The Universal AI Chat Interface

Yes, the interface is free and open source. You only pay the AI providers (OpenAI, Anthropic, Google, xAI, etc.) directly for the API usage. This is typically much cheaper than monthly subscriptions for casual to moderate users.

It is also possible to get access to free models via OpenRouter. See our docs to start using an end to end free tool.

ChatStack AI supports the latest flagship models from all major providers. You can seamlessly switch between:

• OpenAI: GPT-5.4, GPT-5.4 Pro, and Codex Max
• Anthropic: Claude 4.6 Sonnet & Opus
• Google: Gemini 3.1 Pro & Flash
• xAI: Grok 4.1 & Vision
• MoonshotAI: Kimi 2.5
• DeepSeek: DeepSeek V3.2 & Coder
• Alibaba: Qwen 3.5 Max, Plus, Flash & Coder
• Z.ai: GLM 5

Check the full list of supported parameters and prices on our Model Specifications page.

Instead of paying a subscription, you generate an API Key for your preferred AI provider's. Then, you paste that key in Settings > API Keys. This gives you full access to the models at wholesale prices without middleman markups.

Need help finding keys? Visit our API Keys Guide.

Yes, ChatStack includes a dedicated Code Mode for those power users that want the best programming experience. In Code Mode, a Workspace directory will show up in the sidebar and will allow you to connect to your selected local directories.

In this coding workspace you will have the option to select the directories and files that you want to include in the current chat. ChatStack AI will optimize its content when sending them so the LLM can have a full overview of your projects while you focus on the prompt.

ChatStack AI Code Mode is ideal for those who want to maximize the AI power for programming but prefer to avoid AI agents for certain tasks.

Yes, ChatStack has Chat, Image Generation, and Code Modes. When selected, the model selector filters the models that offer text and image output. In Image Generation mode, the chat messages are optimized to display the images created by the AI.

ChatStack AI supports both text-to-image and image-to-image generation within its Image Generation Mode.

Yes. While ChatStack AI is local-first, we offer a Cloud Sync feature. It uses your own credentials to securely synchronize your chat history, folders, prompts, preferences and API Keys between your desktop and mobile devices.

Absolutely. ChatStack AI uses a "Local First" architecture. Your chat history, API keys, and prompts are stored in IndexedDB within your browser. Data is never sent to our servers, only directly to the AI provider you select for inference.

If Cloud Sync is enabled, the data is sent to our servers for synchronize it across all your devices. Your data is never sold or used for advertisement, training, or monetization. See our Privacy Policy.

Since data lives in your browser, clearing your "Site Data" or "Cache" can delete your history. We strongly recommend using our Export Data feature regularly (JSON format) or subscribing to the Cloud Sync service to ensure your prompts and history are backed up safely.

Yes. You can build a personal library of reusable Prompts. You can define System Prompts (to change how the AI behaves) and regular Snippet Prompts (for repetitive tasks). Variables are supported for dynamic insertion.

Organize your chats into nested folders and subfolders. Inside a chat, you can "Edit" any previous message to create a Branch. This allows you to explore different outcomes from a single point in the conversation without losing the original context.

Fully. Choose from multiple themes (Tokyo Night, Catppuccin, Gruvbox), adjust font sizes, and set up the AI workspace in the best way for you. The interface is designed to feel native and snappy.

We optimize documents before sending them to the LLM. PDF, CSV, DOCX, and Code files are parsed and stripped of unnecessary whitespace to save you tokens (money) and improve the model's ability to focus on the content.