Chatbox vs Jan

Chatbox

• People who want the same chat app on desktop, phone and browser
• Users with their own API keys who prefer to pay providers per use
• Trying hosted GPT, Claude and Gemini models on a low-priced plan

Jan

• Running open models offline on your own computer
• People who want one desktop app for local and cloud models
• Developers who want a local OpenAI-compatible endpoint

Chatbox

• Work Mode and the knowledge base are desktop only; the web and mobile apps offer regular chat.
• On the hosted service, advanced models, the knowledge base and MCP services need Pro or Pro+. Lite and Free are limited to standard models.
• Hosted usage is metered in compute points that reset monthly (daily on Free). Extra points are sold as add-on packs valid for 3 months.
• A license works on up to 5 devices at the same time, and switching plans means buying the new plan from the pricing page.

Jan

• Desktop only, on macOS, Windows and Linux. Intel-based Macs are not supported.
• Local models need memory: Jan's Mac guide suggests 8GB of RAM for 3B models, 16GB for 7B models and 32GB for 13B models.
• Cloud models need your own API key from each provider, and those providers see the messages you send them.
• Cowork and the standalone Jan Agent are previews on nightly builds, and the memory feature is marked as coming soon.

Chatbox

Your own keys or hosted models

Add API keys for OpenAI, Claude, Gemini, DeepSeek, OpenRouter and other providers, run local models through Ollama or LM Studio, or subscribe to Chatbox AI for hosted models on one bill.

Work Mode

On desktop, an agent works in a loop of thinking and tool calls: it runs code, reads and writes files, calls MCP servers and queries knowledge bases until the task is done.

File and image chat

Attach PDFs, Word documents, images and code to a conversation so the model can summarize them and answer questions about their content.

Real-time web search

Chat can search the internet for current information. It is toggled from the toolbar in Chat Mode and managed from the control panel in Work Mode.

Local knowledge base

The desktop app stores documents in a local knowledge base the AI can search. Each file must be under 50 MB, in formats such as PDF, DOCX, PPTX, XLSX, CSV and EPUB.

Image generation and rich output

Generates images from a text description and renders Markdown, LaTeX formulas, Mermaid diagrams and code with a live preview.

Jan

Local models

Downloads and runs open models such as Llama, Gemma and Qwen from Hugging Face using llama.cpp or MLX. The Hub shows whether each model fits your hardware.

Cloud providers with your own key

Connects to OpenAI, Anthropic, Gemini, Mistral AI, Groq, OpenRouter and Azure OpenAI, or to any OpenAI- or Anthropic-compatible endpoint, using an API key you supply.

Built-in web search

Web search and page fetch tools are on by default for models that support tool use. They run through a keyless Exa endpoint, so no API key or MCP server is needed.

Projects and assistants

Projects group conversations under shared instructions and files, and custom assistants keep their own instructions for recurring kinds of work.

Local API server

A built-in OpenAI-compatible server at localhost:1337 lets other applications use the models running in Jan, and Claude Code can be set to use them as its backend.

MCP connectors and Cowork preview

MCP servers add tools such as code execution and databases. Cowork, which works through multi-step tasks on files and commands, ships only in nightly builds as a preview.

Chatbox

• Free$0

  Hosted service for light use: 10,000 compute points reset daily, standard models, web search, 5 generated images and a trial of Work Mode.

• Lite$3.50

  per month, billed annually ($3.99 billed monthly)

  2,000,000 compute points a month on standard models, 25 generated images, web search and Work Mode. No advanced models, knowledge base or MCP services.

• Pro$16.70

  per month, billed annually ($19.99 billed monthly)

  12,000,000 compute points a month, advanced GPT, Claude, Gemini and Grok models, 100 generated images, the knowledge base and MCP services.

• Pro+$33.33

  per month, billed annually ($39.99 billed monthly)

  30,000,000 compute points a month and 200 generated images, with the same models and features as Pro.

Jan

• Free$0

  The full desktop app for macOS, Windows and Linux, with local models, cloud provider connections and the local API server.

Chatbox

• Annual discount

  Lower monthly rate with annual billing

  Billed annually, Lite is $3.50 a month instead of $3.99, Pro $16.70 instead of $19.99 and Pro+ $33.33 instead of $39.99, a saving of about 12% to 17%.

Jan

No public discounts listed.