Frequently Asked Questions
Common questions about ModelHub, answered.
What AI models does ModelHub support?
ModelHub provides 6 AI personalities (Claude, GPT, Grok, Gemini, Kimi, Meta) with 30+ variants. Each personality has unique characteristics, but all requests are routed through OpenAI's API with custom system prompts.
Do I need my own API key?
Yes, you need an OpenAI API key for AI interactions. You can get one from platform.openai.com. The key is stored server-side and never exposed to the browser.
What's the difference between providers and variants?
Providers (Claude, GPT, etc.) define the personality and communication style. Variants (Opus-class, GPT-5.1, etc.) determine speed, reasoning depth, context window, and cost tier.
Are my conversations private?
Conversations are stored locally in your browser. They're not synced to any server. However, prompts are sent to OpenAI's API for processing.
Can I use ModelHub offline?
The interface works offline, but AI interactions require an internet connection to reach OpenAI's API.
What file types can I upload?
ModelHub supports code files (.js, .ts, .py, etc.), markup (.html, .css, .md), configuration (.json, .yaml), and text files. Binary files and images are not supported for context.
Is there a message limit?
ModelHub doesn't impose message limits, but OpenAI's API has rate limits based on your plan. Using lighter variants helps stay within limits.
How do I switch models mid-conversation?
Click the model selector in the sidebar or use ⌘K for the quick switcher. Your conversation context is preserved when switching.
What does "Connect Wallet" do?
Wallet connection is a placeholder for future features. Currently, ModelHub doesn't require wallet integration.
How do I report bugs or suggest features?
You can report issues on our GitHub repository or reach out on Twitter/X.