Big-AGI vs Chatbox

Big-AGI

• People with API keys for several providers who compare answers
• Checking an important answer across models before acting on it
• Self-hosters and IT teams that want an MIT-licensed chat interface

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

Big-AGI

• No model access is included: every tier needs your own API keys, and each provider bills usage directly.
• Cloud backup and multi-device sync are Pro features. On Free and Open, chats stay in the browser on one device.
• It runs in the browser and installs as a web app; the site lists no native desktop or mobile apps.
• Team management and SLA guarantees are offered only through a custom Business plan with no public price.

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.

Big-AGI

Beam and Merge

Beam sends one prompt to between 2 and 24 models in parallel, each answering without seeing the others. Merge then fuses the replies into one answer with built-in or custom merge prompts.

Your own keys for 30+ services

Connects directly to OpenAI, Anthropic, Google Gemini, Mistral, DeepSeek, OpenRouter, Azure and AWS Bedrock, and to local servers such as Ollama and LM Studio, with no markup on usage.

Precise model controls

Effort, temperature, verbosity, reasoning budget, search and tools can be set per request or per persona across more than 800 models.

Personas

A persona carries its own instructions, attached documents and images, memory, a fixed model with parameters, and a voice, so a role can be reused across chats.

AI Inspector

Shows the exact request leaving the browser, including the model, parameters, tokens and cost, both before and after it runs.

Local-first with optional sync

Chats and settings stay in the browser by default. Pro adds cloud backup and sync of chats and personas across devices.

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.

Big-AGI

• Big-AGI Open$0

  The open-source codebase under the MIT License, self-hosted with Docker or deployed to Vercel on your own infrastructure.

• Free$0

  The hosted app: everything in Open plus advanced multi-model, Personas and interface features. You bring your own API keys.

• Pro$9

  per month, billed yearly ($108); $10.99 billed monthly

  Everything in Free plus cloud backup of personas and chats, sync across devices with 1 GB of storage, email support and priority access to new features.

• BusinessCustom

  Custom deployments, team management and SLA guarantees, arranged by contacting Big-AGI.

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.

Big-AGI

• Annual discount

  Save 18% with yearly billing

  Pro is $9 a month when billed $108 a year, compared with $10.99 a month on monthly billing.

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%.