true,
  "default_model": "gpt-4o-mini",
  "temperature": 0.7,
  "max_tokens": 4096,
  "context_retention_turns": 8
}
// Tip: Use OpenRouter within TypingMind to access DeepSeek V3 at $0.14/1M tokens!

# check_api_session_cost.py - Real-time terminal token burn tracker
import os
from openai import OpenAI

client = OpenAI(api_key=os.environ.get("OPENAI_API_KEY"))

# Send sample query and calculate exact penny cost
response = client.chat.completions.create(
    model="gpt-4o-mini",
    messages=[{"role": "user", "content": "Explain quantum annealing in 3 paragraphs"}],
    temperature=0.5
)

usage = response.usage
prompt_tokens = usage.prompt_tokens
completion_tokens = usage.completion_tokens

# GPT-4o-mini rates: $0.15/M in, $0.60/M out
cost = (prompt_tokens * (0.15 / 1_000_000)) + (completion_tokens * (0.60 / 1_000_000))

print(f"Tokens: In={prompt_tokens}, Out={completion_tokens}")
print(f"Total Turn Cost: ${cost:.6f} USD")
print(f"You can run {20.0 / cost:,.0f} queries like this for the price of 1 month of ChatGPT Plus!")